Seat resource scheduling method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a seat resource scheduling method and device, electronic equipment and a storage medium, belongs to the technical field of artificial intelligence, and is suitable for the field of financial science and technology. The method comprises the following steps: acquiring real-time state data of a preset object queue; performing anomaly detection on the preset object queue based on the real-time state data to obtain a queue state of the preset object queue; wherein the queue state is used for representing that the preset object queue is in a normal state or an abnormal state; acquiring idle seat resources of the preset object queue according to the queue state; performing gap calculation based on the real-time state data to obtain gap seat resources; for a preset object queue, calculating based on the idle seat resources and the gap seat resources to obtain scheduling seat resources and updated idle seat resources; and resource scheduling is carried out based on the scheduling agent resources and the updated idle agent resources. According to the embodiment of the invention, the seat resource scheduling efficiency can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, and is suitable for the field of financial technology, in particular to a method and device for scheduling agents, an electronic device and a storage medium. BACKGROUND

[0002] In the operation process of a call center, agents (human or intelligent agents) undertake tasks such as answering phone calls, handling customer complaints, and recording business information. The call center classifies and manages agents according to their professional skills and develops appropriate dispatch strategies to ensure efficient handling of various types of business. For example, in the financial technology field, telephone business handling for insurance, financial business, and banking business.

[0003] Currently, agent resource scheduling mainly relies on the management experience of managers to manually adjust the number of agents in each business queue. However, in actual application, when managers find that agent skills do not match customer needs, they need to report to higher levels and obtain approval to complete the adjustment. The overall process requires a lot of time and cannot respond to customer business handling needs in a timely manner, affecting the efficiency of agent resource scheduling.

[0004] Therefore, how to improve the efficiency of agent resource scheduling has become a technical problem to be solved. SUMMARY

[0005] The main purpose of the embodiments of the present application is to propose a method and device for scheduling agents, an electronic device and a storage medium, which aims to solve the technical problem of complicated process and low efficiency when managers manually schedule agent resources, and improve the efficiency of agent resource scheduling.

[0006] To achieve the above purpose, the first aspect of the embodiments of the present application proposes a method for scheduling agents, which comprises: obtaining real-time state data of a preset object queue; performing anomaly detection on the preset object queue based on the real-time state data to obtain a queue state of the preset object queue; wherein the queue state is used to represent that the preset object queue is in a normal state or an abnormal state; obtaining idle agent resources of the preset object queue according to the queue state; performing gap calculation based on the real-time state data to obtain gap agent resources; for the preset object queue, calculating based on the idle agent resources and the gap agent resources to obtain scheduled agent resources and updated idle agent resources; performing resource scheduling based on the scheduled agent resources and the updated idle agent resources.

[0007] In some embodiments, the number of preset object queues is multiple; the resource scheduling based on the scheduled agent resource and the updated idle agent resource comprises: For a certain preset object queue, it is defined as a target object queue, and other queues except the target object queue are defined as candidate object queues; a selected object queue is selected from each candidate object queue based on the idle agent resource of the candidate object queue; wherein the idle agent resource of the selected object queue is greater than zero; Resource scheduling is performed based on the scheduled agent resource of the target object queue and the selected object queue.

[0008] In some embodiments, the selected object queue includes a selected idle resource; the resource scheduling based on the scheduled agent resource of the target object queue and the selected object queue comprises: The selected idle resource is selected from the selected idle resource based on the scheduled agent resource; Obtain the original queue information of the selected object queue; Determine the original call interface of the selected idle resource based on the original queue information; Obtain the target call interface of the target object queue; Modify the original call interface based on the target call interface, so that the selected idle resource can complete the task of the target object queue.

[0009] In some embodiments, the calculation based on the idle agent resource and the gap agent resource obtains the scheduled agent resource and the updated idle agent resource, comprising: If the idle agent resource is greater than or equal to the gap agent resource, the updated idle agent resource is obtained by subtracting the gap agent resource from the idle agent resource, and the scheduled agent resource is determined to be zero; If the idle agent resource is less than the gap agent resource, the scheduled agent resource is obtained by subtracting the idle agent resource from the gap agent resource, and the updated idle agent resource is determined to be zero.

[0010] In some embodiments, the real-time state data includes the total number of outbound calls, the number of connections, the number of abandonments, and the number of telephone collections; the abnormal detection of the preset object queue based on the real-time state data obtains the queue state of the preset object queue, comprising: The telephone connection rate is calculated based on the total number of outbound calls and the number of connections; The telephone call loss rate is calculated based on the total number of outbound calls and the number of abandonments; calculate a phone collection rate based on the total number of outbound calls and the number of phone collections; compare the phone connection rate, the phone loss rate, and the phone collection rate with preset steady-state operation thresholds to obtain the queue state of the preset object queue.

[0011] In some embodiments, the steady-state operation thresholds include a connection rate threshold, a call loss rate threshold, and a collection rate threshold; and the comparison of the phone connection rate, the phone loss rate, and the phone collection rate with preset steady-state operation thresholds to obtain the queue state of the preset object queue includes: comparing the phone connection rate with the connection rate threshold to obtain a connection rate comparison result; comparing the phone call loss rate with the call loss rate threshold to obtain a call loss rate comparison result; comparing the phone collection rate with the collection rate threshold to obtain a collection rate comparison result; generating the queue state of the preset object queue based on the connection rate comparison result, the call loss rate comparison result, and the collection rate comparison result.

[0012] In some embodiments, the real-time state data further includes the number of queued calls and the call duration; and the gap calculation based on the real-time state data to obtain the gap agent resource includes: calculating an average call duration based on the call duration and the number of connections; calculating the gap agent resource based on the number of queued calls and the average call duration.

