Financial customer service agent scheduling method and device, electronic equipment and storage medium

Abstract

The invention provides a financial customer service agent scheduling method and device, electronic equipment and a storage medium, and belongs to the technical field of financial services. The method comprises the following steps: acquiring historical telephone traffic data of each financial service unit; inputting the historical telephone traffic data into a pre-trained telephone traffic prediction model to obtain a predicted call volume and a predicted average call duration of each financial service unit in a preset scheduling period; determining a target response time and a target service level of each financial service unit based on a preset service index; determining the target telephone traffic intensity of each financial service unit in the scheduling period according to the predicted call volume and the predicted average call duration; and according to the target telephone traffic intensity, the target response time and the target service level corresponding to each financial service unit, calculating the number of target seats required by each financial service unit in the scheduling period. According to the invention, the efficiency of financial customer service agent scheduling can be improved.

Description

Technical Field

[0001] The present invention relates to the field of financial business technology, and in particular to a method and device for scheduling financial customer service seats, electronic equipment and storage medium. Background Art

[0002] In the financial business field, financial customer service is mainly responsible for handling the affairs of different financial business units such as customer investment consultation, fund transactions, account management, etc., and its work is directly related to the customer's fund security and investment experience. Due to the particularity of the financial market, in order to ensure the quality of service, financial institutions need to establish a scientific scheduling mechanism to ensure that there are enough professionals to respond to customer needs in a timely manner during business peak periods, avoiding customer loss or missed investment opportunities due to long waiting time.

[0003] In the related technologies, the scheduling of financial customer service agents often relies on senior managers to schedule based on past experience or scheduling software based on call volume theory. Empirical scheduling lacks scientific basis and is difficult to cope with complex market fluctuations. Scheduling software based on call volume theory has low computational efficiency in large-scale scheduling scenarios and is difficult to meet the requirements of modern financial services for refined and dynamic scheduling. Therefore, a more efficient and more practical financial customer service agent scheduling method is urgently needed. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose a method and device for scheduling financial customer service agents, an electronic device and a storage medium, aiming to improve the efficiency of scheduling financial customer service agents.

[0005] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application proposes a method for scheduling financial customer service agents, the method comprising:

[0006] Obtain historical traffic data for each financial business unit;

[0007] Inputting the historical traffic data into a pre-trained traffic prediction model, so that the traffic prediction model makes predictions based on the historical traffic data corresponding to each financial business unit, and obtains the predicted call volume and predicted average call duration of each financial business unit within a preset scheduling cycle;

[0008] Determine the target response time and target service level for each financial business unit based on preset business indicators;

[0009] Determine the target traffic intensity of each financial business unit in the scheduling cycle according to the predicted call volume and the predicted average call duration;

[0010] The target number of agents required for each financial business unit in the scheduling cycle is calculated according to the target traffic intensity, the target answering time and the target service level corresponding to each financial business unit.

[0011] In some embodiments, the historical traffic data is input into a pre-trained traffic prediction model, so that the traffic prediction model makes predictions based on the historical traffic data corresponding to each financial business unit, and obtains the predicted call volume and predicted average call duration of each financial business unit within a preset scheduling cycle:

[0012] Extracting features from the historical call traffic data to obtain statistical distribution features of call volume within a preset shift period;

[0013] Determining the scheduling cycles of different time periods within the scheduling period based on the call volume statistical distribution characteristics;

[0014] The historical traffic data is input into a pre-trained traffic prediction model so that the traffic prediction model makes predictions based on the historical traffic data corresponding to each financial business unit to obtain the predicted call volume and predicted average call duration of each financial business unit within a preset scheduling cycle.

[0015] In some embodiments, the scheduling cycle includes a first cycle, a second cycle, and a third cycle, the first cycle is smaller than the second cycle, the second cycle is smaller than the third cycle, and determining the scheduling cycles of different time periods within the scheduling period based on the call volume statistical distribution characteristics includes:

[0016] According to the statistical distribution characteristics of the call volume, the scheduling time period is divided into a peak traffic period, a flat traffic period and a low traffic period;

[0017] The scheduling period for the peak traffic period is determined as the first period, the scheduling period for the off-peak traffic period is determined as the second period, and the scheduling period for the low traffic period is determined as the third period.

[0018] In some embodiments, determining the target response time and target service level of each financial business unit based on preset business indicators includes:

[0019] Obtain historical response time distribution data and abandonment waiting time distribution data for each financial business unit;

[0020] According to the historical response time distribution data, statistics are collected on response ratios in different time intervals;

[0021] Analyze the abandoned waiting time distribution data of each financial business unit to determine the critical waiting time of the customer's waiting tolerance;

[0022] The target response time and target service level of each financial business unit are determined according to the business priority of each financial business unit, the response ratio data and the critical waiting time.

[0023] In some embodiments, determining the target traffic intensity of each financial business unit in the scheduling cycle according to the predicted call volume and the predicted average call duration includes:

[0024] Calculate the call density according to the predicted call volume and the scheduling cycle of each financial business unit;

[0025] Calculate the basic traffic intensity of each financial business unit in the scheduling period according to the call density and the predicted average call duration;

[0026] Obtaining a repeat call rate according to the historical traffic data;

[0027] According to the repeat call rate and the special period coefficient, the basic traffic intensity is modified to obtain the target traffic intensity; wherein the special period coefficient includes a holiday coefficient, a marketing activity coefficient and a system maintenance coefficient.

