Incoming call resource allocation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides an incoming call resource allocation method and device, electronic equipment and a storage medium, belongs to the technical field of artificial intelligence, and is suitable for financial science and technology scenes. The method comprises the following steps: acquiring a historical incoming call volume; daily incoming call volume prediction is carried out based on the historical incoming call volume to obtain target daily incoming call volume prediction data; based on the historical incoming call volume, performing time period call volume prediction to obtain initial time period incoming call volume prediction data; performing influence duration analysis on a pre-acquired target emergency to obtain an event duration; performing time period division based on the event duration to obtain event time period data; based on the event type of the target emergency and the event time period data, correcting the incoming call volume prediction data in the initial time period to obtain incoming call volume prediction data in the target time period; and carrying out incoming call resource allocation based on the target day incoming call volume prediction data and the target time period incoming call volume prediction data. According to the embodiment of the invention, the accuracy of incoming call resource allocation can be improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and is applicable to the fintech scenario, and particularly relates to a method and device for allocating incoming resources, an electronic device, and a storage medium. Background Art

[0002] In the call center of an enterprise or institution, an incoming call usually refers to the behavior that a customer actively establishes contact with the call center through the telephone channel, which can meet the requirements of business scenarios such as business consultation and feedback of opinions. Incoming call technology can be applied to many application scenarios. For example, in the fintech scenario, financial customers actively initiate contact with the financial institution system through the telephone channel or the like to obtain services such as financial business consultation and solving business problems.

[0003] Currently, in the call center of an enterprise or institution, the method of quantitatively allocating incoming resources is mainly adopted to meet the incoming call requirements of customers. However, in actual applications, due to different business characteristics of the business at different time points, the method of quantitatively allocating incoming resources is difficult to meet the incoming call requirements of customers when the incoming call demand is large.

[0004] Therefore, how to improve the accuracy of incoming resource allocation has become a technical problem to be solved urgently. Summary of the Invention

[0005] The main purpose of the embodiments of the present application is to propose a method and device for allocating incoming resources, an electronic device, and a storage medium, aiming to improve the accuracy of incoming resource allocation.

[0006] To achieve the above object, a first aspect of the embodiments of the present application proposes a method for allocating incoming resources, and the method includes:

[0007] Obtain historical incoming call volume;

[0008] Perform daily call volume prediction based on the historical incoming call volume to obtain target daily incoming call volume prediction data;

[0009] Perform time period call volume prediction based on the historical incoming call volume to obtain initial time period incoming call volume prediction data;

[0010] Analyze the influence duration of a pre-obtained target unexpected event to obtain the event duration;

[0011] Perform time period division based on the event duration to obtain event time period data;

[0012] Correct the initial time period incoming call volume prediction data based on the event type of the target unexpected event and the event time period data to obtain target time period incoming call volume prediction data;

[0013] Perform incoming resource allocation based on the predicted incoming call volume data for the target date and the predicted incoming call volume data for the target time period.

[0014] In some embodiments, the method of correcting the predicted incoming call volume data for the initial time period based on the event type of the target emergency event and the event time period data to obtain the predicted incoming call volume data for the target time period includes:

[0015] Determine a call volume correction parameter based on the emergency type of the emergency event;

[0016] Perform data screening on the predicted incoming call volume data for the initial time period based on the event time period data to obtain candidate predicted incoming call volume data for the time period;

[0017] Adjust the candidate predicted incoming call volume data for the time period based on the call volume correction parameter and the event time period data to obtain the predicted incoming call volume data for the target time period.

[0018] In some embodiments, the method of adjusting the candidate predicted incoming call volume data for the time period based on the call volume correction parameter and the event time period data to obtain the predicted incoming call volume data for the target time period includes:

[0019] Perform coefficient calculation based on the call volume correction parameter and the event time period data to obtain an incoming call volume correction coefficient;

[0020] Perform call volume correction on the candidate predicted incoming call volume data for the time period based on the incoming call volume correction coefficient to obtain corrected predicted incoming call volume data for the time period;

[0021] Perform data update on the predicted incoming call volume data for the initial time period based on the corrected predicted incoming call volume data for the time period to obtain the predicted incoming call volume data for the target time period.

[0022] In some embodiments, the call volume correction parameter includes call volume peak data and call volume standard deviation data; the method of performing coefficient calculation based on the call volume correction parameter and the event time period data to obtain an incoming call volume correction coefficient includes:

[0023] Perform time difference calculation on the candidate predicted incoming call volume data for the time period and the event time period data to obtain an event development factor;

[0024] Perform aggregation calculation based on the event development factor, the call volume peak data, and the call volume standard deviation data to obtain the incoming call volume correction coefficient.

[0025] In some embodiments, the historical incoming call volume includes historical daily incoming call volume; the method of performing daily call volume prediction based on the historical incoming call volume to obtain the predicted incoming call volume data for the target date includes:

[0026] Obtain preset daily call volume prediction parameters; wherein, the daily call volume prediction parameters include first historical weight data and historical daily prediction interference values;

[0027] Based on the aggregation calculation of the first historical weight data and the historical daily incoming call volume, obtain initial daily incoming call volume prediction data;

[0028] Based on the historical daily prediction interference value, adjust the initial daily incoming call volume prediction data to obtain the target daily incoming call volume prediction data.

[0029] In some embodiments, the obtaining of the initial period incoming call volume prediction data by performing period call volume prediction based on the historical incoming call volume includes:

[0030] Perform period division on the historical daily incoming call volume to obtain historical period incoming call volume;

[0031] Obtain preset period call volume prediction parameters; wherein, the period call volume prediction parameters include second historical weight data and historical period prediction interference values;

[0032] Based on the aggregation calculation of the second historical weight data and the historical period incoming call volume, obtain original period incoming call volume prediction data;

[0033] Based on the historical period prediction interference value, adjust the original period incoming call volume prediction data to obtain the initial daily incoming call volume prediction data.

[0034] In some embodiments, the performing of incoming resource allocation based on the target daily incoming call volume prediction data and the target period incoming call volume prediction data includes:

[0035] Obtain a preset seat resource pool;

[0036] Based on the target period incoming call volume prediction data, perform seat calculation to obtain the original number of seats;

[0037] Based on the original number of seats, obtain candidate seat objects from the preset seat resource pool;

[0038] Based on the target daily incoming call volume prediction data and the target period incoming call volume prediction data, perform seat arrangement for the candidate seat objects.