[0013] To achieve the above-mentioned purpose, a second aspect of the embodiments of the present application proposes a kind of agent resource scheduling device, the device includes: a real-time state acquisition module for acquiring real-time state data of a preset object queue; an anomaly detection module for detecting anomalies in the preset object queue based on the real-time state data, to obtain the queue state of the preset object queue;Wherein, the queue state is used to represent the preset object queue is normal state or abnormal state; an idle resource acquisition module for acquiring idle agent resources of the preset object queue according to the queue state; a gap resource acquisition module for gap calculation based on the real-time state data to obtain the gap agent resource; a scheduling resource calculation module for calculating the scheduling agent resource and the updated idle agent resource based on the idle agent resource and the gap agent resource for the preset object queue; The resource scheduling module is configured to perform resource scheduling based on the scheduled agent resources and the updated idle agent resources.

[0014] To achieve the above object, a third aspect of the embodiments of the present application provides an electronic device, which comprises a memory and a processor, the memory stores a computer program, and the processor implements the method of the first aspect when executing the computer program.

[0015] To achieve the above object, a fourth aspect of the embodiments of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the method of the first aspect.

[0016] The agent resource scheduling method and device, electronic device and storage medium provided by the present application can accurately grasp the current running state of the queue by obtaining real-time state data of the preset object queue, and provide data support for subsequent agent resource adjustment. The abnormality of the preset object queue is detected based on the real-time state data to obtain a queue state used to determine whether the preset object queue is in a normal state or an abnormal state, which helps to quickly find the problems existing in the queue. Then, the idle agent resources of the preset object queue are obtained according to the queue state, and the number of available resources is determined. The gap agent resources are obtained by gap calculation based on the real-time state data, and the scheduled agent resources and the updated idle agent resources are obtained by calculation based on the idle agent resources and the gap agent resources for the preset object queue, which can reasonably plan the allocation of agent resources and improve the utilization efficiency of agent resources. Finally, resource scheduling is performed based on the scheduled agent resources and the updated idle agent resources, which can accurately allocate agent resources according to the actual situation, avoid waste or shortage of agent resources, solve the technical problems of complicated process and low efficiency when the management personnel manually schedules agent resources, and improve the efficiency of agent resource scheduling. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 is a flowchart of the agent resource scheduling method provided by the embodiments of the present application; Figure 2 is a flowchart of step S102 in Figure 1 Figure 3 is a flowchart of step S204 in Figure 2 Figure 4 is a flowchart of step S104 in Figure 1 Figure 5 is a flowchart of step S106 in Figure 1 Figure 6 is a flowchart of step S108 in Figure 5 ​​​​the flowchart of step S502 in FIG. 5; Figure 7 is a structural schematic diagram of a seat resource scheduling device provided by an embodiment of the present application; Figure 8 is a hardware structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application is further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0019] It should be noted that although the functional modules are divided in the device schematic diagram, and the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a manner different from the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification and claims and the above-described drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application, and are not intended to limit the present application.

[0021] First, several terms involved in the present application are analyzed: Artificial intelligence (AI): is a new technical science of researching and developing a theory, method, technology and application system for simulating, extending and expanding human intelligence; artificial intelligence is a branch of computer science, and artificial intelligence attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a similar way to human intelligence. The research in this field includes robots, language recognition, image recognition, natural language processing and expert systems, etc. Artificial intelligence can simulate the information process of human consciousness and thinking. Artificial intelligence is also the theory, method, technology and application system of using digital computers or digital computer-controlled machines to simulate, extend and expand human intelligence, to perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0022] In the process of call center operation, the agents (manual or intelligent agents) undertake the tasks of answering phone calls, handling customer demands, recording business information, etc. The call center will classify and manage the agents according to their professional skills and develop corresponding dispatch strategies to ensure efficient handling of various types of businesses. For example, in the financial technology scenario, telephone business handling for insurance business, financial business and bank business.

[0023] Currently, the agent resource scheduling mainly relies on the management experience of the management personnel to manually adjust the number of agents in each business queue. However, in actual application, when the management personnel finds that the agent skills do not match the customer demand, they need to report it to the higher level and go through the approval process to complete the adjustment. The overall process needs to consume a lot of time and cannot respond to the customer's business handling demand in time, which affects the efficiency of agent resource scheduling and also affects the customer's business handling experience.

[0024] Therefore, the embodiments of the present application provide an agent resource scheduling method and device, electronic equipment and storage medium, which aims to solve the technical problem of complicated process and low efficiency when the management personnel manually schedules the agent resources, and improve the efficiency of agent resource scheduling.

[0025] The agent resource scheduling method and device, electronic equipment and storage medium provided by the embodiments of the present application are specifically explained by the following embodiments. First, the agent resource scheduling method in the embodiments of the present application is described.

[0026] The embodiments of the present application can acquire and process related data based on artificial intelligence technology. Among them, artificial intelligence (AI) is to use digital computers or machine controlled by digital computers to simulate, extend and expand human intelligence, perceive environment, acquire knowledge and use knowledge to obtain the best results.

[0027] The basic technology of artificial intelligence generally includes technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction system, mechatronics, etc. The software technology of artificial intelligence mainly includes computer vision technology, robot technology, biometric technology, speech processing technology, natural language processing technology and machine learning / deep learning, etc.

[0028] The application embodiment provides a method for scheduling a resource of a seat, and relates to the technical field of artificial intelligence. The method for scheduling the resource of the seat can be applied to a terminal, a server end, or software running in the terminal or the server end. In some embodiments, the terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, etc. The server end can be configured as a physical server, a server cluster composed of multiple physical servers, or a distributed system, and can also be configured as a cloud server providing basic cloud computing services such as cloud service, cloud database, cloud computing, cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, CDN, and big data and artificial intelligence platform. The software can be an application for implementing the method for scheduling the resource of the seat, but is not limited to the above forms.

