Intelligent scheduling method and device for insurance industry call center and computer equipment

Abstract

The invention relates to an intelligent scheduling method and device for an insurance industry call center and computer equipment. The method comprises the following steps: acquiring historical traffic information and telephone seat information of each area of an insurance industry call center, and identifying incoming call information time feature information and incoming call coordination information of each historical period of time of each area based on each piece of historical traffic information; for each area, based on the incoming call information and the time characteristic information of each historical time period of the area, predicting telephone traffic prediction information of the area in a future time period through an incoming call time sequence prediction model, and based on telephone seat information of the area and incoming call coordination information of each historical time period, identifying telephone traffic processing capability information of the area; and based on the telephone traffic prediction information of the region in the future time period and the telephone traffic processing capability information of the region, generating a telephone traffic processing scheduling table of the region in the future time period through a scheduling planning strategy. By adopting the method, the intelligent scheduling efficiency of the insurance industry call center can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of financial insurance services, and in particular to an intelligent scheduling method, device and computer equipment for a call center in the insurance industry. Background Art

[0002] At present, the call center of the insurance industry mainly relies on outsourced scheduling software. After analyzing the trend of call volume, it schedules shifts according to preset simple rules. The current scheduling method cannot fully match the personalized needs and service capabilities of the target area, and requires a lot of manual adjustments to meet the requirements of personnel management and agent satisfaction. With the development of technology and the continuous pursuit of operational efficiency by enterprises, the future scheduling system will not only rely on basic scheduling functions, but will integrate automation, intelligence and employee experience to make it more intelligent, humane and efficient. Therefore, how to improve the automation, intelligence and efficiency of typesetting is the current research focus.

[0003] In the existing technical solutions, the scheduling of insurance industry call centers is mainly based on the trend of historical operators to predict future call volume. The scheduling administrator makes a lot of manual adjustments based on factors such as vacations and business activities to make the call volume more in line with the business development of the destination area. Then, the shift cycle rules are set to schedule the schedule, and then the final schedule is manually adjusted according to the personalized demands of the seats. However, due to the low accuracy of manual trend prediction and the poor rationality of scheduling, the manual adjustment content angle reduces the scheduling timeliness, resulting in low efficiency of intelligent scheduling for insurance industry call centers. Summary of the invention

[0004] Based on this, it is necessary to provide an intelligent scheduling method, device, computer equipment, computer-readable storage medium and computer program product for an insurance industry call center in response to the above technical problems.

[0005] In a first aspect, the present application provides an intelligent scheduling method for a call center in the insurance industry, comprising:

[0006] Obtain historical call volume information of each region of the insurance industry call center and telephone agent information of each region, and based on the historical call volume information, identify call information of each historical time period of each region, time feature information of each historical time period of each region, and call coordination information of each historical time period of each region;

[0007] For each region, based on the incoming call information of each historical period of the region and the time characteristic information of each historical period of the region, the call volume forecast information of the region in the future period is predicted by using the incoming call timing prediction model, and based on the telephone seat information of the region and the incoming call coordination information of each historical period of the region, the call handling capacity information of the region is identified;

[0008] Based on the traffic volume forecast information of the area in the future time period and the traffic processing capacity information of the area, a traffic processing schedule for the area in the future time period is generated through a scheduling planning strategy.

[0009] Optionally, the identifying, based on the historical traffic volume information, the incoming call information of each historical time period of each area, the time feature information of each historical time period of each area, and the incoming call coordination information of each historical time period of each area includes:

[0010] For each region, splitting the sub-historical traffic volume information of the region into sub-historical information of each historical period, and for each historical period, identifying the call volume distribution information of the historical period and the call scheduling information of the historical period based on the sub-historical information of the historical period;

[0011] Based on the call volume distribution information of the historical period, generating a call distribution curve of the historical period, and based on the call scheduling information of the historical period, identifying the scheduling volume of each call scheduling area of ​​the historical period;

[0012] Based on the dispatch amount of each incoming call dispatch area in the historical period, generate the incoming call dispatch distribution information of the area in the historical period, and based on the regional time feature distribution information of the time area and the incoming call dispatch record information of the time area, identify the time feature information of the historical period and the incoming call dispatch reason of the historical period;

[0013] The incoming call distribution curve of the historical period is used as the incoming call information of the historical period, and the incoming call scheduling distribution information of the historical period and the incoming call scheduling reason of the historical period are used as the incoming call coordination information of the historical period.

[0014] Optionally, the incoming call timing prediction model includes a sub-incoming call timing prediction model of each time type, and based on the incoming call information of each historical time period of the area, the time feature information of each historical time period of the area, and the incoming call coordination information of each historical time period of the area, predicting the traffic volume prediction information of the area in the future time period through the incoming call timing prediction model includes:

[0015] Based on the time characteristic information of each of the historical periods, the time type corresponding to each historical period is identified, and the historical periods of the same time type are divided into the same time group to obtain a historical period group of each time type;

[0016] For each historical period group, based on the call distribution curve of each historical period in the historical period group, identifying the call trend information of each historical period in the sub-future period through a curve fitting algorithm;

[0017] Based on the call trend information of each historical period in the historical period group in the sub-future period, the sub-traffic forecast information of the historical period in the sub-future period is predicted through the sub-call timing prediction model of the time type corresponding to the historical period group, and the sub-traffic forecast information of each historical period in the sub-future period is sorted according to the time sequence of each historical period to obtain the traffic forecast information of the area in the future period.

[0018] Optionally, the identifying the traffic handling capability information of the area based on the telephone seat information of the area and the call coordination information of each historical time period of the area includes:

[0019] Based on the telephone seat information of the area, identifying each call feature information of the area, and based on the call coordination information of each historical time period of the area, identifying the call scheduling preference information of the area;

[0020] Based on the regional time characteristic distribution information of the time zone, the occurrence frequency of the incoming call scheduling preference information of the zone is identified, and based on the traffic characteristic information of each zone and the occurrence frequency of the incoming call scheduling preference information of the zone, the sub-traffic handling capacity information of the zone in each time type is calculated by a traffic handling capacity algorithm;

[0021] The sub-traffic processing capability information of all time types of the area is used as the traffic care capability information of the area.

[0022] Optionally, the generating a call processing schedule for the area in the future time period based on the call volume forecast information of the area in the future time period and the call processing capacity information of the area through a scheduling planning strategy includes:

[0023] Based on the sub-traffic volume forecast information of the historical time period of each time type in the sub-future time period and the sub-traffic processing capacity information of each time type, an initial traffic schedule for each sub-future time period of the area is generated through a scheduling planning strategy;

[0024] Based on the initial traffic schedule of each sub-future time period, the time type corresponding to each sub-future time period, and the sub-traffic processing capacity information of each time type, the scheduling rationality of each sub-future time period is evaluated through a scheduling rationality evaluation strategy;

[0025] In the case where there are abnormal sub-future time periods whose scheduling rationality is lower than the preset scheduling rationality threshold, each of the abnormal sub-future time periods will be replaced by each of the sub-future time periods, and the execution will be returned to the step of generating an initial traffic schedule for each sub-future time period in the area through a scheduling planning strategy based on the sub-traffic forecast information of the historical time periods of each of the time types and the sub-traffic processing capacity information of each of the time types, until there are no abnormal sub-future time periods whose scheduling rationality is lower than the preset scheduling rationality threshold, and the initial traffic schedule for each sub-future time period obtained in each iteration will be used as the traffic processing schedule for the area in the future time period.

