An intelligent outbound calling system using big data technology

Abstract

The present invention relates to the field of intelligent outbound call technology, and discloses an intelligent outbound call system applying big data technology, comprising a task management unit, an outbound call unit, a processing unit, a recording unit, a central unit, a collection unit and a sorting unit, wherein the task management unit is used for selecting an outbound call type, the outbound call unit is used for providing customer outbound call services, the recording unit is used for recording outbound call records within a week and calculating an outbound call volume W, and the processing unit receives the outbound call volume W and sends an analysis instruction to the central unit after processing; the present invention first sets a selection module, which has six types, and the six types can cover most of the existing industries requiring outbound calls, thereby preliminarily meeting the use requirements of different industries, and when used in different industries, data support can be provided through a database to ensure that different industries have corresponding voices to use when making outbound calls, making it more intelligent and adaptable.

Description

Technical Field

[0001] The present invention relates to the field of intelligent outbound calling technology, and more specifically to an intelligent outbound calling system applying big data technology. Background Art

[0002] Outbound call is a communication term, which refers to the outbound service of modern customer service center system that actively initiates calls to customers. The content of outbound call is: the phone automatically dials the user's phone through the computer, and the recorded voice is played to the user through the computer. Outbound call is an indispensable part of the modern customer service center system that integrates computers and phones. Outbound call is divided into two stages: the acquisition of outbound call data and the initiation of outbound call action. The component is responsible for completing the initiation function of the outbound call action.

[0003] When the outbound call system is running, the system first connects the agent's phone and then dials the customer's number. After waiting for the connection process, the operator can talk to the customer. During this process, the computer selects the customer to be dialed and starts dialing. Invalid calls will be skipped. If the customer answers, the call will be quickly transferred to an operator to complete the call;

[0004] When using an outbound call system, it is applied in different fields and has different usage requirements. The traditional outbound call system can only be applied in a single or similar field. When it is used in other fields, a new outbound call system needs to be adopted, which makes the cost of the outbound call system higher. If the same outbound call system is used in similar fields, the outbound call system has differences in different fields, making it not smart enough when used, and there are situations where problems in different fields cannot be completely solved;

[0005] When the outbound call system makes an outbound call, the number of people currently working manually is different, and the types of work used are different. Therefore, the number of outbound calls it can serve is different. Today's outbound call system is unable to calculate the number of outbound calls. At this time, if the same number of outbound calls is used, it cannot meet the usage requirements. There are problems such as too many outbound calls and inability to provide services to customers, or too few outbound calls, resulting in a waste of personnel. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, the implementation regulations of the present invention provide an intelligent outbound call system using big data technology to solve the technical problems raised in the background technology.

[0007] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: an intelligent outbound call system using big data technology, comprising a task management unit, an outbound call unit, a processing unit, a recording unit, a central unit, a collection unit and a sorting unit, wherein the task management unit is used to select an outbound call type, the outbound call unit is used to provide outbound call services to customers, the recording unit is used to record outbound call records within a week and calculate the outbound call volume W, the processing unit receives the outbound call volume W and sends an analysis instruction to the central unit after processing, the central unit receives the analysis instruction and calculates the current outbound call quality data ZL, and the central unit analyzes the calculated outbound call quality data ZL and updates and maintains the outbound call unit, the collection unit is used to collect outbound call service opinions, and the sorting unit is used to prioritize outbound call customers;

[0008] The task management unit includes a selection module, a database module and an improvement module. The selection module is used to select the current work type, the database module is used to provide outbound voice data for the current work type, the improvement module is used to increase or decrease the data of the work type selected in the selection module, and the improvement module can increase the voice data under the current work type.

[0009] In a preferred embodiment, the work types in the selection module are initially set to six types, namely customer service type, marketing type, finance type, appointment type, education type and government type. The customer type is used for customer service, the marketing type is used for product promotion and research, the finance type is used for debt processing, the appointment type is used for catering, medical and travel reservations, the education type is used for course consultation and event notifications, and the government type is used for voter surveys, volunteer recruitment and event notifications.

