WO2019153545A1 - 回访方法、装置、计算机设备及存储介质 - Google Patents

回访方法、装置、计算机设备及存储介质 Download PDF

Info

Publication number
WO2019153545A1
WO2019153545A1 PCT/CN2018/085269 CN2018085269W WO2019153545A1 WO 2019153545 A1 WO2019153545 A1 WO 2019153545A1 CN 2018085269 W CN2018085269 W CN 2018085269W WO 2019153545 A1 WO2019153545 A1 WO 2019153545A1
Authority
WO
WIPO (PCT)
Prior art keywords
value
task
urgency
failure parameter
pool queue
Prior art date
Application number
PCT/CN2018/085269
Other languages
English (en)
French (fr)
Inventor
谢富华
Original Assignee
平安科技（深圳）有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2019153545A1 publication Critical patent/WO2019153545A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/01—Customer relationship services
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/01—Customer relationship services
    • G06Q30/015—Providing customer assistance, e.g. assisting a customer within a business location or via helpdesk
    • G06Q30/016—After-sales

Definitions

  • the present application relates to the field of telephone return visit technology, and in particular, to a return visit method, device, computer device and storage medium.
  • the application provides a method, a device, a computer device and a storage medium for returning a visit.
  • the purpose of the present invention is to solve the problem that the return visit task in the prior art is generally arranged based on the time sequence of the return visit request to the agent task pool, which leads to a real need for a return visit. And the user who guides the operation cannot be promptly returned.
  • the present application provides a return visit method, including:
  • the operation failure parameter corresponding to the urgency value of the returning task is obtained, and the returning task is added to the agent task pool queue.
  • Priority task pool queue
  • the return visit task corresponding to the client information is allocated to the agent terminal corresponding to the service level according to the customer quality level value corresponding to the client information.
  • the application provides a return visit device, including:
  • the urgency value obtaining unit is configured to acquire an operation failure parameter fed back by the client, and use the operation failure parameter as an input of the pre-built urgency calculation model, and acquire an urgency value corresponding to the operation failure parameter;
  • the priority task screening unit is configured to: if the urgency value of the returning task detected in the agent task pool is less than or equal to the preset urgency threshold, obtain an operation failure parameter corresponding to the urgency value of the returning task, and return the task Join the priority task pool queue in the agent task pool queue;
  • the customer quality level value obtaining unit is configured to obtain the client information of the returning task in the priority task pool queue, and use the client information as the input of the pre-built customer quality model to obtain the customer quality level value corresponding to the client information;
  • the return task assignment unit is configured to allocate the return visit task corresponding to the client information to the agent terminal corresponding to the service level according to the customer quality level value corresponding to the client information.
  • the present application further provides a computer device comprising a memory, a processor, and a computer program stored on the memory and operable on the processor, the processor implementing the computer program
  • a computer device comprising a memory, a processor, and a computer program stored on the memory and operable on the processor, the processor implementing the computer program
  • the present application also provides a storage medium, wherein the storage medium stores a computer program, the computer program comprising program instructions, the program instructions, when executed by a processor, causing the processor to execute the application
  • the application provides a return visit method, device, computer device and storage medium.
  • the method can calculate the urgency value according to the operation failure parameter fed back by the client, and immediately add the return visit task whose urgency value is less than the urgency threshold to the priority task pool queue, and the attendant firstly visits the follow-up to improve the return visit efficiency.
  • FIG. 1 is a schematic flowchart of a method for returning back according to an embodiment of the present application
  • FIG. 2 is a schematic diagram of a sub-flow of a return visit method provided by an embodiment of the present application
  • FIG. 3 is a schematic block diagram of a returning device according to an embodiment of the present application.
  • FIG. 4 is a schematic block diagram of a subunit of a return visit device according to an embodiment of the present application.
  • FIG. 5 is a schematic block diagram of a computer device according to an embodiment of the present application.
  • FIG. 1 is a schematic flowchart of a method for returning back according to an embodiment of the present application.
  • the method is applied to terminals such as desktop computers, laptop computers, and tablet computers.
  • the method includes steps S101 to S104.
  • the user experience is reduced, which is a failure to prompt the operation, such as registration failure, login failure, and failure to replace the service. , unsubscribe business failure, consulting business failure, etc.
  • a failure to prompt the operation such as registration failure, login failure, and failure to replace the service.
  • unsubscribe business failure such as registration failure, login failure, and failure to replace the service.
  • the user needs a timely customer service return visit to help the user solve the problem encountered during the use of the APP.
  • the urgency value corresponding to the operation failure parameter may be calculated according to the operation failure parameter and the urgency calculation model, and the priority of the user's return visit is determined based on the urgency value.
  • the operation failure parameter used as the basis for calculating the urgency value is generated according to the operation behavior of the user actually using the APP.
  • the data does not need to be recorded and uploaded by the user, and the calculation process of the urgency value is ensured to be a fully automated process.
  • the operation failure parameter includes: an operation type corresponding value, an operation number, and an operation time.
  • the operation failure parameters including features of multiple dimensions, are not limited to the three parameters listed above.
  • the operation failure parameter including the operation type, the operation times, and the operation time are further described in the present application as an example.
  • the operation failure parameter fed back by the client is obtained in the step S101, including:
  • S1012 Obtain an operation time according to a time interval between a current time of the system and a first operation time of the user;
  • the preset operation type value correspondence table records multiple operation types (operation types include a registered account, a login account, a replacement service, an unsubscribe service, a consulting service, etc.), and a one-to-one correspondence with the operation type.
  • the operation type value correspondence table For example, if the operation of registering an account is based on the operation type correspondence table, the task operation type corresponding value is 2, and the operation of the login account is 1 according to the operation type corresponding to the operation type correspondence table.
  • the above three parameters can be used as the input of the urgency calculation model, and the urgency value corresponding to the operation failure parameter is quickly calculated, and the urgency value is used. Based on the arrangement, whether to give priority to return visits.
  • the urgency calculation model is:
  • Tp INT[(k 1 Ptt+k 2 Pn+k 3 Pt)*Ip]
  • Ptt represents the corresponding value of the task operation type
  • Pn represents the number of operations
  • Pt represents the operation time
  • Ip represents the scheduling granularity of the agent server
  • Tp represents the urgency value corresponding to the operation failure parameter
  • k 1 , k 2 , and k 3 respectively represent
  • the first adjustment coefficient, the second adjustment coefficient, and the third adjustment coefficient, INT[] represent a rounding function.
  • the operation failure parameter includes three features of the operation type corresponding value, the operation number, and the operation time, and includes more dimension features
  • the operation failure parameter includes other multiple dimension features. They are denoted as P 1 , P 2 , ..., P n , respectively, and the first adjustment coefficient corresponding to P 1 is denoted by k 11 , and the second adjustment coefficient corresponding to P 2 is denoted by k 12 , ..., corresponding to P N
  • the agent task pool queue includes a common task pool queue and a priority task pool queue; the return task in the common task pool queue is sorted in ascending order according to the urgency value; The return visit tasks are sorted in ascending order by urgency value.
  • the returning task corresponding to the urgency value whose urgency value is less than or equal to the preset urgency threshold may be added to the priority task pool, and the urgency value is greater than the preset urgency threshold.
  • the retire value corresponding to the return visit task is added to the common task pool queue.
  • the parameter that the return task transmits to the priority task pool queue includes at least the customer ID (the customer ID is the user corresponding to the terminal that feedbacks the operation failure parameter). ID), the urgency value corresponding to the return visit task, and the contact information corresponding to the customer ID (such as the phone number corresponding to the client).
  • the returning task in the normal task pool queue can be sorted according to the ascending order of the urgency value. If the urgency corresponding to the multiple returning tasks is the same, the operating time in the operation failure parameter corresponding to the returning task is sorted in order. ).