[0026] Optionally, the generating of the initial traffic schedule for each sub-future time period of the area based on the sub-traffic volume forecast information of the historical time period of each time type in the sub-future time period and the sub-traffic processing capacity information of each time type through a scheduling planning strategy includes:

[0027] For each sub-future period, based on the sub-traffic volume forecast information of the sub-future period and the sub-traffic processing capacity information of the time type corresponding to the sub-future period, the manpower estimation value of the area in the sub-future period is calculated by a manpower estimation algorithm, and the personnel adjustment and leave information of the area in the sub-future period and the scheduling preference information of the area in the historical period corresponding to the sub-future period are obtained;

[0028] Based on the personnel adjustment information of the sub-future period and the shift preference information corresponding to the sub-future period, a shift distribution table of the sub-future period is generated through a shift generation strategy, and a manpower supply value corresponding to the shift distribution table is calculated;

[0029] Calculate the deviation between the manpower estimation value and the manpower supply value, and if the deviation is not zero, and based on the scheduling preference information corresponding to the sub-future period, adjust the shift distribution table of the sub-future period through a shift adjustment strategy to obtain a new shift distribution table;

[0030] The new shift distribution table is used to replace the previous shift distribution table, and the step of calculating the manpower supply value corresponding to the shift distribution table is returned to execute until the deviation value is zero, and the new shift distribution table obtained by the last iteration is used as the initial traffic schedule for the sub-future period.

[0031] In a second aspect, the present application also provides an intelligent scheduling device for a call center in the insurance industry, including:

[0032] An acquisition module is used to acquire historical call volume information of each region of the insurance industry call center and telephone agent information of each region, and based on the historical call volume information, identify the call information of each historical period of each region, the time feature information of each historical period of each region, and the call coordination information of each historical period of each region;

[0033] an identification module, for predicting the traffic volume prediction information of the region in the future time period based on the call information of each historical time period of the region and the time characteristic information of each historical time period of the region, and identifying the traffic handling capacity information of the region based on the telephone seat information of the region and the call coordination information of each historical time period of the region;

[0034] A generation module is used to generate a call processing schedule for the area in the future time period based on the call volume forecast information of the area in the future time period and the call processing capacity information of the area through a scheduling planning strategy.

[0035] Optionally, the acquisition module is specifically used to:

[0036] For each region, splitting the sub-historical traffic volume information of the region into sub-historical information of each historical period, and for each historical period, identifying the call volume distribution information of the historical period and the call scheduling information of the historical period based on the sub-historical information of the historical period;

[0037] Based on the call volume distribution information of the historical period, generating a call distribution curve of the historical period, and based on the call scheduling information of the historical period, identifying the scheduling volume of each call scheduling area of ​​the historical period;

[0038] Based on the dispatch amount of each incoming call dispatch area in the historical period, generate the incoming call dispatch distribution information of the area in the historical period, and based on the regional time feature distribution information of the time area and the incoming call dispatch record information of the time area, identify the time feature information of the historical period and the incoming call dispatch reason of the historical period;

[0039] The incoming call distribution curve of the historical period is used as the incoming call information of the historical period, and the incoming call scheduling distribution information of the historical period and the incoming call scheduling reason of the historical period are used as the incoming call coordination information of the historical period.

[0040] Optionally, the identification module is specifically used to:

[0041] Based on the time characteristic information of each of the historical periods, the time type corresponding to each historical period is identified, and the historical periods of the same time type are divided into the same time group to obtain a historical period group of each time type;

[0042] For each historical period group, based on the call distribution curve of each historical period in the historical period group, identifying the call trend information of each historical period in the sub-future period through a curve fitting algorithm;

[0043] Based on the call trend information of each historical period in the historical period group in the sub-future period, the sub-traffic forecast information of the historical period in the sub-future period is predicted through the sub-call timing prediction model of the time type corresponding to the historical period group, and the sub-traffic forecast information of each historical period in the sub-future period is sorted according to the time sequence of each historical period to obtain the traffic forecast information of the area in the future period.

[0044] Optionally, the identification module is specifically used to:

[0045] Based on the telephone seat information of the area, identifying each call feature information of the area, and based on the call coordination information of each historical time period of the area, identifying the call scheduling preference information of the area;

[0046] Based on the regional time characteristic distribution information of the time zone, the occurrence frequency of the incoming call scheduling preference information of the zone is identified, and based on the traffic characteristic information of each zone and the occurrence frequency of the incoming call scheduling preference information of the zone, the sub-traffic handling capacity information of the zone in each time type is calculated by a traffic handling capacity algorithm;

[0047] The sub-traffic processing capability information of all time types of the area is used as the traffic care capability information of the area.

[0048] Optionally, the generating module is specifically used for:

[0049] Based on the sub-traffic volume forecast information of the historical time period of each time type in the sub-future time period and the sub-traffic processing capacity information of each time type, an initial traffic schedule for each sub-future time period of the area is generated through a scheduling planning strategy;

[0050] Based on the initial traffic schedule of each sub-future time period, the time type corresponding to each sub-future time period, and the sub-traffic processing capacity information of each time type, the scheduling rationality of each sub-future time period is evaluated through a scheduling rationality evaluation strategy;

[0051] In the case where there are abnormal sub-future time periods whose scheduling rationality is lower than the preset scheduling rationality threshold, each of the abnormal sub-future time periods will be replaced by each of the sub-future time periods, and the execution will be returned to the step of generating an initial traffic schedule for each sub-future time period in the area through a scheduling planning strategy based on the sub-traffic forecast information of the historical time periods of each of the time types and the sub-traffic processing capacity information of each of the time types, until there are no abnormal sub-future time periods whose scheduling rationality is lower than the preset scheduling rationality threshold, and the initial traffic schedule for each sub-future time period obtained in each iteration will be used as the traffic processing schedule for the area in the future time period.

[0052] Optionally, the generating module is specifically used for:

[0053] For each sub-future period, based on the sub-traffic volume forecast information of the sub-future period and the sub-traffic processing capacity information of the time type corresponding to the sub-future period, the manpower estimation value of the area in the sub-future period is calculated by a manpower estimation algorithm, and the personnel adjustment and leave information of the area in the sub-future period and the scheduling preference information of the area in the historical period corresponding to the sub-future period are obtained;

[0054] Based on the personnel adjustment information of the sub-future period and the shift preference information corresponding to the sub-future period, a shift distribution table of the sub-future period is generated through a shift generation strategy, and a manpower supply value corresponding to the shift distribution table is calculated;

[0055] Calculate the deviation between the manpower estimation value and the manpower supply value, and if the deviation is not zero, and based on the scheduling preference information corresponding to the sub-future period, adjust the shift distribution table of the sub-future period through a shift adjustment strategy to obtain a new shift distribution table;

[0056] The new shift distribution table is used to replace the previous shift distribution table, and the step of calculating the manpower supply value corresponding to the shift distribution table is returned to execute until the deviation value is zero, and the new shift distribution table obtained by the last iteration is used as the initial traffic schedule for the sub-future period.

[0057] In a third aspect, the present application provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.