[0029] The application can be used in many general or specific computer system environments or configurations. For example: personal computers, server computers, handheld devices or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The 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 application can also be practiced in a distributed computing environment in which tasks are performed by remote processing devices connected by a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0030] It should be noted that in each specific embodiment of the application, when it is necessary to process relevant data related to the identity or characteristics of the user according to user information, user behavior data, user history data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the application embodiment needs to obtain sensitive personal information of the user, the separate permission or separate consent of the user will be obtained through a pop-up window or a jump to a confirmation page, and after obtaining the separate permission or separate consent of the user, the necessary user-related data for enabling the application embodiment to normally operate will be obtained.

[0031] Figure 1 is an optional flowchart of the method for scheduling a resource of a seat provided by the application embodiment, Figure 1 The method in can include but is not limited to steps S101 to S106.

[0032] Step S101, acquire real-time state data of a preset object queue; Step S102, perform abnormality detection on the preset object queue based on the real-time state data, to obtain a queue state of the preset object queue; wherein the queue state is used to represent that the preset object queue is in a normal state or an abnormal state; Step S103, acquire idle agent resources of the preset object queue according to the queue state; Step S104, perform gap calculation based on the real-time state data, to obtain gap agent resources; Step S105, for the preset object queue, perform calculation based on the idle agent resources and the gap agent resources, to obtain dispatch agent resources and updated idle agent resources; Step S106, perform resource dispatching based on the dispatch agent resources and the updated idle agent resources.

[0033] The steps S101 to S106 shown in the embodiments of the present application can accurately master the current running situation of the queue by acquiring real-time state data of the preset object queue, and provide data support for subsequent agent resource adjustment. The queue state obtained by performing abnormality detection on the preset object queue based on the real-time state data is used to judge whether the preset object queue is in a normal state or an abnormal state, which helps to quickly find problems existing in the queue. Then, the idle agent resources of the preset object queue are acquired according to the queue state, and the available resource quantity is clear. The gap agent resources are obtained by performing gap calculation based on the real-time state data, and for the preset object queue, calculation is performed based on the idle agent resources and the gap agent resources, to obtain the dispatch agent resources and the updated idle agent resources, which can reasonably plan the allocation of agent resources and improve the utilization efficiency of agent resources. Finally, resource dispatching is performed based on the dispatch agent resources and the updated idle agent resources, which can accurately allocate agent resources according to the actual situation, avoid waste or shortage of agent resources, solve the technical problems of tedious process and low efficiency when the management personnel manually performs agent resource dispatching, and improve the efficiency of agent resource dispatching.

[0034] In step S101 of some embodiments, the preset object queue is a set of object collections that are pre-set in the call center and have specific business attributes or functions, such as queues of different business types (such as consultation, claim registration, and complaint) in the call center. Wherein the number of preset object queues is multiple, and each preset object queue corresponds to a business type.

[0035] It should be noted that the preset object queue includes multiple agent resources, and the agent resources can be human agents or intelligent agents, without limitation.

[0036] The real-time state data is various state information reflecting the preset object queue at the current time. The state information of the preset object queue at the current time can be collected through various data collection means such as system interfaces, log records, etc., to provide accurate basic data for subsequent anomaly detection, resource scheduling, etc., and help to improve the timeliness and accuracy of the agent resource scheduling.

[0037] Specifically, the real-time state data includes but is not limited to: total number of outbound calls, number of connected calls, number of abandoned calls, number of phone collection, number of queued calls, and call duration.

[0038] The total number of outbound calls refers to the total number of outbound calls initiated from a certain preset object queue within a certain time period, which can reflect the enthusiasm and work intensity of the preset object queue in actively serving customers. For example, in the insurance claim registration queue, the staff initiates outbound calls to communicate with customers in order to follow up the claim progress. The total number of such calls initiated by the preset object queue within a certain period of time (e.g., within an hour, within half a day, within a day, etc.) is the total number of outbound calls.

[0039] The number of connected calls is the number of successful connections with customers in the total number of outbound calls. That is, the customer answered the phone after the call was made. Answering the phone is one of the important indicators of outbound call effectiveness. For example: in the insurance claim registration queue, 100 outbound calls were initiated in a day, and 70 of them were answered by the customer. Therefore, the number of connected calls is 70.

[0040] The number of abandoned calls is the number of times the call center actively terminated the call due to various reasons, which may include the customer not answering the phone for a long time, phone line failure, staff error, etc. The number of abandoned calls can reflect the problems and obstacles encountered during outbound calls. A higher number of abandoned calls may require the call center to analyze the reasons, such as whether the waiting time is set reasonably, whether the outbound call time is selected when the customer is not convenient to answer the phone, etc., in order to optimize and improve. For example: during the call, the staff sets the maximum waiting time for the customer to answer the phone to 30 seconds. If the customer still does not answer the phone after this time, the staff will hang up the call. This situation is counted as an abandoned call. Assuming that there are 10 such operations in a day, the number of abandoned calls is 10.

[0041] Phone collection times, the total number of times that phone calls dispersed in different channels or lines are concentrated to a specific queue for processing. In a call center, there can be multiple different phone access channels, such as 400 phones, mobile phone direct dial, online customer service transfer phone, etc. Phone collection is to integrate the phones of these different channels into the corresponding preset object queue. For example: a call center has both 400 customer service phones and mobile customer service hotlines as access channels. When a customer inquires a problem through the mobile customer service hotline, the system will automatically collect the phone into the preset object queue corresponding to the consultation business. If such collection operation occurs 50 times within a day, then the phone collection times are 50 times.

