Call center seat scheduling method, device and equipment and storage medium

Abstract

The invention discloses a call center seat scheduling method, device and equipment and a storage medium, and the method comprises the steps: obtaining historical telephone traffic data and space environment data corresponding to a target call center, and constructing a space-time fusion feature tensor according to the historical telephone traffic data and the space environment data; inputting the space-time fusion feature tensor into a pre-trained convolutional long short-term memory network model, and outputting a future traffic demand prediction result corresponding to the target call center through the convolutional long short-term memory network model; and generating a seat scheduling strategy matched with the target call center according to the future telephone traffic demand prediction result. According to the technical scheme provided by the embodiment of the invention, the flexibility of the seat scheduling scheme is improved, and the scheduling scheme can be ensured to effectively cope with real-time fluctuation data, so that the seat utilization rate of the call center is improved.

Description

Technical Field

[0001] This invention relates to the field of call center operation and management technology, and in particular to a call center agent scheduling method, apparatus, equipment and storage medium. Background Technology

[0002] Currently, call centers, as a big data service architecture, are widely used in the insurance industry. The automatic deployment and adjustment of call center agent scheduling schemes are particularly important for improving the operational efficiency of the insurance industry.

[0003] In existing technologies, when setting up call center agent scheduling schemes, simple routing or load rules are usually used. For example, genetic algorithms are used to optimize the scheduling scheme. However, these methods cannot predict users' future call demands, resulting in low scheduling flexibility and an inability to cope with real-time fluctuations in data, which in turn affects the utilization rate of call center agents. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, and storage medium for scheduling call center agents, which improves the flexibility of agent scheduling schemes and ensures that the scheduling schemes can effectively cope with real-time fluctuations in data, thereby improving the utilization rate of call center agents.

[0005] According to one aspect of the present invention, a call center agent scheduling method is provided, the method comprising:

[0006] Obtain historical call data and spatial environment data corresponding to the target call center, and construct a spatiotemporal fusion feature tensor based on the historical call data and spatial environment data;

[0007] The spatiotemporal fusion feature tensor is input into a pre-trained convolutional long short-term memory network model, and the future call demand prediction result corresponding to the target call center is output through the convolutional long short-term memory network model.

[0008] Based on the predicted future call demand for the target call center, a seat scheduling strategy matching the target call center is generated.

[0009] Optionally, based on the historical call data and spatial environment data, a spatiotemporal fusion feature tensor is constructed, including:

[0010] The spatial environment data is converted into a raster image of a preset size;

[0011] The historical call data and the raster image are stacked to form a four-dimensional spatiotemporal fusion feature tensor.

[0012] Optionally, before inputting the spatiotemporal fusion feature tensor into the pre-trained convolutional long short-term memory network model, the method further includes:

[0013] Obtain the original Long Short-Term Memory network model;

[0014] The fully connected layers in the original long short-term memory network model are replaced with convolutional layers to obtain a convolutional long short-term memory network model.

[0015] Optionally, after obtaining the convolutional long short-term memory network model, the following may also be included:

[0016] Obtain multiple data samples corresponding to the target call center; the multiple data samples include call traffic data samples, spatial environment data samples, and call traffic prediction annotation results;

[0017] The convolutional long short-term memory network model is iteratively trained using the multiple data samples until the training termination condition is met.

[0018] Optionally, based on the predicted future call demand for the target call center, a matching agent scheduling strategy is generated, including:

[0019] Obtain the agent constraints corresponding to the target call center;

[0020] The seat constraints include scheduling constraints and call center personnel constraints.

[0021] Based on the predicted future call demand and seat constraints of the target call center, the pre-set scheduling schedule is dynamically adjusted to obtain the seat scheduling strategy that matches the target call center.

[0022] Optionally, the historical call data includes: call volume data of the target call center within a historical time period, and holiday labeling data corresponding to the call volume data;

[0023] The spatial environment data includes: weather data of the area where the target call center is located, public opinion data of the area, and local event calendar data of the area.