[0058] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0059] In a fifth aspect, the present application provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0060] The above-mentioned intelligent scheduling method, device and computer equipment of the insurance industry call center obtain the historical traffic volume information of each area of ​​the insurance industry call center and the telephone seat information of each area, and based on the historical traffic volume information, identify the incoming call information of each historical time period of each area, the time feature information of each historical time period of each area, and the incoming call coordination information of each historical time period of each area; for each area, based on the incoming call information of each historical time period of the area and the time feature information of each historical time period of the area, through the call timing prediction model, predict the traffic volume prediction information of the area in the future time period, and based on the telephone seat information of the area and the incoming call coordination information of each historical time period of the area, identify the traffic processing capacity information of the area; based on the traffic volume prediction information of the area in the future time period and the traffic processing capacity information of the area, generate the traffic processing schedule of the area in the future time period through the scheduling planning strategy. This solution conducts a comprehensive analysis of historical call volumes, and thus predicts the call volumes for future time periods from three perspectives: call information for each historical time period of historical call volume information, time characteristic information, and call coordination information, thereby improving the comprehensiveness of the prediction. This solution then predicts the call volumes for future time periods through an incoming call timing prediction model, thereby enabling the predicted call volumes for future time periods to comprehensively consider time characteristics and historical call volume information, thereby improving the accuracy of the predicted call volume prediction information for future time periods. Then, this solution analyzes the call handling capacity information of each region from the call coordination information and telephone agent information of each region in each historical time period, thereby improving the comprehensiveness of the analysis of the call handling capacity and call handling characteristics of each region. Then, based on the call handling capacity information of each region and the call volume forecast information of future time periods, the call handling schedule is generated through the scheduling planning strategy involved in this solution, so that the constructed call handling schedule can be more adapted to the call handling preferences and working rules of the region, thereby comprehensively improving the intelligent scheduling efficiency of the insurance industry call center. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0062] Figure 1 A flowchart of an intelligent scheduling method for a call center in the insurance industry in one embodiment;

[0063] Figure 2 A screenshot of the traffic forecast of a call center in the insurance industry in one embodiment;

[0064] Figure 3 This is a schematic diagram of a call processing schedule for an insurance industry call center in one embodiment;

[0065] Figure 4 A flowchart of an example of intelligent scheduling for a call center in the insurance industry in one embodiment;

[0066] Figure 5 It is a structural block diagram of an intelligent scheduling device for a call center in the insurance industry in one embodiment;

[0067] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0069] The intelligent scheduling method for the insurance industry call center provided in the embodiment of the present application can be applied to the application environment of the intelligent scheduling of the insurance industry call center. The method can be applied to a terminal, a server, or a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, laptops, medium-sized computers, etc. The terminal comprehensively analyzes the historical traffic volume, thereby predicting the traffic volume of the future time period from three perspectives: the call information of each historical time period of the historical traffic volume information, the time characteristic information, and the call coordination information, thereby improving the comprehensiveness of the prediction. Then, the scheme predicts the traffic volume of the future time period through the call timing prediction model, so that the predicted traffic volume of the future time period can comprehensively consider the time characteristics and the historical traffic volume information, thereby improving the accuracy of the predicted traffic volume prediction information of the predicted future time period. Then, this solution analyzes the call handling capacity information of each region from the call coordination information and telephone agent information of each region in each historical time period, thereby improving the comprehensiveness of the analysis of the call handling capacity and call handling characteristics of each region. Then, based on the call handling capacity information of each region and the call volume forecast information of future time periods, the call handling schedule is generated through the scheduling planning strategy involved in this solution, so that the constructed call handling schedule can be more adapted to the call handling preferences and working rules of the region, thereby comprehensively improving the intelligent scheduling efficiency of the insurance industry call center.

[0070] In an exemplary embodiment, Figure 1 As shown, a smart scheduling method for a call center in the insurance industry is provided, and the method is applied to a terminal as an example for explanation, including the following steps S101 to S103. Among them:

[0071] Step S101, obtain the historical call volume information of each area of ​​the insurance industry call center and the telephone seat information of each area, and based on the historical call volume information, identify the incoming call information of each historical time period in each area, the time feature information of each historical time period in each area, and the incoming call coordination information of each historical time period in each area.

[0072] In this embodiment, the terminal obtains the historical traffic volume information of each area from the traffic record information uploaded by each area, and obtains the telephone seat information of each area in response to the information upload operation of the call center manager of each area, wherein the area is obtained by manually splitting all the areas covered by the insurance industry, wherein the area can be divided into provinces or cities, etc. The historical traffic volume information of each area includes but is not limited to the sub-historical traffic volume information of each historical period, wherein each sub-historical traffic volume information is the distribution information of the incoming volume of the historical period, and the incoming call scheduling information, wherein the incoming volume distribution information is used to represent the distribution information obtained by distributing the incoming volume at each time point of the historical period in chronological order, and the incoming call scheduling information is the scheduling information for dispatching the incoming call information of the area to other areas for assistance in answering at each time point of the historical period. Among them, the historical time period is the time period of each same time interval in a time interval. For example, the time interval is 5 years, and the time interval is one month, then the historical time periods are Y year M month, ..., (Y-1) year (M-1) month, M month, (Y-2) year (M-1) month, ..., (Y-4) year M month. Among them, when the time period includes holidays, adjusted holidays, and major holidays, the time period needs to be marked. Then, based on the historical traffic information, the terminal identifies the incoming call information of each historical time period in each area, the time feature information of each historical time period in each area, and the incoming call coordination information of each historical time period in each area. Among them, the time feature information includes but is not limited to holiday features, first quarter features, second quarter features and other feature information. The specific identification process will be described in detail later.

[0073] Step S102, for each area, based on the incoming call information of each historical time period of the area and the time feature information of each historical time period of the area, the call volume forecast information of the area in the future time period is predicted through the incoming call timing prediction model, and based on the telephone seat information of the area and the incoming call coordination information of each historical time period of the area, the call processing capacity information of the area is identified.

[0074] In this embodiment, for each region, the terminal predicts the traffic volume forecast information of the region in the future time period based on the call information of each historical period of the region and the time feature information of each historical period of the region through the call sequence forecast model, and identifies the traffic handling capacity information of the region based on the telephone seat information of the region and the call coordination information of each historical period of the region. Among them, the call sequence forecast model includes a sub-call sequence forecast model of each time type, and each time type corresponds to a time feature information, and the time type includes but is not limited to holiday type, first quarter type, second quarter type and other time types. Then, among them, the sub-call sequence forecast model is a SARIMA time series forecast model. The specific forecast process will be described in detail later, and the telephone seat information includes but is not limited to the adjustment preference of the telephone seat in the region, the average time per call, the target connection rate, the shift preference employee skill proficiency and other information. The traffic handling capacity information is the value of the incoming volume processing per unit time of the region in different time types. The specific calculation process will be described in detail later.

[0075] Step S103, based on the traffic volume forecast information of the region in the future time period and the traffic processing capacity information of the region, a traffic processing schedule for the region in the future time period is generated through a scheduling planning strategy.

[0076] In this embodiment, the terminal generates a traffic processing schedule for the region in the future period based on the traffic volume forecast information of the region in the future period and the traffic processing capacity information of the region through the scheduling planning strategy. Among them, the scheduling planning strategy is a planning strategy for scheduling adjustment after scheduling based on the traffic margin forecast information and the traffic processing capacity. The specific planning process will be described in detail later.

