Context-aware service work order assignment method and system

Abstract

The present application relates to the technical field of work order distribution, and particularly relates to a service work order distribution method and system based on context awareness, comprising: determining the work order type and corresponding technical bias and standard time consumption of each work order; determining the estimated processing time consumption of each processing end for each work order type; determining the processing score of each processing end for each technical bias based on each estimated processing time consumption; distributing each work order to each processing end; identifying the average time consumption change rate of each technical bias to determine whether the distribution of the work order is qualified, and adjusting the work order distribution parameters based on the abnormal time consumption dispersion amount when determining that the distribution of each work order is abnormal, including adjusting the rhythm cycle length or correcting the work order depth; determining whether to perform associated work order identification based on the work order inflow amount; determining whether to correct the mixed sending mechanism based on the number of associated work orders, monitoring the dynamic change of the average time consumption under each technical bias, and identifying the distribution processing efficiency anomaly in a timely manner, thereby improving the work order distribution efficiency.

Description

Technical Field

[0001] This invention relates to the field of work order allocation technology, and in particular to a context-aware service work order allocation method and system. Background Technology

[0002] As enterprise digital systems continue to expand, service tickets have become a crucial component of operations management, customer support, and business assurance. Service tickets typically originate from user submissions, system monitoring alerts, business process anomalies, or feedback from third-party systems, involving various technical areas such as networking, databases, application services, permission configuration, API calls, and data synchronization. Because different service tickets have varying technical focuses and processing complexities, and different processing endpoints have different processing capabilities and historical experience, the appropriate allocation of service tickets to suitable processing endpoints directly impacts service response efficiency and service quality.

[0003] Chinese Patent Publication No. CN119047755A discloses a work order allocation method, apparatus, electronic device, and readable storage medium. The method includes: acquiring a work order allocation request; generating at least one work order in at least one business domain based on the work order allocation request; determining at least one user associated with each business domain; determining the matching degree between each work order and each user in each business domain when a preset time has not been reached at the current time and / or the number of at least one work order is less than or equal to a first number; for each work order in each business domain, determining a target matching degree corresponding to each work order based on the matching degree between each work order and each user in the business domain according to allocation rules; determining the user corresponding to each target matching degree as a first target user; and sending the corresponding work order to the user terminal of each first target user. It is evident that the above technical solution has the following problems: it does not consider the dynamic changes in the average time consumption under each technical bias, and cannot promptly identify abnormal allocation processing efficiency, thus affecting the work order allocation efficiency. Summary of the Invention

[0004] To address this issue, the present invention provides a context-aware service work order allocation method and system to overcome the problem in the prior art that the dynamic changes in the average time consumption of each technology under different conditions are not considered, making it impossible to identify abnormal allocation and processing efficiency in a timely manner, thus affecting the efficiency of work order allocation.

[0005] On one hand, the present invention provides a context-aware service order allocation method, including: Determine the work order type, corresponding technical focus, and standard time consumption for each work order; Determine the estimated processing time for each processing terminal for each work order type; Based on the estimated processing time, a processing score for each processing end is determined for each technical bias. Distribute each work order to the respective processing terminal; Identify the average time change rate of each technical bias to determine whether the work order allocation is qualified. When it is determined that the allocation of each work order is abnormal, adjust the work order allocation parameters based on the abnormal time dispersion, including adjusting the rhythm cycle duration or correcting the work order depth. Determine whether to perform associated work order identification based on the influx of work orders; Whether to correct the mixed-issue mechanism is determined based on the number of associated work orders.

[0006] Furthermore, the estimated processing time for a single processing terminal for a single work order type is the average processing time for the corresponding work order type in historical data; A single technical preference corresponds to several work order types.