[0010] In a preferred embodiment, the recording unit is used to count the connection ratio data information JT of the inbound and outbound calls in the previous week, the ratio data information RG of the manual demand after connection and the number of connected people, and the average call duration data information SC after connection. The recording unit sends the collected data information to the outbound call unit, and the outbound call unit receives the data collected by the recording unit and calculates the outbound call volume W. The calculation formula of the inbound and outbound call volume W of the outbound call unit is: , where floor is the rounding function, ZX is the current number of human agents working, and BZ is the preset standard call duration.

[0011] In a preferred embodiment, the recording unit sends the calculated outbound call volume W to the processing unit, and the processing unit receives the outbound call volume W. When the outbound call volume W received by the processing unit is a positive number, the outbound call unit adopts the outbound call volume W to determine the maximum number of outbound calls currently being made. When the outbound call volume W received by the processing unit is 0 or a negative number, the processing unit adopts the revised outbound call volume X to determine the current number of outbound calls. The calculation formula of the revised outbound call volume X is: , T is the adjustment value, its initial value is 0.5, and the management personnel can automatically adjust the adjustment value T.

[0012] In a preferred embodiment, when the connection ratio data information JT is calculated in the recording unit, the connection ratio data information JT is the ratio between the number of effectively connected outbound calls and the total number of outbound calls. The number of effectively connected outbound calls is the number of calls after the outbound customer is connected and the call duration is ten seconds or more. The recording unit compares the connection ratio data information JT with its internal threshold value Y. When the connection ratio data information JT ≥ threshold value Y, the recording unit does not send an instruction. When the connection ratio data information JT < threshold value Y, the recording unit sends an analysis instruction to the central unit.

[0013] In a preferred embodiment, the central unit receives the analysis instruction and calculates the current outbound call quality data ZL. The calculation formula of the outbound call quality data ZL is: , where FY is the reaction time required for the outbound call to make a sound, FB is the decibel when the customer answers the outbound call, SJ is the call time of the current outbound call, k1 and k2 are both weights, and 0≤k1≤1, 0≤k≤1, k1+k2=0.

[0014] In a preferred embodiment, the central unit compares the calculated outbound call quality data ZL with its internal preset call quality YS. When the outbound call quality data ZL is less than the preset call quality YS, the central unit does not process it. When the outbound call quality data ZL is greater than or equal to the preset call quality YS, the central unit controls the outbound call unit to update and maintain it.

[0015] In a preferred embodiment, the collection unit is used to collect outbound call opinions, and after collecting the outbound call opinions, the collection unit counts the number of repetitions of the outbound call opinions, puts the opinions with the highest number of repetitions at the front, and all the outbound call opinions are sorted in order according to the number of repetitions.

[0016] In a preferred embodiment, the sorting unit uses the priority value YX to perform priority sorting, and the calculation formula of the priority value YX is: , where W1 is the number of customers' businesses, W2 is the customer's reputation value, and W3 is the matching degree between the customer and the outbound call service. The sorting unit sorts the calculated priority values ​​YX from large to small, and the outbound call order of the customers corresponding to the priority values ​​YX is consistent with the order of the priority values.

[0017] Technical effects and advantages of the present invention:

[0018] The present invention first sets a selection module, which has six types. These six types can cover most of the industries that need outbound calls, and thus preliminarily meet the use requirements of different industries. When used in different industries, data support can be provided by the database to ensure that different industries have corresponding voices to use when making outbound calls. The work type can be increased by improving the module to make it more intelligent and adaptable.

[0019] The present invention takes the number of manual agents as a benchmark, divides the connection ratio data information JT and the ratio data information RG of the manual demand and the number of connections, and then preliminarily obtains the outbound call volume. Subsequently, the average call duration data information SC and the preset standard call duration are used for correction to ensure the accuracy of the outbound call volume. When the number of manual agents ZX is taken as a benchmark, the number of manual agents ZX is reduced by one, so that one manual agent can be freed up to remedy sudden situations.