  • the return visit task in the priority task pool queue is sorted according to the ascending order of the urgency value, and a customer quality grade value is calculated for each return visit task, and the corresponding agent is arranged to return the visit according to the customer quality grade value, the purpose is not only to return in time, It is also targeted for return visits by experienced service agents.
  • the client information includes: a terminal model corresponding value, a geographic location information corresponding value of the user, and a terminal usage time period.
  • the client information including features of multiple dimensions, is not limited to the three parameters listed above.
  • the client information includes: the corresponding value of the terminal model, the corresponding value of the geographical location information of the user, and the terminal usage time period are further described as an example.
  • the preset terminal model correspondence table records a plurality of terminal models (such as iPhone X, iPhone 8, Huawei P10, Huawei P10, Huawei 5X, etc.), and terminal model corresponding values corresponding to the terminal models one by one. .
  • the terminal model corresponding to the iPhone X terminal model has a corresponding value of 2
  • the terminal model corresponding to the terminal model of the Huawei 5X has a corresponding value of 1.
  • the corresponding value of the geographical location information of the user is obtained according to the preset city correspondence table, and multiple city names are recorded in the city correspondence table, and corresponding values of the geographical location information of the user corresponding to the city name are one-to-one, for example, the user is located in Beijing.
  • the corresponding geographical location information of the corresponding user is 2, for example, the corresponding geographic location information of the user when the user is located in Dongguan is 1.
  • the customer quality model is:
  • P 1 represents a terminal model corresponding value record
  • P 2 represents a corresponding value of the geographical location information of the user
  • P 3 represents a terminal usage time period
  • k 4 , k 5 , k 6 respectively represent a fourth adjustment coefficient and a fifth adjustment.
  • Coefficient, sixth adjustment factor, QL represents the customer's premium rating.
  • the client information includes three characteristics of the terminal model corresponding value, the geographic location information corresponding to the user, and the terminal usage time period, and includes more dimension features
  • the client is The characteristics of the information including other dimensions are denoted as PP 1 , PP 2 , ..., PP n , respectively
  • the first adjustment coefficient corresponding to PP 1 is denoted as k 21
  • the second adjustment coefficient corresponding to PP 2 is denoted as k 22
  • the Nth adjustment coefficient corresponding to PP N is recorded as k 2N , then Calculate the customer quality level value corresponding to the client information.
  • the customers who need to return to the visit according to the client information are divided into the purpose of assigning the potential high-quality customers to the agents with strong business ability to conduct the return visit tracking, so as to promote the potential customers to develop into the actual use of the APP customers. .
  • the method can calculate the urgency value according to the operation failure parameter fed back by the client, and immediately add the return task with the urgency value less than the urgency threshold to the priority task pool queue, and the attendant firstly visits the follow-up to improve the return visit efficiency.
  • the embodiment of the present application further provides a returning device, which is used to perform any of the foregoing returning methods.
  • a returning device which is used to perform any of the foregoing returning methods.
  • FIG. 3 is a schematic block diagram of a return visit device provided by an embodiment of the present application.
  • the returning device 100 can be installed in a desktop computer, a tablet computer, a laptop computer, or the like.
  • the returning device 100 includes an urgency value obtaining unit 101, a priority task screening unit 102, a customer quality level value acquiring unit 103, and a returning task assigning unit 104.
  • the urgency value obtaining unit 101 is configured to acquire an operation failure parameter fed back by the client, and use the operation failure parameter as an input of the pre-built urgency calculation model to acquire an urgency value corresponding to the operation failure parameter.
  • the user experience is reduced, which is a failure to prompt the operation, such as registration failure, login failure, and failure to replace the service. , unsubscribe business failure, consulting business failure, etc.
  • a failure to prompt the operation such as registration failure, login failure, and failure to replace the service.
  • unsubscribe business failure such as registration failure, login failure, and failure to replace the service.
  • the user needs a timely customer service return visit to help the user solve the problem encountered during the use of the APP.
  • the urgency value corresponding to the operation failure parameter may be calculated according to the operation failure parameter and the urgency calculation model, and the priority of the user's return visit is determined based on the urgency value.
  • the operation failure parameter used as the basis for calculating the urgency value is generated according to the operation behavior of the user actually using the APP.
  • the data does not need to be recorded and uploaded by the user, and the calculation process of the urgency value is ensured to be a fully automated process.
  • the operation failure parameter includes: an operation type corresponding value, an operation number, and an operation time.
  • the operation failure parameters including features of multiple dimensions, are not limited to the three parameters listed above.
  • the operation failure parameter including the operation type, the operation times, and the operation time are further described in the present application as an example.
  • the urgency value acquisition unit 101 includes the following subunits:
  • the first obtaining unit 1011 is configured to obtain a corresponding value of the task operation type according to the operation type and the preset operation type value correspondence table;
  • the second obtaining unit 1012 is configured to acquire an operation time according to a time interval between a current time of the system and a first operation time of the user;
  • the third obtaining unit 1013 is configured to acquire the number of operations according to the number of clicks on the designated virtual operation button during the operation time.
  • the preset operation type value correspondence table records multiple operation types (operation types include a registered account, a login account, a replacement service, an unsubscribe service, a consulting service, etc.), and a one-to-one correspondence with the operation type.
  • the operation type value correspondence table For example, if the operation of registering an account is based on the operation type correspondence table, the task operation type corresponding value is 2, and the operation of the login account is 1 according to the operation type corresponding to the operation type correspondence table.
  • the above three parameters can be used as the input of the urgency calculation model, and the urgency value corresponding to the operation failure parameter is quickly calculated, and the urgency value is used. Based on the arrangement, whether to give priority to return visits.
  • the urgency calculation model is:
  • Tp INT[(k 1 Ptt+k 2 Pn+k 3 Pt)*Ip]
  • Ptt represents the corresponding value of the task operation type
  • Pn represents the number of operations
  • Pt represents the operation time
  • Ip represents the scheduling granularity of the agent server
  • Tp represents the urgency value corresponding to the operation failure parameter
  • k 1 , k 2 , and k 3 respectively represent
  • the first adjustment coefficient, the second adjustment coefficient, and the third adjustment coefficient, INT[] represent a rounding function.
  • the operation failure parameter includes three features of the operation type corresponding value, the operation number, and the operation time, and includes more dimension features
  • the operation failure parameter includes other multiple dimension features. They are denoted as P 1 , P 2 , ..., P n , respectively, and the first adjustment coefficient corresponding to P 1 is denoted by k 11 , and the second adjustment coefficient corresponding to P 2 is denoted by k 12 , ..., corresponding to P N
  • the priority task screening unit 102 is configured to: if it is detected in the agent task pool that the urgency value of the returning task is less than or equal to the preset urgency threshold, obtain an operation failure parameter corresponding to the urgency value of the returning task, and return the interview The task joins the priority task pool queue in the agent task pool queue.
  • the agent task pool queue includes a common task pool queue and a priority task pool queue; the return task in the common task pool queue is sorted in ascending order according to the urgency value; The return visit tasks are sorted in ascending order by urgency value.
  • the returning task corresponding to the urgency value whose urgency value is less than or equal to the preset urgency threshold may be added to the priority task pool, and the urgency value is greater than the preset urgency threshold.
  • the retire value corresponding to the return visit task is added to the common task pool queue.
  • the parameter that the return task transmits to the priority task pool queue includes at least the customer ID (the customer ID is the user corresponding to the terminal that feedbacks the operation failure parameter). ID), the urgency value corresponding to the return visit task, and the contact information corresponding to the customer ID (such as the phone number corresponding to the client).
  • the returning task in the normal task pool queue can be sorted according to the ascending order of the urgency value. If the urgency corresponding to the multiple returning tasks is the same, the operating time in the operation failure parameter corresponding to the returning task is sorted in order. ).