[0007] Furthermore, the process of identifying the average time change rate for each technical bias to determine whether the allocation of work orders is appropriate includes, The average time consumption of each work order corresponding to a single technical bias is determined within the preset control period to obtain the technical time consumption. Based on the time consumption of each technology for each preset control duration, determine the time-technology consumption curve for a single technology bias, determine the slope of the time-technology consumption curve at the current time node, and obtain the average time consumption change rate for a single technology bias. Obtain the maximum value among the average time-consuming change rates of each technology bias to obtain the maximum change rate; When the maximum change rate exceeds the preset change rate, the work order allocation is identified as abnormal. The work order allocation parameters are adjusted based on the abnormal time dispersion, including adjusting the rhythm cycle duration or correcting the work order depth.

[0008] Furthermore, the process of adjusting work order allocation parameters based on the abnormal time consumption dispersion includes: Identify the abnormal time-consuming events for a single processing end, calculate the time interval between each adjacent abnormal time-consuming event, calculate the variance of each time interval, and obtain the abnormal time-consuming dispersion. Determine the minimum value of the abnormal time distribution at each processing end to obtain the minimum distribution; When the minimum dispersion amount is less than or equal to the preset dispersion amount, the lag allocation of the rhythm cycle for each processing end is performed, and the duration of the rhythm cycle is adjusted based on the dispersion level. When the minimum dispersion amount is greater than the preset dispersion amount, the work order depth of each work order is corrected based on the maximum change rate and the technical bias corresponding to the maximum change rate.

[0009] Furthermore, the process of performing a lag allocation for the rhythmic cycles of each processing end includes, The difference between the actual processing time and the estimated processing time for a single work order at a single processing terminal is determined to obtain the time deviation. Determine the time-duration deviation curve for a single processing end. When the slope of the time-duration deviation curve is lower than the preset trough slope, determine the rhythm start node for a single user at the corresponding time node, and perform lag allocation within the rhythm cycle.

[0010] Furthermore, the duration of the rhythm cycle is adjusted based on the magnitude of the dispersion, where, The dispersion magnitude is the number of abnormal time dispersions that are less than the preset dispersion magnitude. The increase in rhythm cycle duration is positively correlated with the magnitude of dispersion.

[0011] Furthermore, the process of adjusting the work order depth based on the maximum change rate includes: Obtain the work order submission frequency of the corresponding user who submitted the work order, and adjust the work order depth based on the work order submission frequency; The increase in work order depth is positively correlated with the frequency of work order submission; The increase in work order depth is positively correlated with the maximum change rate; The standard time for a single work order is the product of the initial standard time and the work order depth.

[0012] Furthermore, after completing the work order depth correction, the system determines whether to perform associated work order identification based on the influx of work orders, including: The total number of work orders within the current preset control period is used to determine the work order inflow. When the number of incoming work orders exceeds the preset number of incoming work orders, perform associated work order identification.

[0013] Furthermore, the process of determining whether to correct the mixed-issue mechanism based on the number of associated work order groups includes: When the number of associated work order groups exceeds the preset number of impacts, determine the proportion of mixed transmissions in the correction mixed transmission mechanism; The increase in the proportion of mixed-issue work is positively correlated with the number of related work order groups.

[0014] On the other hand, the present invention also provides a context-aware service order allocation system, comprising: The work order recognition module is used to determine the work order type, corresponding technical bias, and standard time consumption of each work order based on the work order text. The processing module includes several processing terminals for processing each work order, a processing database for storing the estimated processing time of each processing terminal for each work order type, and a scoring statistics unit for determining the processing score of each processing terminal for each technical bias based on the estimated processing time. The allocation module is connected to the work order identification module and the processing module respectively, and is used to allocate each work order to each processing terminal; The allocation monitoring module is connected to the work order identification module, the processing module and the allocation module respectively. It is used to determine whether the allocation of the work order is qualified based on the average time change rate of each technical bias. When it is determined that the allocation of each work order is abnormal, the work order allocation parameters are adjusted based on the abnormal time dispersion, including the adjustment rhythm cycle duration of each processing end, or the work order depth of each work order. The work order analysis module is connected to the allocation monitoring module and the work order identification module respectively, and is used to determine whether to perform associated work order identification based on the influx of work orders. The work order processing module is connected to the work order identification module, the processing module, the allocation module, the allocation monitoring module, and the work order analysis module, respectively, and is used to determine whether to correct the mixed-issue mechanism based on the number of associated work orders.