[0024] According to another aspect of the present invention, a call center agent scheduling device is provided, the device comprising:

[0025] The data acquisition module is used to acquire historical call data and spatial environment data corresponding to the target call center, and construct a spatiotemporal fusion feature tensor based on the historical call data and spatial environment data.

[0026] The model prediction module is used to input the spatiotemporal fusion feature tensor into a pre-trained convolutional long short-term memory network model, and output the future call demand prediction result corresponding to the target call center through the convolutional long short-term memory network model.

[0027] The scheduling optimization module is used to generate a seat scheduling strategy that matches the target call center based on the predicted future call demand for the target call center.

[0028] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0029] At least one processor; and

[0030] A memory communicatively connected to the at least one processor; wherein,

[0031] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the call center agent scheduling method according to any embodiment of the present invention.

[0032] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the call center agent scheduling method according to any embodiment of the present invention.

[0033] According to another aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program that, when executed by a processor, implements the call center agent scheduling method according to any embodiment of the present invention.

[0034] The technical solution provided by this invention involves acquiring historical call traffic data and spatial environment data corresponding to a target call center, constructing a spatiotemporal fusion feature tensor based on the historical call traffic data and spatial environment data, inputting the spatiotemporal fusion feature tensor into a pre-trained convolutional long short-term memory network model, outputting a prediction result of future call traffic demand corresponding to the target call center through the convolutional long short-term memory network model, and generating a matching agent scheduling strategy for the target call center based on the prediction result of future call traffic demand corresponding to the target call center. This technical means can optimize the current agent scheduling plan by combining the prediction result of future call traffic demand of the target call center, thereby improving the flexibility of the agent scheduling plan, ensuring that the scheduling plan can effectively cope with real-time fluctuating data, and thus improving the agent utilization rate of the call center.

[0035] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 This is a flowchart of a call center agent scheduling method provided by an embodiment of the present invention;

[0038] Figure 2a This is a flowchart of another call center agent scheduling method provided by an embodiment of the present invention;

[0039] Figure 2b This is a schematic diagram of the data structure corresponding to a convolutional long short-term memory network model provided in an embodiment of the present invention;

[0040] Figure 2c This is a schematic diagram of the internal structure of a convolutional long short-term memory network model provided in an embodiment of the present invention;

[0041] Figure 3 This is a schematic diagram of a call center agent scheduling device according to an embodiment of the present invention;

[0042] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the call center agent scheduling method according to an embodiment of the present invention. Detailed Implementation

[0043] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0044] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0045] Figure 1 This is a flowchart illustrating a call center agent scheduling method provided in an embodiment of the present invention. This embodiment is applicable to optimizing the agent scheduling method for insurance industry call centers. The method can be executed by a call center agent scheduling device, which can be implemented in hardware and / or software and configured in an electronic device (e.g., a terminal or server). Figure 1 As shown, the method includes:

[0046] Step 110: Obtain historical call data and spatial environment data corresponding to the target call center, and construct a spatiotemporal fusion feature tensor based on the historical call data and spatial environment data.

[0047] In this embodiment, the target call center can be a specific call center in the insurance industry. Such call centers typically utilize computer communication technology to handle telephone inquiries from businesses and users, possess the capacity to process a large volume of calls simultaneously, and also feature caller ID display. They can automatically assign incoming calls to personnel with the appropriate skills and record and store all call information.

[0048] Specifically, the target call center may include an agent layer, a session access layer, a session control layer, a softswitch layer, a persistence layer, and a boundary control layer. The agent layer can be divided into different departments, skill groups, etc., based on work areas. The session access layer provides functions such as agent registration, session initiation, media proxy, and interface capabilities. The session control layer implements functions such as session control, service monitoring, Interactive Voice and Video Response (IVVR) broadcasting, queuing, call detail records (CDRs), and intelligent services. The softswitch layer implements functions such as Session Initiation Protocol (SIP) softswitching, routing, protocol encapsulation, audio / video encoding / decoding, and analog-to-digital conversion. The persistence layer provides all the common components required by the call center. The boundary control layer connects the call center to the carrier network.