  • the return visit task in the priority task pool queue is sorted according to the ascending order of the urgency value, and a customer quality grade value is calculated for each return visit task, and the corresponding agent is arranged to return the visit according to the customer quality grade value, the purpose is not only to return in time, It is also targeted for return visits by experienced service agents.
  • the client information includes: a terminal model corresponding value, a geographic location information corresponding value of the user, and a terminal usage time period.
  • the client information including features of multiple dimensions, is not limited to the three parameters listed above.
  • the client information includes: the corresponding value of the terminal model, the corresponding value of the geographical location information of the user, and the terminal usage time period are further described as an example.
  • the preset terminal model correspondence table records a plurality of terminal models (such as iPhone X, iPhone 8, Huawei P10, Huawei P10, Huawei 5X, etc.), and terminal model corresponding values corresponding to the terminal models one by one. .
  • the terminal model corresponding to the iPhone X terminal model has a corresponding value of 2
  • the terminal model corresponding to the terminal model of the Huawei 5X has a corresponding value of 1.
  • the corresponding value of the geographical location information of the user is obtained according to the preset city correspondence table, and multiple city names are recorded in the city correspondence table, and corresponding values of the geographical location information of the user corresponding to the city name are one-to-one, for example, the user is located in Beijing.
  • the corresponding geographical location information of the corresponding user is 2, for example, the corresponding geographic location information of the user when the user is located in Dongguan is 1.
  • the customer quality level value obtaining unit 103 is configured to obtain the client information of the returning task in the priority task pool queue, and use the client information as the input of the pre-built customer quality model to obtain the customer quality level value corresponding to the client information. .
  • the customer quality model is:
  • P 1 represents a terminal model corresponding value record
  • P 2 represents a corresponding value of the geographical location information of the user
  • P 3 represents a terminal usage time period
  • k 4 , k 5 , k 6 respectively represent a fourth adjustment coefficient and a fifth adjustment.
  • Coefficient, sixth adjustment factor, QL represents the customer's premium rating.
  • the client information includes three characteristics of the terminal model corresponding value, the geographic location information corresponding to the user, and the terminal usage time period, and includes more dimension features
  • the client is The characteristics of the information including other dimensions are denoted as PP 1 , PP 2 , ..., PP n , respectively
  • the first adjustment coefficient corresponding to PP 1 is denoted as k 21
  • the second adjustment coefficient corresponding to PP 2 is denoted as k 22
  • the Nth adjustment coefficient corresponding to PP N is denoted as k 2N
  • QL (k 4 P 1 + k 5 P 2 + k 6 P 3 + k 21 PP 1 + k 22 Calculate the customer quality level value corresponding to the client information.
  • the returning task assignment unit 104 is configured to allocate the returning task corresponding to the client information to the agent terminal corresponding to the service level according to the customer quality level value corresponding to the client information.
  • the customers who need to return to the visit according to the client information are divided into the purpose of assigning the potential high-quality customers to the agents with strong business ability to conduct the return visit tracking, so as to promote the potential customers to develop into the actual use of the APP customers. .
  • the device can calculate the urgency value according to the operation failure parameter fed back by the client, and immediately add the return task with the urgency value less than the urgency threshold to the priority task pool queue, and the attendant firstly visits the follow-up to improve the return visit efficiency.
  • the above-mentioned return visit device can be implemented in the form of a computer program that can be run on a computer device as shown in FIG.
  • FIG. 5 is a schematic block diagram of a computer device according to an embodiment of the present application.
  • the computer device 500 device can be a terminal.
  • the terminal can be an electronic device such as a tablet computer, a notebook computer, a desktop computer, or a personal digital assistant.
  • the computer device 500 includes a processor 502, a memory and a network interface 505 connected by a system bus 501, wherein the memory can include a non-volatile storage medium 503 and an internal memory 504.
  • the non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032.
  • the computer program 5032 includes program instructions that, when executed, cause the processor 502 to perform a return visit method.
  • the processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500.
  • the internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503, which when executed by the processor 502, causes the processor 502 to perform a return method.
  • the network interface 505 is used for network communication, such as sending assigned tasks and the like. It will be understood by those skilled in the art that the structure shown in FIG. 5 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation of the computer device 500 to which the solution of the present application is applied, and a specific computer device. 500 may include more or fewer components than shown, or some components may be combined, or have different component arrangements.
  • the processor 502 is configured to run a computer program 5032 stored in the memory to implement the following functions: acquiring an operation failure parameter fed back by the client, and using the operation failure parameter as an input of a pre-built urgency calculation model, Obtaining the urgency value corresponding to the operation failure parameter; if the urgency value of the returning task detected in the agent task pool is less than or equal to the preset urgency threshold, obtaining an operation failure parameter corresponding to the urgency value of the returning task Add the return task to the priority task pool queue in the agent task pool queue; obtain the client information of the return task in the priority task pool queue, and use the client information as the input of the pre-built customer quality model to obtain the client The customer's premium level value corresponding to the information; the return visit task corresponding to the client information is assigned to the agent terminal corresponding to the service level according to the customer quality level value corresponding to the client information.
  • the operation failure parameter includes: an operation type corresponding value, an operation number, and an operation time;
  • the urgency calculation model is:
  • Tp INT[(k 1 Ptt+k 2 Pn+k 3 Pt)*Ip]
  • Ptt represents the corresponding value of the task operation type
  • Pn represents the number of operations
  • Pt represents the operation time
  • Ip represents the scheduling granularity of the agent server
  • Tp represents the urgency value corresponding to the operation failure parameter
  • k 1 , k 2 , and k 3 respectively represent
  • the first adjustment coefficient, the second adjustment coefficient, and the third adjustment coefficient, INT[] represent a rounding function.
  • the client information includes: a terminal model corresponding value, a geographic location information corresponding value of the user, and a terminal usage time period;
  • the customer quality model is:
  • P 1 represents a terminal model corresponding value record
  • P 2 represents a corresponding value of the geographical location information of the user
  • P 3 represents a terminal usage time period
  • k 4 , k 5 , k 6 respectively represent a fourth adjustment coefficient and a fifth adjustment.
  • Coefficient, sixth adjustment factor, QL represents the customer's premium rating.
  • the processor 502 further performs the following operations: acquiring a corresponding value of the task operation type according to the operation type and the preset operation type value correspondence table; and obtaining the operation according to the time interval between the current time of the system and the initial operation time of the user. Time; the number of operations is obtained based on the number of clicks on the specified virtual action button during the operation time.
  • the processor 502 further performs the following operations: the agent task pool queue includes a common task pool queue, and a priority task pool queue; and the return task in the common task pool queue is sorted in ascending order by urgency value The return visit tasks in the priority task pool queue are sorted in ascending order by the urgency value.
  • the embodiment of the computer device shown in FIG. 5 does not constitute a limitation on the specific configuration of the computer device.
  • the computer device may include more or fewer components than illustrated. Or combine some parts, or different parts.
  • the computer device may include only a memory and a processor. In such an embodiment, the structure and function of the memory and the processor are the same as those of the embodiment shown in FIG. 5, and details are not described herein again.
  • the processor 502 may be a central processing unit (CPU), and the processor 502 may also be another general-purpose processor, a digital signal processor (DSP), Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, etc.
  • the general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
  • a storage medium in another embodiment of the present application, is provided.
  • the storage medium can be a storage medium.
  • the storage medium stores a computer program, wherein the computer program includes program instructions.
  • the program instruction is executed by the processor, the operation failure parameter fed back by the client is obtained, and the operation failure parameter is used as an input of the pre-built urgency calculation model, and the urgency value corresponding to the operation failure parameter is obtained;
  • the urgency value of the returning task is less than or equal to the preset urgency threshold, and the operation failure parameter corresponding to the urgency value of the returning task is obtained, and the returning task is added to the priority task in the agent task pool queue.