[0015] Compared with the prior art, the beneficial effects of the present invention are that it determines the average time change rate based on the time-technology time consumption curve, identifies the dynamic change trend of work order processing time under different technology biases, thereby reducing the interference of occasional anomalies on the allocation strategy; at the same time, it triggers the adjustment of work order allocation parameters when the maximum change rate exceeds the preset change rate, timely detects situations such as allocation strategy deviations, improves the stability, real-time performance and adaptability of work order allocation, and further improves the efficiency of service work order allocation.

[0016] Furthermore, the dispersion of abnormal time consumption is used to characterize the concentration and periodicity of abnormal time consumption events in the time dimension. When the dispersion of abnormal time consumption is less than or equal to the preset dispersion, it indicates that the time interval between abnormal time consumption events is relatively stable, and there is a rhythmic trough in the processing end. Therefore, delayed allocation is performed, and the duration of the rhythmic cycle is adjusted according to the dispersion magnitude. When the dispersion of abnormal time consumption is greater than the preset dispersion, it indicates that the abnormal time consumption events do not have obvious periodicity, and the anomaly is caused by the increase in work order complexity under the work order depth and technical bias. The work order depth of each work order under the corresponding technical bias is corrected based on the maximum change rate. Work order allocation anomalies are further divided into processing end rhythm anomalies and work order complexity anomalies, and different adjustment strategies are adopted for different anomaly types. For processing end rhythm anomalies, delayed allocation and priority allocation of work orders with low standard time consumption are used to reduce the probability of accepting high-complexity work orders during the processing end trough. For work order complexity anomalies, the work order depth is corrected by the work order submission frequency and the maximum change rate, so that the corrected standard time consumption is closer to the actual processing time. The system improves the targeting of work order allocation parameter adjustments, reduces the probability of timeout processing at the processing end, enhances the stability and adaptability of the work order allocation system in high-fluctuation scenarios, and further improves the efficiency of service work order allocation.

[0017] Furthermore, when the influx of work orders is low or within the normal range, abnormal processing times at each processing end can be corrected through rhythmic cycle adjustment or work order depth correction. However, when the influx of work orders exceeds the preset influx limit, it indicates that the current situation may be affected by sudden events, common root cause failures, or concentrated user feedback. In this case, a large number of work orders are not independent of each other. If work orders are still allocated independently as individual work orders, it is easy for related work orders caused by the same reason to be assigned to processing ends that are only proficient in a single technology, resulting in incomplete investigation. Therefore, when the influx of work orders exceeds the preset influx limit, related work order identification is performed to identify work orders with common root causes or causal links as related work order groups and dispatch them to the balanced processing end for processing. After identifying related work order groups, the number of related work order groups is used to determine whether to correct the mixed dispatch mechanism. The larger the number of related work order groups, the more common root cause or chain-effect work orders there are in the current influx of work orders, and the overall allocation strategy needs to improve its exploratory capabilities. Therefore, by increasing the proportion of mixed-processing orders and randomly allocating some work orders to various processing terminals, it is possible to avoid the tendency of similar technologies to concentrate work orders on a few processing terminals, thereby reducing the risk of localized processing capacity degradation. This improves the robustness of work order processing and overall processing efficiency in scenarios with a sudden influx of work orders. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating the steps of the context-aware service order allocation method according to an embodiment of the present invention. Figure 2 This is a block diagram of the context-aware service order allocation system according to an embodiment of the present invention. Detailed Implementation

