Call frequency adjustment method and device for predictive outbound call, and storage medium

Abstract

The invention provides a call frequency adjustment method and device of predictive outbound and a storage medium, and relates to the technical field of communication, the method comprises the following steps: based on a preset adjustment period, according to a sampling frequency corresponding to the adjustment period, collecting telephone traffic index data of a call center in the current adjustment period; predicting the number of newly initiated calls in the next adjustment period by using the traffic index data; and adjusting the call frequency of the call center according to the number of newly initiated calls. According to the invention, the call loss rate can be reduced on the premise of improving the seat efficiency.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a method, device and storage medium for adjusting call frequency of predictive outbound calls. Background Art

[0002] In a complete outbound call process, at least the following stages are involved: initiating an outbound call -> ringing and waiting -> call communication -> call hanging up. In the actual call business process, only the call communication stage is meaningful to the agent. However, the time spent on the call communication stage often accounts for a small proportion of the time spent in the entire outbound call process, resulting in very low work efficiency of the agent, which in turn easily affects the agent's enthusiasm.

[0003] In the prior art, in order to improve the work efficiency of agents, a human-machine coupled outbound call mode is adopted, that is, each agent calls multiple calls with specific concurrency at the same time. After the customer is connected, the robot will answer the call first, and the agent can selectively intervene in the call manually. However, this mode has a natural disadvantage, that is, when multiple calls are answered by the customer at the same time, since the agent can only answer one call, the other calls will be regarded as call losses, resulting in a waste of resources. In addition, the call loss rate and the agent call waiting time are mutually exclusive, that is, the higher the concurrency is set, the higher the call loss rate, but the lower the agent call waiting time.

[0004] Based on this, how to improve agent efficiency while reducing call loss rate has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] In view of this, in order to solve the above technical problems, the present invention provides a method, device and storage medium for adjusting call frequency of predictive outbound calls.

[0006] The present invention adopts the following technical solution:

[0007] In a first aspect, the present invention provides a method for adjusting call frequency of predictive outbound calls, comprising:

[0008] Based on a preset adjustment period, and at a sampling frequency corresponding to the adjustment period, collecting the call center's traffic indicator data in the current adjustment period;

[0009] Using the traffic indicator data, predicting the number of newly initiated calls in the next adjustment period;

[0010] The call frequency of the call center is adjusted according to the number of newly initiated calls.

[0011] Optionally, the traffic indicator data includes: agent indicators and call indicators.

[0012] Optionally, the agent indicator includes:

[0013] The current number of online agents, the number of agents currently involved in calls, the number of agents currently in post-call processing, the preset agent post-call processing time, the average agent post-call processing time in the first preset time period, and the preset agent efficiency.

[0014] Optionally, the call indicator includes:

[0015] The duration of each current call, the average call duration in the second preset time period, the duration of each current ringing, the number of calls currently in progress, the number of calls currently being answered by the customer, the ringing connection rate in the third preset time period, and the initiation connection rate in the third preset time period.

[0016] Optionally, using the traffic indicator data, predicting the number of newly initiated calls in the next adjustment period specifically includes:

[0017] Substitute the traffic indicator data into the following formula to obtain the number of newly initiated calls in the next adjustment period:

[0018]

[0019] Among them, Y is the number of newly initiated calls; E is the number of current online agents; G is the preset agent efficiency; A is the number of calls currently being answered by customers; N is the number of agents currently in post-call processing; L is the preset ringing duration; icr is the origination connection rate in the third preset time period; T is the adjustment period; R is the number of calls currently ringing; β is the ringing duration of each current ring; rcr is the ringing connection rate in the third preset time period; M is the number of agents currently involved in calls; λ is the average call duration in the second preset time period; γ is the average agent post-call processing duration in the first preset time period; ω is the call duration of each current call; μ is the preset agent post-call processing duration.

[0020] Optionally, the preset ringing duration is 30S.

[0021] Optionally, the adjustment period is shorter than the preset ringing duration.

[0022] Optionally, the predictive outbound call frequency adjustment method of the present invention further includes:

[0023] In response to the user's adjustment operation, the preset seat efficiency is adjusted.