  • the pool queue obtains the client information of the return visit task in the priority task pool queue, and uses the client information as the input of the pre-built customer quality model to obtain the customer quality level value corresponding to the client information; according to the client information
  • the customer's premium rating value is assigned to the agent's terminal corresponding to the service level.
  • the operation failure parameter includes: an operation type corresponding value, an operation number, and an operation time;
  • the urgency calculation model is:
  • Tp INT[(k 1 Ptt+k 2 Pn+k 3 Pt)*Ip]
  • Ptt represents the corresponding value of the task operation type
  • Pn represents the number of operations
  • Pt represents the operation time
  • Ip represents the scheduling granularity of the agent server
  • Tp represents the urgency value corresponding to the operation failure parameter
  • k 1 , k 2 , and k 3 respectively represent
  • the first adjustment coefficient, the second adjustment coefficient, and the third adjustment coefficient, INT[] represent a rounding function.
  • the client information includes: a terminal model corresponding value, a geographic location information corresponding value of the user, and a terminal usage time period;
  • the customer quality model is:
  • P 1 represents a terminal model corresponding value record
  • P 2 represents a corresponding value of the geographical location information of the user
  • P 3 represents a terminal usage time period
  • k 4 , k 5 , k 6 respectively represent a fourth adjustment coefficient and a fifth adjustment.
  • Coefficient, sixth adjustment factor, QL represents the customer's premium rating.
  • the corresponding value of the task operation type is obtained according to the operation type and the preset operation type value correspondence table; and according to the time interval between the current time of the system and the initial operation time of the user, Get the operation time; get the number of operations based on the number of clicks on the specified virtual operation button during the operation time.
  • the agent task pool queue when the program instruction is executed by the processor, the agent task pool queue includes a common task pool queue and a priority task pool queue; and the return task in the common task pool queue is performed according to the urgency value.
  • the ascending order is arranged; the returning tasks in the priority task pool queue are sorted in ascending order according to the urgency value.
  • the storage medium may be an internal storage unit of the aforementioned device, such as a hard disk or a memory of the device.
  • the storage medium may also be an external storage device of the device, such as a plug-in hard disk equipped on the device, a smart memory card (SMC), a secure digital (SD) card, and a flash memory card. (Flash Card), etc.
  • the storage medium may also include both an internal storage unit of the device and an external storage device.

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Finance (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Computer And Data Communications (AREA)
  • Telephonic Communication Services (AREA)

Abstract

本申请公开了一种回访方法、装置、计算机设备及存储介质。该方法包括：将客户端所反馈的操作失败参数作为紧急度计算模型的输入，获取紧急度值；若在坐席员任务池中检测到有回访任务的紧急度值小于等于紧急度阈值，获取与紧急度值对应的操作失败参数，将相应回访任务加入优先任务池队列；将加入优先任务池队列中回访任务的客户端信息作为预先构建的客户优质度模型的输入，获取客户优质等级值；根据客户端信息对应的客户优质等级值，将客户端信息对应的回访任务分配至对应服务等级的坐席员终端。该方法能够根据客户端所反馈的操作失败参数计算紧急度值，并将紧急度值小于紧急度阈值的回访任务安排回访跟进，提高了回访效率。

Description

回访方法、装置、计算机设备及存储介质
本申请要求于2018年2月12日提交中国专利局、申请号为201810145747.4、申请名称为“回访方法、装置、计算机设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及电话回访技术领域，尤其涉及一种回访方法、装置、计算机设备及存储介质。