[0019] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0020] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0021] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0022] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0023] Please see Figure 1 The figures shown are flowcharts illustrating the steps of the context-aware service order allocation method according to an embodiment of the present invention. The method of the present invention includes: S1, determine the work order type, corresponding technical bias, and standard time consumption for each work order; S2, determine the estimated processing time for each processing end for each work order type; S3, based on the estimated processing time, determine the processing score for each processing end for each technical bias; S4 distributes each work order to each processing terminal; S5 identifies the average time change rate of each technical bias to determine whether the work order allocation is qualified. When it is determined that the allocation of each work order is abnormal, the work order allocation parameters are adjusted based on the abnormal time dispersion, including adjusting the rhythm cycle duration or correcting the work order depth. S6 determines whether to perform associated work order identification based on the influx of work orders; S7 determines whether to correct the mixed-issue mechanism based on the number of associated work orders.

[0024] Please see Figure 2 The diagrams shown are module block diagrams of a context-aware service order allocation system according to an embodiment of the present invention. The system of the present invention includes: The work order recognition module is used to determine the work order type, corresponding technical bias, and standard time consumption of each work order based on the work order text. The processing module includes several processing terminals for processing each work order, a processing database for storing the estimated processing time of each processing terminal for each work order type, and a scoring statistics unit for determining the processing score of each processing terminal for each technical bias based on the estimated processing time. The allocation module is connected to the work order identification module and the processing module respectively, and is used to allocate each work order to each processing terminal; The allocation monitoring module is connected to the work order identification module, the processing module and the allocation module respectively. It is used to determine whether the allocation of the work order is qualified based on the average time change rate of each technical bias. When it is determined that the allocation of each work order is abnormal, the work order allocation parameters are adjusted based on the abnormal time dispersion, including the adjustment rhythm cycle duration of each processing end, or the work order depth of each work order. The work order analysis module is connected to the allocation monitoring module and the work order identification module respectively, and is used to determine whether to perform associated work order identification based on the influx of work orders. The work order processing module is connected to the work order identification module, the processing module, the allocation module, the allocation monitoring module, and the work order analysis module, respectively, and is used to determine whether to correct the mixed-issue mechanism based on the number of associated work orders.

[0025] Specifically, in S1, each work order type has a pre-stored standard time consumption and technical bias. Each work order type has a unique technical bias, and all historical time consumption is within the corresponding time range.

[0026] In a single embodiment, the standard time for a single work order type is the average time taken by each processing end to process each work order of the corresponding work order type in historical data.

[0027] In this embodiment, the process of determining the work order type of each work order includes extracting features from the title, body, error code, and log fragments of the work order to be assigned, and inputting the extracted work order features into the work order classification model to obtain the corresponding work order type; wherein, the work order classification model is trained based on historical work orders and their labeled work order types, which is existing technology and will not be described in detail.

[0028] Specifically, the estimated processing time for a single work order type is the average processing time for the corresponding work order type in historical data.

[0029] Specifically, a single technology preference corresponds to several work order types; In a single embodiment, the process of determining the processing score based on the processing end's technical bias may include, Calculate the time difference between the standard processing time for a single work order type and the estimated processing time for a single processing terminal; Calculate the average of the time difference for each work order type under a single technical bias to obtain the processing score for that single technical bias.

[0030] In S5, the process of identifying the average time change rate of each technical bias to determine whether the allocation of work orders is appropriate includes, The average time consumption of each work order corresponding to a single technical bias is determined within the preset control period to obtain the technical time consumption. Based on the time consumption of each technology for each preset control duration, determine the time-technology consumption curve for a single technology bias, determine the slope of the time-technology consumption curve at the current time node, and obtain the average time consumption change rate for a single technology bias. Obtain the maximum value among the average time-consuming change rates of each technology bias to obtain the maximum change rate; When the maximum change rate is less than or equal to the preset change rate, the allocation of each work order is deemed qualified, and the current work order allocation parameters are continuously used to complete the allocation of each work order. When the maximum change rate exceeds the preset change rate, the work order allocation is identified as abnormal. The work order allocation parameters are adjusted based on the abnormal time dispersion, including adjusting the rhythm cycle duration or correcting the work order depth.