[0028] In some embodiments, the calculation of the target number of agents required for each financial business unit in the scheduling cycle according to the target traffic intensity, the target answering time, and the target service level corresponding to each financial business unit includes:

[0029] Initialize the seat count value and the inverse of the traffic blocking probability of each financial service unit, and round up the target traffic intensity to obtain a first initial value;

[0030] For each financial service unit, when the corresponding seat count value is less than the first initial value, the seat count value is gradually increased, and the inverse of the traffic blocking probability under different seat count values ​​is iteratively calculated according to the first preset formula;

[0031] For each financial service unit, when the corresponding agent count value is greater than or equal to the first initial value, the agent count value is gradually increased, and the traffic blocking probability under different agent count values ​​is iteratively calculated according to the second preset formula, the call waiting probability under different agent count values ​​is iteratively calculated according to the traffic blocking probability and the third preset formula, and the service level under different agent count values ​​is calculated according to the call waiting probability and the target answering time, until the service level under the agent count value is greater than or equal to the target service level;

[0032] The seat count value corresponding to each financial service unit is determined as the target number of seats for the financial service unit.

[0033] In some embodiments, after calculating the target number of seats required for each financial business unit in the scheduling cycle according to the target traffic intensity, the target answering time and the target service level corresponding to each financial business unit, the method further includes:

[0034] Obtain the number of seats to be scheduled within the scheduling cycle;

[0035] When the number of seats to be scheduled is greater than or equal to the sum of the target number of seats of each financial business unit, the number of seats is allocated according to the target number of seats of each financial business unit;

[0036] When the number of seats to be scheduled is less than the sum of the target number of seats for each financial business unit, the financial business units are sorted according to their priorities, and the corresponding target number of seats is allocated to high-priority financial business units. For low-priority financial business units, the minimum guaranteed number of seats for the financial business units is calculated, and the actual number of scheduled seats is determined based on the minimum guaranteed number of seats and the remaining number of seats to be scheduled.

[0037] To achieve the above-mentioned purpose, a second aspect of the embodiment of the present application proposes a financial customer service agent scheduling device, the device comprising:

[0038] An acquisition module, used to acquire historical traffic data of each financial business unit; wherein the historical traffic data includes historical call records and call waiting time;

[0039] A prediction module, used for inputting the historical traffic data into a pre-trained traffic prediction model, so that the traffic prediction model makes predictions based on the historical traffic data corresponding to each financial business unit, and obtains the predicted call volume and predicted average call duration of each financial business unit within a preset scheduling cycle;

[0040] A target module, used to determine the target response time and target service level of each financial business unit based on preset business indicators;

[0041] A traffic intensity module, used to determine the target traffic intensity of each financial business unit in the scheduling cycle according to the predicted call volume and the predicted average call duration;

[0042] The agent number module is used to calculate the target number of agents required for each financial business unit in the scheduling cycle according to the target traffic intensity, the target response time and the target service level corresponding to each financial business unit.

[0043] To achieve the above objectives, a third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method described in the first aspect is implemented.

[0044] To achieve the above-mentioned purpose, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0045] The financial customer service agent scheduling method and device, electronic device and storage medium proposed in the present application obtain the historical traffic data of each financial business unit; input the historical traffic data into a pre-trained traffic prediction model, so that the traffic prediction model makes predictions based on the historical traffic data corresponding to each financial business unit, and obtains the predicted call volume and predicted average call duration of each financial business unit within a preset scheduling cycle; determines the target answering time and target service level of each financial business unit based on preset business indicators; determines the target traffic intensity of each financial business unit in the scheduling cycle based on the predicted call volume and predicted average call duration; calculates the target number of agents required for each financial business unit in the scheduling cycle based on the target traffic intensity, target answering time and target service level corresponding to each financial business unit.

[0046] This application first obtains the historical call data of each financial business unit, introduces a pre-trained call prediction model, and can accurately predict the call volume and average call duration of different financial business units based on the historical call data, thereby improving the prediction accuracy; based on the classification prediction method of the financial business unit, it avoids the loss of accuracy caused by mixed prediction of all businesses, and realizes differentiated service quality management by setting the target response time and target service level for each business unit separately, so as to better meet the needs of different financial business scenarios; through the calculation of the target call intensity, a scientific mapping relationship between business prediction and staffing is established; according to the target call intensity, target response time and target service level corresponding to each financial business unit, the target number of seats required for each financial business unit in the scheduling cycle is calculated, thereby improving the efficiency of financial customer service seat scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a flow chart of the method for scheduling financial customer service agents provided in an embodiment of the present application;

[0048] Figure 2 yes Figure 1 Flow chart of step S102 in FIG.

[0049] Figure 3 yes Figure 2Flow chart of step S202 in FIG.

[0050] Figure 4 yes Figure 1 Flow chart of step S103 in FIG.

[0051] Figure 5 yes Figure 1 Flow chart of step S104 in FIG.

[0052] Figure 6 yes Figure 1 Flow chart of step S105 in FIG.

[0053] Figure 7 yes Figure 1 The flowchart after step S105 in FIG.

[0054] Figure 8 It is a structural schematic diagram of a financial customer service agent scheduling device provided in an embodiment of the present application;

[0055] Fig. 9 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0056] 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.

[0057] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0058] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0059] First, some nouns involved in this application are analyzed:

[0060] Artificial Intelligence (AI): It is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. AI is a branch of computer science. AI attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Research in this field includes robots, language recognition, image recognition, natural language processing and expert systems. AI can simulate the information process of human consciousness and thinking. AI is also a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0061] Financial Business Unit: refers to an independent service department divided according to business attributes and professional skills requirements in the financial customer service center. Each business unit is responsible for a specific type of financial services, such as: the investment consulting unit is responsible for consulting on investment products such as funds and stocks, the trading service unit handles customer buying and selling orders, transaction confirmation and other matters, the account management unit is responsible for basic business such as account opening, account cancellation, and information change, the financial service unit provides financial product consulting and after-sales service, and the risk management unit handles abnormal transactions, risk warnings and other matters. Different business units have different professional requirements for customer service personnel. For example, the customer service of the trading service unit needs to be familiar with securities trading rules and trading system operations, while the customer service of the investment consulting unit needs to have financial market analysis capabilities and product knowledge reserves. This unit-based service model can improve service professionalism and ensure that customer questions are answered professionally and accurately.

[0062] Based on this, the embodiments of the present application provide a method and device for scheduling financial customer service agents, an electronic device and a storage medium, aiming to improve the efficiency of scheduling financial customer service agents.