[0077] Based on the above scheme, through comprehensive analysis of historical call volume, the call volume of future time periods is predicted from three angles: call information of each historical time period of historical call volume information, time characteristic information, and call coordination information, thereby improving the comprehensiveness of the prediction. Then, this scheme predicts the call volume of future time periods through the call sequence prediction model, so that the predicted call volume of future time periods can comprehensively consider the time characteristics and historical call volume information, thereby improving the accuracy of the predicted call volume prediction information of future time periods. Then, this solution analyzes the call handling capacity information of each region from the call coordination information and telephone agent information of each region in each historical time period, thereby improving the comprehensiveness of the analysis of the call handling capacity and call handling characteristics of each region. Then, based on the call handling capacity information of each region and the call volume forecast information of future time periods, the call handling schedule is generated through the scheduling planning strategy involved in this solution, so that the constructed call handling schedule can be more adapted to the call handling preferences and working rules of the region, thereby comprehensively improving the intelligent scheduling efficiency of the insurance industry call center.

[0078] Optionally, based on each historical traffic volume information, the call information of each historical time period of each area, the time feature information of each historical time period of each area, and the call coordination information of each historical time period of each area are identified, including: for each area, the sub-historical traffic volume information of the area is split into sub-historical information of each historical time period, and for each historical time period, based on the sub-historical information of the historical time period, the call volume distribution information of the historical time period and the call scheduling information of the historical time period are identified; based on the call volume distribution information of the historical time period, the call distribution curve of the historical time period is generated, and based on the call volume distribution information of the historical time period, the call coordination information of the historical time period is generated; Call dispatch information, identifying the dispatch amount of each incoming call dispatch area in the historical period; based on the dispatch amount of each incoming call dispatch area in the historical period, generating the incoming call dispatch distribution information of the area in the historical period, and based on the regional time feature distribution information of the time area in the historical period, and the incoming call dispatch record information of the time area, identifying the time feature information of the historical period, and the incoming call dispatch reason of the historical period; using the incoming call distribution curve of the historical period as the incoming call information of the historical period, and using the incoming call dispatch distribution information of the historical period and the incoming call dispatch reason of the historical period as the incoming call coordination information of the historical period.

[0079] In this embodiment, for each area, the terminal divides the sub-historical traffic volume information of the area into sub-historical information of each historical period, and for each historical period, based on the sub-historical information of the historical period, identifies the call volume distribution information of the historical period and the call scheduling information of the historical period. Among them, the causes of the call scheduling information include but are not limited to the causes caused by night calls, sudden typhoons, earthquakes and other disasters.

[0080] Then, based on the call volume distribution information of the historical period, the terminal generates a call distribution curve of the historical period through a curve fitting algorithm, and identifies the dispatch volume of each call dispatch area of ​​the historical period based on the call dispatch information of the historical period. The dispatch volume of each call dispatch area of ​​the historical period is the total dispatch volume of each call dispatch area of ​​the historical period.

[0081] Afterwards, the terminal generates the call dispatch distribution information of the region in the historical period based on the dispatch volume of each call dispatch area in the historical period, and identifies the time feature information of the historical period and the call dispatch reason of the historical period based on the regional time feature distribution information of the time area of ​​the historical period and the call dispatch record information of the time area. Among them, the regional time feature distribution information includes the time feature of each historical period, and the time feature of each historical period is used to characterize the influencing factors of the historical period on the traffic volume. For example, holiday feature information and adjustment feature information will produce a call dispatch situation with fewer staff shifts and more incoming calls. The third quarter feature information and the fourth quarter feature information involve year-end audits and year-end summaries, so the number of incoming calls will increase, and call dispatch situations will also be generated. The call dispatch record information, while recording the daily incoming calls, also includes the dispatch influencing information such as daily weather, climate, and emergencies. In the case of bad weather or sudden emergencies, call dispatch situations will be generated. Therefore, the terminal uses the time feature information and the scheduling impact information of the incoming call scheduling record information as the call scheduling reason of the incoming call scheduling in each historical period, which is convenient for the recognition accuracy of each incoming call scheduling reason and the scheduling prediction accuracy. Finally, the terminal uses the incoming call distribution curve of the historical period as the incoming call information of the historical period, and uses the incoming call scheduling distribution information of the historical period and the incoming call scheduling reason of the historical period as the incoming call coordination information of the historical period.

[0082] Based on the above scheme, a comprehensive analysis is performed through the call volume distribution and call scheduling information to identify the call distribution curve and call coordination information for each historical period, thereby improving the comprehensiveness and accuracy of call distribution and call coordination.

[0083] Optionally, a call sequence prediction model includes sub-call sequence prediction models for each time type, based on the call information of each historical time period of the region, the time characteristic information of each historical time period of the region, and the call coordination information of each historical time period of the region, and predicts the call volume prediction information of the region in the future time period through the call sequence prediction model, including: based on the time characteristic information of each historical time period, identifying the time type corresponding to each historical time period, and dividing the historical time periods of the same time type into the same time group to obtain a historical time period group of each time type; for each historical time period group, based on the call distribution curve of each historical time period in the historical time period group, identifying the call trend information of each historical time period in the sub-future time period through a curve fitting algorithm; based on the call trend information of each historical time period in the sub-future time period of the historical time period group, predict the sub-traffic prediction information of the historical time period in the sub-future time period through the sub-call sequence prediction model of the time type corresponding to the historical time period group, and sort the sub-traffic prediction information of each historical time period in the sub-future time period according to the time sequence of each historical time period to obtain the call volume prediction information of the region in the future time period.

[0084] In this embodiment, the terminal identifies the time type corresponding to each historical period based on the time feature information of each historical period, and divides the historical periods of the same time type into the same time group to obtain a historical period group of each time type. Each time feature information corresponds to a time type, and the terminal divides the historical periods of the same time type into the same historical period group.

[0085] For each historical period group, the terminal identifies the call trend information of each historical period in the sub-future period based on the call distribution curve of each historical period in the historical period group through a curve fitting algorithm. Then, based on the call trend information of each historical period in the sub-future period of the historical period group, the terminal predicts the sub-traffic forecast information of the historical period in the sub-future period through the sub-call sequence forecast model of the time type corresponding to the historical period group, and sorts the sub-traffic forecast information of each historical period in the sub-future period according to the time sequence of each historical period to obtain the traffic forecast information of the area in the future period. Figure 2 As shown, the traffic volume forecast information of part of the future time period is predicted, and the traffic volume forecast information includes the traffic volume forecast value at each time point of each day in the future time period.

[0086] Based on the above scheme, the call volume of each future sub-time period is predicted through the sub-incoming call time series prediction model of each time type, which improves the accuracy and comprehensiveness of the prediction.

[0087] Optionally, based on the telephone seat information of the region and the call coordination information of each historical time period of the region, the call handling capability information of the region is identified, including: based on the telephone seat information of the region, identifying the call feature information of each region, and based on the call coordination information of each historical time period of the region, identifying the call scheduling preference information of the region; identifying the frequency of occurrence of the call scheduling preference information of the region based on the regional time feature distribution information of the time zone, and based on the call feature information of each region and the frequency of occurrence of the call scheduling preference information of the region, calculating the sub-call handling capability information of the region in each time type through a call handling capability algorithm; using the sub-call handling capability information of all time types of the region as the call care capability information of the region.