[0031] In a single embodiment, the preset change rate can be the sum of the mean of the average time change rate of each technical bias under the historical stable allocation state and twice the standard deviation. The preset change rate enables the identification of work order allocation deviations.

[0032] In this embodiment, the average time change rate is determined based on the time-technology time consumption curve, and the dynamic change trend of work order processing time under different technology biases is identified, thereby reducing the interference of occasional anomalies on the allocation strategy. At the same time, when the maximum change rate exceeds the preset change rate, the work order allocation parameters are adjusted to detect the deviation of the allocation strategy in a timely manner, thereby improving the stability, real-time performance and adaptability of work order allocation, and further improving the efficiency of service work order allocation.

[0033] Specifically, the process of adjusting work order allocation parameters based on the abnormal time consumption dispersion includes: Identify the abnormal time-consuming events for a single processing end, calculate the time interval between each adjacent abnormal time-consuming event, calculate the variance of each time interval, and obtain the abnormal time-consuming dispersion. The smaller the abnormal time-consuming dispersion, the more significant the periodic occurrence of abnormal time-consuming events caused by the processing end's decreased execution function due to periodic troughs. Determine the minimum value of the abnormal time distribution at each processing end to obtain the minimum distribution; When the minimum dispersion amount is less than or equal to the preset dispersion amount, the lag allocation of the rhythm cycle for each processing end is performed, and the duration of the rhythm cycle is adjusted based on the dispersion level. When the minimum dispersion amount is greater than the preset dispersion amount, the work order depth of each work order is corrected based on the maximum change rate and the technical bias corresponding to the maximum change rate.

[0034] In a single embodiment, the preset dispersion amount is determined by obtaining the 95th percentile value of the dispersion amount of abnormal time consumption in historical periodic abnormal samples. The preset dispersion amount is used to identify the periodic cycle of each abnormal time consumption event at the processing end.

[0035] Specifically, when the time consumption deviation is greater than the preset elastic duration, the processing event of a single work order by a single processing terminal is determined to be an abnormal time consumption event.

[0036] In a single embodiment, the process of determining the preset elastic duration can be as follows: obtain the time consumption deviation of each processing terminal when processing each work order under the historical normal processing state, calculate the mean and standard deviation of each time consumption deviation, and determine the sum of the mean and twice the standard deviation as the preset elastic duration, so as to realize the identification of excessively long processing events of the processing terminal.

[0037] Specifically, the process of performing a lag allocation for the rhythmic cycles of each processing terminal includes, The difference between the actual processing time and the estimated processing time for a single work order at a single processing terminal is determined to obtain the time deviation. Determine the time-duration deviation curve for a single processing end. When the slope of the time-duration deviation curve is lower than the preset trough slope, determine the rhythm start node for a single user at the corresponding time node, and perform lag allocation within the rhythm cycle.

[0038] Specifically, delayed allocation includes allocating work orders to processing terminals within the rhythm cycle after completing the allocation of work orders to each processing terminal, and prioritizing the allocation of work orders with low standard processing time.

[0039] Specifically, the duration of the rhythm cycle is adjusted based on the magnitude of the dispersion, where... The dispersion magnitude is the number of abnormal time dispersions that are less than the preset dispersion magnitude. The increase in rhythm cycle duration is positively correlated with the magnitude of dispersion.

[0040] The larger the dispersion magnitude, the more likely it is that abnormal time-consuming events from multiple processing ends will appear in a periodic cluster. In other words, the more processing ends with rhythmic troughs there are, the more significantly the overall processing capacity will be affected by periodic fluctuations.

[0041] The longer the rhythm cycle duration, the longer the corresponding processing end is in a rhythm trough state.