[0063] The financial customer service agent scheduling method and device, electronic device and storage medium provided in the embodiments of the present application are specifically illustrated through the following embodiments. First, the financial customer service agent scheduling method in the embodiments of the present application is described.

[0064] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0065] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0066] The financial customer service agent scheduling method provided in the embodiment of the present application relates to the field of financial business technology. The financial customer service agent scheduling method provided in the embodiment of the present application can be applied to the terminal, can also be applied to the server side, and can also be software running in the terminal or the server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or it can be configured as a server cluster or distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the financial customer service agent scheduling method, etc., but is not limited to the above forms.

[0067] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0068] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0069] Figure 1 This is an optional flow chart of the financial customer service agent scheduling method provided in the embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S105.

[0070] Step S101, obtaining historical traffic data of each financial service unit.

[0071] Step S102, inputting the historical traffic data into a pre-trained traffic prediction model, so that the traffic prediction model makes predictions based on the historical traffic data corresponding to each financial business unit, and obtains the predicted call volume and predicted average call duration of each financial business unit within a preset scheduling cycle.

[0072] Step S103: determining the target response time and target service level of each financial business unit based on preset business indicators.

[0073] Step S104, determining the target traffic intensity of each financial business unit in the scheduling cycle according to the predicted call volume and the predicted average call duration.

[0074] Step S105, calculating the target number of agents required for each financial service unit in the scheduling cycle according to the target traffic intensity, target response time and target service level corresponding to each financial service unit.

[0075] In steps S101 to S105 shown in the embodiment of the present application, the historical traffic data of each financial business unit is first obtained, and a pre-trained traffic prediction model is introduced. The call volume and average call duration of different financial business units can be accurately predicted based on the historical traffic data, thereby improving the prediction accuracy. The classification prediction method based on the financial business unit avoids the loss of accuracy caused by mixed prediction of all businesses. By setting the target response time and target service level for each business unit separately, differentiated service quality management is achieved to better meet the needs of different financial business scenarios. By calculating the target traffic intensity, a scientific mapping relationship between business prediction and staffing is established. According to the target traffic intensity, target response time and target service level corresponding to each financial business unit, the target number of agents required for each financial business unit in the scheduling cycle is calculated, thereby improving the efficiency of financial customer service agent scheduling.

[0076] In step S101 of some embodiments, historical call data of each financial business unit is obtained, including call volume data (number of incoming calls), call duration data (duration of each call), and answer data (waiting time before the call is connected) of each business unit in the past time period. The data comes from the call center system records and is classified and stored according to different financial business units.

[0077] For example, historical call data of the past six months is extracted from the call center database and classified according to financial business units. For example, the data of the investment consulting unit includes consulting records of stocks, funds, and financial products; the transaction service unit includes business records such as entrusted transactions and transaction confirmations; and the account management unit includes basic service records such as account opening, account cancellation, and information changes.

[0078] In step S102 of some embodiments, the historical traffic data is input into a pre-trained traffic prediction model, which analyzes the historical data characteristics of each financial business unit and outputs two key indicators: the predicted call volume and the predicted average call duration of each financial business unit within a preset scheduling cycle. The prediction model needs to consider influencing factors such as time characteristics and business characteristics.

[0079] It is understandable that historical call data is used as input information to be imported into the pre-trained call prediction model for analysis. The model uses machine learning algorithms to analyze the patterns and characteristics in historical data and generates two key prediction indicators for each financial business unit: predicted call volume and predicted average call duration. For example, for the trading service unit, the model analyzes the peak call characteristics before and after the opening of the market and predicts that the call volume in the next scheduling cycle will be 150 calls / hour and the average call duration will be 4.5 minutes. The model also considers external factors such as market fluctuations and new product releases to adjust the prediction results.

[0080] See also Figure 2 In some embodiments, step S102 may include but is not limited to steps S201 to S203:

[0081] Step S201, extracting features from historical call traffic data to obtain statistical distribution features of call traffic within a preset shift period.

[0082] Step S202, based on the statistical distribution characteristics of the call volume, determine the scheduling cycles of different time periods within the scheduling period.

[0083] Step S203, input the historical traffic data into the pre-trained traffic prediction model, so that the traffic prediction model makes predictions based on the historical traffic data corresponding to each financial business unit, and obtains the predicted call volume and predicted average call duration of each financial business unit within the preset scheduling cycle.

[0084] In step S201 of some embodiments, features are extracted from historical call data to obtain statistical distribution patterns of call volume, which may include: call distribution features by time period (such as a peak before market opening, a trough at noon, etc.), call features by business type (such as a transaction peak, intensive settlement, etc.), and call features by period (such as the beginning and end of the month, holidays, etc.). These features provide a data basis for the subsequent determination of the scheduling cycle.

[0085] It is understandable that a comprehensive feature extraction and analysis of historical call data is required. In terms of time, intraday trading features will be identified, such as the peak of consultations usually occurs at 9:15-9:30 before the market opens, the business trough period is 11:30-13:30 at noon, and the trading intensive period occurs at 14:45-15:00 before the market closes. At the same time, weekly patterns will be analyzed, such as the large number of consultations on Monday morning and the business peak caused by futures delivery on Friday. At the monthly level, a large number of fund transfers are usually faced at the beginning of the month, and settlement matters are concentrated at the end of the month. In addition, seasonal features will be extracted, such as the business characteristics of special periods such as the financial report release period of listed companies and the dividend payment period. From the business dimension, different types of business are classified and counted, including the concentration of trading business at the opening call auction, the concentration of investment consulting during the issuance of new stocks and new funds, and the distribution pattern of account services in different time periods.