[0039] To achieve the above object, a second aspect of the embodiments of the present application proposes an incoming resource allocation device, the device includes:

[0040] A historical data acquisition module, configured to acquire historical incoming call volume;

[0041] The daily call volume prediction module is used to predict the daily call volume based on the historical incoming call volume to obtain the target daily incoming call volume prediction data;

[0042] The time period call volume prediction module is used to predict the call volume in a time period based on the historical incoming call volume to obtain the initial incoming call volume prediction data for the time period;

[0043] The time duration analysis module is used to analyze the impact duration of a pre-acquired target emergency event to obtain the event duration;

[0044] The event time period division module is used to divide time periods based on the event duration to obtain event time period data;

[0045] The time period call volume correction module is used to correct the initial incoming call volume prediction data for the time period based on the event type of the target emergency event and the event time period data to obtain the target incoming call volume prediction data for the time period;

[0046] The resource allocation module is used to allocate incoming resources based on the target daily incoming call volume prediction data and the target incoming call volume prediction data for the time period.

[0047] To achieve the above object, a third aspect of the embodiments of the present application proposes an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the method described in the first aspect above is implemented.

[0048] To achieve the above object, a fourth aspect of the embodiments of the present application proposes a computer-readable storage medium, 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 above is implemented.

[0049] The incoming resource allocation method and device, electronic device, and storage medium proposed in this application predict the daily call volume and the call volume in different time periods based on historical incoming call volumes, obtain the target daily incoming call volume prediction data and the initial incoming call volume prediction data in different time periods, and thus obtain the benchmark call volume prediction data. Then, a target unexpected event is introduced, the influence duration of the target unexpected event is analyzed to obtain the event duration, and time period division is performed based on the event duration to obtain the event time period data. Furthermore, based on the event type of the target unexpected event and the event time period data, the initial incoming call volume prediction data in different time periods is corrected to obtain the target incoming call volume prediction data in different time periods, which can combine the influence of the target unexpected event on the initial incoming call volume prediction data and perform correction to obtain more accurate target incoming call volume prediction data in different time periods, facilitating subsequent outbound resource arrangement. Finally, incoming resource allocation is performed based on the target daily incoming call volume prediction data and the target incoming call volume prediction data in different time periods, which can not only meet the daily peak and valley call demands but also quickly respond to unexpected events, improve the accuracy and adaptability of incoming resource allocation, and enhance the service response efficiency and customer satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is a flowchart of the incoming resource allocation method provided by an embodiment of this application;

[0051] Figure 2 is Figure 1 a flowchart of step S102 in

[0052] Figure 3 is Figure 1 a flowchart of step S103 in

[0053] Figure 4 is Figure 1 a flowchart of step S106 in

[0054] Figure 5 is Figure 4 a flowchart of step S403 in

[0055] Figure 6 is Figure 5 a flowchart of step S501 in

[0056] Figure 7 is Figure 1 a flowchart of step S107 in

[0057] Figure 8 is a schematic structural diagram of the incoming resource allocation device provided by an embodiment of this application;

[0058] Figure 9 is a schematic hardware structure diagram of the electronic device provided by an embodiment of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0059] In order to make the objectives, technical solutions and advantages of this application more clear and understandable, the following further describes this application in detail in combination with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit this application.

[0060] It should be noted that although functional module division is performed in the device schematic diagram and the logical sequence is shown in the flowchart, in some cases, the steps shown or described can be executed in a different module division in the device or a different order in the flowchart. Terms such as "first" and "second" in the specification, claims and the above-mentioned drawings are used to distinguish similar objects and do not necessarily need to describe a specific order or sequence.

[0061] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field 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.

[0062] First, several terms involved in this application are analyzed:

[0063] Artificial Intelligence (AI): It is a new technical science that studies, develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence; artificial intelligence is a branch of computer science. Artificial intelligence attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a way similar to human intelligence. The research in this field includes robots, speech recognition, image recognition, natural language processing and expert systems, etc. Artificial intelligence can simulate the information process of human consciousness and thinking. Artificial intelligence also 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 in terms of theories, methods, technologies and application systems.

[0064] Inbound Call, in the call center of an enterprise or institution, inbound call refers to the communication behavior in which a customer or user actively establishes contact with the call center through the telephone channel, and is usually used in demand scenarios such as business consultation, complaint, after-sales support, order inquiry, etc. In the fields of customer service and telemarketing, inbound call is one of the core channels for customers to initiate interactions. Enterprises manage the answering process through a call center system (such as IVR voice navigation, ACD intelligent queuing, etc.) to ensure efficient allocation to agents or AI customer service for processing. Its characteristics include passive responsiveness, diverse demands and high requirements for service timeliness, forming an active and passive business model difference from "Outbound Call". The quality of inbound call services directly affects customer satisfaction.

[0065] The incoming call technology can be applied to many application scenarios. For example, in the fintech scenario, financial customers actively initiate contact with the financial institution system through channels such as telephone to obtain services such as financial business consultation and solving business problems.

[0066] Currently, in the call centers of enterprises or institutions, the method of quantitatively allocating incoming call resources is mainly adopted to meet the incoming call needs of customers. However, in actual applications, due to different business characteristics at different time points, the incoming call volume may show different trends from Monday to Sunday, and there are also differences in the trends at different times of the day. When the incoming call demand is large, the method of quantitatively allocating incoming call resources is difficult to meet the incoming call needs of customers.

[0067] Based on this, the embodiments of the present application provide a method and device for allocating incoming call resources, an electronic device, and a storage medium, aiming to improve the accuracy of incoming call resource allocation.

[0068] The method and device for allocating incoming call resources, the electronic device, and the storage medium provided by the embodiments of the present application are specifically described through the following embodiments. First, the method for allocating incoming call resources in the embodiments of the present application is described.

[0069] 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.

[0070] Artificial intelligence basic technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, and mechatronics. Artificial intelligence software technologies mainly include several major directions such as computer vision technology, robotics, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0071] The incoming resource allocation method provided by the embodiments of the present application relates to the field of artificial intelligence technology. The incoming resource allocation method provided by the embodiments of the present application can be applied to a terminal, or to a server side, or can be software running on a terminal or a 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 can be configured as a server cluster or a distributed system composed of multiple physical servers, or can be configured as a cloud server providing 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 incoming resource allocation method, etc., but is not limited to the above forms.