[0024] In a second aspect, the present invention provides a predictive outbound call frequency adjustment device, comprising:

[0025] A collection module, used to collect the call center's traffic indicator data in the current adjustment period based on a preset adjustment period and at a sampling frequency corresponding to the adjustment period;

[0026] A prediction module, used to use the traffic indicator data to predict the number of newly initiated calls in the next adjustment period;

[0027] The adjustment module is used to adjust the call frequency of the call center according to the number of newly initiated calls.

[0028] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method for adjusting the call frequency of predictive outbound calls as described above are implemented.

[0029] The present invention adopts the above technical solution, a predictive outbound call frequency adjustment method, including: based on a preset adjustment cycle, according to the sampling frequency corresponding to the adjustment cycle, collecting the call center's traffic indicator data in the current adjustment cycle; using the traffic indicator data to predict the number of newly initiated calls in the next adjustment cycle; adjusting the call center's call frequency according to the number of newly initiated calls. Based on this, by predicting the number of newly initiated calls in the next adjustment cycle according to the traffic indicator data, and adjusting the call center's call frequency according to the number of newly initiated calls, the present invention can improve the accuracy of the call frequency adjustment result, and thus can reduce the call loss rate while improving the seat efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0031] Figure 1 It is a flow chart of a method for adjusting call frequency of predictive outbound calls provided by an embodiment of the present invention;

[0032] Figure 2 It is a structural schematic diagram of a predictive outbound call frequency adjustment device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0033] To make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described in detail below. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other implementation methods obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0034] In order to make the solution of the present invention easier to understand, some professional terms that may be involved in the present invention are explained below:

[0035] Agent call waiting time: the time interval from when the agent hangs up the current call to when the agent answers the next call. The shorter this time interval is, the higher the agent's work efficiency is.

[0036] Call loss rate: the ratio of the number of calls that are successfully connected but fail to receive human service follow-up to the total number of calls initiated within a certain period of time.

[0037] In a complete outbound call process, at least the following stages are involved: initiating an outbound call -> ringing and waiting -> call communication -> call hanging up. In the actual call business process, only the call communication stage is meaningful to the agent. However, the time spent on the call communication stage often accounts for a small proportion of the time spent in the entire outbound call process, resulting in very low work efficiency of the agent, which in turn easily affects the agent's enthusiasm.

[0038] In the prior art, in order to improve the work efficiency of agents, a human-machine coupled outbound call mode is adopted, that is, each agent calls multiple calls with specific concurrency at the same time. After the customer is connected, the robot will answer the call first, and the agent can selectively intervene in the call manually. However, this mode has a natural disadvantage, that is, when multiple calls are answered by the customer at the same time, since the agent can only answer one call, the other calls will be regarded as call losses, resulting in a waste of resources. In addition, the call loss rate and the agent call waiting time are mutually exclusive, that is, the higher the concurrency is set, the higher the call loss rate, but the lower the agent call waiting time.

[0039] Based on this, in order to improve the seat efficiency and reduce the call loss rate at the same time, the present invention provides a predictive outbound call frequency adjustment method, device and storage medium. The technical solution of the present invention is described in detail below in conjunction with the accompanying drawings.

[0040] Figure 1 FIG. 1 is a flow chart of a method for adjusting the frequency of a predictive outbound call provided by an embodiment of the present invention. Figure 1 As shown, this process includes:

[0041] Step 101: Based on a preset adjustment cycle and at a sampling frequency corresponding to the adjustment cycle, the call center's traffic indicator data in the current adjustment cycle is collected.

[0042] In actual application, the call center can collect traffic indicator data in the current adjustment cycle by tracking key nodes. Key nodes include but are not limited to agent online and offline, call initiation, customer answering, call allocation, manual intervention and call hang-up, among which call allocation specifically refers to allocating the connected customer call to a specific agent.

[0043] In the embodiment of the present invention, the traffic index data may include: agent index and call index. The agent index may include: the number of currently online agents E, the number of agents currently involved in the call M, the number of agents currently in the post-call processing N, the preset agent post-call processing time μ, the average agent post-call processing time γ in the first preset time period, and the preset agent efficiency G.