[0042] Queued phone number, the number of phone calls waiting for allocation of agents for service at the current time. The queued phone number is an important indicator reflecting the current business busy degree and service pressure of the call center. A higher queued phone number can mean that the agent resource is insufficient, and the number of agents needs to be increased or the agent allocation strategy needs to be optimized to reduce customer waiting time. For example: in the consultation business queue, there are currently 5 customers waiting for agents to answer the phone, so the queued phone number is 5.

[0043] Call duration, which refers to the length of time that a customer and an agent actually communicate, usually measured in seconds or minutes. Call duration can be calculated from the perspective of a single call, or the duration of all calls within a certain period of time can be averaged to obtain the average call duration. Call duration can reflect the efficiency and complexity of agents solving problems for customers. Longer call duration can indicate that the problem is more complex and requires more time for communication and explanation by the agent; while shorter call duration can mean that the problem is relatively simple and the processing speed is faster. Through analysis of call duration, the call center can evaluate the work performance of agents, optimize service processes, and improve service quality.

[0044] Please refer to Figure 2 In some embodiments, step S102 can include, but is not limited to, steps S201 to S204: Step S201, calculating the phone connection rate based on the total number of outbound calls and the number of connections; Step S202, calculating the phone loss rate based on the total number of outbound calls and the number of abandonments; Step S203, calculating the phone collection rate based on the total number of outbound calls and the number of phone collections; Step S204, comparing the phone connection rate, the phone loss rate, and the phone collection rate with the preset steady-state running threshold to obtain the queue state of the preset object queue.

[0045] The steps S201 to S204 shown in the embodiments of the present application can obtain the telephone connection rate by calculating based on the total number of outbound calls and the number of connections, so as to understand the telephone connection success; the telephone loss rate is calculated based on the total number of outbound calls and the number of abandonments, so as to clearly understand the call loss degree caused by various reasons; the telephone collection rate is calculated based on the total number of outbound calls and the number of telephone collections, so as to master the telephone collection status. Finally, the queue state of the preset object queue is obtained by comparing the telephone connection rate, the telephone loss rate and the telephone collection rate with the preset steady-state running threshold value, so that the preset object queue state can be comprehensively and accurately judged, and abnormalities can be found in time, thereby providing a basis for subsequent agent resource adjustment.

[0046] In step S201 of some embodiments, the number of connections is divided by the total number of outbound calls to obtain a percentage value, that is, the telephone connection rate. The telephone connection rate can intuitively reflect the quality and efficiency of outbound services. High connection rate means that more calls are successfully converted into effective calls, which helps to improve business transaction rate, customer satisfaction and the like.

[0047] For example: Assuming that a certain preset object queue initiates outbound calls 200 times in a day, and the number of connections is 180 times, then the telephone connection rate = 180 ÷ 200 × 100% = 80%.

[0048] In step S202 of some embodiments, the number of abandonments is divided by the total number of outbound calls to obtain a percentage value, that is, the telephone loss rate. The telephone loss rate can reflect the call loss caused by various reasons. Lower loss rate indicates that the system can more effectively utilize resources, reduce call waste caused by various reasons, and improve overall business efficiency.

[0049] For example: Assuming that a certain preset object queue initiates outbound calls 200 times in a day, and the number of abandonments is 10 times, then the telephone connection rate = 10 ÷ 200 × 100% = 5%.

[0050] In step S203 of some embodiments, the number of telephone collections is divided by the total number of outbound calls to obtain a percentage value, that is, the telephone collection rate. The telephone collection rate can reflect the degree of call collection in outbound services, which helps to optimize business processes and improve service efficiency. By collecting related calls, repeated operations and resource waste can be reduced, and more efficient service provision can be achieved.

[0051] For example: Assuming that a certain preset object queue initiates outbound calls 200 times in a day, and the number of telephone collections is 190 times, then the telephone connection rate = 190 ÷ 200 × 100% = 95%.

[0052] In some embodiments, the preset steady-state operation threshold is constructed in advance by the call center according to the business demand, communication environment and service quality requirement of the actual business scenario, and the steady-state operation threshold includes a connection rate threshold, a call loss rate threshold and a collection rate threshold. The connection rate threshold is used to determine whether the telephone connection rate reaches an acceptable level. The call loss rate threshold is used to control the call loss of the telephone communication system to ensure that the service quality of the system is within a certain range. The collection rate threshold is used to measure the standard value of the telephone collection effect, which is determined according to the business demand and management target.

[0053] Referring to Figure 3 In some embodiments, step S204 can include but is not limited to steps S301 to S304: Step S301, comparing the telephone connection rate with the connection rate threshold to obtain a connection rate comparison result; Step S302, comparing the telephone call loss rate with the call loss rate threshold to obtain a call loss rate comparison result; Step S303, comparing the telephone collection rate with the collection rate threshold to obtain a collection rate comparison result; Step S304, generating the queue state of the preset object queue based on the connection rate comparison result, the call loss rate comparison result and the collection rate comparison result.

[0054] The steps S301 to S304 shown in the embodiments of the present application can determine whether the connection meets the standard by comparing the telephone connection rate with the connection rate threshold to obtain a connection rate comparison result, determine whether the call loss meets the standard by comparing the telephone call loss rate with the call loss rate threshold to obtain a call loss rate comparison result, and determine whether the collection meets the standard by comparing the telephone collection rate with the collection rate threshold to obtain a collection rate comparison result. Finally, the queue state of the preset object queue is generated based on the connection rate comparison result, the call loss rate comparison result and the collection rate comparison result, which can comprehensively and accurately reflect the overall operation status of the preset object queue and provide a basis for subsequent allocation of agent resources.