[0088] In this embodiment, the terminal identifies the call feature information of each area based on the telephone seat information of the area, and identifies the call scheduling preference information of the area based on the call coordination information of each historical period of the area. The call scheduling preference information includes the preferred scheduling area of ​​the area and the preferred scheduling reason of the area. The preferred scheduling area is the average scheduling amount greater than the average scheduling amount threshold preset in the terminal, and the preferred scheduling reason is the scheduling reason of the number of times the scheduling is preset in the terminal.

[0089] Then, based on the regional time feature distribution information of the time zone, the terminal identifies the frequency of occurrence of the incoming call scheduling preference information of the region, and based on the traffic feature information of each region and the frequency of occurrence of the incoming call scheduling preference information of the region, the terminal calculates the sub-traffic handling capacity information of the region in each time type through the traffic handling capacity algorithm. Among them, the regional time feature distribution information of the time zone includes the occurrence time point of each scheduling reason of each time type of the time zone. Then, the terminal divides the number of occurrences of the preference scheduling reasons contained in each historical time period corresponding to each time type by the number of occurrences of all scheduling reasons in all historical time periods corresponding to each time type, and obtains the frequency of occurrence of each preference scheduling reason of each time type. Among them, the calculation formula of the traffic handling capacity algorithm is: traffic handling capacity = total traffic volume of the historical time period - frequency of occurrence of incoming call scheduling preference information * scheduling traffic volume of the historical time period.

[0090] Finally, the terminal uses the sub-traffic processing capability information of all time types of the area as the traffic care capability information of the area.

[0091] Based on the above solution, by calculating the sub-traffic handling capacity information of each event type from the perspective of time type, the recognition accuracy and comprehensiveness of the correlation information between the traffic handling capacity of the area and the time type are improved.

[0092] Optionally, based on the traffic volume forecast information of the region in the future time period and the traffic processing capacity information of the region, a traffic processing schedule for the region in the future time period is generated through a scheduling planning strategy, including: based on the sub-traffic volume forecast information of the historical time period of each time type in the sub-future time period and the sub-traffic processing capacity information of each time type, an initial traffic schedule for each sub-future time period of the region is generated through a scheduling planning strategy; based on the initial traffic schedule for each sub-future time period, the time type corresponding to each sub-future time period, and the sub-traffic processing capacity information of each time type, a scheduling rationality evaluation strategy is used to evaluate the traffic scheduling of each sub-future time period. Scheduling rationality; in the case of abnormal sub-future time periods whose scheduling rationality is lower than the preset scheduling rationality threshold, each abnormal sub-future time period will be replaced by each sub-future time period, and the execution will be returned to the sub-traffic forecast information in the sub-future time period based on the historical time period of each time type, and the sub-traffic processing capacity information of each time type, and the initial traffic scheduling step of each sub-future time period in the area will be generated through the scheduling planning strategy, until there are no abnormal sub-future time periods whose scheduling rationality is lower than the preset scheduling rationality threshold, and the initial traffic scheduling of each sub-future time period obtained in each iteration will be used as the traffic processing scheduling of the area in the future time period.

[0093] In this embodiment, the terminal generates the initial traffic schedule for each sub-future period of the region through the scheduling planning strategy based on the sub-traffic volume forecast information of the historical period of each time type in the sub-future period and the sub-traffic processing capacity information of each time type. Among them, the scheduling planning strategy is a strategy for scheduling planning based on the manpower measurement value of the region, the scheduling preference of the region, and the sub-traffic processing capacity information of each event type in the region. The specific planning method of the scheduling planning strategy will be described in detail later.

[0094] Then, the terminal evaluates the scheduling rationality of each sub-future time period based on the initial traffic schedule of each sub-future time period, the time type corresponding to each sub-future time period, and the sub-traffic processing capacity information of each time type through the scheduling rationality evaluation strategy. Specifically, the terminal identifies the shift distribution information, shift distribution frequency, average manpower demand value and other information of each initial traffic schedule based on the initial traffic schedule of each sub-future time period, and the scheduling rationality evaluation strategy includes the evaluation value corresponding to each shift distribution range, the evaluation value corresponding to the shift distribution frequency, and the evaluation value corresponding to the average manpower demand value. The terminal identifies the first evaluation value corresponding to each initial traffic schedule based on the shift distribution information, shift distribution frequency, average manpower demand value and other information of each initial traffic schedule, and the second evaluation value corresponding to the deviation value range to which the deviation value between the time type of the sub-future time period corresponding to each initial traffic schedule and the shift distribution frequency of each initial traffic schedule belongs. Then, the terminal sums each first evaluation value with each second evaluation value respectively to obtain the scheduling rationality of each sub-future time period.

[0095] In the case of abnormal sub-future time periods whose scheduling rationality is lower than the preset scheduling rationality threshold, each abnormal sub-future time period is replaced by each sub-future time period, and the sub-traffic forecast information of the historical time period of each time type in the sub-future time period and the sub-traffic processing capacity information of each time type are returned to generate the initial traffic schedule of each sub-future time period of the region through the scheduling planning strategy, until there is no abnormal sub-future time period whose scheduling rationality is lower than the preset scheduling rationality threshold, and the initial traffic schedule of each sub-future time period obtained in each iteration is used as the traffic processing schedule of the region in the future time period. Among them, if Figure 3 As shown, this is an example diagram of a call processing schedule. The schedule generated by this solution not only includes the schedules for each time period, but also includes a summary display of the daily schedule volume, which improves the call center's awareness of future schedules.

[0096] Based on the above scheme, after considering the sub-traffic forecast information and sub-traffic processing capacity information, the scheduling planning strategy involved in this scheme is used to perform intelligent scheduling planning, which improves the rationality of the scheduling planning and its adaptability to the region. Then, through the scheduling rationality evaluation, the initial traffic schedule obtained by the intelligent scheduling is iteratively optimized to avoid the inefficiency and low accuracy of manual adjustment. Thus, the efficiency and accuracy of the traffic processing schedule for each region in the future period are comprehensively improved.

[0097] Optionally, based on the sub-traffic forecast information of the historical time periods of each time type in the sub-future time periods, and the sub-traffic processing capacity information of each time type, an initial traffic schedule for each sub-future time period of the region is generated through a scheduling planning strategy, including: for each sub-future time period, based on the sub-traffic forecast information of the sub-future time period, and the sub-traffic processing capacity information of the time type corresponding to the sub-future time period, a manpower measurement algorithm is used to calculate the manpower measurement value of the region in the sub-future time period, and obtain the personnel adjustment and leave information of the region in the sub-future time period, and the scheduling preference information of the historical time period corresponding to the sub-future time period; based on the personnel adjustment and leave information of the sub-future time period, and the scheduling preference information corresponding to the sub-future time period, generate a shift distribution table for the sub-future time period through the shift generation strategy, and calculate the manpower supply value corresponding to the shift distribution table; calculate the deviation value between the manpower measurement value and the manpower supply value, and when the deviation value is not zero, and based on the scheduling preference information corresponding to the sub-future time period, adjust the shift distribution table of the sub-future time period through the shift adjustment strategy to obtain a new shift distribution table; replace the shift distribution table with the new shift distribution table, and return to execute the step of calculating the manpower supply value corresponding to the shift distribution table, until the deviation value is zero, and use the new shift distribution table obtained by the last iteration as the initial traffic scheduling table for the sub-future time period.