背景技术
目前，当用户在通过智能终端访问APP并进行操作时，一般会进行注册、登录、办理业务、查询业务等操作。当用户进行上述操作，有多次失败的情况发生时，此时用户是需要APP的后台客服回访并对其进行指导操作，该客户因操作失败的产生的回访需求会上传至坐席员任务池，但坐席员任务池中的回访任务一般是基于回访需求上传至坐席员任务池的时间先后顺序来排列，这就导致真正急需回访和操作引导的用户，不能被及时的回访。
发明内容
本申请提供了一种回访方法、装置、计算机设备及存储介质，旨在解决现有技术中回访任务一般是基于回访需求上传至坐席员任务池的时间先后顺序来排列，这就导致真正急需回访和操作引导的用户，不能被及时的回访的问题。
第一方面，本申请提供了一种回访方法，其包括：
当获取客户端所反馈的操作失败参数，并将操作失败参数作为预先构建的紧急度计算模型的输入，获取与操作失败参数对应的紧急度值；
若在坐席员任务池中检测到有回访任务的紧急度值小于或等于预设的紧急度阈值，获取与回访任务的紧急度值对应的操作失败参数，将回访任务加入坐席员任务池队列中的优先任务池队列；
获取加入优先任务池队列中回访任务的客户端信息，将客户端信息作为预 先构建的客户优质度模型的输入，获取与客户端信息对应的客户优质等级值；
根据客户端信息对应的客户优质等级值，将客户端信息对应的回访任务分配至对应服务等级的坐席员终端。
第二方面，本申请提供了一种回访装置，其包括：
紧急度值获取单元，用于获取客户端所反馈的操作失败参数，并将操作失败参数作为预先构建的紧急度计算模型的输入，获取与操作失败参数对应的紧急度值；
优先任务筛选单元，用于若在坐席员任务池中检测到有回访任务的紧急度值小于或等于预设的紧急度阈值，获取与回访任务的紧急度值对应的操作失败参数，将回访任务加入坐席员任务池队列中的优先任务池队列；
客户优质等级值获取单元，用于获取加入优先任务池队列中回访任务的客户端信息，将客户端信息作为预先构建的客户优质度模型的输入，获取与客户端信息对应的客户优质等级值；
回访任务分配单元，用于根据客户端信息对应的客户优质等级值，将客户端信息对应的回访任务分配至对应服务等级的坐席员终端。
第三方面，本申请又提供了一种计算机设备，包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现本申请提供的任一项所述的回访方法。
第四方面，本申请还提供了一种存储介质，其中所述存储介质存储有计算机程序，所述计算机程序包括程序指令，所述程序指令当被处理器执行时使所述处理器执行本申请提供的任一项所述的回访方法。
本申请提供一种回访方法、装置、计算机设备及存储介质。该方法能够根据客户端所反馈的操作失败参数计算紧急度值，将紧急度值小于紧急度阈值的回访任务立即加入优先任务池队列，坐席员优先回访跟进，提高了回访效率。
附图说明
为了更清楚地说明本申请实施例技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本申请实施例提供的一种回访方法的示意流程图；
图2是本申请实施例提供的一种回访方法的子流程示意图；
图3为本申请实施例提供的一种回访装置的示意性框图；
图4为本申请实施例提供的一种回访装置的子单元示意性框图；
图5为本申请实施例提供的一种计算机设备的示意性框图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
请参阅图1，图1是本申请实施例提供的一种回访方法的示意流程图。该方法应用于台式电脑、手提电脑、平板电脑等终端中。如图1所示，该方法包括步骤S101～S104。
S101、获取客户端所反馈的操作失败参数，并将操作失败参数作为预先构建的紧急度计算模型的输入，获取与操作失败参数对应的紧急度值。
在本实施例中，当用户在智能终端上打开并运行APP，在APP的UI界面上进行各种操作时，导致用户体验降低的是提示失败的操作，例如注册失败、登录失败、更换业务失败、退订业务失败、咨询业务失败等。当遇到上述失败提示时，用户在无法自行解决问题时，需要的是及时的客服回访，以帮助用户解决APP使用过程中遇到的问题。为了准确甄别每一用户对坐席回访的紧急程度，可根据操作失败参数及紧急度计算模型，计算得到操作失败参数对应的紧急度值，并以紧急度值为依据来判断用户回访的优先程度。
作为计算紧急度值依据的操作失败参数，是根据用户实际使用APP中的操作行为产生，这些数据无需用户去记录和上传，确保了紧急度值的计算过程是一全自动化的过程。
在一实施例中，所述操作失败参数包括：操作类型对应值、操作次数、操作时间。在实际实施的过程中，所述操作失败参数，包括多个维度的特征，并不仅仅局限于上述列举的三个参数。但为了便于理解本申请的技术方案，本申请中以操作失败参数包括操作类型、操作次数、操作时间为实例来进一步说明。
如图2所示，所述步骤S101中获取客户端所反馈的操作失败参数，包括：
S1011、根据操作类型、及预设的操作类型值对应表，获取任务操作类型对应值；
S1012、根据系统当前时间与用户初次操作时间的时间间隔，获取操作时间；
S1013、根据在操作时间内对指定虚拟操作按钮的点击次数，获取操作次数。
在本实施例中，预设的操作类型值对应表中记录多种操作类型(操作类型包括注册账户、登录账户、更换业务、退订业务、咨询业务等)、及与操作类型一一对应的操作类型值对应表。例如注册账户这一操作根据操作类型对应表查询得到的任务操作类型对应值为2，登录账户这一操作根据操作类型对应表查询得到的任务操作类型对应值为1等。操作时间记为Pt，且通过Pt＝t 2-t 1(其中，t 2表示当前系统时间，t 1表示用户初次操作时间)来计算操作时间。获取用户在APP的UI界面上对指定虚拟操作按钮的点击次数，来获取操作次数。当操作类型对应值、操作次数、操作时间均被获取后，即可将上述三个参数作为紧急度计算模型的输入，快速计算与操作失败参数对应的紧急度值，并以紧急度值的大小为依据来安排是否优先回访。
在一实施例中，所述紧急度计算模型为：
Tp＝INT[(k 1Ptt+k 2Pn+k 3Pt)*Ip]；
其中，Ptt表示任务操作类型对应值，Pn表示操作次数，Pt表示操作时间，Ip表示坐席服务器的调度粒度，Tp表示与操作失败参数对应的紧急度值，k 1、k 2、k 3分别表示第一调节系数、第二调节系数、第三调节系数，INT[]表示取整函数。通过所述紧急度计算模型，能计算得到一个合理的紧急度值，能以该紧急度值进一步作为回访优先级的依据。
在本实施例中，若所述操作失败参数除了包括操作类型对应值、操作次数、操作时间这三个特征，还包括更多维度的特征时，将操作失败参数所包括其他多个维度的特征分别记为P 1、P 2、……、P n，与P 1对应的第一调节系数记为k 11、与P 2对应的第二调节系数记为k 12、……、与P N对应的第N调节系数记为k 1N，则根据Tp＝INT[(k 1P tt+k 2P n+k 3Pt+k 11P 1+k 12P 2+……+k 1NP N)*Ip]计算每一操作失败参数对应的紧急度值，其中Ip表示坐席服务器的调度粒度，Tp表示与操作失败参数对应的紧急度值，INT[]表示取整函数。
S102、若在坐席员任务池中检测到有回访任务的紧急度值小于或等于预设 的紧急度阈值，获取与回访任务的紧急度值对应的操作失败参数，将回访任务加入坐席员任务池队列中的优先任务池队列。
在一实施例中，所述坐席员任务池队列包括普通任务池队列，及优先任务池队列；所述普通任务池队列中的回访任务按紧急度值进行升序排列；所述优先任务池队列中的回访任务按紧急度值进行升序排列。
在本实施例中，与操作失败参数对应的紧急度值的取值越小，则表示该事件越紧急，需要坐席员立即进行回访，以避免因回访不及时而导致客户流失。为了更清楚的区分回访任务的优先程度，可将紧急度值小于或等于预设的紧急度阈值的紧急度值所对应回访任务加入优先任务池队，将紧急度值大于预设的紧急度阈值的紧急度值所对应回访任务加入普通任务池队列。其中，将回访任务加入坐席员任务池队列中的优先任务池队列中时，回返任务传输至优先任务池队列中的参数至少包客户ID(该客户ID即为反馈操作失败参数的终端所对应用户ID)、回访任务对应的紧急度值、客户ID对应的联系信息(如客户端所对应的电话号码)。
在普通任务池队列中回访任务根据紧急度值的升序排序即可(如有多个回访任务对应的紧急度相同，则根据该回访任务对应的操作失败参数中所包括操作时间的先后顺序依次排序)。在优先任务池队列中回访任务根据紧急度值的升序排序，而且针对每一回访任务还要计算一客户优质等级值，根据客户优质等级值安排相应坐席员进行回访，目的在于不仅是及时回访，而且是有针对性的由服务经验丰富的坐席员进行回访。