[0020] When calculating the outbound call quality data ZL of the present invention, three data are used: the reaction time required for the outbound call to make a sound, the decibel when the customer answers the outbound call, and the outbound call time. The calculated outbound call quality data ZL can accurately represent the current situation of the customer, and the larger the outbound call quality data ZL, the higher the customer's dissatisfaction. When the outbound call quality data ZL exceeds the preset call quality YS, the present application is updated and maintained in time to avoid greater adverse consequences.

[0021] When making an outbound call, the present invention uses a priority value YX for sequential arrangement. The priority value YX comprehensively considers the customer's business quantity, reputation value and matching degree. The calculated priority value YX is more representative. Therefore, when making an outbound call, the priority value YX of the present application can be arranged in size, so that the present application is more organized when used. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a schematic diagram of the overall structure of the system of the present invention. DETAILED DESCRIPTION

[0023] The technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention. In addition, the forms of the various structures recorded in the following embodiments are only examples. The intelligent outbound call system using big data technology involved in the present invention is not limited to the various structures recorded in the following embodiments. All other implementations obtained by ordinary technicians in this field without making creative work belong to the scope of protection of the present invention.

[0024] Reference Figure 1 The present invention provides an intelligent outbound call system using big data technology, including a task management unit, an outbound call unit, a processing unit, a recording unit, a central unit, a collection unit and a sorting unit, wherein the task management unit is used to select an outbound call type, the outbound call unit is used to provide outbound call services to customers, the recording unit is used to record outbound call records within a week and calculate an outbound call volume W, the processing unit receives the outbound call volume W and sends an analysis instruction to the central unit after processing, the central unit receives the analysis instruction and calculates the current outbound call quality data ZL, and the central unit analyzes the calculated outbound call quality data ZL and updates and maintains the outbound call unit, the collection unit is used to collect outbound call service opinions, and the sorting unit is used to prioritize outbound call customers.

[0025] In the embodiment of the present application, when the present application makes an outbound call, since multiple fields require outbound calls, the present application first selects the type of outbound call to ensure that the system of the present application is applicable to the required field type, thereby meeting different usage requirements, and when making an outbound call, the number of outbound calls will be calculated to ensure that when the present application makes an outbound call, the manpower will not be occupied and unable to provide services when it needs manpower due to a large number of outbound calls, and the manpower resources will not be wasted due to a small number of outbound calls. In addition, the present application will be updated and maintained while it is running to ensure that the present application is in a state of continuous improvement.

[0026] Reference Figure 1The task management unit includes a selection module, a database module and an improvement module. The selection module is used to select the current work type. The database module is used to provide outbound voice data for the current work type. The improvement module is used to increase or decrease the data of the work type selected in the selection module, and the improvement module can increase the voice data under the current work type. The work types in the selection module are initially set to six types, namely customer service type, marketing type, financial type, appointment type, education type and government type. The customer type is used for customer service, the marketing type is used for product promotion and research, the financial type is used for debt processing, the appointment type is used for catering, medical and travel reservations, the education type is used for course consultation and event notification, and the government type is used for voter surveys, volunteer recruitment and event notifications.

[0027] In the embodiment of the present application, since outbound calls can be used in various industries, the present application first sets up a selection module. There are six types in the selection module. These six types can cover most of the existing industries that require outbound calls, and thus preliminarily meet the use requirements of different industries. When used in different industries, data support can be provided by the database to ensure that different industries have corresponding voices to use when making outbound calls. For some small industries that are not included in the six types, the work type can be increased through the improvement module. At this time, a voice search can be performed in the database. If there is no voice that meets the industry, the voice data under the current work type can be increased through the improvement module so that it can meet the use requirements;

[0028] The six types of this application are customer service type, marketing type, financial type, appointment type, education type and government type. When the customer type is used in the customer service center, it can help solve customer problems, provide technical support and handle complaints. The marketing type can be used for sales phone calls, market research, customer relationship management, etc., to help companies establish connections with potential customers and promote products or services. The entry type can be used for debt recovery and collection agencies to communicate with debtors, remind repayments, negotiate payment plans, etc. The appointment type can be used in restaurants, medical institutions, tourism and hotel industries to remind appointments, confirm reservations, send service reminders, etc. The education type can be used in schools, training institutions, online education platforms, etc. for student admissions, course consultations, event notifications, etc. The government type can be used in government departments and non-profit organizations for voter surveys, volunteer recruitment, event notifications, etc.