[0042] Specifically, the process of adjusting work order depth based on the maximum change rate includes: Obtain the work order submission frequency of the corresponding user who submitted the work order, and adjust the work order depth based on the work order submission frequency; The increase in work order depth is positively correlated with the frequency of work order submission; The increase in work order depth is positively correlated with the maximum change rate; The standard time for a single work order is the product of the initial standard time and the work order depth.

[0043] The work order depth is the initial correction factor for the standard time consumption. The higher the frequency of work orders, the more times the corresponding user submits work orders in a short period of time, indicating a longer problem chain. Therefore, the actual understanding cost of a single work order is much greater than that of a regular work order.

[0044] The higher the maximum change rate, the faster the average time of a work order increases under a certain technology bias, indicating that the actual processing difficulty of such work orders is increasing rapidly.

[0045] The greater the depth of a work order, the more the standard time for that work order is increased, and the more contextual understanding and complex problem-solving costs are required for that work order.

[0046] Specifically, the dispersion of abnormal time consumption is used to characterize the concentration and periodicity of abnormal time consumption events over time. When the dispersion of abnormal time consumption is less than or equal to a preset dispersion, it indicates that the time interval between abnormal time consumption events is relatively stable, and there is a rhythmic trough in the processing end. Therefore, delayed allocation is performed, and the duration of the rhythmic cycle is adjusted according to the dispersion magnitude. When the dispersion of abnormal time consumption is greater than the preset dispersion, it indicates that the abnormal time consumption events do not have obvious periodicity, and the anomaly is caused by the increase in work order complexity under the work order depth and technical bias. The work order depth of each work order under the corresponding technical bias is corrected based on the maximum change rate. Work order allocation anomalies are further divided into processing end rhythm anomalies and work order complexity anomalies, and different adjustment strategies are adopted for different anomaly types. For processing end rhythm anomalies, delayed allocation and priority allocation of work orders with low standard time consumption are used to reduce the probability of accepting high-complexity work orders during the processing end trough. For work order complexity anomalies, the work order depth is corrected by the work order submission frequency and the maximum change rate, so that the corrected standard time consumption is closer to the actual processing time. The system improves the targeting of work order allocation parameter adjustments, reduces the probability of timeout processing at the processing end, enhances the stability and adaptability of the work order allocation system in high-fluctuation scenarios, and further improves the efficiency of service work order allocation.

[0047] Specifically, after completing the work order depth correction, the system determines whether to perform associated work order identification based on the influx of work orders, including: The total number of work orders within the current preset control period is used to determine the work order inflow. When the number of incoming work orders exceeds the preset number of incoming work orders, perform associated work order identification; When the number of incoming work orders is less than or equal to the preset number of incoming work orders, the current work order allocation parameters are continuously used to complete the allocation of each work order.

[0048] Specifically, the preset work order inflow volume is the average of the inflow volume of each work order in the historical data, in order to identify situations where a large number of work orders that need to be processed cause processing abnormalities at each processing end.

[0049] Specifically, the process of identifying related work orders includes determining related work order groups through a causal discovery algorithm and dispatching each work order in the related work order group to the load balancer.

[0050] The balanced processing end is a processing end where the estimated processing time for each work order type is lower than the corresponding standard processing time.

[0051] A group of related work orders consists of several related work orders.

[0052] In a single embodiment, the specific process of determining the associated work order group using the causal discovery algorithm includes: obtaining each work order within the current preset control period, and extracting the submission time, work order type, technical bias, submitting user, error code, keywords, processing result, and actual time consumption of each work order to obtain a work order feature set; constructing a work order variable matrix based on the work order feature set; inputting the work order variable matrix into the causal discovery algorithm to obtain a causal relationship graph used to characterize the causal dependencies between each work order variable; in the causal relationship graph, determining that several work orders that have at least one of a common parent node, a direct causal edge, or an indirect causal path are the same associated work order group. This is prior art and will not be described in detail here.