在一实施例中，所述客户端信息包括：终端机型对应值、用户所处地理位置信息对应值、终端使用时间段。在实际实施的过程中，所述客户端信息，包括多个维度的特征，并不仅仅局限于上述列举的三个参数。但为了便于理解本申请的技术方案，本申请中以客户端信息包括：终端机型对应值、用户所处地理位置信息对应值、终端使用时间段为实例来进一步说明。
其中，预设的终端机型对应表中记录多种终端机型(如iPhone X、iPhone 8、华为P10、华为P10，小米5X等)、及与终端机型一一对应的终端机型对应值。例如iPhone X这一终端机型对应的终端机型对应值为2，小米5X这一终端机型对应的终端机型对应值为1等。用户所处地理位置信息对应值根据预设城市对应表来获取，在城市对应表中记录多个城市名称，及与城市名称一一对应的用 户所处地理位置信息对应值，例如用户定位在北京时对应的用户所处地理位置信息对应值为2，例如用户定位在东莞时对应的用户所处地理位置信息对应值为1。
S103、获取加入优先任务池队列中回访任务的客户端信息，将客户端信息作为预先构建的客户优质度模型的输入，获取与客户端信息对应的客户优质等级值。
在一实施例中，所述客户优质度模型为：
Figure PCTCN2018085269-appb-000001
其中，P 1表示终端机型对应值记、P 2表示用户所处地理位置信息对应值、P 3表示终端使用时间段，k 4、k 5、k 6分别表示第四调节系数、第五调节系数、第六调节系数，QL表示客户优质等级值。
在本实施例中，若所述客户端信息除了包括终端机型对应值、用户所处地理位置信息对应值、终端使用时间段这三个特征，还包括更多维度的特征时，将客户端信息所包括其他多个维度的特征分别记为PP 1、PP 2、……、PP n，与PP 1对应的第一调节系数记为k 21、与PP 2对应的第二调节系数记为k 22、……、与PP N对应的第N调节系数记为k 2N，则根据
Figure PCTCN2018085269-appb-000002
Figure PCTCN2018085269-appb-000003
计算客户端信息对应的客户优质等级值。
S104、根据客户端信息对应的客户优质等级值，将客户端信息对应的回访任务分配至对应服务等级的坐席员终端。
在本实施例中，根据客户端信息将需进行回访的客户进行划分，是为了将潜在的优质客户分配至业务能力较强的坐席员进行回访跟踪，以促成潜在客户发展为实际使用APP的客户。
可见，该方法能够根据客户端所反馈的操作失败参数计算紧急度值，将紧急度值小于紧急度阈值的回访任务立即加入优先任务池队列，坐席员优先回访跟进，提高了回访效率。
本申请实施例还提供一种回访装置，该回访装置用于执行前述任一项回访方法。具体地，请参阅图3，图3是本申请实施例提供的一种回访装置的示意性框图。回访装置100可以安装于台式电脑、平板电脑、手提电脑、等终端中。
如图3所示，回访装置100包括紧急度值获取单元101、优先任务筛选单元 102、客户优质等级值获取单元103、回访任务分配单元104。
紧急度值获取单元101，用于获取客户端所反馈的操作失败参数，并将操作失败参数作为预先构建的紧急度计算模型的输入，获取与操作失败参数对应的紧急度值。
在本实施例中，当用户在智能终端上打开并运行APP，在APP的UI界面上进行各种操作时，导致用户体验降低的是提示失败的操作，例如注册失败、登录失败、更换业务失败、退订业务失败、咨询业务失败等。当遇到上述失败提示时，用户在无法自行解决问题时，需要的是及时的客服回访，以帮助用户解决APP使用过程中遇到的问题。为了准确甄别每一用户对坐席回访的紧急程度，可根据操作失败参数及紧急度计算模型，计算得到操作失败参数对应的紧急度值，并以紧急度值为依据来判断用户回访的优先程度。
作为计算紧急度值依据的操作失败参数，是根据用户实际使用APP中的操作行为产生，这些数据无需用户去记录和上传，确保了紧急度值的计算过程是一全自动化的过程。
在一实施例中，所述操作失败参数包括：操作类型对应值、操作次数、操作时间。在实际实施的过程中，所述操作失败参数，包括多个维度的特征，并不仅仅局限于上述列举的三个参数。但为了便于理解本申请的技术方案，本申请中以操作失败参数包括操作类型、操作次数、操作时间为实例来进一步说明。
如图4所示，所述紧急度值获取单元101包括以下子单元：
第一获取单元1011，用于根据操作类型、及预设的操作类型值对应表，获取任务操作类型对应值；
第二获取单元1012，用于根据系统当前时间与用户初次操作时间的时间间隔，获取操作时间；
第三获取单元1013，用于根据在操作时间内对指定虚拟操作按钮的点击次数，获取操作次数。
在本实施例中，预设的操作类型值对应表中记录多种操作类型(操作类型包括注册账户、登录账户、更换业务、退订业务、咨询业务等)、及与操作类型一一对应的操作类型值对应表。例如注册账户这一操作根据操作类型对应表查询得到的任务操作类型对应值为2，登录账户这一操作根据操作类型对应表查询得到的任务操作类型对应值为1等。操作时间记为Pt，且通过Pt＝t 2-t 1(其中， t 2表示当前系统时间，t 1表示用户初次操作时间)来计算操作时间。获取用户在APP的UI界面上对指定虚拟操作按钮的点击次数，来获取操作次数。当操作类型对应值、操作次数、操作时间均被获取后，即可将上述三个参数作为紧急度计算模型的输入，快速计算与操作失败参数对应的紧急度值，并以紧急度值的大小为依据来安排是否优先回访。
在一实施例中，所述紧急度计算模型为：
Tp＝INT[(k 1Ptt+k 2Pn+k 3Pt)*Ip]；
其中，Ptt表示任务操作类型对应值，Pn表示操作次数，Pt表示操作时间，Ip表示坐席服务器的调度粒度，Tp表示与操作失败参数对应的紧急度值，k 1、k 2、k 3分别表示第一调节系数、第二调节系数、第三调节系数，INT[]表示取整函数。通过所述紧急度计算模型，能计算得到一个合理的紧急度值，能以该紧急度值进一步作为回访优先级的依据。
在本实施例中，若所述操作失败参数除了包括操作类型对应值、操作次数、操作时间这三个特征，还包括更多维度的特征时，将操作失败参数所包括其他多个维度的特征分别记为P 1、P 2、……、P n，与P 1对应的第一调节系数记为k 11、与P 2对应的第二调节系数记为k 12、……、与P N对应的第N调节系数记为k 1N，则根据Tp＝INT[(k 1P tt+k 2P n+k 3Pt+k 11P 1+k 12P 2+……+k 1NP N)*Ip]计算每一操作失败参数对应的紧急度值，其中Ip表示坐席服务器的调度粒度，Tp表示与操作失败参数对应的紧急度值，INT[]表示取整函数。
优先任务筛选单元102，用于若在坐席员任务池中检测到有回访任务的紧急度值小于或等于预设的紧急度阈值，获取与回访任务的紧急度值对应的操作失败参数，将回访任务加入坐席员任务池队列中的优先任务池队列。
在一实施例中，所述坐席员任务池队列包括普通任务池队列，及优先任务池队列；所述普通任务池队列中的回访任务按紧急度值进行升序排列；所述优先任务池队列中的回访任务按紧急度值进行升序排列。
在本实施例中，与操作失败参数对应的紧急度值的取值越小，则表示该事件越紧急，需要坐席员立即进行回访，以避免因回访不及时而导致客户流失。为了更清楚的区分回访任务的优先程度，可将紧急度值小于或等于预设的紧急度阈值的紧急度值所对应回访任务加入优先任务池队，将紧急度值大于预设的紧急度阈值的紧急度值所对应回访任务加入普通任务池队列。其中，将回访任 务加入坐席员任务池队列中的优先任务池队列中时，回返任务传输至优先任务池队列中的参数至少包客户ID(该客户ID即为反馈操作失败参数的终端所对应用户ID)、回访任务对应的紧急度值、客户ID对应的联系信息(如客户端所对应的电话号码)。
在普通任务池队列中回访任务根据紧急度值的升序排序即可(如有多个回访任务对应的紧急度相同，则根据该回访任务对应的操作失败参数中所包括操作时间的先后顺序依次排序)。在优先任务池队列中回访任务根据紧急度值的升序排序，而且针对每一回访任务还要计算一客户优质等级值，根据客户优质等级值安排相应坐席员进行回访，目的在于不仅是及时回访，而且是有针对性的由服务经验丰富的坐席员进行回访。
在一实施例中，所述客户端信息包括：终端机型对应值、用户所处地理位置信息对应值、终端使用时间段。在实际实施的过程中，所述客户端信息，包括多个维度的特征，并不仅仅局限于上述列举的三个参数。但为了便于理解本申请的技术方案，本申请中以客户端信息包括：终端机型对应值、用户所处地理位置信息对应值、终端使用时间段为实例来进一步说明。