[0029] Furthermore, the recording unit is used to collect data information JT of the connection ratio of inbound and outbound calls in the previous week, data information RG of the ratio of the manual demand after connection to the number of connected persons, and data information SC of the average call duration after connection. The recording unit sends the collected data information to the outbound call unit. The outbound call unit receives the data collected by the recording unit and calculates the outbound call volume W. The calculation formula of the inbound and outbound call volume W of the outbound call unit is: , where floor is a rounding function, ZX is the current number of manual agents, BZ is the preset standard call duration, the recording unit sends the calculated outbound call volume W to the processing unit, the processing unit receives the outbound call volume W, when the outbound call volume W received by the processing unit is a positive number, the outbound call unit uses the outbound call volume W to determine the maximum number of outbound calls currently made, when the outbound call volume W received by the processing unit is 0 or a negative number, the processing unit uses the revised outbound call volume X to determine the current number of outbound calls, and the calculation formula of the revised outbound call volume X is: , T is the adjustment value, its initial value is 0.5, and the management personnel can automatically adjust the adjustment value T.

[0030] In the embodiment of the present application, when making an outbound call, there will be a certain number of manual seats for manual service, but the number of manual seats is limited. In order to ensure that all outbound customers can receive good service, the number of manual seats is used as a benchmark, and the connection ratio data information JT and the ratio data information RG of the manual demand and the number of connected people are divided. At this time, the outbound call volume can be preliminarily obtained, and the average call duration data information SC and the preset standard call duration are used for correction to ensure the accuracy of the outbound call volume. When the number of manual seats ZX is used as a benchmark, the number of manual seats ZX is reduced by one, so that one manual service can be freed up to remedy sudden situations. The present application adopts the floor function, which is a rounding function. Therefore, when the calculated outbound call volume W has a decimal after the integer, the decimal is directly discarded to avoid rounding up, when the manual service cannot meet the customer's needs.

[0031] When the outbound call volume W is 0 or a negative number, it means that the average call duration data information SC after the customer is connected is high. At this time, the average call duration data information SC is twice or more than the preset standard call duration, which means that when making an outbound call, good communication is carried out with the customer. Therefore, the probability of the customer being transferred to manual service is high. Therefore, the revised outbound call volume X is directly used to determine the number of outbound calls, so that the customer can get good communication. The revised outbound call volume X uses the adjustment value T when calculating, and the specific value of the adjustment value T can be set by the actual user, so that it can be well used by customers in different industries.

[0032] Furthermore, when the connection ratio data information JT is calculated in the recording unit, the connection ratio data information JT is the ratio between the number of effectively connected outbound calls and the total number of outbound calls. The number of effectively connected outbound calls is the number of calls after the outbound customer is connected and the call duration is ten seconds or more. The recording unit compares the connection ratio data information JT with its internal threshold value Y. When the connection ratio data information JT ≥ threshold value Y, the recording unit does not send an instruction. When the connection ratio data information JT < threshold value Y, the recording unit sends an analysis instruction to the central unit. The central unit receives the analysis instruction and calculates the current outbound call quality data ZL. The calculation formula of the outbound call quality data ZL is: , where FY is the reaction time required for the outbound call to make a sound, FB is the decibel when the customer answers the outbound call, SJ is the call time of the current outbound call, k1 and k2 are weights, and 0≤k1≤1, 0≤k≤1, k1+k2=0, the central unit compares the calculated outbound call quality data ZL with its internal preset call quality YS, when the outbound call quality data ZL<preset call quality YS, the central unit does not process it, when the outbound call quality data ZL≥preset call quality YS, the central unit will control the outbound call unit to update and maintain.