[0053] Specifically, the process of determining whether to correct the mixed-issue mechanism based on the number of associated work order groups includes: When the number of associated work order groups exceeds the preset number of impacts, determine the proportion of mixed transmissions in the correction mixed transmission mechanism; The increase in the proportion of mixed-issue work is positively correlated with the number of related work order groups.

[0054] The higher the proportion of mixed dispatches, the greater the need to improve the load diffusion and random exploration of work order allocation, in order to avoid concentrated dispatch of related work orders or work orders with similar technical biases to at least a few processing ends, which would lead to the degradation of the processing capacity of some processing ends or some technologies.

[0055] The larger the number of associated work order groups, the more work order clusters are caused by a common root cause in the current work order influx, and the stronger the causal relationship and linkage between work orders.

[0056] In step S4, the process of assigning each work order to each processing terminal includes, The work orders with the highest proportion of mixed dispatches are randomly assigned to each processing terminal.

[0057] Specifically, when the influx of work orders is low or within the normal range, abnormal processing times at each processing end can be corrected through rhythmic cycle adjustment or work order depth correction. However, when the influx of work orders exceeds the preset limit, it indicates that the current situation may be affected by sudden events, common root cause failures, or concentrated user feedback. In this case, a large number of work orders are not independent of each other. If work orders are still allocated independently as individual work orders, it is easy for related work orders caused by the same reason to be assigned to processing ends that are only proficient in a single technology, resulting in incomplete investigation. Therefore, when the influx of work orders exceeds the preset limit, related work order identification is performed to identify work orders with common root causes or causal links as related work order groups and dispatch them to the balanced processing end for processing. After identifying related work order groups, the number of related work order groups is used to determine whether to correct the mixed dispatch mechanism. The larger the number of related work order groups, the more common root cause or chain-effect work orders there are in the current work order influx, and the overall allocation strategy needs to improve its exploratory capabilities. Therefore, by increasing the proportion of mixed-processing orders and randomly allocating some work orders to various processing terminals, it is possible to avoid the tendency of similar technologies to concentrate work orders on a few processing terminals, thereby reducing the risk of localized processing capacity degradation. This improves the robustness of work order processing and overall processing efficiency in scenarios with a sudden influx of work orders.

[0058] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0059] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A context-aware service order allocation method, characterized in that, include: Determine the work order type, corresponding technical focus, and standard time consumption for each work order; Determine the estimated processing time for each processing terminal for each work order type; Based on the estimated processing time, a processing score for each processing end is determined for each technical bias. Distribute each work order to the respective processing terminal; Identify the average time change rate of each technical bias to determine whether the work order allocation is qualified. When it is determined that the allocation of each work order is abnormal, adjust the work order allocation parameters based on the abnormal time dispersion, including adjusting the rhythm cycle duration or correcting the work order depth. Determine whether to perform associated work order identification based on the influx of work orders; Whether to correct the mixed-issue mechanism is determined based on the number of associated work orders.

2. The service order allocation method based on context awareness according to claim 1, characterized in that, The estimated processing time for a single processing terminal for a single work order type is the average processing time for the corresponding work order type in historical data. A single technical preference corresponds to several work order types.

3. The context-aware service order allocation method according to claim 2, characterized in that, The process of identifying the average rate of change of time for each technical bias to determine whether the allocation of work orders is appropriate includes, The average time consumption of each work order corresponding to a single technical bias is determined within the preset control period to obtain the technical time consumption. Based on the time consumption of each technology for each preset control duration, determine the time-technology consumption curve for a single technology bias, determine the slope of the time-technology consumption curve at the current time node, and obtain the average time consumption change rate for a single technology bias. Obtain the maximum value among the average time-consuming change rates of each technology bias to obtain the maximum change rate; When the maximum change rate exceeds the preset change rate, the work order allocation is identified as abnormal. The work order allocation parameters are adjusted based on the abnormal time dispersion, including adjusting the rhythm cycle duration or correcting the work order depth.