其中，预设的终端机型对应表中记录多种终端机型(如iPhone X、iPhone 8、华为P10、华为P10，小米5X等)、及与终端机型一一对应的终端机型对应值。例如iPhone X这一终端机型对应的终端机型对应值为2，小米5X这一终端机型对应的终端机型对应值为1等。用户所处地理位置信息对应值根据预设城市对应表来获取，在城市对应表中记录多个城市名称，及与城市名称一一对应的用户所处地理位置信息对应值，例如用户定位在北京时对应的用户所处地理位置信息对应值为2，例如用户定位在东莞时对应的用户所处地理位置信息对应值为1。
客户优质等级值获取单元103，用于获取加入优先任务池队列中回访任务的客户端信息，将客户端信息作为预先构建的客户优质度模型的输入，获取与客户端信息对应的客户优质等级值。
在一实施例中，所述客户优质度模型为：
Figure PCTCN2018085269-appb-000004
其中，P 1表示终端机型对应值记、P 2表示用户所处地理位置信息对应值、P 3表示终端使用时间段，k 4、k 5、k 6分别表示第四调节系数、第五调节系数、第 六调节系数，QL表示客户优质等级值。
在本实施例中，若所述客户端信息除了包括终端机型对应值、用户所处地理位置信息对应值、终端使用时间段这三个特征，还包括更多维度的特征时，将客户端信息所包括其他多个维度的特征分别记为PP 1、PP 2、……、PP n，与PP 1对应的第一调节系数记为k 21、与PP 2对应的第二调节系数记为k 22、……、与PP N对应的第N调节系数记为k 2N，则根据QL＝(k 4P 1+k 5P 2+k 6P 3+k 21PP 1+k 22
Figure PCTCN2018085269-appb-000005
计算客户端信息对应的客户优质等级值。
回访任务分配单元104，用于根据客户端信息对应的客户优质等级值，将客户端信息对应的回访任务分配至对应服务等级的坐席员终端
在本实施例中，根据客户端信息将需进行回访的客户进行划分，是为了将潜在的优质客户分配至业务能力较强的坐席员进行回访跟踪，以促成潜在客户发展为实际使用APP的客户。
可见，该装置能够根据客户端所反馈的操作失败参数计算紧急度值，将紧急度值小于紧急度阈值的回访任务立即加入优先任务池队列，坐席员优先回访跟进，提高了回访效率。
上述回访装置可以实现为一种计算机程序的形式，该计算机程序可以在如图5所示的计算机设备上运行。
请参阅图5，图5是本申请实施例提供的一种计算机设备的示意性框图。该计算机设备500设备可以是终端。该终端可以是平板电脑、笔记本电脑、台式电脑、个人数字助理等电子设备。
参阅图5，该计算机设备500包括通过系统总线501连接的处理器502、存储器和网络接口505，其中，存储器可以包括非易失性存储介质503和内存储器504。
该非易失性存储介质503可存储操作系统5031和计算机程序5032。该计算机程序5032包括程序指令，该程序指令被执行时，可使得处理器502执行一种回访方法。
该处理器502用于提供计算和控制能力，支撑整个计算机设备500的运行。
该内存储器504为非易失性存储介质503中的计算机程序5032的运行提供环境，该计算机程序5032被处理器502执行时，可使得处理器502执行一种回 访方法。
该网络接口505用于进行网络通信，如发送分配的任务等。本领域技术人员可以理解，图5中示出的结构，仅仅是与本申请方案相关的部分结构的框图，并不构成对本申请方案所应用于其上的计算机设备500的限定，具体的计算机设备500可以包括比图中所示更多或更少的部件，或者组合某些部件，或者具有不同的部件布置。
其中，所述处理器502用于运行存储在存储器中的计算机程序5032，以实现如下功能：获取客户端所反馈的操作失败参数，并将操作失败参数作为预先构建的紧急度计算模型的输入，获取与操作失败参数对应的紧急度值；若在坐席员任务池中检测到有回访任务的紧急度值小于或等于预设的紧急度阈值，获取与回访任务的紧急度值对应的操作失败参数，将回访任务加入坐席员任务池队列中的优先任务池队列；获取加入优先任务池队列中回访任务的客户端信息，将客户端信息作为预先构建的客户优质度模型的输入，获取与客户端信息对应的客户优质等级值；根据客户端信息对应的客户优质等级值，将客户端信息对应的回访任务分配至对应服务等级的坐席员终端。
在一实施例中，所述操作失败参数包括：操作类型对应值、操作次数、操作时间；
所述紧急度计算模型为：
Tp＝INT[(k 1Ptt+k 2Pn+k 3Pt)*Ip]；
其中，Ptt表示任务操作类型对应值，Pn表示操作次数，Pt表示操作时间，Ip表示坐席服务器的调度粒度，Tp表示与操作失败参数对应的紧急度值，k 1、k 2、k 3分别表示第一调节系数、第二调节系数、第三调节系数，INT[]表示取整函数。
在一实施例中，所述客户端信息包括：终端机型对应值、用户所处地理位置信息对应值、终端使用时间段；
所述客户优质度模型为：
Figure PCTCN2018085269-appb-000006
其中，P 1表示终端机型对应值记、P 2表示用户所处地理位置信息对应值、P 3表示终端使用时间段，k 4、k 5、k 6分别表示第四调节系数、第五调节系数、第六调节系数，QL表示客户优质等级值。
在一实施例中，处理器502还执行如下操作：根据操作类型、及预设的操作类型值对应表，获取任务操作类型对应值；根据系统当前时间与用户初次操作时间的时间间隔，获取操作时间；根据在操作时间内对指定虚拟操作按钮的点击次数，获取操作次数。
在一实施例中，处理器502还执行如下操作：所述坐席员任务池队列包括普通任务池队列，及优先任务池队列；所述普通任务池队列中的回访任务按紧急度值进行升序排列；所述优先任务池队列中的回访任务按紧急度值进行升序排列。
本领域技术人员可以理解，图5中示出的计算机设备的实施例并不构成对计算机设备具体构成的限定，在其他实施例中，计算机设备可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。例如，在一些实施例中，计算机设备可以仅包括存储器及处理器，在这样的实施例中，存储器及处理器的结构及功能与图5所示实施例一致，在此不再赘述。
应当理解，在本申请实施例中，处理器502可以是中央处理单元(Central Processing Unit，CPU)，该处理器502还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。其中，通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
在本申请的另一实施例中提供一种存储介质。该存储介质可以为存储介质。该存储介质存储有计算机程序，其中计算机程序包括程序指令。该程序指令被处理器执行时实现：获取客户端所反馈的操作失败参数，并将操作失败参数作为预先构建的紧急度计算模型的输入，获取与操作失败参数对应的紧急度值；若在坐席员任务池中检测到有回访任务的紧急度值小于或等于预设的紧急度阈值，获取与回访任务的紧急度值对应的操作失败参数，将回访任务加入坐席员任务池队列中的优先任务池队列；获取加入优先任务池队列中回访任务的客户端信息，将客户端信息作为预先构建的客户优质度模型的输入，获取与客户端信息对应的客户优质等级值；根据客户端信息对应的客户优质等级值，将客户端信息对应的回访任务分配至对应服务等级的坐席员终端。
在一实施例中，所述操作失败参数包括：操作类型对应值、操作次数、操 作时间；
所述紧急度计算模型为：
Tp＝INT[(k 1Ptt+k 2Pn+k 3Pt)*Ip]；
其中，Ptt表示任务操作类型对应值，Pn表示操作次数，Pt表示操作时间，Ip表示坐席服务器的调度粒度，Tp表示与操作失败参数对应的紧急度值，k 1、k 2、k 3分别表示第一调节系数、第二调节系数、第三调节系数，INT[]表示取整函数。
在一实施例中，所述客户端信息包括：终端机型对应值、用户所处地理位置信息对应值、终端使用时间段；
所述客户优质度模型为：
Figure PCTCN2018085269-appb-000007
其中，P 1表示终端机型对应值记、P 2表示用户所处地理位置信息对应值、P 3表示终端使用时间段，k 4、k 5、k 6分别表示第四调节系数、第五调节系数、第六调节系数，QL表示客户优质等级值。
在一实施例中，该程序指令被处理器执行时实现：根据操作类型、及预设的操作类型值对应表，获取任务操作类型对应值；根据系统当前时间与用户初次操作时间的时间间隔，获取操作时间；根据在操作时间内对指定虚拟操作按钮的点击次数，获取操作次数。
在一实施例中，该程序指令被处理器执行时实现：所述坐席员任务池队列包括普通任务池队列，及优先任务池队列；所述普通任务池队列中的回访任务按紧急度值进行升序排列；所述优先任务池队列中的回访任务按紧急度值进行升序排列。