[0098] In this embodiment, for each sub-future time period, the terminal calculates the manpower estimation value of the area in the sub-future time period through a manpower estimation algorithm based on the sub-traffic prediction information of the sub-future time period and the sub-traffic processing capacity information of the time type corresponding to the sub-future time period.

[0099] The manpower calculation algorithm is: Required manpower (i.e. manpower calculation value) = 1 + (Traffic volume forecast value * target connection rate * average time per call (seconds)) / 30 * 60 .

[0100] In the above formula, To round up, the traffic volume forecast value, target connection rate, and average time per call (in seconds) are taken as the minimum time unit of 30 minutes. In some areas, if there is a large deviation in employee skills or a large deviation between historical data and current data, the manpower estimation method can increase the weight value in the original algorithm, that is, required manpower = 1 + (Traffic volume forecast value * target connection rate * average time per call (seconds)) / 30 * 60 *a.

[0101] In the above formula, a is the manually added weight value, which ensures that the required manpower measurement value is consistent with the current situation in the area.

[0102] Then, the terminal obtains the personnel adjustment information of the area in the sub-future period and the scheduling preference information of the historical period corresponding to the sub-future period; based on the personnel adjustment information of the sub-future period and the scheduling preference information corresponding to the sub-future period, the shift distribution table of the sub-future period is generated through the shift generation strategy, and the manpower supply value corresponding to the shift distribution table is calculated. Among them, the shift generation strategy includes each adjustment information and the shift distribution template corresponding to each scheduling preference information. Then, the terminal adapts the personnel adjustment information of the area in the sub-future period and the target shift distribution template corresponding to the scheduling preference information of the area in the historical period corresponding to the sub-future period in each shift distribution template, and obtains the shift distribution table of the sub-future period. Among them, the manpower supply value is the total manpower value that can be supplied in the shift distribution table.

[0103] Afterwards, the terminal calculates the deviation between the manpower calculation value and the manpower supply value, and when the deviation value is not zero, based on the scheduling preference information corresponding to the sub-future period, the terminal adjusts the shift distribution table of the sub-future period through the shift adjustment strategy to obtain a new shift distribution table. The shift adjustment strategy includes different scheduling preference information and the shift distribution adjustment logic corresponding to the personnel adjustment information. Then, in the shift distribution table, the terminal adjusts the shift distribution table through the shift distribution adjustment logic to obtain a new shift distribution table, wherein the shift adjustment strategy includes different scheduling preference ranges, the corresponding relationship between the adjustment information range and the shift distribution adjustment logic. The terminal determines the shift distribution adjustment logic of the region in the sub-future period by identifying the personnel adjustment information of the region in the sub-future period The personnel adjustment information belongs to the range, and the scheduling preference information of the region in the historical period corresponding to the sub-future period belongs to the scheduling preference range.

[0104] Finally, the terminal returns to execute the step of calculating the manpower supply value corresponding to the shift distribution table until the deviation value is zero, and uses the new shift distribution table obtained by the last iteration as the initial call schedule for the sub-future period.

[0105] Based on the above solution, the shift preferences and adjustment information of each area are used to adapt the corresponding shift distribution adjustment logic of each area, thereby improving the adaptability of the initial call schedule to the area and the scheduling accuracy.

[0106] This application also provides an example of intelligent scheduling for a call center in the insurance industry, such as Figure 4 As shown, the specific processing process includes the following steps:

[0107] Step S401, obtaining historical call volume information of each area of ​​the insurance industry call center and telephone agent information of each area.

[0108] Step S402, for each area, split the sub-historical traffic volume information of the area into sub-historical information of each historical period, and for each historical period, identify the call volume distribution information of the historical period and the call scheduling information of the historical period based on the sub-historical information of the historical period.

[0109] Step S403, based on the incoming call volume distribution information of the historical period, generate the incoming call distribution curve of the historical period, and based on the incoming call scheduling information of the historical period, identify the scheduling volume of each incoming call scheduling area of ​​the historical period.

[0110] Step S404, based on the scheduling amount of each incoming call scheduling area in the historical period, generate the incoming call scheduling distribution information of the area in the historical period, and based on the regional time feature distribution information of the time area in the historical period, and the incoming call scheduling record information of the time area, identify the time feature information of the historical period, and the incoming call scheduling reason of the historical period.

[0111] Step S405: using the incoming call distribution curve of the historical period as the incoming call information of the historical period, and using the incoming call scheduling distribution information of the historical period and the incoming call scheduling reason of the historical period as the incoming call coordination information of the historical period.

[0112] Step S406, based on the time feature information of each historical period, identify the time type corresponding to each historical period, and divide the historical periods of the same time type into the same time group to obtain a historical period group of each time type.

[0113] Step S407, for each historical period group, based on the call distribution curve of each historical period in the historical period group, identify the call trend information of each historical period in the sub-future period through a curve fitting algorithm.

[0114] Step S408, based on the incoming call trend information of each historical period in the sub-future period of the historical period group, predict the sub-traffic forecast information of the historical period in the sub-future period through the sub-incoming call timing prediction model of the time type corresponding to the historical period group, and sort the sub-traffic forecast information of each historical period in the sub-future period according to the time sequence of each historical period to obtain the traffic forecast information of the area in the future period.

[0115] Step S409, based on the telephone agent information of the area, identifying the call feature information of each area, and based on the call coordination information of each historical time period of the area, identifying the call scheduling preference information of the area.

[0116] Step S410, based on the regional time characteristic distribution information of the time zone, identifies the frequency of occurrence of the call scheduling preference information of the region, and based on the traffic characteristic information of the region and the frequency of occurrence of the call scheduling preference information of the region, calculates the sub-traffic processing capacity information of the region in each time type through the traffic processing capacity algorithm.

[0117] Step S411: The sub-traffic processing capability information of all time types of the area is used as the traffic care capability information of the area.

[0118] Step S412, for each sub-future time period, based on the sub-traffic forecast information of the sub-future time period and the sub-traffic processing capacity information of the time type corresponding to the sub-future time period, the manpower estimation algorithm is used to calculate the manpower estimation value of the area in the sub-future time period, and obtain the personnel adjustment information of the area in the sub-future time period and the scheduling preference information of the area in the historical time period corresponding to the sub-future time period.

[0119] Step S413, based on the personnel adjustment information of the sub-future period and the scheduling preference information corresponding to the sub-future period, a shift distribution table of the sub-future period is generated through a shift generation strategy, and the manpower supply value corresponding to the shift distribution table is calculated.

[0120] Step S414, calculate the deviation between the manpower estimation value and the manpower supply value, and when the deviation value is not zero, and based on the scheduling preference information corresponding to the sub-future time period, adjust the shift distribution table of the sub-future time period through the shift adjustment strategy to obtain a new shift distribution table.

[0121] Step S415, replace the shift distribution table with the new shift distribution table, and return to execute the step of calculating the manpower supply value corresponding to the shift distribution table, until the deviation value is zero, and use the new shift distribution table obtained by the last iteration as the initial call schedule for the sub-future period.