[0044] Call indicators may include: the current call duration ω of each call, the average call duration λ in the second preset time period, the current ringing duration β of each ring, the number of calls in the current ring R, the number of calls currently being answered by the customer A, the ring connection rate rcr in the third preset time period and the initiation connection rate icr in the third preset time period.

[0045] It should be noted that when an initiated call is blocked by a blacklist or an anti-disturbance rule, the initiated connection rate icr is not equal to the ringing connection rate rcr, and when no initiated call is blocked by a blacklist or an anti-disturbance rule, the initiated connection rate icr is equal to the ringing connection rate rcr. Each preset time period can be configured according to actual conditions, and the present invention does not make specific limitations.

[0046] Step 102: Use the traffic indicator data to predict the number of new calls initiated in the next adjustment period.

[0047] Specifically, when the inventors were deriving the algorithm of the present invention, they collected a large amount of call data, divided the call data into multiple groups, and plotted a ringing duration distribution curve (a two-dimensional coordinate system, the x-axis represents the ringing duration, the y-axis represents the number of calls, and each group corresponds to a curve) and a call duration distribution curve (a two-dimensional coordinate system, the x-axis represents the call duration, the y-axis represents the number of calls, and each group corresponds to a curve). The inventors analyzed the two curves and found that the ringing duration distribution curve roughly satisfies the mean distribution in the range of 0 to 30 seconds, and the call duration distribution curve satisfies the Poisson distribution.

[0048] Based on this, the mean distribution probability formula The probability formula for the ringing end is as follows:

[0049]

[0050] Wherein, L is a preset ringing duration. In the embodiment of the present invention, L may be 30S; x is the actual ringing duration, 0<x<L.

[0051] Based on the probability formula of Poisson distribution Since the average agent post-call processing time in the first preset time period has a relatively small change, the distribution of the agent changing from the on-call state to the idle state is obtained. Basically, the call duration distribution curve is translated rightward along the x-axis to the average agent post-call processing time in the first preset time period, which can be regarded as the time distribution curve of the agent changing from the on-call state to the idle state. Therefore, the probability formula of the agent changing from the on-call state to the idle state is:

[0052]

[0053] Here, k is the time point at which the agent is expected to be free from the call transfer.

[0054] The present invention adjusts the call frequency according to a preset adjustment cycle. In any adjustment cycle, some agents who are in a call state may hang up the call. At this time, manpower will be released; there will also be some calls in a ringing state, which will be assigned to the agent after the customer answers. In this way, manpower will be occupied after the agent picks up the call.

[0055] Based on this, the calculation formula for the number of seats F expected to be released in the next adjustment cycle is as follows:

[0056]

[0057] Among them, P(ω) is the probability that an agent in the call state will become idle when the call duration is ω.

[0058] The calculation formula for the expected number of received calls P in the next adjustment period is as follows:

[0059]

[0060] Among them, Y is the number of newly initiated calls; L is the preset ringing duration.

[0061] On this basis, the inventors carried out the following formula derivation process:

[0062] In an ideal scenario and without considering call loss, it is assumed that the customer is immediately assigned to an agent to answer the call after it is connected. Therefore, the number of calls in progress = the number of agents answering the call, that is, the number of calls hung up during the call H = the number of agents in the call to the post-call processing state.

[0063] Furthermore, the expected number of customer-answered calls = the number of calls currently being answered by customers A + the expected number of connected calls (RP+IP) - the expected number of calls being hung up H = A+(RP+IP)-H...... (5)

[0064] Estimated number of seats for post-call processing = number of seats currently in post-call processing N + number of seats in the call to post-call processing state (i.e. number of calls hung up during the call H) - estimated number of seats released F = N + HF......(6)

[0065] Current number of online seats E*preset seat efficiency G=expected number of non-idle seats

[0066] = Estimated number of call seats + Estimated number of post-call processing seats

[0067] = Estimated number of customer-answered calls + Estimated number of post-call processing seats

[0068] =(A+RP+IP-H)+(N+HF)=A+RP+IP+NF...... (7)

[0069] therefore,

[0070] The calculation formula for the number of newly initiated calls Y in the next adjustment period is as follows:

[0071]

[0072] Among them, Y is the number of newly initiated calls; E is the number of current online agents; G is the preset agent efficiency; A is the number of calls currently being answered by customers; N is the number of agents currently in post-call processing; L is the preset ringing duration; icr is the origination connection rate in the third preset time period; T is the adjustment period; R is the number of calls currently ringing; β is the ringing duration of each current ring; rcr is the ringing connection rate in the third preset time period; M is the number of agents currently involved in calls; λ is the average call duration in the second preset time period; γ is the average agent post-call processing duration in the first preset time period; ω is the call duration of each current call; μ is the preset agent post-call processing duration.