[0049] In this embodiment, the target call center can be deployed within a unified customer service platform corresponding to the insurance industry. Optionally, the unified customer service platform may include two centrally deployed multimedia contact center systems for unified access and processing of voice, video, and multimedia customer service requests related to insurance business. The service platform may deploy an intelligent voice navigation layer to automatically identify user needs and quickly navigate to corresponding service resources based on the user's natural language description, achieving flattened interaction, shortening user interaction time, and improving user experience.

[0050] Both centrally deployed multimedia contact center systems can uniformly manage and utilize external access channels and internal agent resources, respectively handling service data for different regions, and serving as disaster recovery options for each other. When one multimedia contact center system fails and cannot continue to provide services, the other multimedia contact center system will take over the services corresponding to the failed system, and the corresponding agent resources can also be switched to the other multimedia contact center system for continued use.

[0051] Optionally, the unified customer service platform may include a data layer, a support layer, a core capability layer, and a service layer. It boasts strong overall configurability and scalability, providing value-added service expansion capabilities. Specifically, the data layer stores system data, including business data, configuration data, platform data, log data, and end-to-end audio call data. The support layer supports system service operation, including a SIP voice service platform, data analysis, session configuration, session routing, encapsulated file services, and the core capabilities involved in the system. The core capability layer deploys artificial intelligence algorithms, call capabilities, cloud recording capabilities, gateway routing settings, etc., and can interact with the system's general management module to complete management functions such as user roles and resource configuration. The service layer provides various business services, including agent workstations and intelligent outbound calling services.

[0052] In this step, for a target call center in the insurance industry, historical call data and spatial environment data corresponding to the target call center can be collected, and the historical call data and spatial environment data can be feature-encoded to obtain a spatiotemporal fusion feature tensor.

[0053] Step 120: Input the spatiotemporal fusion feature tensor into the pre-trained convolutional long short-term memory network model, and output the future call demand prediction result corresponding to the target call center through the convolutional long short-term memory network model.

[0054] In this embodiment, the convolutional long short-term memory network model is a deep learning model that combines the advantages of convolutional neural networks (CNN) and long short-term memory networks (LSTM).

[0055] The advantage of this setup is that existing LSTM models can only process time-series data. Since call center traffic data is affected by both time and space factors (such as regional weather and local events), by combining LSTM models with CNN models, the final deep learning model can effectively capture the spatiotemporal features of the traffic data, thereby improving the accuracy and reliability of subsequent model output results.

[0056] Optionally, in this step, after inputting the spatiotemporal fusion feature tensor into the convolutional long short-term memory network model, the convolutional long short-term memory network model can predict the future call demand of the target call center based on the pre-trained model parameters and output the future call demand prediction results.

[0057] Step 130: Generate an agent scheduling strategy that matches the target call center based on the predicted future call demand for the target call center.

[0058] In this embodiment, optionally, after outputting the future call demand prediction result corresponding to the target call center through the convolutional long short-term memory network model, the existing agent scheduling scheme of the target call center can be optimized based on the future call demand prediction result, with the goal of minimizing human costs and maximizing service levels, to obtain the agent scheduling strategy matched to the target call center.

[0059] The technical solution provided by this invention involves acquiring historical call traffic data and spatial environment data corresponding to a target call center, constructing a spatiotemporal fusion feature tensor based on the historical call traffic data and spatial environment data, inputting the spatiotemporal fusion feature tensor into a pre-trained convolutional long short-term memory network model, outputting a prediction result of future call traffic demand corresponding to the target call center through the convolutional long short-term memory network model, and generating a matching agent scheduling strategy for the target call center based on the prediction result of future call traffic demand corresponding to the target call center. This technical means can optimize the current agent scheduling plan by combining the prediction result of future call traffic demand of the target call center, thereby improving the flexibility of the agent scheduling plan, ensuring that the scheduling plan can effectively cope with real-time fluctuating data, and thus improving the agent utilization rate of the call center.