[0072] 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, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on. 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 a distributed computing environment where 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.

[0073] It should be noted that in each specific embodiment of the present application, when it comes to relevant processing that needs to be based on data related to the user's identity or characteristics, such as user information, user behavior data, user historical data, and user location information, etc., the user's permission or consent will be obtained first. Moreover, the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiments of the present application need to obtain the user's sensitive personal information, the user's separate permission or separate consent will be obtained through methods such as pop-up windows or jumping to a confirmation page. After clearly obtaining the user's separate permission or separate consent, the necessary user-related data for the normal operation of the embodiments of the present application will be obtained.

[0074] Figure 1 is an optional flowchart of the incoming resource allocation method provided by the embodiments of the present application, Figure 1 The method in may include but is not limited to steps S101 to S107.

[0075] Step S101: Obtain the historical incoming call volume;

[0076] Step S102: Based on the historical incoming call volume, perform daily call volume prediction to obtain the target daily incoming call volume prediction data;

[0077] Step S103: Based on the historical incoming call volume, perform time period call volume prediction to obtain the initial time period incoming call volume prediction data;

[0078] Step S104: Analyze the impact duration of the pre - obtained target unexpected event to obtain the event duration;

[0079] Step S105: Based on the event duration, perform time period division to obtain the event time period data;

[0080] Step S106: Based on the event type of the target unexpected event and the event time period data, correct the initial time period incoming call volume prediction data to obtain the target time period incoming call volume prediction data;

[0081] Step S107: Perform incoming resource allocation based on the target daily incoming call volume prediction data and the target time period incoming call volume prediction data.

[0082] Steps S101 to S107 shown in the embodiments of the present application, by performing daily call volume prediction and time period call volume prediction based on the historical incoming call volume, obtain the target daily incoming call volume prediction data and the initial time period incoming call volume prediction data, thereby obtaining the benchmark call volume prediction data. Then, introduce the target unexpected event, analyze the impact duration of the target unexpected event to obtain the event duration, perform time period division based on the event duration to obtain the event time period data; furthermore, based on the event type of the target unexpected event and the event time period data, correct the initial time period incoming call volume prediction data to obtain the target time period incoming call volume prediction data, which can combine and correct the impact of the target unexpected event on the initial time period incoming call volume prediction data to obtain more accurate target time period incoming call volume prediction data, facilitating subsequent resource allocation. Finally, perform incoming resource allocation based on the target daily incoming call volume prediction data and the target time period incoming call volume prediction data, which can not only meet the daily call volume peak - valley requirements but also quickly respond to unexpected events, improve the accuracy and adaptability of incoming resource allocation, and enhance the service response efficiency and customer satisfaction.

[0083] In step S101 of some embodiments, the historical incoming call volume is the data obtained after being pre - collected and processed in a specific application scenario.

[0084] For example, in a fintech scenario, the inbound call volume data of an insurance department's call center over a preset time period in the past can be obtained and processed. Here, the preset time period can be one month, one quarter, or one year, and specifically, it needs to be set in combination with the actual application scenario, not limited to this.

[0085] In some embodiments, step S101 may include but is not limited to the following steps:

[0086] Obtain the original inbound call volume;

[0087] Perform a missing value test on the original inbound call volume to obtain the initial inbound call volume;

[0088] Perform an outlier test on the initial inbound call volume to obtain the historical inbound call volume.

[0089] Specifically, the original inbound call volume is the original data collected from a specific application scenario without any preprocessing.

[0090] For the missing values in the original inbound call volume, the mean value of the original inbound call volume or a preset value can be used for filling to obtain the initial inbound call volume. Here, the preset value needs to be set by business personnel according to the actual application scenario, not limited to this.

[0091] Further, after processing the missing values, an outlier detection is performed on the initial inbound call volume based on a preset outlier threshold; where the preset outlier threshold is obtained by performing statistics on the initial inbound call volume. Specifically, a box plot statistic can be performed on the initial inbound call volume, and the preset outlier threshold is set to Q1 - 1.5×IQR or Q3 + 1.5×IQR. Data exceeding the preset outlier threshold is regarded as an outlier.

[0092] If there are outliers, the mean value or median of the initial inbound call volume can be used to replace the outliers; linear interpolation, polynomial interpolation, etc. can also be used to replace the outliers; in addition, manual identification can also be used to detect outliers in the historical inbound call volume and replace the outliers based on manual experience, not limited to this.

[0093] It should be noted that the historical inbound call volume includes the historical daily inbound call volume, which is used to represent the inbound call volume of each day in the past, and each historical daily inbound call volume also records the inbound call volume of each time period on that day. For example, from 09:00 to 10:00 in the morning, the inbound call volume is 500 times.

[0094] In step S102 of some embodiments, the historical incoming call volume is predicted for the daily call volume through a preset daily call volume prediction model to obtain the target daily incoming call volume prediction data. Specifically, the daily call volume prediction model can adopt an autoregressive model. The autoregressive model can predict the current value of a variable based on historical values and is suitable for the task of predicting future incoming call volumes based on historical incoming call volumes.

[0095] It should be noted that the daily call volume prediction model predicts the target daily incoming call volume prediction data for the next week based on the historical daily incoming call volumes in the past preset number of weeks, rather than blindly selecting all historical daily incoming call volumes, which may affect the accuracy of predicting future incoming call volumes. Among them, the preset number of weeks can be set to 3 weeks, 4 weeks, 8 weeks, etc., and specific settings need to be combined with the actual application scenario and are not limited to this.

[0096] It can be understood that there is a large degree of uncertainty in the incoming call volumes in the next few weeks or months. Therefore, the daily call volume prediction model only predicts the target daily incoming call volume prediction data for the next week, which can reduce the interference of long-term uncontrollable variables, meet the actual business needs, and help improve the accuracy and practicality of the prediction.

[0097] However, in some other embodiments, the daily call volume prediction model can also predict the target daily incoming call volume prediction data for the next few weeks or months, and specific settings need to be combined with the actual application scenario and are not limited to this.