[0122] Step S416, based on the initial traffic schedule of each sub-future time period, the time type corresponding to each sub-future time period, and the sub-traffic processing capacity information of each time type, the scheduling rationality of each sub-future time period is evaluated through the scheduling rationality evaluation strategy.

[0123] Step S417, in the case where there are abnormal sub-future time periods whose scheduling rationality is lower than the preset scheduling rationality threshold, each abnormal sub-future time period is replaced by each sub-future time period, and the execution is returned to the step of generating the initial traffic schedule for each sub-future time period in the area through the scheduling planning strategy based on the sub-traffic forecast information of the historical time period of each time type in the sub-future time period and the sub-traffic processing capacity information of each time type, until there are no abnormal sub-future time periods whose scheduling rationality is lower than the preset scheduling rationality threshold, and the initial traffic schedule for each sub-future time period obtained in each iteration is used as the traffic processing schedule for the area in the future time period.

[0124] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0125] Based on the same inventive concept, the embodiment of the present application also provides an intelligent scheduling device for an insurance industry call center for implementing the intelligent scheduling method for an insurance industry call center involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of the intelligent scheduling device for one or more insurance industry call centers provided below can refer to the limitations of the intelligent scheduling method for insurance industry call centers above, and will not be repeated here.

[0126] In an exemplary embodiment, Figure 5 As shown, an intelligent scheduling device for a call center in the insurance industry is provided, comprising: an acquisition module 510, an identification module 520 and a generation module 530, wherein:

[0127] The acquisition module 510 is used to acquire the historical traffic volume information of each area of ​​the insurance industry call center and the telephone seat information of each area, and based on the historical traffic volume information, identify the call information of each historical period of each area, the time feature information of each historical period of each area, and the call coordination information of each historical period of each area;

[0128] The identification module 520 is used to predict the traffic volume prediction information of the region in the future time period based on the incoming call information of each historical time period of the region and the time feature information of each historical time period of the region through the incoming call time series prediction model for each region, and to identify the traffic handling capacity information of the region based on the telephone seat information of the region and the incoming call coordination information of each historical time period of the region;

[0129] The generation module 530 is used to generate a traffic processing schedule for the area in the future time period based on the traffic volume prediction information of the area in the future time period and the traffic processing capacity information of the area through a scheduling planning strategy.

[0130] Optionally, the acquisition module 510 is specifically configured to:

[0131] For each region, splitting the sub-historical traffic volume information of the region into sub-historical information of each historical period, and for each historical period, identifying the call volume distribution information of the historical period and the call scheduling information of the historical period based on the sub-historical information of the historical period;

[0132] Based on the call volume distribution information of the historical period, generating a call distribution curve of the historical period, and based on the call scheduling information of the historical period, identifying the scheduling volume of each call scheduling area of ​​the historical period;

[0133] Based on the dispatch amount of each incoming call dispatch area in the historical period, generate the incoming call dispatch distribution information of the area in the historical period, and based on the regional time feature distribution information of the time area and the incoming call dispatch record information of the time area, identify the time feature information of the historical period and the incoming call dispatch reason of the historical period;

[0134] The incoming call distribution curve of the historical period is used as the incoming call information of the historical period, and the incoming call scheduling distribution information of the historical period and the incoming call scheduling reason of the historical period are used as the incoming call coordination information of the historical period.

[0135] Optionally, the identification module 520 is specifically configured to:

[0136] Based on the time characteristic information of each of the historical periods, the time type corresponding to each historical period is identified, and the historical periods of the same time type are divided into the same time group to obtain a historical period group of each time type;

[0137] For each historical period group, based on the call distribution curve of each historical period in the historical period group, identifying the call trend information of each historical period in the sub-future period through a curve fitting algorithm;

[0138] Based on the call trend information of each historical period in the historical period group in the sub-future period, the sub-traffic forecast information of the historical period in the sub-future period is predicted through the sub-call timing prediction model of the time type corresponding to the historical period group, and the sub-traffic forecast information of each historical period in the sub-future period is sorted according to the time sequence of each historical period to obtain the traffic forecast information of the area in the future period.

[0139] Optionally, the identification module 520 is specifically configured to:

[0140] Based on the telephone seat information of the area, identifying each call feature information of the area, and based on the call coordination information of each historical time period of the area, identifying the call scheduling preference information of the area;

[0141] Based on the regional time characteristic distribution information of the time zone, the occurrence frequency of the incoming call scheduling preference information of the zone is identified, and based on the traffic characteristic information of each zone and the occurrence frequency of the incoming call scheduling preference information of the zone, the sub-traffic handling capacity information of the zone in each time type is calculated by a traffic handling capacity algorithm;

[0142] The sub-traffic processing capability information of all time types of the area is used as the traffic care capability information of the area.

[0143] Optionally, the generating module 530 is specifically configured to:

[0144] Based on the sub-traffic volume forecast information of the historical time period of each time type in the sub-future time period and the sub-traffic processing capacity information of each time type, an initial traffic schedule for each sub-future time period of the area is generated through a scheduling planning strategy;

[0145] Based on the initial traffic schedule of each sub-future time period, the time type corresponding to each sub-future time period, and the sub-traffic processing capacity information of each time type, the scheduling rationality of each sub-future time period is evaluated through a scheduling rationality evaluation strategy;

[0146] In the case where there are abnormal sub-future time periods whose scheduling rationality is lower than the preset scheduling rationality threshold, each of the abnormal sub-future time periods will be replaced by each of the sub-future time periods, and the execution will be returned to the step of generating an initial traffic schedule for each sub-future time period in the area through a scheduling planning strategy based on the sub-traffic forecast information of the historical time periods of each of the time types and the sub-traffic processing capacity information of each of the time types, until there are no abnormal sub-future time periods whose scheduling rationality is lower than the preset scheduling rationality threshold, and the initial traffic schedule for each sub-future time period obtained in each iteration will be used as the traffic processing schedule for the area in the future time period.

[0147] Optionally, the generating module 530 is specifically configured to:

[0148] For each sub-future period, based on the sub-traffic volume forecast information of the sub-future period and the sub-traffic processing capacity information of the time type corresponding to the sub-future period, the manpower estimation value of the area in the sub-future period is calculated by a manpower estimation algorithm, and the personnel adjustment and leave information of the area in the sub-future period and the scheduling preference information of the area in the historical period corresponding to the sub-future period are obtained;

[0149] Based on the personnel adjustment information of the sub-future period and the shift preference information corresponding to the sub-future period, a shift distribution table of the sub-future period is generated through a shift generation strategy, and a manpower supply value corresponding to the shift distribution table is calculated;

[0150] Calculate the deviation between the manpower estimation value and the manpower supply value, and if the deviation is not zero, and based on the scheduling preference information corresponding to the sub-future period, adjust the shift distribution table of the sub-future period through a shift adjustment strategy to obtain a new shift distribution table;

[0151] The new shift distribution table is used to replace the previous shift distribution table, and the step of calculating the manpower supply value corresponding to the shift distribution table is returned to execute until the deviation value is zero, and the new shift distribution table obtained by the last iteration is used as the initial traffic schedule for the sub-future period.

[0152] Each module in the above-mentioned intelligent scheduling device for the insurance industry call center can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0153] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 6As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, an intelligent scheduling method for a call center in the insurance industry is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0154] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0155] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, steps of an intelligent scheduling method for a call center in the insurance industry are implemented.