[0086] In step S202 of some embodiments, the cycle of the scheduling period, i.e., the scheduling cycle, is scientifically divided based on the statistical distribution characteristics of the call volume. Reasonable scheduling cycles are set according to different business characteristics and call volume distribution. During peak financial trading periods, such as 15 minutes before the opening and the period of important financial information release, a shorter 15-minute scheduling cycle is adopted to respond to intensive business needs in a timely manner. During regular trading hours, a 30-minute scheduling cycle can be used to maintain service continuity. For low-peak periods such as lunch breaks, a 60-minute scheduling cycle can be used. Dynamic adjustments will also be made for special periods, such as adjusting the scheduling cycle according to the expected subscription quantity on the new stock subscription day, shortening the scheduling cycle on the stock index futures delivery day to cope with concentrated trading needs, and flexibly adjusting the scheduling cycle before and after holidays based on historical data characteristics.

[0087] See also Figure 3 In some embodiments, the shift scheduling cycle includes a first cycle, a second cycle, and a third cycle, the first cycle is smaller than the second cycle, and the second cycle is smaller than the third cycle. Step S202 may include, but is not limited to, steps S301 to S302:

[0088] Step S301, according to the statistical distribution characteristics of call volume, the scheduling time period is divided into a peak traffic period, a normal traffic period and a low traffic period.

[0089] Step S302, determining the scheduling cycle of the peak traffic period as the first cycle, determining the scheduling cycle of the non-peak traffic period as the second cycle, and determining the scheduling cycle of the low traffic period as the third cycle.

[0090] In step S301 of some embodiments, the scheduling period is scientifically divided into three business periods according to the statistical distribution characteristics of the call volume. The peak traffic period is a time period when the call volume is significantly higher than the average level, the flat traffic period is a time period when the call volume is at the average level, and the low traffic period is a time period when the call volume is significantly lower than the average level. The peak traffic period mainly includes the concentrated trading period before the opening, the major financial information release period, the peak period for new stock subscription, and other time periods when the call volume increases significantly. The flat traffic period usually refers to the daily trading period, when the business volume is relatively stable, but sufficient service capacity must still be maintained. The low traffic period includes the lunch break period, daily non-trading period, and other periods when the business volume is significantly reduced. This time period division based on business volume can more accurately match the service needs of different time periods.

[0091] In step S302 of some embodiments, the scheduling cycle is the basic time unit for personnel scheduling, and corresponding scheduling cycles are set for different traffic periods. For example, for peak traffic periods, a first cycle of 15 minutes is used to adjust the number of seats in time to respond to business fluctuations. During off-peak traffic periods, a second cycle of 30 minutes is used to maintain the stability of service capabilities. During low-peak traffic periods, a third cycle of 60 minutes is used to avoid over-allocation of human resources. This differentiated cycle setting ensures the optimal balance between service quality and resource utilization.

[0092] Through the above steps S301 to S302, through the time division based on the statistical distribution characteristics of call volume and the differentiated scheduling cycle setting, human resources can be predicted and allocated more accurately. During peak hours, short-cycle scheduling can quickly respond to business needs, and during off-peak hours, long-cycle scheduling can improve resource utilization efficiency, which not only ensures service quality but also optimizes labor costs. This method overcomes the limitations of traditional fixed-cycle scheduling and improves the operational efficiency and service level of financial customer service centers.

[0093] In step S203 of some embodiments, the processed historical traffic data is input into the traffic prediction model, which will analyze the historical data characteristics of each financial business unit and predict the predicted call volume and average call duration of each business unit within the set scheduling cycle. In terms of predicting call volume, the model will analyze historical data for the same period, evaluate the impact of market conditions, consider the impact of new business development, and anticipate the impact of major events. In terms of predicting average call duration, the model will consider factors such as the standard processing time of different business types, the proficiency of agents, changes in business complexity, and customer service level requirements.

[0094] Through the above steps S201 to S203, by extracting multi-dimensional features from historical call data, the statistical distribution of call volumes in different time periods and different business types can be accurately identified, and the scheduling cycle can be dynamically divided according to the call volume distribution characteristics, thus realizing flexible adjustment of the scheduling cycle. A shorter scheduling cycle is adopted during peak business periods to ensure service quality; the cycle is appropriately extended during off-peak periods to improve the efficiency of human resource utilization, effectively solving the problem that traditional fixed-cycle scheduling cannot cope with business fluctuations. Through the application of the call prediction model, the call volume and average call duration in the future scheduling cycle can be accurately predicted.

[0095] In step S103 of some embodiments, based on preset business indicators (such as regulatory requirements, service standards, etc.), a target response time and a target service level (the proportion of calls answered within the target response time) are set for each financial business unit, and these indicators will be used as constraints for staffing. For example, the target response time of the transaction service unit in the financial business unit is set to 15 seconds, and the target service level is 90%, which means that a 90% connection rate is required within 15 seconds; while the investment consulting unit can be set to answer 85% of the calls within 20 seconds.

[0096] See also Figure 4 In some embodiments, step S103 may include but is not limited to steps S401 to S404:

[0097] Step S401, obtaining historical response time distribution data and abandonment waiting time distribution data of each financial service unit.

[0098] Step S402: Count the response ratio data in different time intervals according to the historical response time distribution data.

[0099] Step S403, analyzing the abandonment waiting time distribution data of each financial business unit to determine the critical waiting time of the customer's waiting tolerance.

[0100] Step S404, determining the target response time and target service level of each financial business unit according to the business priority, response ratio data and critical waiting time of each financial business unit.

[0101] In step S401 of some embodiments, the historical answering time distribution data is a statistical data recording the time taken by the customer service to answer the phone, and the abandoning waiting time distribution data is a statistical data recording how long the customer gave up waiting. The historical data of each financial business unit in the recent period is collected and analyzed, including the time distribution of each call from the time it was connected to the time it was answered, and the time distribution of the customer giving up waiting. For example, for the product consulting unit, the historical answering time distribution data shows that 40% of the calls are answered within 10 seconds, and 35% are answered within 11-20 seconds; the abandoning waiting time distribution data shows that 15% of the customers give up before 20 seconds, and 35% give up within 21-30 seconds.