[0098] Please refer to Figure 2 , in some embodiments, step S102 may include but is not limited to steps S201 to S203:

[0099] Step S201, obtain the preset daily call volume prediction parameters; among them, the daily call volume prediction parameters include the first historical weight data and the historical daily prediction interference value;

[0100] Step S202, perform aggregation calculation based on the first historical weight data and the historical daily incoming call volume to obtain the initial daily incoming call volume prediction data;

[0101] Step S203, adjust the initial daily incoming call volume prediction data based on the historical daily prediction interference value to obtain the target daily incoming call volume prediction data.

[0102] Steps S201 to S203 shown in the embodiments of the present application, by obtaining preset daily call volume prediction parameters, which include first historical weight data and historical daily prediction interference values, ensure that the daily call volume prediction can conform to the historical call volume pattern and fluctuation situation. Then, based on the aggregation calculation of the first historical weight data and the historical daily incoming call volume, the initial daily incoming call volume prediction data is obtained, and the initial daily incoming call volume prediction data is adjusted based on the historical daily prediction interference value to obtain the target daily incoming call volume prediction data, which can combine long-term rules and short-term corrections, avoid simply relying on historical data, and achieve more accurate daily call volume prediction.

[0103] In step S201 of some embodiments, the preset daily call volume prediction parameters are the model parameters of the daily call volume prediction model, where the daily call volume prediction model is pre-trained according to historical sample data.

[0104] The daily call volume prediction parameters include first historical weight data, historical daily prediction interference values, and first historical week parameters;

[0105] Among them, the first historical weight data is used to represent the reference degree of the incoming call volume in a certain week in the past to the incoming call volume in the next week. For example: the shorter the distance from the current time, the larger the first historical weight data, and the longer the distance from the current time, the smaller the first historical weight data.

[0106] The historical daily prediction interference value is used to add some volatility to the predicted incoming call volume data to avoid mechanically relying on historical incoming call volume for prediction.

[0107] The first historical week parameter is used to represent how many weeks of historical daily incoming call volume in the past are selected for prediction.

[0108] Specifically, for the calculation formula of the target daily incoming call volume prediction data, refer to formula (1):

[0109]

[0110] Among them, the value of d ranges from 1 to 7, representing the 1st day to the 7th day of a week,

[0111] Num_call d represents the target daily incoming call volume prediction data for the dth day of the next week,

[0112] m represents pushing forward m weeks, that is, the first historical week parameter,

[0113] represents the historical daily incoming call volume on the dth day of the ith week pushed forward,

[0114] represents the first historical weight data of the ith week pushed forward,

[0115] represents the predicted data of the incoming call volume on the initial day.

[0116] represents the historical daily prediction interference value on the d-th day of the i-th week counted backwards.

[0117] In some embodiments, the first historical week parameter m can be the past two weeks, the past three weeks, or the past four weeks. Specifically, it needs to be selected in combination with the actual application scenario and is not limited to this.

[0118] In step S103 of some embodiments, the historical incoming call volume is predicted for the time period through a preset time period call volume prediction model to obtain the predicted data of the initial time period incoming call volume. Specifically, the time period call volume prediction model can adopt an autoregressive model. The autoregressive model can predict the current value of a variable based on historical values and is suitable for the task of predicting future incoming call volumes based on historical incoming call volumes.

[0119] It should be noted that the time period call volume prediction model predicts the predicted data of the initial time period incoming call volume for the next week based on the historical time period incoming call volume in the past preset number of weeks, rather than blindly selecting all historical time period incoming call volumes, which may affect the accuracy of predicting future incoming call volumes. Among them, the preset number of weeks can be set to 3 weeks, 4 weeks, 8 weeks, etc. Specifically, it needs to be set in combination with the actual application scenario and is not limited to this.

[0120] It can be understood that there is a large uncertainty in the incoming call volume in the next few weeks or months. Therefore, the time period call volume prediction model only predicts the predicted data of the initial time period incoming call volume for the next week, which can reduce the interference of long-term uncontrollable variables, fit the actual business needs, and help improve the accuracy and practicality of the prediction.

[0121] In some other embodiments, the time period call volume prediction model can also predict the predicted data of the target time period incoming call volume for the next few weeks or months. Specifically, it needs to be set in combination with the actual application scenario and is not limited to this.

[0122] Please refer to Figure 3 , in some embodiments, step S103 may include but is not limited to steps S301 to S304:

[0123] Step S301, divide the historical daily incoming call volume into time periods to obtain the historical time period incoming call volume;

[0124] Step S302, obtain the preset time period call volume prediction parameters; among them, the time period call volume prediction parameters include the second historical weight data and the historical time period prediction interference value;

[0125] Step S303: Based on the second historical weight data and the incoming call volume in the historical period, perform aggregation calculation to obtain the predicted incoming call volume data for the original period.

[0126] Step S304: Adjust the predicted incoming call volume data for the original period based on the predicted interference value in the historical period to obtain the initial predicted incoming call volume data for the day.

[0127] Steps S301 to S304 illustrated in the embodiments of the present application, by dividing the historical daily incoming call volume into time periods, obtain the incoming call volume in the historical period, which is convenient for subsequent implementation of more fine-grained prediction of the incoming call volume. Then, obtain the preset time period call volume prediction parameters, which include the second historical weight data and the predicted interference value in the historical period, to ensure that the call volume prediction in the time period can conform to the historical call volume law and fluctuation situation. Further, based on the second historical weight data and the incoming call volume in the historical period, perform aggregation calculation to obtain the predicted incoming call volume data for the original period, and adjust the predicted incoming call volume data for the original period based on the predicted interference value in the historical period to obtain the initial predicted incoming call volume data for the time period, which can combine long-term rules and short-term corrections, avoid simply relying on historical data, and achieve more accurate prediction of the call volume in the time period.

[0128] In step S301 of some embodiments, based on the preset time period division threshold, divide the historical daily incoming call volume into time periods to obtain the incoming call volume in the historical period. Among them, the preset time period division threshold can be selected as 15 minutes, or 20 minutes, or 30 minutes, one hour, etc. Specifically, it needs to be set in combination with the actual application scenario, and is not limited thereto.

[0129] In step S302 of some embodiments, the preset time period call volume prediction parameter is the model parameter of the time period call volume prediction model, where the time period call volume prediction model is pre-trained according to historical sample data.