[0073] And, the adjustment period T is less than the preset ringing duration L.

[0074] Based on this, in an embodiment of the present invention, using the traffic indicator data to predict the number of newly initiated calls in the next adjustment period may specifically include:

[0075] Substitute the traffic indicator data into formula (9) to obtain the number of newly initiated calls in the next adjustment period.

[0076] Step 103: Adjust the call frequency of the call center according to the number of newly initiated calls.

[0077] Specifically, when Y is a positive number, the call frequency should be increased, otherwise, the call frequency should be decreased. In a specific implementation process, when Y is a positive number, the call frequency may be increased by a preset value, otherwise, when Y is a negative number, the call frequency may be decreased by a preset value, and when Y is 0, the call frequency may not be adjusted. In addition, other methods may be used to implement the process of adjusting the call frequency of the call center according to the number of newly initiated calls.

[0078] In an embodiment of the present invention, the predictive outbound call frequency adjustment method of the present invention may further include:

[0079] In response to the user's adjustment operation, the preset agent efficiency is adjusted, so as to meet the demand of manual intervention to control the initiation frequency (agent efficiency) in abnormal situations.

[0080] It should be noted that the method of the present invention is suitable for scenarios where a large number of seats are used simultaneously. When the number of people is small, the algorithm prediction value may be distorted due to a small number of small-probability indicators.

[0081] The embodiment of the present invention adopts the above technical solution, a predictive outbound call frequency adjustment method, including: based on a preset adjustment period, according to the sampling frequency corresponding to the adjustment period, collecting the call center's traffic indicator data in the current adjustment period; using the traffic indicator data to predict the number of newly initiated calls in the next adjustment period; adjusting the call center's call frequency according to the number of newly initiated calls. Based on this, by predicting the number of newly initiated calls in the next adjustment period according to the traffic indicator data, and adjusting the call center's call frequency according to the number of newly initiated calls, the present invention can improve the accuracy of the call frequency adjustment result, and thus can reduce the call loss rate while improving the agent efficiency.

[0082] Based on a general inventive concept, the present invention also provides a call frequency adjustment device for predictive outbound calls. Figure 2 FIG. 1 is a schematic diagram of the structure of a predictive outbound call frequency adjustment device provided by an embodiment of the present invention. Figure 2 As shown, the device comprises:

[0083] The collection module 21 is used to collect the call center's traffic indicator data in the current adjustment period based on a preset adjustment period and at a sampling frequency corresponding to the adjustment period.

[0084] The prediction module 22 is used to use the traffic indicator data to predict the number of newly initiated calls in the next adjustment period.

[0085] The adjustment module 23 is used to adjust the call frequency of the call center according to the number of newly initiated calls.

[0086] Optionally, the traffic indicator data includes: agent indicators and call indicators.

[0087] Optionally, the agent indicator includes:

[0088] The current number of online agents, the number of agents currently involved in calls, the number of agents currently in post-call processing, the preset agent post-call processing time, the average agent post-call processing time in the first preset time period, and the preset agent efficiency.

[0089] Optionally, the call indicator includes:

[0090] The duration of each current call, the average call duration in the second preset time period, the duration of each current ringing, the number of calls currently in progress, the number of calls currently being answered by the customer, the ringing connection rate in the third preset time period, and the initiation connection rate in the third preset time period.