[0102] In step S402 of some embodiments, based on the historical response time distribution data, the response ratio data of each time interval is calculated. For example, the data of the product consultation unit shows that the response ratio within 10 seconds is 40%, the cumulative response ratio within 20 seconds reaches 75% (40% + 35%), and the cumulative response ratio within 30 seconds reaches 90% (40% + 35% + 15%).

[0103] In step S403 of some embodiments, customer waiting tolerance refers to the longest time a customer is willing to wait. The critical waiting time refers to the time point when the customer abandonment rate significantly increases. By analyzing the abandonment waiting time distribution data, the critical point of customer waiting tolerance is identified. Taking the product consulting unit as an example, the data shows that the abandonment rate before 20 seconds is low (15%), while the abandonment rate in the 20-30 second interval increases significantly (35%). Based on this, the critical waiting time is determined to be 20 seconds. This critical point reflects the turning point of the customer's willingness to wait.

[0104] In step S404 of some embodiments, the business priority refers to the ranking of the importance of different financial business units, and a reasonable target response time and target service level are set by comprehensively considering the business priority, response ratio data and critical waiting time. For example, if product consultation is a medium-priority business, its target response time is set to 20 seconds (in line with the critical waiting time) and the target service level is set to 75% (in line with historical response capabilities). This setting takes into account both customer acceptance and actual service capabilities.

[0105] Through the above steps S401 to S404, the determination of the target response time and the target service level is a scientific process based on objective data analysis, which takes into account both historical service capabilities and customer acceptance, and is reasonably set in combination with business priorities, thereby ensuring the scientific nature and achievability of the target response time and the target service level.

[0106] In step S104 of some embodiments, the target traffic intensity of each financial business unit in the scheduling cycle is calculated based on the obtained predicted call volume and predicted average call duration. The target traffic intensity reflects the workload per unit time and is an important parameter for determining the number of required seats. The target traffic intensity can be calculated by multiplying the predicted call volume and the predicted average call duration by the observation time. For example, if a unit predicts that it will receive 38 calls every 15 minutes and the average call duration is 175 seconds, the target traffic intensity is 7.39 traffic intensity units.

[0107] See also Figure 5 In some embodiments, step S104 may include but is not limited to steps S501 to S504:

[0108] Step S501, calculating the call density according to the predicted call volume and the scheduling cycle of each financial business unit.

[0109] Step S502, calculating the basic call intensity of each financial business unit in the scheduling cycle according to the call density and the predicted average call duration.

[0110] Step S503, obtaining the repeat call rate according to the historical traffic data.

[0111] Step S504: According to the repeat call rate and the special period coefficient, the basic traffic intensity is corrected to obtain the target traffic intensity.

[0112] Among them, special period coefficients include holiday coefficients, marketing activity coefficients and system maintenance coefficients.

[0113] In step S501 of some embodiments, call density refers to the number of calls per unit time, which can be measured in calls / hour. The scheduling cycle is the basic time unit for personnel scheduling. The predicted call volume data of each financial business unit in different scheduling cycles is obtained. For example, for the scheduling cycle 9:00-10:00, if the predicted call volume is 300 calls / hour, according to the formula "call density = predicted call volume / time interval", the call density is 300 calls / hour. The call density is calculated for each scheduling cycle to form a complete density distribution map. For scheduling cycles of different lengths, the calculation unit will be adjusted accordingly to ensure the accuracy and comparability of the data.

[0114] In step S502 of some embodiments, the predicted average call duration data is obtained, such as a call duration of 240 seconds, or 0.067 hours. The basic traffic intensity is an uncorrected raw workload indicator, and the basic traffic intensity = call density × average call duration is calculated. In the above example, the basic traffic intensity is 300 × 0.067 = 20 Erlangs. This calculation process is performed for each time period separately to form a basic traffic intensity distribution curve.

[0115] In step S503 of some embodiments, the repeat call rate refers to the proportion of calls that are repeatedly dialed due to failure to connect for the first time to the total number of calls. The repeat call rate is calculated by analyzing historical traffic data. The specific calculation formula is "repeat call rate = number of repeated calls / total number of calls". For example, if there are 1000 total calls in a certain period of time, of which 150 are repeated calls, the repeat call rate is 15%. The repeat call situation of different periods and different business types can be counted to provide a basis for subsequent corrections.

[0116] In step S504 of some embodiments, the target traffic intensity refers to the final workload index after multiple corrections. The basic traffic intensity is corrected multiple times. First, it is corrected according to the repeat call rate. For example, if the basic traffic intensity is 20 erlangs and the repeat call rate is 15%, it is corrected to 17 erlangs. Then, considering the influence of the traffic transfer rate, if the traffic transfer rate is 10%, it is further corrected to 15.37 erlangs. Finally, it is adjusted according to the special period coefficient. For example, if the holiday coefficient is 1.3, the final traffic intensity is 19.98 erlangs.

[0117] Through the above steps S501 to S504, by introducing the repeat call rate, traffic transfer rate and special period coefficient, the accuracy of traffic intensity calculation is greatly improved, which can flexibly respond to various business scenarios and period characteristics, and reflect the actual business situation through the combination of different coefficients. Whether it is holidays, marketing activities or system maintenance, the target traffic intensity can be accurately calculated.

[0118] In step S105 of some embodiments, the three parameters of target traffic intensity, target response time and target service level of each financial business unit are used to calculate the target number of agents required by each financial business unit within the scheduling cycle through a mathematical model to ensure that the service quality requirements are met.

[0119] See also Figure 6 In some embodiments, step S105 may include but is not limited to steps S601 to S604:

[0120] Step S601, initialize the seat count value and the inverse of the traffic blocking probability of each financial service unit, and round up the target traffic intensity to obtain a first initial value.

[0121] Step S602: for each financial service unit, when the corresponding seat count value is less than the first initial value, the seat count value is gradually increased, and the inverse of the traffic blocking probability under different seat count values ​​is iteratively calculated according to the first preset formula.