[0055] In step S301 of some embodiments, the connection rate comparison result includes two cases: the connection rate meets the standard (the telephone connection rate is greater than or equal to the connection rate threshold) and the connection rate does not meet the standard (the telephone connection rate is less than the connection rate threshold).

[0056] In step S302 of some embodiments, the call loss rate comparison result includes two cases: the call loss rate meets the standard (the telephone call loss rate is less than or equal to the call loss rate threshold) and the call loss rate does not meet the standard (the telephone call loss rate is greater than the call loss rate threshold).

[0057] In step S303 of some embodiments, the collection rate comparison result includes two cases: the collection rate meets the standard (the telephone collection rate is greater than or equal to the collection rate threshold) and the collection rate does not meet the standard (the telephone collection rate is less than the collection rate threshold).

[0058] In step S304 of some embodiments, the connection rate comparison result, the call loss rate comparison result, and the collection rate comparison result are combined to obtain a combination result, and then a queue state of the preset object queue is generated according to the combination result.

[0059] The combination result includes: Combination one: the connection rate meets the standard, the call loss rate meets the standard, and the collection rate meets the standard; Combination two: the connection rate meets the standard, the call loss rate meets the standard, and the collection rate does not meet the standard; Combination three: the connection rate meets the standard, the call loss rate does not meet the standard, and the collection rate meets the standard; Combination four: the connection rate meets the standard, the call loss rate does not meet the standard, and the collection rate does not meet the standard; Combination five: the connection rate does not meet the standard, the call loss rate meets the standard, and the collection rate meets the standard; Combination six: the connection rate does not meet the standard, the call loss rate meets the standard, and the collection rate does not meet the standard; Combination seven: the connection rate does not meet the standard, the call loss rate does not meet the standard, and the collection rate meets the standard; Combination eight: the connection rate does not meet the standard, the call loss rate does not meet the standard, and the collection rate does not meet the standard. Specifically, when the combination result is combination one, the queue state of the preset object queue represents that the preset object queue is in a normal state. When the combination result is combination two / combination three / combination four / combination five / combination six / combination seven / combination eight, the queue state of the preset object queue represents that the preset object queue is in an abnormal state.

[0060] It can be understood that through the specific implementation shown in steps S201 to S204 and steps S301 to S304, the queue state of each preset object queue can be obtained, which provides a basis for agent resource scheduling.

[0061] It should be noted that if the queue state of any queue in the plurality of preset object queues represents that the preset object queue is in an abnormal state, agent resource scheduling needs to be performed, and subsequent operations, i.e., steps S103 to S106, are executed.

[0062] In step S103 of some embodiments, when the queue state of the preset object queue represents that the preset object queue is in an abnormal state, the idle agent resources of each preset object queue are obtained. Specifically, the idle agent resources of each preset object queue can be calculated in units of one minute / five minutes.

[0063] It should be noted that the idle agent resource is an idle human agent or intelligent agent.

[0064] Please refer to Figure 4 In some embodiments, step S104 can include but is not limited to steps S401-S402: Step S401, based on the call duration and the number of connections, the average call duration is obtained by calculation; Step S402, based on the number of queued calls and the average call duration, the gap agent resource is calculated.

[0065] The steps S401-S402 shown in the embodiments of the application, by calculating based on the call duration and the number of connections, the average call duration is obtained, and the average time consumption of each call is accurately mastered. Then, based on the number of queued calls and the average call duration, the gap agent resource is calculated, which can reasonably plan the number of agents, improve resource utilization, and improve service efficiency.

[0066] In step S401 of some embodiments, the call duration is divided by the number of connections to obtain the average call duration. The average call duration can intuitively reflect the average time for an agent to handle a customer inquiry or business transaction, and is an important reference index for evaluating call service efficiency and service quality.

[0067] In step S402 of some embodiments, the gap agent resource is the number of agent requirements five minutes after the current time. Specifically, the calculation formula of the gap agent resource is as follows: Gap agent resource = number of queued calls * average call duration / 5 * 60.

[0068] It should be noted that the gap agent resource is the human agent or intelligent agent that the preset object queue is lacking. For example, the gap agent resource of a certain preset object queue is 5 people.

[0069] In step S105 of some embodiments, if the idle agent resource of the preset object queue is greater than or equal to the gap agent resource, the updated idle agent resource is obtained by subtracting the gap agent resource from the idle agent resource, and the dispatch agent resource of the preset object queue is determined to be zero; If the idle agent resource of the preset object queue is less than the gap agent resource, the dispatch agent resource of the preset object queue is obtained by subtracting the idle agent resource from the gap agent resource, and the updated idle agent resource is determined to be zero.

[0070] It should be noted that the scheduling seat resources refer to the human or intelligent seats that need to be scheduled from other queues for this preset object queue. For example, the scheduling seat resources for a certain preset object queue are 6 people. By clearly defining the scheduling seat resources and available seat resources for each preset object queue, it is helpful to rationally plan resource allocation, ensuring that while meeting the needs of the preset object queue itself, the impact on other preset object queues is minimized, thereby improving the overall utilization efficiency of resources.

[0071] For example, in a call center, suppose there is an object queue A, with 5 available agent seats and 6 available agent seats. Then the dispatch agent resources are 0, and the updated available agent resources are 1.

[0072] Assuming there is an object queue B, with 5 available seats and 3 free seats, then the scheduled seat resources are 2, and the updated free seat resources are 0.