[0060] Figure 2a A flowchart of another call center agent scheduling method provided in an embodiment of the present invention is shown below. Figure 2a As shown, the method includes:

[0061] Step 210: Obtain the original Long Short-Term Memory (LSTM) network model, and replace the fully connected layers in the original LSM network model with convolutional layers to obtain the convolutional LSM network model.

[0062] In this embodiment, Figure 2b This can be a schematic diagram of the data structure corresponding to the convolutional long short-term memory network model, such as... Figure 2b As shown, replacing the fully connected layers in the original Long Short-Term Memory network model with convolutional layers can transform the input data, hidden state data, and cell state data in the replaced model from two-dimensional tensors to three-dimensional tensors. This allows the model to effectively capture the dependencies between temporal and spatial data.

[0063] Step 220: Obtain multiple data samples corresponding to the target call center; the multiple data samples include call traffic data samples, spatial environment data samples, and call traffic prediction labeling results.

[0064] Step 230: Use the multiple data samples to iteratively train the convolutional long short-term memory network model until the convolutional long short-term memory network model meets the training termination condition.

[0065] In this embodiment, optionally, the multiple data samples can be input into the convolutional long short-term memory network model in batches, and the model parameters can be trained according to the output results of the convolutional long short-term memory network model until the output results of the model meet the preset test standards.

[0066] Step 240: Obtain historical call data and spatial environment data corresponding to the target call center, convert the spatial environment data into a raster image of a preset size, and stack the historical call data and the raster image into a four-dimensional spatiotemporal fusion feature tensor.

[0067] In this embodiment, the historical call volume data includes: call volume data of the target call center within a historical time period (e.g., 15 minutes), and holiday labeling data corresponding to the call volume data. The spatial environment data includes: weather data of the area where the target call center is located, public opinion data (e.g., social media public opinion heat map) of the area, and local event calendar data of the area.

[0068] In this step, specifically, the spatial environment data can be converted to 50km. A 50km raster map is used, and then the historical call traffic data is stacked with the raster map to form a four-dimensional spatiotemporal fusion feature tensor with the format (batch, timesteps, height, width, channels). Where batch is the data batch size, timesteps is the time step, height and width are the height and width, respectively, and channels is the number of channels.

[0069] Step 250: Input the spatiotemporal fusion feature tensor into the pre-trained convolutional long short-term memory network model, and output the future call demand prediction result corresponding to the target call center through the convolutional long short-term memory network model.

[0070] In this embodiment, specifically, Figure 2c This can be a schematic diagram of the internal structure of a convolutional long short-term memory network model, such as... Figure 2c As shown, the model may include three data processing layers. The first layer is used to extract spatiotemporal features from the spatiotemporal fusion feature tensor; the second layer is used to process the results extracted by the first layer using a spatial attention mechanism; and the third layer is used to predict future call demand based on the outputs of the first two layers.

[0071] In a specific embodiment, it is assumed that the input data for each data processing layer in the model is: The output of each layer can be determined by the following formula:

[0072]

[0073] in, Indicates weight, Indicates bias. This represents the convolution operation. This indicates element-wise multiplication.

[0074] In this step, specifically, the convolutional long short-term memory network model can output the predicted call demand for each area of ​​the target call center for the next 24 hours.

[0075] Step 260: Obtain the seat constraints corresponding to the target call center, including scheduling constraints and call center personnel constraints.

[0076] In this step, specifically, the scheduling constraints may include parameters such as minimum working hours and number of consecutive shifts, and the call center constraints may include parameters such as the call center staff skill matching degree and preference shift satisfaction rate.

[0077] Step 270: Based on the future call demand forecast results and seat constraints corresponding to the target call center, dynamically adjust the pre-set scheduling plan to obtain the seat scheduling strategy matched to the target call center.

[0078] In this embodiment, optionally, after outputting the future call demand prediction result corresponding to the target call center through the convolutional long short-term memory network model, the target call center's scheduling plan can be dynamically adjusted based on the future call demand prediction result and the agent constraints, with the goal of minimizing human costs and maximizing service levels, using a multi-objective optimization algorithm to obtain the agent scheduling strategy matched to the target call center.