[0130] The time period call volume prediction parameters include the second historical weight data, the predicted interference value in the historical period, and the second historical week parameter;

[0131] Among them, the second historical weight data is used to represent the reference degree of the incoming call volume in a certain week in the past to the predicted incoming call volume in the next week. For example: the shorter the distance from the current time, the larger the second historical weight data, and the longer the distance from the current time, the smaller the second historical weight data.

[0132] It should be noted that the first historical weight data and the second historical weight data are different data.

[0133] The predicted interference value in the historical period is used to add some volatility to the predicted incoming call volume data to avoid mechanically relying on the historical incoming call volume for prediction.

[0134] The second historical week parameter is used to characterize how many weeks of historical incoming call volume in the past are selected for prediction.

[0135] It should be noted that the first historical week parameter and the second historical week parameter can be the same data or different data.

[0136] Specifically, the preset time period division threshold can be selected as 15 minutes, that is, one time period is 15 minutes. For the calculation formula of the predicted data of the incoming call volume in the initial time period, see formula (2):

[0137]

[0138] Among them, the value of d is 1 - 7, representing the 1st day to the 7th day of a week.

[0139] The value of t is 1 - 96, that is, 60 minutes divided by 15 minutes, and then multiplied by 24, representing the 1st time period to the 96th time period of a day.

[0140] Num_call d*t Represents the predicted data of the initial incoming call volume at the t-th moment on the d-th day of the next week.

[0141] n represents pushing back n weeks, that is, the second historical week parameter.

[0142] Represents the incoming call volume of the historical time period at the t-th moment on the d-th day of the i-th week pushed back.

[0143] Represents the second historical weight data of the i-th week pushed back.

[0144] Represents the predicted data of the original time period incoming call volume.

[0145] Represents the historical time period prediction interference value at the t-th moment on the d-th day of the i-th week pushed back.

[0146] In some embodiments, the second historical week parameter n can be the past two weeks, or the past three weeks, or the past four weeks. Specifically, it needs to be selected in combination with the actual application scenario, and is not limited to this.

[0147] It should be noted that if the preset time period division threshold can be selected as 30 minutes, then the value of t is 1 - 48, that is, 60 minutes divided by 30 minutes, and then multiplied by 24.

[0148] In step S104 of some embodiments, the pre-obtained target emergency events are emergency events that may occur within the next week, including but not limited to sudden climate events generated based on weather forecasts, SMS marketing events generated based on business requirements, market sales events based on e-commerce or other channels, etc., and are not limited thereto.

[0149] Among them, each target emergency event has a time attribute. For example:

[0150] The sudden climate event will have an expected time. For example, in the case of a typhoon, it will land in a certain place at about X o'clock on X day of X month, and extremely heavy rain will occur locally within the next 24 / 48 hours;

[0151] The SMS marketing event and the marketing event will have the start time and end time of the marketing activity.

[0152] Therefore, it is necessary to analyze the influence duration of the time attribute of the target emergency event to obtain the event duration.

[0153] In step S105 of some embodiments, the standard for dividing the event duration into time periods is the same as the standard for dividing the historical daily incoming call volume into time periods, that is, based on a preset time period division threshold, the event duration is divided into time periods to obtain event time period data.

[0154] In some embodiments, each target emergency event also has a type attribute, that is, the emergency type of the emergency event; among them, the emergency type of the emergency event is used to characterize the emergency level of the target emergency event.

[0155] Please refer to Figure 4 , in some embodiments, step S106 may include but not limited to steps S401 to S403:

[0156] Step S401, determining the call volume correction parameter based on the emergency type of the emergency event;

[0157] Step S402, screening the initial time period incoming call volume prediction data based on the event time period data to obtain the candidate time period incoming call volume prediction data;

[0158] Step S403, adjusting the candidate time period incoming call volume prediction data based on the call volume correction parameter and the event time period data to obtain the target time period incoming call volume prediction data.

[0159] Steps S401 to S403 shown in the embodiments of the present application determine preset call volume correction parameters based on the event type of the target emergency event to ensure the matching of the correction parameters with the target emergency event. Then, based on the event period data, data screening is performed on the initial period incoming call volume prediction data to exclude irrelevant periods, lock the initial period incoming call volume prediction data that needs to be corrected, and confirm it as the candidate period incoming call volume prediction data, which helps to achieve fine-grained incoming call volume correction. Finally, based on the call volume correction parameters and the event period data, the candidate period incoming call volume prediction data is adjusted, and combined with the non-linear impact of the target emergency event, the target period incoming call volume prediction data is obtained, which can effectively solve the problem that the call volume prediction model cannot respond to sudden factors, especially applicable to scenarios where the incoming call volume suddenly changes such as meteorological time, e-commerce big promotions, and public crises, improve the accuracy of incoming call volume prediction, and provide a more reliable decision-making basis for incoming resource allocation.

[0160] In step S401 of some embodiments, the call volume correction parameters are pre-set according to the actual application scenario, and the call volume correction parameters include call volume peak data and call volume standard deviation data.

[0161] It should be noted that through research and analysis, it is known that the impact of emergency events on the incoming call volume approximately satisfies a normal distribution with a mean of 0, and the standard deviation of the normal distribution needs to be determined according to the emergency type of the emergency event. For different emergency events, with different emergency types of emergency events, the standard deviation of the normal distribution is also different.

[0162] Therefore, it is necessary to determine the corresponding standard deviation of the normal distribution based on the emergency type of the emergency event, and confirm the standard deviation as the call volume standard deviation data;

[0163] The call volume peak data is used to characterize the peak number of incoming call volume increases after the occurrence of the target emergency event.

[0164] For example: The emergency types of emergency events can be divided into four levels, which are sorted from high to low in terms of emergency degree as follows: the first level, the second level, the third level, and the fourth level.

[0165] Among them, the call volume peak data of the first level is x1, and the call volume standard deviation data is y1;

[0166] The call volume peak data of the second level is x2, and the call volume standard deviation data is y2;

[0167] The call volume peak data of the third level is x3, and the call volume standard deviation data is y3;

[0168] The call volume peak data of the fourth level is x4, and the call volume standard deviation data is y4;

[0169] where x1 > x2 > x3 > x4 and y4 > y3 > y2 > y1;

[0170] It should be noted that the smaller the standard deviation data of the call volume, the "sharper" the normal distribution curve, that is, the stronger the concentration of the incoming call volume brought by emergencies.