4. The context-aware service order allocation method according to claim 3, characterized in that, The process of adjusting work order allocation parameters based on abnormal time consumption dispersion includes: Identify the abnormal time-consuming events for a single processing end, calculate the time interval between each adjacent abnormal time-consuming event, calculate the variance of each time interval, and obtain the abnormal time-consuming dispersion. Determine the minimum value of the abnormal time distribution at each processing end to obtain the minimum distribution; When the minimum dispersion amount is less than or equal to the preset dispersion amount, the lag allocation of the rhythm cycle for each processing end is performed, and the duration of the rhythm cycle is adjusted based on the dispersion level. When the minimum dispersion amount is greater than the preset dispersion amount, the work order depth of each work order is corrected based on the maximum change rate and the technical bias corresponding to the maximum change rate.

5. The context-aware service order allocation method according to claim 4, characterized in that, The process of performing lag allocation for the rhythm cycles of each processing terminal includes, The difference between the actual processing time and the estimated processing time for a single work order at a single processing terminal is determined to obtain the time deviation. Determine the time-duration deviation curve for a single processing end. When the slope of the time-duration deviation curve is lower than the preset trough slope, determine the rhythm start node for a single user at the corresponding time node, and perform lag allocation within the rhythm cycle.

6. The context-aware service order allocation method according to claim 5, characterized in that, The duration of the rhythm cycle is adjusted based on the magnitude of the dispersion, where... The dispersion magnitude is the number of abnormal time dispersions that are less than the preset dispersion magnitude. The increase in rhythm cycle duration is positively correlated with the magnitude of dispersion.

7. The context-aware service order allocation method according to claim 6, characterized in that, The process of adjusting work order depth based on the maximum change rate includes: Obtain the work order submission frequency of the corresponding user who submitted the work order, and adjust the work order depth based on the work order submission frequency; The increase in work order depth is positively correlated with the frequency of work order submission; The increase in work order depth is positively correlated with the maximum change rate; The standard time for a single work order is the product of the initial standard time and the work order depth.

8. The context-aware service order allocation method according to claim 7, characterized in that, After completing the work order depth correction, determine whether to perform associated work order identification based on the influx of work orders, including: The total number of work orders within the current preset control period is used to determine the work order inflow. When the number of incoming work orders exceeds the preset number of incoming work orders, perform associated work order identification.

9. The service order allocation method based on context awareness according to claim 8, characterized in that, The process of determining whether to correct the mixed-issue mechanism based on the number of associated work order groups includes: When the number of associated work order groups exceeds the preset number of impacts, determine the proportion of mixed transmissions in the correction mixed transmission mechanism; The increase in the proportion of mixed-issue work is positively correlated with the number of related work order groups.

10. A service order allocation system using the service order allocation method according to any one of claims 1-9, characterized in that, include: The work order recognition module is used to determine the work order type, corresponding technical bias, and standard time consumption of each work order based on the work order text. The processing module includes several processing terminals for processing each work order, a processing database for storing the estimated processing time of each processing terminal for each work order type, and a scoring statistics unit for determining the processing score of each processing terminal for each technical bias based on the estimated processing time. The allocation module is connected to the work order identification module and the processing module respectively, and is used to allocate each work order to each processing terminal; The allocation monitoring module is connected to the work order identification module, the processing module and the allocation module respectively. It is used to determine whether the allocation of the work order is qualified based on the average time change rate of each technical bias. When it is determined that the allocation of each work order is abnormal, the work order allocation parameters are adjusted based on the abnormal time dispersion, including the adjustment rhythm cycle duration of each processing end, or the work order depth of each work order. The work order analysis module is connected to the allocation monitoring module and the work order identification module respectively, and is used to determine whether to perform associated work order identification based on the influx of work orders. The work order processing module is connected to the work order identification module, the processing module, the allocation module, the allocation monitoring module, and the work order analysis module, respectively, and is used to determine whether to correct the mixed-issue mechanism based on the number of associated work orders.

Images