[0073] Please see Figure 5 In some embodiments, step S106 may include, but is not limited to, steps S501 to S502: Step S501: For a certain preset object queue, define it as a target object queue, and define other queues besides the target object queue as candidate object queues; select alternative object queues from the candidate object queues based on the available seat resources of each candidate object queue; wherein, the available seat resources of the alternative object queues are greater than zero. Step S502: Perform resource scheduling based on the scheduling agent resources of the target object queue and the alternative object queue.

[0074] Steps S501 to S502, as illustrated in this embodiment, distinguish between a target object queue and a candidate object queue in the preset object queue, and then select a backup object queue from the candidate object queue where the available seat resources are greater than zero. This clarifies the scope of resource scheduling and improves resource selection efficiency. Next, resource scheduling is performed based on the scheduling seat resources of the target object queue and the backup object queue. This fully utilizes the available seats in the backup object queue, rationally allocates resources, and improves the efficiency of seat resource scheduling.

[0075] In step S501 of some embodiments, queues with non-zero scheduling agent resources are selected from all preset object queues and designated as indirect object queues. Then, for a given indirect object queue, this indirect object queue is defined as a target object queue, and the other preset object queues besides the target object queue are defined as candidate object queues. It is understood that the candidate object queues can be queues with zero scheduling agent resources.

[0076] Then, the queue in which the idle agent resource is greater than zero is filtered from the candidate object queue as a candidate object queue, that is, the candidate object queue has idle agent resources while meeting its own scheduling requirements.

[0077] Specifically, the number of candidate object queues is at least one, and each candidate object queue includes a candidate idle resource, which is an agent resource (that is, a human agent or an intelligent agent).

[0078] Further, after determining the candidate object queue, resource scheduling is performed based on the scheduling agent resource of the target object queue and the candidate object queue.

[0079] Please refer to Figure 6 In some embodiments, step S502 includes but is not limited to steps S601 to S605: Step S601: Filtering a scheduling idle resource from the candidate idle resource based on the scheduling agent resource; Step S602: Obtaining original queue information of the candidate object queue; Step S603: Determining an original call interface of the scheduling idle resource based on the original queue information; Step S604: Obtaining a target call interface of the target object queue; Step S605: Modifying the original call interface based on the target call interface, so that the scheduling idle resource can complete the task of the target object queue.

[0080] The steps S601 to S605 shown in the embodiments of the present application filter a scheduling idle resource from the candidate idle resource based on the scheduling agent resource, ensuring that the resource participating in scheduling is schedulable. Then, the original queue information of the candidate object queue is obtained, and the original call interface of the scheduling idle resource is determined based on the original queue information, which clearly defines the original call interface used by the resource.

[0081] Further, the target call interface of the target object queue is obtained, and the original call interface is modified based on the target call interface, so as to realize scheduling of the resource, so that the scheduling idle resource can complete the outbound call task of the target object queue, and improve the resource utilization and task processing efficiency of the call center.

[0082] In step S601 of some embodiments, a corresponding number of resources are filtered from the candidate idle resource based on the number of resources required by the scheduling agent resource as the scheduling idle resource; Suppose that the candidate idle resource of one candidate object queue cannot meet the requirements of the scheduling agent resource, the scheduling idle resource can also be filtered from the remaining candidate object queues.

[0083] In step S602 of some embodiments, original queue information of the candidate object queue corresponding to the idle resource is obtained, and the original queue information is used to indicate the queue name of the candidate object queue and the service type to which the queue belongs.

[0084] Further, the original call interface of the idle resource can be determined based on the original queue information. The original call interface is an interface mode used by the idle resource to access a call or a service originally, and determines how the resource communicates with an external system or a customer. For example, in a call center, the original call interface can be a specific telephone line interface, a network voice interface, etc.

[0085] It can be understood that different object queues have different call interfaces. For example, the call interface of the queue for consultation services is interface one, and the call interface of the queue for claim registration services is interface two, where interface one and interface two are different. The agent resource uses a specific interface, and the services handled by the agent resource when calling in or calling out are also different.

[0086] In step S604 of some embodiments, the target call interface of the target object queue is obtained, which provides a clear target direction for modifying the original call interface of the idle resource, and ensures that the resource can successfully access the target object queue and complete the task. The target call interface is an interface mode required or used by the target object queue to access a call or a service, and is an interface standard that the idle resource needs to adapt to.

[0087] In step S605 of some embodiments, the original call interface of the idle resource is adjusted and configured according to the target call interface, so that the idle resource can access and provide services according to the requirements of the target object queue, realize reasonable allocation and effective use of resources, ensure seamless connection between resources of different queues, and improve overall service efficiency and customer satisfaction.

[0088] For example, the candidate object queue is used to handle consultation services, and the original call interface used is the first interface. Through screening, a dispatch agent A (using the first interface to handle services) is obtained. The target object queue is used to handle complaint services, and the target call interface used is the second interface. The call interface of the dispatch agent A is modified to the second interface, so that the dispatch agent A can answer the complaint call of the target object queue and complete the complaint service task of the target object queue.

[0089] The method for scheduling the agent resources provided in the embodiments of the present application can continuously monitor the running states of the preset object queues after one scheduling (steps S101 to S106) is performed, and cyclically optimize the scheduling strategy according to new data, that is, repeatedly perform steps S101 to S106, so as to ensure that each preset object queue is in a normal state, solve the technical problem of complicated process and low efficiency when the management personnel manually schedules the agent resources, reduce the need for manual intervention, and significantly improve the utilization rate of the agent resources.

[0090] In addition, the method for scheduling the agent resources provided in the embodiments of the present application can be applied to other application scenarios, such as retail and e-commerce scenarios, education scenarios, tourism promotion scenarios, and the like, but is not limited thereto.