[0171] In step S402 of some embodiments, based on the event period data, the initial period incoming call volume prediction data is screened, the initial period incoming call volume prediction data that needs to be corrected is locked, and it is confirmed as the candidate period incoming call volume prediction data, which helps to achieve fine-grained correction of the incoming call volume.

[0172] Please refer to Figure 5 , in some embodiments, step S403 may further include but is not limited to steps S501 to S503:

[0173] Step S501, calculate a coefficient based on the call volume correction parameter and the event period data to obtain an incoming call volume correction coefficient;

[0174] Step S502, perform call volume correction on the candidate period incoming call volume prediction data based on the incoming call volume correction coefficient to obtain the corrected period incoming call volume prediction data;

[0175] Step S503, update the initial period incoming call volume prediction data based on the corrected period incoming call volume prediction data to obtain the target period incoming call volume prediction data.

[0176] Steps S501 to S503 shown in the embodiments of the present application calculate a coefficient through the call volume correction parameter and the event period data to obtain an incoming call volume correction coefficient. Then, based on the incoming call volume correction coefficient, the candidate period incoming call volume prediction data is corrected to obtain the corrected period incoming call volume prediction data. Finally, based on the corrected corrected period incoming call volume prediction data, the initial period incoming call volume prediction data is updated to obtain the target period incoming call volume prediction data, which can improve the accuracy of the incoming call volume prediction and provide a more reliable decision-making basis for the allocation of incoming resources.

[0177] Please refer to Figure 6 , in some embodiments, step S501 includes but is not limited to steps S601 to S602:

[0178] Step S601, calculate the time difference between the candidate period incoming call volume prediction data and the event period data to obtain an event development factor;

[0179] Step S602, perform aggregation calculation based on the event development factor, the call volume peak data, and the call volume standard deviation data to obtain an incoming call volume correction coefficient.

[0180] In the steps S601 to S602 illustrated in the embodiments of the present application, by calculating the time difference between the predicted incoming call volume data in the candidate time period and the event time period data, the time difference between the time period where the predicted incoming call volume data in the candidate time period is located and the peak of the normal distribution is measured, so as to evaluate the stage where the time period where the predicted incoming call volume data in the candidate time period is located in the development process of the target unexpected event, and an event development factor is obtained. Further, based on the event development factor, the call volume peak data and the call volume standard deviation data, an aggregation calculation is performed to obtain an incoming call volume correction coefficient, which is convenient for subsequent call volume correction based on the incoming call volume correction coefficient, and improves the accuracy of the predicted incoming call volume.

[0181] In step S601 of some embodiments, first, obtain the number of time periods included in the event time period data to obtain the first number of time periods, and after rounding the midpoint of the first number of time periods, obtain the event peak time period number. Then, obtain the original time period number of the time period where the predicted incoming call volume data in the candidate time period is located, and perform a difference calculation between the original time period number and the event peak time period number to obtain the event development factor.

[0182] In step S602 of some embodiments, based on the event development factor, the call volume peak data and the call volume standard deviation data, an aggregation calculation is performed to obtain an incoming call volume correction coefficient. For details, refer to formula (3):

[0183]

[0184] Among them, f(N) is the incoming call volume correction coefficient,

[0185] Pvalue is the call volume peak data,

[0186] N is the original time period number, μ is the event peak time period number, (N - μ) is the event development factor,

[0187] σ is the call volume standard deviation data.

[0188] In step S502 of some embodiments, after calculating the incoming call volume correction coefficient, perform a multiplication operation on the incoming call volume correction coefficient and the predicted incoming call volume data in the candidate time period to obtain the predicted incoming call volume data in the corrected time period, so as to realize the call volume correction of the predicted incoming call volume data in the candidate time period. For details, refer to formula (4):

[0189] Num_call′ N =f(N)*Num_call N (4);

[0190] Among them, Num_call′ N is the predicted incoming call volume data in the corrected time period, and Num_call N is the predicted incoming call volume data in the candidate time period.

[0191] In step S503 of some embodiments, after calculating the predicted incoming call volume data for the correction period, the corresponding data in the predicted incoming call volume data for the initial period is replaced based on the predicted incoming call volume data for the correction period to obtain the predicted incoming call volume data for the target period.

[0192] Please refer to Figure 7 , in some embodiments, step S107 may include but is not limited to steps S701 to S704:

[0193] Step S701, obtain a preset seat resource pool;

[0194] Step S702, perform seat calculation based on the predicted incoming call volume data for the target period to obtain the original number of seats;

[0195] Step S703, obtain candidate seat objects by acquiring resources from the preset seat resource pool based on the original number of seats;

[0196] Step S704, perform seat arrangement for the candidate seat objects based on the predicted incoming call volume data for the target day and the predicted incoming call volume data for the target period.

[0197] Steps S701 to S704 illustrated in the embodiments of the present application calculate the original number of seats by performing seat calculation based on the predicted incoming call volume data for the target period to meet the basic seat resource requirements for the current day. Then, candidate seat objects are obtained by acquiring resources from the preset seat resource pool based on the original number of seats. Finally, refined seat arrangement is performed for the candidate seat objects in combination with the predicted incoming call volume data for the target day and the predicted incoming call volume data for the target period to meet the seat resource requirements for different periods, improving the accuracy of incoming resource allocation.

[0198] In step S701 of some embodiments, the preset seat resource pool is a pre-constructed set containing multiple alternative seat objects for providing seat resources for actual business. Among them, the alternative seat objects are artificial seats.

[0199] In step S702 of some embodiments, the largest data among all the predicted incoming call volume data for the target period on the current day is obtained and determined as the maximum incoming call volume and the peak period. Then, seat calculation is performed based on the maximum incoming call volume to obtain the original number of seats.

[0200] For example:

[0201] Taking 15 minutes as a period, the maximum incoming call volume is 150 calls. It is calculated that the incoming call volume is 10 calls per minute. The average call duration for each incoming call is 180 seconds, and the average post-processing duration is 60 seconds, that is, the average processing time for one incoming call is 4 minutes.

[0202] Next, set a redundancy coefficient, such as 1.3, to avoid the long-term occupation of agent resources due to special incoming calls, which may affect the connection of subsequent incoming calls.

[0203] Perform a product calculation on the preset queuing coefficient, incoming call volume, and average processing time, that is, 1.3 * 10 * 4 = 52. Therefore, the original number of agents is 52.