[0033] In the embodiment of the present application, when the connection ratio data information JT is calculated, it is the ratio between the number of effectively connected outbound calls and the total number of outbound calls, because for some calls, although the customer chooses to answer the outbound call, the customer will directly hang up the phone after answering the call. Therefore, although it is a connected call, it has no effect. Therefore, it is also considered as an invalid call that is not connected, thereby ensuring the accuracy of the calculation of the connection ratio data information JT;

[0034] When the connection ratio data information JT is lower than the threshold, it means that the current customers have not chosen to answer the outbound call. Therefore, the central unit receives the analysis instruction and performs cause analysis. At this time, the outbound call quality data ZL is calculated. When calculating the outbound call quality data ZL, three data are used: the reaction time required for the outbound call to make a sound, the decibel when the customer answers the outbound call, and the outbound call time. The reaction time required for the outbound call to make a sound is an assessment of the system itself. When the self-reaction time is slow, the customer will fail to get feedback in time after answering the outbound call, resulting in subsequent outbound calls. Rejection, and the decibel level when the customer answers an outbound call can reflect the customer's current mood. When the customer has no major emotional fluctuations, the decibel level is between 40-60. When the situation fluctuates greatly, the farther away from this range it will be. And the shorter the customer's call time, the higher the degree of dissatisfaction. Therefore, the outbound call quality data ZL calculated by this application using these three data can accurately represent the customer's current situation, and the larger the outbound call quality data ZL, the higher the customer's dissatisfaction. When the outbound call quality data ZL exceeds the preset call quality YS, this application will be updated and maintained in time to avoid greater adverse consequences.

[0035] Furthermore, the collection unit is used to collect outbound opinions, and after collecting the outbound opinions, the collection unit counts the number of repetitions of the outbound opinions, and puts the opinions with the highest number of repetitions at the front, and all the outbound opinions are sorted in order of the number of repetitions, and the opinions with the highest number of repetitions are put at the front, indicating that this problem has been noticed by more people and needs to be dealt with in a timely manner to ensure that this application can develop in a healthy manner.

[0036] Furthermore, the sorting unit uses the priority value YX to perform priority sorting, and the calculation formula of the priority value YX is: , where W1 is the number of customers' businesses, W2 is the customer's reputation value, and W3 is the matching degree between the customer and the outbound call service. The sorting unit sorts the calculated priority values ​​YX from large to small, and the outbound call order of the customers corresponding to the priority values ​​YX is consistent with the order of the priority values.

[0037] In an embodiment of the present application, when making an outbound call, the order of the outbound calls needs to be set, and at this time, the priority value YX is used to represent it. The priority value YX comprehensively considers the customer's business quantity, reputation value and matching degree, and the calculated priority value YX is more representative. Therefore, when making an outbound call, it can be arranged according to the priority value YX of the present application, so that the present application is more organized when used.

[0038] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions according to the embodiments of the present application are generated in whole or in part.