[0122] Step S603, for each financial business unit, when the corresponding agent count value is greater than or equal to the first initial value, the agent count value is gradually increased, and the traffic blocking probability under different agent count values ​​is iteratively calculated according to the second preset formula, the call waiting probability under different agent count values ​​is iteratively calculated according to the traffic blocking probability and the third preset formula, and the service level under different agent count values ​​is calculated according to the call waiting probability and the target answering time, until the service level under the agent count value is greater than or equal to the target service level.

[0123] Step S604: determine the seat count value corresponding to each financial service unit as the target number of seats for the financial service unit.

[0124] In step S601 of some embodiments, the seat count value m represents the number of seats that need to be configured for the financial service unit. When the calculation starts, the seat count value of each financial service unit is initialized to 1, the inverse of the traffic blocking probability is 1, and the target traffic intensity is rounded up to obtain the first initial value a. For example, if the target traffic intensity u=7.39, the first initial value a=8.

[0125] In step S602 of some embodiments, for each financial service unit, when the corresponding seat count value m is less than the first initial value a, the seat count value m is gradually increased, and the inverse of the traffic blocking probability E under different seat count values ​​is iteratively calculated according to the first preset formula. B (m,u) -1 , where the first preset formula is as follows:

[0126]

[0127] Where m is the seat count value, u is the target traffic intensity, and E B (m,u) -1 It is the inverse of the traffic blocking probability under different agent count values.

[0128] In step S603 of some embodiments, for each financial business unit, when the corresponding agent count value is greater than or equal to the first initial value, that is, starting from m=a, the agent count value is gradually increased, and the traffic blocking probability under different agent count values ​​is iteratively calculated according to the second preset formula, the call waiting probability under different agent count values ​​is iteratively calculated according to the traffic blocking probability and the third preset formula, and the service level under different agent count values ​​is calculated according to the call waiting probability and the target answering time, until the service level under the agent count value is greater than or equal to the target service level.

[0129] Exemplarily, starting from the seat count value m being equal to the first initial value a, the traffic blocking probability under different seat count values ​​is iteratively calculated according to the second preset formula, and the second preset formula is as follows:

[0130]

[0131] Where m is the seat count value, u is the target traffic intensity, and E B (m,u) is the traffic blocking probability under different agent count values. The call waiting probability under different agent count values ​​is calculated iteratively according to the traffic blocking probability and the third preset formula. The third preset formula is as follows:

[0132]

[0133] Where m is the seat count value, u is the target traffic intensity, and E B (m,u) is the traffic blocking probability under different agent count values, E C (m,u) is the call waiting probability under different agent count values. The service level under different agent count values ​​is calculated based on the call waiting probability and the target answering time. The calculation of the service level W(t) is as follows:

[0134]

[0135] Where t is the target response time, W(t) is the service level under different agent count values, e is the base of the natural logarithm, i.e. 2.71828182, Ts is the predicted average call duration, m is the agent count value, and u is the target traffic intensity. If W(t) is greater than or equal to the target service level W d (t), the iteration can be terminated, otherwise m=m+1 is set to continue the iterative calculation until the service level under the seat count value m is greater than or equal to the target service level.

[0136] In step S604 of some embodiments, the target number of seats ultimately required for each financial service unit is determined, which is the seat count value when the service level reaches or exceeds the target service level for the first time.

[0137] Through the above steps S601 to S604, the traditional E C The factorial operation in the (m,u) formula is performed using E B (m,u) recursively calculate E C (m,u), which reduces the computational complexity and effectively utilizes historical computation information, supports multi-threaded parallel computing, and is suitable for large-scale scheduling scenarios.

[0138] See also Figure 7 In some embodiments, step S105 may include but is not limited to steps S701 to S703:

[0139] Step S701, obtaining the number of seats to be scheduled within the scheduling cycle.

[0140] Step S702: when the number of seats to be scheduled is greater than or equal to the sum of the target number of seats of each financial business unit, the number of seats is allocated according to the target number of seats of each financial business unit.

[0141] Step S703, when the number of seats to be scheduled is less than the sum of the target number of seats of each financial business unit, the financial business units are sorted according to the priority of each financial business unit, and the corresponding target number of seats is allocated to the high-priority financial business units. For the low-priority financial business units, the minimum guaranteed number of seats for the financial business units is calculated, and the actual number of scheduled seats is determined based on the minimum guaranteed number of seats and the remaining number of seats to be scheduled.

[0142] In step S701 of some embodiments, the number of seats to be scheduled refers to the total number of seats actually available for scheduling. The total number of seats actually available for scheduling is obtained, including full-time seats (FTE) and converted part-time seats. For example, a call center has 45 full-time seats and 10 part-time seats, then the total number of seats to be scheduled is 50 (45+10×0.5). The accuracy and timeliness of these personnel data must be ensured.

[0143] In step S702 of some embodiments, when the number of seats to be scheduled meets or exceeds the total demand of each financial business unit, the seats are allocated according to the previously calculated target value. For example, if the transaction service unit needs 20 people, the investment consulting unit needs 15 people, and the account management unit needs 10 people, the total demand is 45 people, and the actual number of seats to be scheduled is 50, then the seats can be allocated completely according to the target number of seats of each financial business unit to ensure service quality.

[0144] In step S703 of some embodiments, priority refers to the ranking of the importance of each financial business unit, the minimum guaranteed number of seats is the minimum number of people required to ensure basic services, and the remaining number of seats to be scheduled is the remaining manpower after the high-priority units are allocated. When the number of seats to be scheduled is less than the sum of the target number of seats for each financial business unit (such as the sum of the target number of seats is 45, but there are actually only 35 seats to be scheduled), sort by priority, such as: trading services (high priority): 20 people; investment consulting (medium priority): 15 people; account management (low priority): 10 people. First, give priority to guaranteeing high-priority units, such as allocating all 20 people to trading services, and calculating the minimum guaranteed number of remaining units: the minimum requirement for investment consulting is 12 people, and the minimum requirement for account management is 8 people. The remaining 15 seats to be scheduled are reasonably distributed between medium and low priority units, with 9 people allocated to investment consulting and 6 people allocated to account management.