[0204] It should be noted that after calculating the incoming call volume and average processing time, in addition to using the product calculation method, other calculation formulas can also be used; in addition, the queuing coefficient can be set to 1.2, 1.5, etc. in addition to 1.3, and is not limited thereto.

[0205] It can be understood that if the original number of agents can meet the requirements during the period with the largest predicted incoming call volume in the target time period, it can meet the requirements of the remaining time periods. Therefore, the agent scheduling is based on the original number of agents.

[0206] In step S703 of some embodiments, candidate agent objects are selected from the preset agent resource pool based on the original number of agents to obtain candidate agent objects;

[0207] It can be understood that if the alternative agent objects are human agents, they belong to human resources. Therefore, the act of selecting alternative agent objects from the preset agent resource pool belongs to a resource acquisition act.

[0208] It should be noted that the alternative agent objects can perform outbound tasks or inbound tasks, while the candidate agent objects determined from the preset agent resource pool based on the original number of agents mainly perform inbound tasks, that is, answering the calls actively made by customers or users to meet the needs of customers or users such as business consultation, complaint, after-sales support, order query, etc.

[0209] In step S704 of some embodiments, the peak time period is determined based on the predicted incoming call volume data for the target time period;

[0210] Based on the peak time period, determine the initial scheduling time periods, such as 08:00 - 16:00, 14:00 - 22:00. Among them, the overlapping parts between the initial scheduling time periods need to cover the peak time period so that the incoming call requirements during the peak time period can be met.

[0211] Next, calculate the proportion of incoming call volume based on the predicted incoming call volume data for the target day and the predicted incoming call volume data for the target time period to obtain the proportion data of incoming call volume for each time period;

[0212] Finally, allocate the corresponding candidate agent objects to each initial scheduling time period based on the proportion data of incoming call volume for each time period.

[0213] For example, if the peak period is from 15:00 to 15:15, the initial scheduling period can be set to 08:00 - 16:00 and 14:00 - 22:00; the original number of agents is 52, that is, there are 52 candidate agent objects.

[0214] Based on the proportion data of the incoming call volume in each period, determine the number of candidate agent objects corresponding to each initial scheduling period as follows:

[0215] 08:00 - 16:00, 22 people;

[0216] 14:00 - 22:00, 30 people.

[0217] In some other embodiments, the initial scheduling period can also be divided into more fine-grained scheduling periods, so as to support adjusting the agent scheduling according to the period, avoiding the situation of insufficient or excessive redundant agent resources, and improving the accuracy of incoming resource allocation.

[0218] Please refer to Figure 8 , the embodiment of the present application also provides an incoming resource allocation device, which can implement the above incoming resource allocation method. The device includes:

[0219] A historical data acquisition module 801, configured to acquire historical incoming call volumes;

[0220] A daily call volume prediction module 802, configured to predict the daily call volume based on the historical incoming call volumes to obtain target daily incoming call volume prediction data;

[0221] A period call volume prediction module 803, configured to predict the period call volume based on the historical incoming call volumes to obtain initial period incoming call volume prediction data;

[0222] A time duration analysis module 804, configured to analyze the impact duration of a pre-acquired target unexpected event to obtain the event duration;

[0223] An event period division module 805, configured to divide the period based on the event duration to obtain event period data;

[0224] A period call volume correction module 806, configured to correct the initial period incoming call volume prediction data based on the event type of the target unexpected event and the event period data to obtain target period incoming call volume prediction data;

[0225] A resource allocation module 807, configured to perform incoming resource allocation based on the target daily incoming call volume prediction data and the target period incoming call volume prediction data.

[0226] The specific implementation manner of this incoming resource allocation device is basically the same as the specific embodiment of the above incoming resource allocation method, and will not be elaborated here.

[0227] The embodiment of the present application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the above-mentioned incoming resource allocation method is implemented. The electronic device can be any intelligent terminal including a tablet computer, a vehicle-mounted computer, etc.

[0228] Please refer to Figure 9 , Figure 9 which shows the hardware structure of the electronic device in another embodiment. The electronic device includes:

[0229] A processor 901, which can be implemented in ways such as a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided by the embodiments of the present application;

[0230] A memory 902, which can be implemented in forms such as 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 application programs. When implementing the technical solutions provided by the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 902 and are called by the processor 901 to execute the incoming resource allocation method of the embodiments of the present application;

[0231] An input / output interface 903, which is used to implement information input and output;

[0232] A communication interface 904, which is used to implement communication interaction between this device and other devices, and can implement communication through a wired method (such as USB, network cable, etc.) or through a wireless method (such as a mobile network, WIFI, Bluetooth, etc.);

[0233] A bus 905, which transmits information between various components of the device (such as the processor 901, the memory 902, the input / output interface 903, and the communication interface 904);

[0234] Among them, the processor 901, the memory 902, the input / output interface 903, and the communication interface 904 are communicatively connected to each other inside the device through the bus 905.

[0235] The embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the above-mentioned incoming resource allocation method is implemented.

[0236] As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory may optionally include a memory remotely provided relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the above-mentioned network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0237] The incoming resource allocation method, device, electronic device, and storage medium provided by the embodiment of the present application predict the daily call volume and the call volume in time periods based on the historical incoming call volume, so as to obtain the target daily incoming call volume prediction data and the initial call volume prediction data in time periods, and thus obtain the benchmark call volume prediction data. Then, a target unexpected event is introduced, the influence duration of the target unexpected event is analyzed to obtain the event duration, and time period division is performed based on the event duration to obtain the event time period data; furthermore, the initial call volume prediction data in time periods is corrected based on the event type and the event time period data of the target unexpected event to obtain the target call volume prediction data in time periods, which can combine the influence of the target unexpected event on the initial call volume prediction data in time periods and perform correction to obtain more accurate target call volume prediction data in time periods, facilitating subsequent outbound resource arrangement. Finally, incoming resource allocation is performed based on the target daily incoming call volume prediction data and the target call volume prediction data in time periods, which can not only meet the daily call volume peak and valley requirements, but also quickly respond to unexpected events, improve the accuracy and adaptability of incoming resource allocation, and enhance the service response efficiency and customer satisfaction.

[0238] The embodiments described in the embodiments of the present application are for more clearly illustrating the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art know that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.

[0239] Those skilled in the art can understand 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 those shown in the figures, or combine some steps, or different steps.