[0091] Please refer to Figure 7 The embodiments of the present application further provide a device for scheduling agent resources, which can implement the above method for scheduling the agent resources. The device comprises: The real-time state acquisition module 701 is configured to acquire real-time state data of the preset object queue. The abnormality detection module 702 is configured to perform abnormality detection on the preset object queue based on the real-time state data, and obtain a queue state of the preset object queue. The queue state is used to represent whether the preset object queue is in a normal state or an abnormal state. The idle resource acquisition module 703 is configured to acquire idle agent resources of the preset object queue according to the queue state. The gap resource acquisition module 704 is configured to perform gap calculation based on the real-time state data, and obtain gap agent resources. The scheduling resource calculation module 705 is configured to calculate the scheduling agent resources and the updated idle agent resources of the preset object queue based on the idle agent resources and the gap agent resources. The resource scheduling module 706 is configured to perform resource scheduling based on the scheduling agent resources and the updated idle agent resources.

[0092] The specific implementation of the device for scheduling the agent resources is basically the same as the specific embodiments of the above method for scheduling the agent resources, and thus will not be described herein again.

[0093] The embodiments of the present application further provide an electronic device, which comprises a memory and a processor. The memory stores a computer program, and the processor implements the above method for scheduling the agent resources when executing the computer program. The electronic device can be any intelligent terminal, such as a tablet computer or a vehicle-mounted computer.

[0094] Please refer to Figure 8 , Figure 8The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device comprises: The processor 801 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits, and is configured to execute related programs to implement the technical solutions provided by the embodiments of the present application. The memory 802 can be implemented by a ROM (ReadOnly Memory), a static storage device, a dynamic storage device, or a RAM (Random Access Memory), and the like. The memory 802 can store an operating system and other application programs. When the technical solutions provided by the embodiments of the present application are implemented by software or firmware, the related program codes are stored in the memory 802 and are called and executed by the processor 801 to implement the agent resource scheduling method of the embodiments of the present application. The input / output interface 803 is configured to realize information input and output. The communication interface 804 is configured to realize the communication interaction between the device and other devices. The communication can be realized by a wired manner (for example, a USB, a network cable, and the like) or a wireless manner (for example, a mobile network, WIFI, Bluetooth, and the like). The bus 805 is configured to transmit information between various components (for example, the processor 801, the memory 802, the input / output interface 803, and the communication interface 804) of the device. The processor 801, the memory 802, the input / output interface 803, and the communication interface 804 are connected to each other through the bus 805 to realize the communication connection between the device.

[0095] The embodiments of the present application further provide a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the above-mentioned agent resource scheduling method.

[0096] The memory is a non-transitory computer readable storage medium, which can be used to store a non-transitory software program and a non-transitory computer executable program. In addition, the memory can include a high-speed random access memory, and can further include a non-transitory memory, for example, at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some embodiments, the memory can optionally include a memory remotely arranged relative to the processor, and the remote memory can be connected to the processor through a network. Examples of the network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0097] The application embodiment provides a method and device for scheduling agent resources, an electronic device and a storage medium. The method can accurately grasp the current operation of the queue by obtaining real-time state data of a preset object queue, and provide data support for subsequent agent resource adjustment. The preset object queue is detected based on the real-time state data to obtain a queue state used to determine whether the preset object queue is in a normal state or an abnormal state, which helps to quickly find problems in the queue. Then, the idle agent resources of the preset object queue are obtained based on the queue state, and the available resource quantity is determined. The gap agent resources are obtained based on the real-time state data, and the idle agent resources and the gap agent resources are calculated based on the preset object queue to obtain the scheduled agent resources and the updated idle agent resources, which can reasonably plan the allocation of the agent resources and improve the utilization efficiency of the agent resources. Finally, the resource scheduling is performed based on the scheduled agent resources and the updated idle agent resources, which can accurately allocate the agent resources according to the actual situation, avoid waste or shortage of the agent resources, solve the technical problems of complicated process and low efficiency when the management personnel manually schedules the agent resources, and improve the efficiency of the agent resource scheduling.

[0098] The embodiments described in the application embodiments are used to more clearly illustrate the technical solutions of the application embodiments, and do not constitute a limitation on the technical solutions provided by the application embodiments. Those skilled in the art can know that, with the evolution of technology and the appearance of new application scenarios, the technical solutions provided by the application embodiments are also applicable to similar technical problems.

[0099] Those skilled in the art can understand that the technical solutions shown in the figures do not constitute a limitation on the application embodiments, and can include more or fewer steps than the figures, or combine certain steps or different steps.

[0100] The device embodiments described above are only schematic, and the units illustrated as separate components can be or can not be physically separated, that is, can be located in one place or can be distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments.

[0101] Those skilled in the art can understand that all or some steps in the above disclosed method, the functions of the modules / units in the system and the device can be implemented as software, firmware, hardware and their appropriate combinations.

[0102] The terms "first", "second", "third", "fourth", and the like in the description and in the claims of this application, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the use of the terms so termed is interchangeable under appropriate circumstances such that the embodiments of the application described herein are, for example, capable of orderly or chronological mundane operation, reverse order operation, based on circuitry availability, based on stated preference or the like, and that "default" or other orderings are thus permissible. Further, the terms "comprise", "comprising", "include", "including", and the like, are specifically intended to be open-ended. That is, references to individual steps and the like do not suhstantially exclude the presence of two or more of a given step or its integral presence in the process, method, system, article, or apparatus having been made with a wider scope. The use of notation such as "first", "second", "third", etc. does not generally limit the areas, but can be used for clarity, and merely establishes the order unless otherwise stated below.