[0145] Through the above steps S701 to S703, when manpower is sufficient, allocation is strictly carried out according to the calculated target number of seats to ensure that each financial business unit can achieve the expected service level. When manpower is insufficient, allocation is carried out through the priority mechanism and the minimum guarantee mechanism, which not only ensures the service quality of high-priority businesses, but also maintains the basic operation of low-priority businesses. It has strong practicality and adaptability, and can adjust the priority and guarantee standards in time according to business development and market changes, establish a safety threshold for human resource allocation, and ensure that basic service capabilities can be maintained even in extreme cases by setting the minimum number of guaranteed seats, effectively preventing operational risks and achieving the optimal configuration of financial customer service seat scheduling.

[0146] The financial customer service agent scheduling method and device, electronic device and storage medium proposed in the present application obtain the historical traffic data of each financial business unit; input the historical traffic data into a pre-trained traffic prediction model, so that the traffic prediction model makes predictions based on the historical traffic data corresponding to each financial business unit, and obtains the predicted call volume and predicted average call duration of each financial business unit within a preset scheduling cycle; determines the target answering time and target service level of each financial business unit based on preset business indicators; determines the target traffic intensity of each financial business unit in the scheduling cycle based on the predicted call volume and predicted average call duration; calculates the target number of agents required for each financial business unit in the scheduling cycle based on the target traffic intensity, target answering time and target service level corresponding to each financial business unit.

[0147] This application first obtains the historical call data of each financial business unit, introduces a pre-trained call prediction model, and can accurately predict the call volume and average call duration of different financial business units based on the historical call data, thereby improving the prediction accuracy; based on the classification prediction method of the financial business unit, it avoids the loss of accuracy caused by mixed prediction of all businesses, and realizes differentiated service quality management by setting the target response time and target service level for each business unit separately, so as to better meet the needs of different financial business scenarios; through the calculation of the target call intensity, a scientific mapping relationship between business prediction and staffing is established; according to the target call intensity, target response time and target service level corresponding to each financial business unit, the target number of seats required for each financial business unit in the scheduling cycle is calculated, thereby improving the efficiency of financial customer service seat scheduling.

[0148] See also Figure 8 The embodiment of the present application also provides a financial customer service agent scheduling device, which can implement the above-mentioned financial customer service agent scheduling method, and the device includes:

[0149] An acquisition module, used to acquire historical call data of each financial business unit; wherein the historical call data includes historical call records and call waiting time;

[0150] A prediction module, used to input historical traffic data into a pre-trained traffic prediction model, so that the traffic prediction model makes predictions based on the historical traffic data corresponding to each financial business unit, and obtains the predicted call volume and predicted average call duration of each financial business unit within a preset scheduling cycle;

[0151] A target module, used to determine the target response time and target service level of each financial business unit based on preset business indicators;

[0152] The traffic intensity module is used to determine the target traffic intensity of each financial business unit in the scheduling cycle based on the predicted call volume and the predicted average call duration;

[0153] The agent number module is used to calculate the target number of agents required for each financial business unit in the scheduling cycle based on the target traffic intensity, target response time and target service level corresponding to each financial business unit.

[0154] The specific implementation of the financial customer service agent scheduling device is basically the same as the specific implementation of the above-mentioned financial customer service agent scheduling method, and will not be repeated here.

[0155] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned financial customer service agent scheduling method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0156] See also Fig. 9 , Fig. 9 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0157] The processor 901 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0158] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other applications. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 902, and the processor 901 calls and executes the financial customer service agent scheduling method of the embodiment of this application;

[0159] Input / output interface 903, used to implement information input and output;

[0160] Communication interface 904, used to realize communication interaction between the device and other devices, which can be realized by wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0161] A bus 905 that transmits information between various components of the device (e.g., the processor 901, the memory 902, the input / output interface 903, and the communication interface 904);

[0162] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0163] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned financial customer service agent scheduling method is implemented.

[0164] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0165] The financial customer service agent scheduling method and device, electronic device and storage medium proposed in the present application obtain the historical traffic data of each financial business unit; input the historical traffic data into a pre-trained traffic prediction model, so that the traffic prediction model makes predictions based on the historical traffic data corresponding to each financial business unit, and obtains the predicted call volume and predicted average call duration of each financial business unit within a preset scheduling cycle; determines the target answering time and target service level of each financial business unit based on preset business indicators; determines the target traffic intensity of each financial business unit in the scheduling cycle based on the predicted call volume and predicted average call duration; calculates the target number of agents required for each financial business unit in the scheduling cycle based on the target traffic intensity, target answering time and target service level corresponding to each financial business unit.

[0166] This application first obtains the historical call data of each financial business unit, introduces a pre-trained call prediction model, and can accurately predict the call volume and average call duration of different financial business units based on the historical call data, thereby improving the prediction accuracy; based on the classification prediction method of the financial business unit, it avoids the loss of accuracy caused by mixed prediction of all businesses, and realizes differentiated service quality management by setting the target response time and target service level for each business unit separately, so as to better meet the needs of different financial business scenarios; through the calculation of the target call intensity, a scientific mapping relationship between business prediction and staffing is established; according to the target call intensity, target response time and target service level corresponding to each financial business unit, the target number of seats required for each financial business unit in the scheduling cycle is calculated, thereby improving the efficiency of financial customer service seat scheduling.