[0240] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0241] Those of ordinary skill in the art can understand that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, and their appropriate combinations.

[0242] As used in the specification of this application and the above-mentioned drawings, the terms "first", "second", "third", "fourth", etc. (if any) are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily limit to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0243] It should be understood that in this application, "at least one (item)" means one or more, and "multiple" means two or more. "And / or" is used to describe the association relationship of associated objects and indicates that three relationships can exist. For example, "A and / or B" can represent: only A exists, only B exists, and both A and B exist at the same time. Among them, A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after. "At least one (item) of the following" or its similar expression refers to any combination of these items, including any combination of single item (item) or plural items (items). For example, at least one (item) of a, b, or c can represent: 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.

[0244] In several embodiments provided in this 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 merely illustrative. For example, the above division of units is only a logical function division. In actual implementation, there may be other division methods. For example, 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 displayed or discussed couplings or direct couplings or communication connections between each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be in electrical, mechanical or other forms.

[0245] The units described above as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0246] In addition, in each embodiment of this application, each functional unit can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0247] 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 such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in each embodiment of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store programs.

[0248] The preferred embodiments of the embodiments of this application have been described above with reference to the accompanying drawings, but this does not limit the scope of rights of the embodiments of this application. Any modifications, equivalent replacements, and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of this application shall be within the scope of rights of the embodiments of this application.

Claims

1. A method for allocating incoming resources, characterized in that, The method includes: Obtaining historical incoming call volume; Performing daily call volume prediction based on the historical incoming call volume to obtain target daily incoming call volume prediction data; Performing time period call volume prediction based on the historical incoming call volume to obtain initial time period incoming call volume prediction data; Analyzing the impact duration of a pre-obtained target emergency event to obtain the event duration; Performing time period division based on the event duration to obtain event time period data; Correcting the initial time period incoming call volume prediction data based on the event type of the target emergency event and the event time period data to obtain target time period incoming call volume prediction data; Performing incoming resource allocation based on the target daily incoming call volume prediction data and the target time period incoming call volume prediction data.

2. The method according to claim 1, characterized in that The correcting the initial time period incoming call volume prediction data based on the event type of the target emergency event and the event time period data to obtain target time period incoming call volume prediction data includes: Determining a call volume correction parameter based on the emergency type of the emergency event; Performing data screening on the initial time period incoming call volume prediction data based on the event time period data to obtain candidate time period incoming call volume prediction data; Adjusting the candidate time period incoming call volume prediction data based on the call volume correction parameter and the event time period data to obtain the target time period incoming call volume prediction data.

3. The method according to claim 2, characterized in that, The adjusting the candidate time period incoming call volume prediction data based on the call volume correction parameter and the event time period data to obtain the target time period incoming call volume prediction data includes: Calculating a coefficient based on the call volume correction parameter and the event time period data to obtain an incoming call volume correction coefficient; Performing call volume correction on the candidate time period incoming call volume prediction data based on the incoming call volume correction coefficient to obtain corrected time period incoming call volume prediction data; Updating the data of the initial time period incoming call volume prediction data based on the corrected time period incoming call volume prediction data to obtain the target time period incoming call volume prediction data.

4. The method according to claim 3, wherein The call volume correction parameter includes call volume peak data and call volume standard deviation data; the calculating a coefficient based on the call volume correction parameter and the event time period data to obtain an incoming call volume correction coefficient includes: Calculating a time difference between the candidate time period incoming call volume prediction data and the event time period data to obtain an event development factor; Performing aggregation calculation based on the event development factor, the call volume peak data, and the call volume standard deviation data to obtain the incoming call volume correction coefficient.

5. The method according to claim 1, wherein The historical incoming call volume includes historical daily incoming call volume; the performing daily call volume prediction based on the historical incoming call volume to obtain target daily incoming call volume prediction data includes: Obtaining preset daily call volume prediction parameters; wherein, the daily call volume prediction parameters include first historical weight data and historical daily prediction interference values; Performing aggregation calculation based on the first historical weight data and the historical daily incoming call volume to obtain initial daily incoming call volume prediction data; Adjusting the initial daily incoming call volume prediction data based on the historical daily prediction interference values to obtain the target daily incoming call volume prediction data.

6. The method according to claim 5, wherein Performing call volume prediction for time periods based on the historical incoming call volume to obtain initial predicted data for incoming call volume in time periods, including: Dividing the historical daily incoming call volume into time periods to obtain the historical incoming call volume in time periods; Obtaining preset prediction parameters for call volume in time periods; wherein, the prediction parameters for call volume in time periods include second historical weight data and historical time period prediction interference values; Performing aggregation calculation based on the second historical weight data and the historical incoming call volume in time periods to obtain original predicted data for incoming call volume in time periods; Adjusting the original predicted data for incoming call volume in time periods based on the historical time period prediction interference values to obtain the initial predicted data for daily incoming call volume.

7. The method according to any one of claims 1 to 6, characterized in that Performing allocation of incoming call resources based on the predicted data for the target daily incoming call volume and the predicted data for the target incoming call volume in time periods, including: Obtaining a preset seat resource pool; Performing seat calculation based on the predicted data for the target incoming call volume in time periods to obtain the original number of seats; Obtaining candidate seat objects from the preset seat resource pool based on the original number of seats; Performing seat arrangement for the candidate seat objects based on the predicted data for the target daily incoming call volume and the predicted data for the target incoming call volume in time periods.

8. An incoming resource allocation device, characterized in that, The apparatus includes: A historical data acquisition module for acquiring the historical incoming call volume; A daily call volume prediction module for performing daily call volume prediction based on the historical incoming call volume to obtain predicted data for the target daily incoming call volume; A call volume prediction module for time periods for performing call volume prediction for time periods based on the historical incoming call volume to obtain initial predicted data for incoming call volume in time periods; A time duration analysis module for analyzing the impact duration of a pre-acquired target emergency event to obtain the event duration; An event time period division module for dividing time periods based on the event duration to obtain event time period data; A call volume correction module for time periods for correcting the initial predicted data for incoming call volume in time periods based on the event type of the target emergency event and the event time period data to obtain predicted data for the target incoming call volume in time periods; A resource allocation module for performing allocation of incoming call resources based on the predicted data for the target daily incoming call volume and the predicted data for the target incoming call volume in time periods.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the method according to any one of claims 1 to 7 is implemented.

Images