[0156] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the intelligent scheduling method for a call center in the insurance industry are implemented.

[0157] In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps of an intelligent scheduling method for a call center in the insurance industry.

[0158] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0159] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0160] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0161] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An intelligent scheduling method for a call center in the insurance industry, characterized in that: The method comprises: Obtain historical call volume information of each region of the insurance industry call center and telephone agent information of each region, and based on the historical call volume information, identify call information of each historical time period of each region, time feature information of each historical time period of each region, and call coordination information of each historical time period of each region; For each region, based on the incoming call information of each historical period of the region and the time characteristic information of each historical period of the region, the call volume forecast information of the region in the future period is predicted by using the incoming call timing prediction model, and based on the telephone seat information of the region and the incoming call coordination information of each historical period of the region, the call handling capacity information of the region is identified; Based on the traffic volume forecast information of the area in the future time period and the traffic processing capacity information of the area, a traffic processing schedule for the area in the future time period is generated through a scheduling planning strategy.

2. The method according to claim 1, characterized in that The identifying, based on the historical traffic volume information, the incoming call information of each historical time period of each area, the time feature information of each historical time period of each area, and the incoming call coordination information of each historical time period of each area includes: For each region, splitting the sub-historical traffic volume information of the region into sub-historical information of each historical period, and for each historical period, identifying the call volume distribution information of the historical period and the call scheduling information of the historical period based on the sub-historical information of the historical period; Based on the call volume distribution information of the historical period, generating a call distribution curve of the historical period, and based on the call scheduling information of the historical period, identifying the scheduling volume of each call scheduling area of ​​the historical period; Based on the dispatch amount of each incoming call dispatch area in the historical period, generate the incoming call dispatch distribution information of the area in the historical period, and based on the regional time feature distribution information of the time area and the incoming call dispatch record information of the time area, identify the time feature information of the historical period and the incoming call dispatch reason of the historical period; The incoming call distribution curve of the historical period is used as the incoming call information of the historical period, and the incoming call scheduling distribution information of the historical period and the incoming call scheduling reason of the historical period are used as the incoming call coordination information of the historical period.

3. The method according to claim 2, characterized in that The incoming call timing prediction model includes a sub-incoming call timing prediction model of each time type, and based on the incoming call information of each historical time period of the area, the time feature information of each historical time period of the area, and the incoming call coordination information of each historical time period of the area, the incoming call timing prediction model is used to predict the traffic volume prediction information of the area in the future time period, including: Based on the time characteristic information of each of the historical periods, the time type corresponding to each historical period is identified, and the historical periods of the same time type are divided into the same time group to obtain a historical period group of each time type; For each historical period group, based on the call distribution curve of each historical period in the historical period group, identifying the call trend information of each historical period in the sub-future period through a curve fitting algorithm; Based on the call trend information of each historical period in the historical period group in the sub-future period, the sub-traffic forecast information of the historical period in the sub-future period is predicted through the sub-call timing prediction model of the time type corresponding to the historical period group, and the sub-traffic forecast information of each historical period in the sub-future period is sorted according to the time sequence of each historical period to obtain the traffic forecast information of the area in the future period.

4. The method according to claim 2, characterized in that: The identifying the traffic handling capability information of the area based on the telephone seat information of the area and the call coordination information of each historical time period of the area includes: Based on the telephone seat information of the area, identifying each call feature information of the area, and based on the call coordination information of each historical time period of the area, identifying the call scheduling preference information of the area; Based on the regional time characteristic distribution information of the time zone, the occurrence frequency of the incoming call scheduling preference information of the zone is identified, and based on the traffic characteristic information of each zone and the occurrence frequency of the incoming call scheduling preference information of the zone, the sub-traffic handling capacity information of the zone in each time type is calculated by a traffic handling capacity algorithm; The sub-traffic processing capability information of all time types of the area is used as the traffic care capability information of the area.

5. The method according to claim 4, characterized in that The generating of a call processing schedule for the area in the future time period based on the call volume forecast information of the area in the future time period and the call processing capacity information of the area through a scheduling planning strategy includes: Based on the sub-traffic volume forecast information of the historical time period of each time type in the sub-future time period and the sub-traffic processing capacity information of each time type, an initial traffic schedule for each sub-future time period of the area is generated through a scheduling planning strategy; Based on the initial traffic schedule of each sub-future time period, the time type corresponding to each sub-future time period, and the sub-traffic processing capacity information of each time type, the scheduling rationality of each sub-future time period is evaluated through a scheduling rationality evaluation strategy; In the case where there are abnormal sub-future time periods whose scheduling rationality is lower than the preset scheduling rationality threshold, each of the abnormal sub-future time periods will be replaced by each of the sub-future time periods, and the execution will be returned to the step of generating an initial traffic schedule for each sub-future time period in the area through a scheduling planning strategy based on the sub-traffic forecast information of the historical time periods of each of the time types and the sub-traffic processing capacity information of each of the time types, until there are no abnormal sub-future time periods whose scheduling rationality is lower than the preset scheduling rationality threshold, and the initial traffic schedule for each sub-future time period obtained in each iteration will be used as the traffic processing schedule for the area in the future time period.

6. The method according to claim 5, characterized in that The method of generating an initial traffic schedule for each sub-future time period of the area based on the sub-traffic volume forecast information of the historical time period of each time type in the sub-future time period and the sub-traffic processing capacity information of each time type through a scheduling planning strategy includes: For each sub-future period, based on the sub-traffic volume forecast information of the sub-future period and the sub-traffic processing capacity information of the time type corresponding to the sub-future period, the manpower estimation value of the area in the sub-future period is calculated by a manpower estimation algorithm, and the personnel adjustment and leave information of the area in the sub-future period and the scheduling preference information of the area in the historical period corresponding to the sub-future period are obtained; Based on the personnel adjustment information of the sub-future period and the shift preference information corresponding to the sub-future period, a shift distribution table of the sub-future period is generated through a shift generation strategy, and a manpower supply value corresponding to the shift distribution table is calculated; Calculate the deviation between the manpower estimation value and the manpower supply value, and if the deviation is not zero, and based on the scheduling preference information corresponding to the sub-future period, adjust the shift distribution table of the sub-future period through a shift adjustment strategy to obtain a new shift distribution table; The new shift distribution table is used to replace the previous shift distribution table, and the step of calculating the manpower supply value corresponding to the shift distribution table is returned to execute until the deviation value is zero, and the new shift distribution table obtained by the last iteration is used as the initial traffic schedule for the sub-future period.

7. An intelligent scheduling device for a call center in the insurance industry, characterized in that: The device comprises: An acquisition module is used to acquire historical call volume information of each region of the insurance industry call center and telephone agent information of each region, and based on the historical call volume information, identify the call information of each historical period of each region, the time feature information of each historical period of each region, and the call coordination information of each historical period of each region; an identification module, for predicting the traffic volume prediction information of the region in the future time period based on the call information of each historical time period of the region and the time characteristic information of each historical time period of the region, and identifying the traffic handling capacity information of the region based on the telephone seat information of the region and the call coordination information of each historical time period of the region; A generation module is used to generate a call processing schedule for the area in the future time period based on the call volume forecast information of the area in the future time period and the call processing capacity information of the area through a scheduling planning strategy.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images