[0079] The technical solution provided by this invention improves the flexibility of the agent scheduling scheme by obtaining the original Long Short-Term Memory (LSTM) network model, replacing the fully connected layers in the original LSM network model with convolutional layers to obtain a Convolutional LSM network model, acquiring multiple data samples corresponding to the target call center, iteratively training the Convolutional LSM network model using the multiple data samples until the Convolutional LSM network model meets the training termination condition, acquiring historical call traffic data and spatial environment data corresponding to the target call center, converting the spatial environment data into a raster image of a preset size, stacking the historical call traffic data and the raster image into a four-dimensional spatiotemporal fusion feature tensor, inputting the spatiotemporal fusion feature tensor into the Convolutional LSM network model, outputting the future call traffic demand prediction result through the Convolutional LSM network model, obtaining the agent constraints corresponding to the target call center, and dynamically adjusting the pre-set scheduling plan according to the future call traffic demand prediction result and agent constraints to obtain the agent scheduling strategy. This technical means improves the flexibility of the agent scheduling scheme, ensures that the scheduling scheme can effectively cope with real-time fluctuation data, and thus improves the agent utilization rate of the call center.

[0080] Figure 3 This is a schematic diagram of a call center agent scheduling device provided in an embodiment of the present invention. The device is applied in electronic equipment, such as... Figure 3 As shown, the device includes: a data acquisition module 310, a model prediction module 320, and a scheduling optimization module 330.

[0081] Data acquisition module 310 is used to acquire historical call data and spatial environment data corresponding to the target call center, and construct a spatiotemporal fusion feature tensor based on the historical call data and spatial environment data;

[0082] The model prediction module 320 is used to input the spatiotemporal fusion feature tensor into a pre-trained convolutional long short-term memory network model, and output the future call demand prediction result corresponding to the target call center through the convolutional long short-term memory network model.

[0083] The scheduling optimization module 330 is used to generate a seat scheduling strategy that matches the target call center based on the prediction results of future call demand corresponding to the target call center.

[0084] The technical solution provided by this invention involves acquiring historical call traffic data and spatial environment data corresponding to a target call center, constructing a spatiotemporal fusion feature tensor based on the historical call traffic data and spatial environment data, inputting the spatiotemporal fusion feature tensor into a pre-trained convolutional long short-term memory network model, outputting a prediction result of future call traffic demand corresponding to the target call center through the convolutional long short-term memory network model, and generating a matching agent scheduling strategy for the target call center based on the prediction result of future call traffic demand corresponding to the target call center. This technique can optimize the current agent scheduling plan by combining the prediction result of future call traffic demand of the target call center, thereby improving the flexibility of the agent scheduling plan, ensuring that the scheduling plan effectively copes with real-time fluctuating data, and thus improving the agent utilization rate of the call center.

[0085] Based on the above embodiments, the historical call data includes: call volume data of the target call center within a historical time period, and holiday labeling data corresponding to the call volume data; the spatial environment data includes: weather data of the area to which the target call center belongs, public opinion data corresponding to the area, and local event calendar data corresponding to the area.

[0086] The data acquisition module 310 includes:

[0087] The feature encoding unit is used to convert the spatial environment data into a raster image of a preset size, and to stack the historical call data and the raster image into a four-dimensional spatiotemporal fusion feature tensor.

[0088] The scheduling optimization module 330 includes:

[0089] The constraint acquisition unit is used to acquire the agent constraints corresponding to the target call center; wherein, the agent constraints include scheduling constraints and call center personnel constraints.

[0090] The scheduling adjustment unit is used to dynamically adjust the pre-set scheduling schedule based on the future call demand forecast results and seat constraints corresponding to the target call center, so as to obtain the seat scheduling strategy that matches the target call center.

[0091] The device further includes:

[0092] The model building module is used to obtain the original long short-term memory network model, and replace the fully connected layers in the original long short-term memory network model with convolutional layers to obtain a convolutional long short-term memory network model.