[0103] It should be understood that, in the application, "at least one" means one or more, and "multiple" means two or more. "And / or" is used to describe the relationship between associated objects, which means that there can be three relationships, for example, "A and / or B" can mean that there are only A, only B, and A and B at the same time, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects. "At least one of the following" or the like means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b or c can mean a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0104] In several embodiments provided in the application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the above units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be omitted or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed objects can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0105] The units described above as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e. they can be located in one place or distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0106] In addition, each function unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software function unit.

[0107] When the integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, essentially or in the form of a contribution to the prior art, or all or part of the technical solutions can be embodied in the form of a software product. The 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 the embodiments of the present application. The foregoing storage medium includes various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0108] The non-company software tools or components appearing in the embodiments of the present application are only used for example introduction, and do not represent actual use.

[0109] The preferred embodiments of the embodiments of the present application are described above with reference to the accompanying drawings, and are not limited to the scope of the embodiments of the present application. Any modification, equivalent replacement, and improvement made by those skilled in the art without departing from the scope and essence of the embodiments of the present application shall be within the scope of the embodiments of the present application.

Claims

1. A method for scheduling agent resources, characterized in that, The method includes: Obtain real-time status data of a preset object queue; Anomaly detection is performed on the preset object queue based on the real-time status data to obtain the queue status of the preset object queue; wherein, the queue status is used to characterize whether the preset object queue is in a normal state or an abnormal state. The available agent resources of the preset object queue are obtained according to the queue status; Based on the real-time status data, the gap is calculated to obtain the available agent resources; For the preset object queue, calculations are performed based on the available seat resources and the available seat resources to obtain the scheduled seat resources and the updated available seat resources; Resource scheduling is performed based on the scheduled agent resources and the updated idle agent resources.

2. The method according to claim 1, characterized in that, The number of preset object queues is multiple; the resource scheduling based on the scheduling agent resources and the updated idle agent resources includes: For a given preset object queue, a target object queue is defined, and other queues besides the target object queue are defined as candidate object queues; alternative object queues are selected from the candidate object queues based on the available seat resources of each candidate object queue; wherein the available seat resources of the alternative object queues are greater than zero; Resource scheduling is performed based on the scheduling agent resources of the target object queue and the alternative object queue.

3. The method according to claim 2, characterized in that, The candidate object queue includes candidate idle resources; the resource scheduling based on the scheduling agent resources of the target object queue and the candidate object queue includes: Based on the scheduling agent resources, scheduling idle resources are selected from the candidate idle resources to obtain scheduling idle resources; Obtain the original queue information of the candidate object queue; The original call interface for scheduling idle resources is determined based on the original queue information; Obtain the target call interface of the target object queue; The original call interface is modified based on the target call interface so that the scheduled idle resources can complete the tasks of the target object queue.

4. The method according to claim 1, characterized in that, The calculation based on the available seat resources and the unavailable seat resources to obtain the scheduled seat resources and the updated available seat resources includes: If the available seat resources are greater than or equal to the available seat resources, the available seat resources are updated by subtracting the available seat resources from the available seat resources, and the scheduled seat resources are determined to be zero. If the available seat resources are less than the available seat resources, the available seat resources are subtracted from the available seat resources to obtain the scheduled seat resources, and the updated available seat resources are determined to be zero.

5. The method according to any one of claims 1 to 4, characterized in that, The real-time status data includes the total number of outbound calls, the number of calls connected, the number of calls abandoned, and the number of calls collected. The step of performing anomaly detection on the preset object queue based on the real-time status data to obtain the queue status of the preset object queue includes: The call connection rate is calculated based on the total number of outbound calls and the number of connected calls. The call loss rate is calculated based on the total number of outbound calls and the number of abandoned calls. The call aggregation rate is calculated based on the total number of outbound calls and the number of call aggregations. The queue state of the preset object queue is obtained by comparing the call connection rate, the call loss rate, and the call aggregation rate with a preset steady-state operating threshold.

6. The method according to claim 5, characterized in that, The steady-state operating thresholds include a call connection rate threshold, a call loss rate threshold, and a call aggregation rate threshold; the process of comparing the call connection rate, the call loss rate, and the call aggregation rate with the preset steady-state operating thresholds to obtain the queue state of the preset object queue includes: The call connection rate and the connection rate threshold are compared to obtain the connection rate comparison result. The call loss rate and the call loss rate threshold are compared to obtain the call loss rate comparison result. The telephone collection rate and the collection rate threshold are compared to obtain the collection rate comparison result. The queue status of the preset object queue is generated based on the connection rate comparison result, the call loss rate comparison result, and the aggregation rate comparison result.

7. The method according to claim 5, characterized in that, The real-time status data also includes the number of queued calls and the call duration; The process of calculating the shortage of agent resources based on the real-time status data includes: The average call duration is calculated based on the call duration and the number of times the call was connected. The shortage of agent seats is calculated based on the number of queued calls and the average call duration.

8. A seat resource scheduling device, characterized in that, The device includes: The real-time status acquisition module is used to acquire real-time status data of a preset object queue; An anomaly detection module is used to perform anomaly detection on the preset object queue based on the real-time status data to obtain the queue status of the preset object queue; wherein, the queue status is used to characterize whether the preset object queue is in a normal state or an abnormal state. The idle resource acquisition module is used to acquire the idle seat resources of the preset object queue according to the queue status; The gap resource acquisition module is used to calculate the gap based on the real-time status data to obtain the gap seat resources; The scheduling resource calculation module is used to calculate the scheduled seat resources and the updated idle seat resources for the preset object queue based on the idle seat resources and the available seat resources. The resource scheduling module is used to perform resource scheduling based on the scheduled agent resources and the updated idle agent resources.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method according to any one of claims 1 to 7.

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

Images