[0091] The prediction module 22 can be specifically used for:

[0092] Substitute the traffic indicator data into the following formula to obtain the number of newly initiated calls in the next adjustment period:

[0093]

[0094] Among them, Y is the number of newly initiated calls; E is the number of current online agents; G is the preset agent efficiency; A is the number of calls currently being answered by customers; N is the number of agents currently in post-call processing; L is the preset ringing duration; icr is the origination connection rate in the third preset time period; T is the adjustment period; R is the number of calls currently ringing; β is the ringing duration of each current ring; rcr is the ringing connection rate in the third preset time period; M is the number of agents currently involved in calls; λ is the average call duration in the second preset time period; γ is the average agent post-call processing duration in the first preset time period; ω is the call duration of each current call; μ is the preset agent post-call processing duration.

[0095] Optionally, the preset ringing duration is 30S.

[0096] Optionally, the adjustment period is shorter than the preset ringing duration.

[0097] Optionally, the predictive outbound call frequency adjustment device of the present invention may further include:

[0098] The seat efficiency adjustment module is used to adjust the preset seat efficiency in response to the user's adjustment operation.

[0099] Based on a general inventive concept, the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, each step in the method for adjusting the call frequency of predictive outbound calls as described above is implemented.

[0100] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0101] It should be noted that, in the description of the present invention, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "plurality" refers to at least two.

[0102] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present invention belong.

[0103] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0104] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0105] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0106] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0107] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0108] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for adjusting the frequency of a predictive outbound call, characterized in that: include: Based on a preset adjustment period, and at a sampling frequency corresponding to the adjustment period, collecting the call center's traffic indicator data in the current adjustment period; Using the traffic indicator data, predicting the number of newly initiated calls in the next adjustment period; The call frequency of the call center is adjusted according to the number of newly initiated calls.

2. The predictive outbound call frequency adjustment method according to claim 1, characterized in that: The traffic index data includes: agent index and call index.

3. The predictive outbound call frequency adjustment method according to claim 2, characterized in that: The agent indicators include: The current number of online agents, the number of agents currently involved in calls, the number of agents currently in post-call processing, the preset agent post-call processing time, the average agent post-call processing time in the first preset time period, and the preset agent efficiency.

4. The predictive outbound call frequency adjustment method according to claim 3, characterized in that: The call indicators include: The duration of each current call, the average call duration in the second preset time period, the duration of each current ringing, the number of calls currently in progress, the number of calls currently being answered by the customer, the ringing connection rate in the third preset time period, and the initiation connection rate in the third preset time period.

5. The method for adjusting the frequency of predictive outbound calls according to claim 4, characterized in that: Using the traffic indicator data, predicting the number of newly initiated calls in the next adjustment period, specifically including: Substitute the traffic indicator data into the following formula to obtain the number of newly initiated calls in the next adjustment period: Among them, Y is the number of newly initiated calls; E is the number of current online agents; G is the preset agent efficiency; A is the number of calls currently being answered by customers; N is the number of agents currently in post-call processing; L is the preset ringing duration; icr is the origination connection rate in the third preset time period; T is the adjustment period; R is the number of calls currently ringing; β is the ringing duration of each current ring; rcr is the ringing connection rate in the third preset time period; M is the number of agents currently involved in calls; λ is the average call duration in the second preset time period; γ is the average agent post-call processing duration in the first preset time period; ω is the call duration of each current call; μ is the preset agent post-call processing duration.

6. The method for adjusting the frequency of predictive outbound calls according to claim 5, characterized in that: The preset ringing duration is 30S.

7. The method for adjusting the frequency of predictive outbound calls according to claim 5, characterized in that: The adjustment period is shorter than the preset ringing duration.

8. The method for adjusting the frequency of predictive outbound calls according to claim 3, characterized in that: Also includes: In response to the user's adjustment operation, the preset seat efficiency is adjusted.

9. A predictive outbound call frequency adjustment device, characterized in that: include: A collection module, used to collect the call center's traffic indicator data in the current adjustment period based on a preset adjustment period and at a sampling frequency corresponding to the adjustment period; A prediction module, used to use the traffic indicator data to predict the number of newly initiated calls in the next adjustment period; The adjustment module is used to adjust the call frequency of the call center according to the number of newly initiated calls.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, each step of the method for adjusting the call frequency of predictive outbound calls as claimed in any one of claims 1 to 8 is implemented.

Images