[0093] The model training module is used to acquire multiple data samples corresponding to the target call center; the multiple data samples include call traffic data samples, spatial environment data samples, and call traffic prediction annotation results; the convolutional long short-term memory network model is iteratively trained using the multiple data samples until the convolutional long short-term memory network model meets the training termination condition.

[0094] The above-described apparatus can execute the methods provided in all the foregoing embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the above methods. Technical details not described in detail in the embodiments of the present invention can be found in the methods provided in all the foregoing embodiments of the present invention.

[0095] Figure 4 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0096] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from the storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0097] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0098] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processing (DSP) processors, and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as call center agent scheduling methods.

[0099] In some embodiments, the call center agent scheduling method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the call center agent scheduling method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the call center agent scheduling method by any other suitable means (e.g., by means of firmware).

[0100] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chips (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0101] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0102] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0103] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a cathode ray tube (CRT) or a liquid crystal display (LCD)) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0104] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0105] A computing system can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system. It addresses the shortcomings of traditional physical hosts and Virtual Private Servers (VPS) in terms of management difficulty and weak business scalability.

[0106] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0107] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for scheduling call center agents, characterized in that, The method includes: Obtain historical call data and spatial environment data corresponding to the target call center, and construct a spatiotemporal fusion feature tensor based on the historical call data and spatial environment data; The spatiotemporal fusion feature tensor is input into a pre-trained convolutional long short-term memory network model, and the future call demand prediction result corresponding to the target call center is output through the convolutional long short-term memory network model. Based on the predicted future call demand for the target call center, a seat scheduling strategy matching the target call center is generated.

2. The method according to claim 1, characterized in that, Based on the historical call traffic data and spatial environment data, a spatiotemporal fusion feature tensor is constructed, including: The spatial environment data is converted into a raster image of a preset size; The historical call data and the raster image are stacked to form a four-dimensional spatiotemporal fusion feature tensor.

3. The method according to claim 1, characterized in that, Before inputting the spatiotemporal fusion feature tensor into the pre-trained convolutional long short-term memory network model, the following steps are also included: Obtain the original Long Short-Term Memory network model; The fully connected layers in the original long short-term memory network model are replaced with convolutional layers to obtain a convolutional long short-term memory network model.

4. The method according to claim 3, characterized in that, After obtaining the convolutional long short-term memory network model, the following is also included: Obtain multiple data samples corresponding to the target call center; the multiple data samples include call traffic data samples, spatial environment data samples, and call traffic prediction annotation results; The convolutional long short-term memory network model is iteratively trained using the multiple data samples until the training termination condition is met.

5. The method according to claim 1, characterized in that, Based on the predicted future call volume for the target call center, a matching agent scheduling strategy is generated, including: Obtain the agent constraints corresponding to the target call center; The seat constraints include scheduling constraints and call center personnel constraints. Based on the predicted future call demand and seat constraints of the target call center, the pre-set scheduling schedule is dynamically adjusted to obtain the seat scheduling strategy that matches the target call center.

6. The method according to claim 1, characterized in that, The historical call data includes: call volume data of the target call center within a historical time period, and holiday labeling data corresponding to the call volume data; The spatial environment data includes: weather data of the area where the target call center is located, public opinion data of the area, and local event calendar data of the area.

7. A call center agent scheduling device, characterized in that, The device includes: The data acquisition module is used to acquire historical call data and spatial environment data corresponding to the target call center, and construct a spatiotemporal fusion feature tensor based on the historical call data and spatial environment data. The model prediction module is used to input the spatiotemporal fusion feature tensor into a pre-trained convolutional long short-term memory network model, and output the future call demand prediction result corresponding to the target call center through the convolutional long short-term memory network model. The scheduling optimization module is used to generate a seat scheduling strategy that matches the target call center based on the predicted future call demand for the target call center.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the call center agent scheduling method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the call center agent scheduling method according to any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the call center agent scheduling method according to any one of claims 1-6.

Images