[0039] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0040] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0041] In the several embodiments provided in the present application, it should be understood that the disclosed systems, 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 units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0042] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0043] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent outbound calling system using big data technology, characterized by: It includes a task management unit, an outbound call unit, a processing unit, a recording unit, a central unit, a collection unit and a sorting unit. The task management unit is used to select an outbound call type. The outbound call unit is used to provide outbound call services to customers. The recording unit is used to record outbound call records within a week and calculate the outbound call volume W. The processing unit receives the outbound call volume W and sends an analysis instruction to the central unit after processing. The central unit receives the analysis instruction and calculates the current outbound call quality data ZL. The central unit analyzes the calculated outbound call quality data ZL and updates and maintains the outbound call unit. The collection unit is used to collect outbound call service opinions. The sorting unit is used to prioritize outbound call customers. The task management unit includes a selection module, a database module and an improvement module, wherein the selection module is used to select the current work type, the database module is used to provide outbound voice data for the current work type, the improvement module is used to increase or decrease the data of the work type selected in the selection module, and the improvement module can increase the voice data under the current work type; The recording unit is used to collect data information JT of the connection ratio of inbound and outbound calls in the previous week, data information RG of the ratio of the manual demand after connection to the number of connected people, and data information SC of the average call duration after connection. The recording unit sends the collected data information to the outbound call unit. The outbound call unit receives the data collected by the recording unit and calculates the outbound call volume W. The calculation formula of the inbound and outbound call volume W of the outbound call unit is: , where is a rounding-down function, ZX is the current number of human agents working, and BZ is the preset standard call duration; The recording unit sends the calculated outbound call volume W to the processing unit, and the processing unit receives the outbound call volume W. When the outbound call volume W received by the processing unit is a positive number, the outbound call unit adopts the outbound call volume W to determine the maximum number of outbound calls currently being made. When the outbound call volume W received by the processing unit is 0 or a negative number, the processing unit adopts the revised outbound call volume X to determine the current number of outbound calls. The calculation formula of the revised outbound call volume X is: , T is the adjustment value, its initial value is 0.5, and the management personnel can automatically adjust the adjustment value T.

2. According to claim 1, the intelligent outbound calling system using big data technology is characterized by: The work types in the selection module are initially set to six types, namely customer service type, marketing type, finance type, appointment type, education type and government type. The customer service type is used for customer service, the marketing type is used for product promotion and research, the finance type is used for debt processing, the appointment type is used for restaurant, medical and travel reservations, the education type is used for course consultation and event notifications, and the government type is used for voter surveys, volunteer recruitment and event notifications.

3. According to claim 2, the intelligent outbound calling system using big data technology is characterized by: When the connection ratio data information JT is calculated in the recording unit, the connection ratio data information JT is the ratio between the number of effectively connected outbound calls and the total number of outbound calls. The number of effectively connected outbound calls is the number of calls after the outbound customer is connected and the call duration is ten seconds or more. The recording unit compares the connection ratio data information JT with its internal threshold value Y. When the connection ratio data information JT ≥ threshold value Y, the recording unit does not send any instructions. When the connection ratio data information JT < threshold value Y, the recording unit sends an analysis instruction to the central unit.

4. According to claim 3, the intelligent outbound calling system using big data technology is characterized by: The central unit receives the analysis instruction and calculates the current outbound call quality data ZL. The calculation formula of the outbound call quality data ZL is: , where FY is the reaction time required to make a sound when making an outbound call, FB is the decibel when the customer answers the outbound call, SJ is the call time of the current outbound call, k1 and k2 are both weights, and 0≤k1≤1, 0≤k≤1, k1+k2=0.

5. According to claim 4, the intelligent outbound calling system using big data technology is characterized by: The central unit compares the calculated outbound call quality data ZL with its internal preset call quality YS. When the outbound call quality data ZL is less than the preset call quality YS, the central unit does not process it. When the outbound call quality data ZL is greater than or equal to the preset call quality YS, the central unit controls the outbound call unit to update and maintain it.

6. The intelligent outbound calling system using big data technology according to claim 1, characterized in that: The collecting unit is used to collect outbound call opinions, and after collecting the outbound call opinions, the collecting unit counts the number of repetitions of the outbound call opinions, puts the opinion with the highest number of repetitions at the front, and sorts all the outbound call opinions in order of the number of repetitions.

7. The intelligent outbound calling system using big data technology according to claim 1, characterized in that: The sorting unit uses the priority value YX to perform priority sorting. The calculation formula of the priority value YX is: , where W1 is the number of customers' businesses, W2 is the customer's reputation value, and W3 is the matching degree between the customer and the outbound call service. The sorting unit sorts the calculated priority values ​​YX from large to small, and the outbound call order of the customers corresponding to the priority values ​​YX is consistent with the order of the priority values.

Images