[0167] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0168] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0169] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0170] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0171] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0172] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one item (one) of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0173] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0174] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0175] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0176] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0177] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A method for scheduling financial customer service agents, characterized in that: include: Obtain historical traffic data for each financial business unit; Inputting the historical traffic data into a pre-trained traffic prediction model, so that the traffic prediction model makes predictions based on the historical traffic data corresponding to each financial business unit, and obtains the predicted call volume and predicted average call duration of each financial business unit within a preset scheduling cycle; Determine the target response time and target service level for each financial business unit based on preset business indicators; Determine the target traffic intensity of each financial business unit in the scheduling cycle according to the predicted call volume and the predicted average call duration; The target number of agents required for each financial business unit in the scheduling cycle is calculated according to the target traffic intensity, the target answering time and the target service level corresponding to each financial business unit.

2. The method for scheduling financial customer service agents according to claim 1, characterized in that: The historical traffic data is input into a pre-trained traffic prediction model, so that the traffic prediction model makes predictions based on the historical traffic data corresponding to each financial business unit, and obtains the predicted call volume and predicted average call duration of each financial business unit within a preset scheduling cycle: Extracting features from the historical call traffic data to obtain statistical distribution features of call volume within a preset shift period; Determining the scheduling cycles of different time periods within the scheduling period based on the call volume statistical distribution characteristics; The historical traffic data is input into a pre-trained traffic prediction model so that the traffic prediction model makes predictions based on the historical traffic data corresponding to each financial business unit to obtain the predicted call volume and predicted average call duration of each financial business unit within a preset scheduling cycle.

3. The method for scheduling financial customer service agents according to claim 2, characterized in that: The scheduling cycle includes a first cycle, a second cycle and a third cycle, the first cycle is smaller than the second cycle, the second cycle is smaller than the third cycle, and the determining of the scheduling cycles of different time periods within the scheduling period based on the call volume statistical distribution characteristics includes: According to the statistical distribution characteristics of the call volume, the scheduling time period is divided into a peak traffic period, a flat traffic period and a low traffic period; The scheduling period for the peak traffic period is determined as the first period, the scheduling period for the off-peak traffic period is determined as the second period, and the scheduling period for the low traffic period is determined as the third period.

4. The method for scheduling financial customer service agents according to claim 1, characterized in that: Determining the target response time and target service level of each financial business unit based on preset business indicators includes: Obtain historical response time distribution data and abandonment waiting time distribution data for each financial business unit; According to the historical response time distribution data, statistics are collected on response ratios in different time intervals; Analyze the abandoned waiting time distribution data of each financial business unit to determine the critical waiting time of the customer's waiting tolerance; The target response time and target service level of each financial business unit are determined according to the business priority of each financial business unit, the response ratio data and the critical waiting time.

5. The method for scheduling financial customer service agents according to claim 1, characterized in that: Determining the target traffic intensity of each financial business unit in the scheduling cycle according to the predicted call volume and the predicted average call duration includes: Calculate the call density according to the predicted call volume and the scheduling cycle of each financial business unit; Calculate the basic call intensity of each financial business unit in the scheduling period according to the call density and the predicted average call duration; Obtaining a repeat call rate according to the historical traffic data; According to the repeat call rate and the special period coefficient, the basic traffic intensity is modified to obtain the target traffic intensity; wherein the special period coefficient includes a holiday coefficient, a marketing activity coefficient and a system maintenance coefficient.

6. The method for scheduling financial customer service agents according to claim 1, characterized in that: The calculating, according to the target traffic intensity, the target answering time and the target service level corresponding to each financial business unit, the target number of seats required by each financial business unit in the scheduling cycle includes: Initialize the seat count value and the inverse of the traffic blocking probability of each financial service unit, and round up the target traffic intensity to obtain a first initial value; For each financial service unit, when the corresponding seat count value is less than the first initial value, the seat count value is gradually increased, and the inverse of the traffic blocking probability under different seat count values ​​is iteratively calculated according to the first preset formula; For each financial service unit, when the corresponding agent count value is greater than or equal to the first initial value, the agent count value is gradually increased, and the traffic blocking probability under different agent count values ​​is iteratively calculated according to the second preset formula, the call waiting probability under different agent count values ​​is iteratively calculated according to the traffic blocking probability and the third preset formula, and the service level under different agent count values ​​is calculated according to the call waiting probability and the target answering time, until the service level under the agent count value is greater than or equal to the target service level; The seat count value corresponding to each financial service unit is determined as the target number of seats for the financial service unit.

7. The method for scheduling financial customer service agents according to claim 1, characterized in that: After calculating the target number of seats required for each financial business unit in the scheduling cycle according to the target traffic intensity, the target answering time, and the target service level corresponding to each financial business unit, the method further includes: Obtain the number of seats to be scheduled within the scheduling cycle; When the number of seats to be scheduled is greater than or equal to the sum of the target number of seats of each financial business unit, the number of seats is allocated according to the target number of seats of each financial business unit; When the number of seats to be scheduled is less than the sum of the target number of seats for each financial business unit, the financial business units are sorted according to their priorities, and the corresponding target number of seats is allocated to high-priority financial business units. For low-priority financial business units, the minimum guaranteed number of seats for the financial business units is calculated, and the actual number of scheduled seats is determined based on the minimum guaranteed number of seats and the remaining number of seats to be scheduled.

8. A financial customer service agent scheduling device, characterized in that: include: An acquisition module, used to acquire historical traffic data of each financial business unit; wherein the historical traffic data includes historical call records and call waiting time; A prediction module, used for inputting the historical traffic data into a pre-trained traffic prediction model, so that the traffic prediction model makes predictions based on the historical traffic data corresponding to each financial business unit, and obtains the predicted call volume and predicted average call duration of each financial business unit within a preset scheduling cycle; A target module, used to determine the target response time and target service level of each financial business unit based on preset business indicators; A traffic intensity module, used to determine the target traffic intensity of each financial business unit in the scheduling cycle according to the predicted call volume and the predicted average call duration; The agent number module is used to calculate the target number of agents required for each financial business unit in the scheduling cycle according to the target traffic intensity, the target response time and the target service level corresponding to each financial business unit.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method for scheduling financial customer service agents as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The storage medium stores a program, and the program is executed by a processor to implement the financial customer service agent scheduling method as described in any one of claims 1 to 7.

Images