所述存储介质可以是前述设备的内部存储单元，例如设备的硬盘或内存。所述存储介质也可以是所述设备的外部存储设备，例如所述设备上配备的插接式硬盘，智能存储卡(Smart Media Card，SMC)，安全数字(Secure Digital，SD)卡，闪存卡(Flash Card)等。进一步地，所述存储介质还可以既包括所述设备的内部存储单元也包括外部存储设备。
所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，上述描述的设备、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到各种等效的修改或替换，这些修改或替换都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以权利要求的保护范围为准。

Claims (20)

  1. 一种回访方法，其特征在于，包括：
    获取客户端所反馈的操作失败参数，并将操作失败参数作为预先构建的紧急度计算模型的输入，获取与操作失败参数对应的紧急度值；
    若在坐席员任务池中检测到有回访任务的紧急度值小于或等于预设的紧急度阈值，获取与回访任务的紧急度值对应的操作失败参数，将回访任务加入坐席员任务池队列中的优先任务池队列；
    获取加入优先任务池队列中回访任务的客户端信息，将客户端信息作为预先构建的客户优质度模型的输入，获取与客户端信息对应的客户优质等级值；
    根据客户端信息对应的客户优质等级值，将客户端信息对应的回访任务分配至对应服务等级的坐席员终端。
  2. 根据权利要求1所述的回访方法，其特征在于，所述操作失败参数包括：操作类型对应值、操作次数、操作时间；
    所述紧急度计算模型为：
    Tp＝INT[(k 1Ptt+k 2Pn+k 3Pt)*Ip]；
    其中，Ptt表示任务操作类型对应值，Pn表示操作次数，Pt表示操作时间，Ip表示坐席服务器的调度粒度，Tp表示与操作失败参数对应的紧急度值，k 1、k 2、k 3分别表示第一调节系数、第二调节系数、第三调节系数，INT[]表示取整函数。
  3. 根据权利要求1所述的回访方法，其特征在于，所述客户端信息包括：终端机型对应值、用户所处地理位置信息对应值、终端使用时间段；
    所述客户优质度模型为：
    Figure PCTCN2018085269-appb-100001
    其中，P 1表示终端机型对应值记、P 2表示用户所处地理位置信息对应值、P 3表示终端使用时间段，k 4、k 5、k 6分别表示第四调节系数、第五调节系数、第六调节系数，QL表示客户优质等级值。
  4. 根据权利要求2所述的回访方法，其特征在于，所述获取客户端所反馈的操作失败参数，包括：
    根据操作类型、及预设的操作类型值对应表，获取任务操作类型对应值；
    根据系统当前时间与用户初次操作时间的时间间隔，获取操作时间；
    根据在操作时间内对指定虚拟操作按钮的点击次数，获取操作次数。
  5. 根据权利要求1所述的回访方法，其特征在于，所述坐席员任务池队列包括普通任务池队列，及优先任务池队列；所述普通任务池队列中的回访任务按紧急度值进行升序排列；所述优先任务池队列中的回访任务按紧急度值进行升序排列。
  6. 一种回访装置，其特征在于，包括：
    紧急度值获取单元，用于获取客户端所反馈的操作失败参数，并将操作失败参数作为预先构建的紧急度计算模型的输入，获取与操作失败参数对应的紧急度值；
    优先任务筛选单元，用于若在坐席员任务池中检测到有回访任务的紧急度值小于或等于预设的紧急度阈值，获取与回访任务的紧急度值对应的操作失败参数，将回访任务加入坐席员任务池队列中的优先任务池队列；
    客户优质等级值获取单元，用于获取加入优先任务池队列中回访任务的客户端信息，将客户端信息作为预先构建的客户优质度模型的输入，获取与客户端信息对应的客户优质等级值；
    回访任务分配单元，用于根据客户端信息对应的客户优质等级值，将客户端信息对应的回访任务分配至对应服务等级的坐席员终端。
  7. 根据权利要求6所述的回访装置，其特征在于，所述操作失败参数包括：操作类型对应值、操作次数、操作时间；
    所述紧急度计算模型为：
    Tp＝INT[(k 1Ptt+k 2Pn+k 3Pt)*Ip]；
    其中，Ptt表示任务操作类型对应值，Pn表示操作次数，Pt表示操作时间，Ip表示坐席服务器的调度粒度，Tp表示与操作失败参数对应的紧急度值，k 1、k 2、k 3分别表示第一调节系数、第二调节系数、第三调节系数，INT[]表示取整函数。
  8. 根据权利要求6所述的回访装置，其特征在于，所述客户端信息包括：终端机型对应值、用户所处地理位置信息对应值、终端使用时间段；
    所述客户优质度模型为：
    Figure PCTCN2018085269-appb-100002
    其中，P 1表示终端机型对应值记、P 2表示用户所处地理位置信息对应值、P 3表示终端使用时间段，k 4、k 5、k 6分别表示第四调节系数、第五调节系数、第六调节系数，QL表示客户优质等级值。
  9. 根据权利要求7所述的回访装置，其特征在于，所述紧急度值获取单元，包括：
    第一获取单元，用于根据操作类型、及预设的操作类型值对应表，获取任务操作类型对应值；
    第二获取单元，用于根据系统当前时间与用户初次操作时间的时间间隔，获取操作时间；
    第三获取单元，用于根据在操作时间内对指定虚拟操作按钮的点击次数，获取操作次数。
  10. 根据权利要求6所述的回访装置，其特征在于，所述坐席员任务池队列包括普通任务池队列，及优先任务池队列；所述普通任务池队列中的回访任务按紧急度值进行升序排列；所述优先任务池队列中的回访任务按紧急度值进行升序排列。
  11. 一种计算机设备，包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，其特征在于，所述处理器执行所述计算机程序时实现以下步骤：
    获取客户端所反馈的操作失败参数，并将操作失败参数作为预先构建的紧急度计算模型的输入，获取与操作失败参数对应的紧急度值；
    若在坐席员任务池中检测到有回访任务的紧急度值小于或等于预设的紧急度阈值，获取与回访任务的紧急度值对应的操作失败参数，将回访任务加入坐席员任务池队列中的优先任务池队列；
    获取加入优先任务池队列中回访任务的客户端信息，将客户端信息作为预先构建的客户优质度模型的输入，获取与客户端信息对应的客户优质等级值；
    根据客户端信息对应的客户优质等级值，将客户端信息对应的回访任务分配至对应服务等级的坐席员终端。
  12. 根据权利要求11所述的计算机设备，其特征在于，所述操作失败参数包括：操作类型对应值、操作次数、操作时间；
    所述紧急度计算模型为：
    Tp＝INT[(k 1Ptt+k 2Pn+k 3Pt)*Ip]；
    其中，Ptt表示任务操作类型对应值，Pn表示操作次数，Pt表示操作时间，Ip表示坐席服务器的调度粒度，Tp表示与操作失败参数对应的紧急度值，k 1、k 2、k 3分别表示第一调节系数、第二调节系数、第三调节系数，INT[]表示取整函数。
  13. 根据权利要求11所述的计算机设备，其特征在于，所述客户端信息包括：终端机型对应值、用户所处地理位置信息对应值、终端使用时间段；
    所述客户优质度模型为：
    Figure PCTCN2018085269-appb-100003
    其中，P 1表示终端机型对应值记、P 2表示用户所处地理位置信息对应值、P 3表示终端使用时间段，k 4、k 5、k 6分别表示第四调节系数、第五调节系数、第六调节系数，QL表示客户优质等级值。
  14. 根据权利要求12所述的计算机设备，其特征在于，所述获取客户端所反馈的操作失败参数，包括：
    根据操作类型、及预设的操作类型值对应表，获取任务操作类型对应值；
    根据系统当前时间与用户初次操作时间的时间间隔，获取操作时间；
    根据在操作时间内对指定虚拟操作按钮的点击次数，获取操作次数。
  15. 根据权利要求11所述的计算机设备，其特征在于，所述坐席员任务池队列包括普通任务池队列，及优先任务池队列；所述普通任务池队列中的回访任务按紧急度值进行升序排列；所述优先任务池队列中的回访任务按紧急度值进行升序排列。
  16. 一种存储介质，其特征在于，所述存储介质存储有计算机程序，所述计算机程序包括程序指令，所述程序指令当被处理器执行时使所述处理器执行以下操作：
    获取客户端所反馈的操作失败参数，并将操作失败参数作为预先构建的紧急度计算模型的输入，获取与操作失败参数对应的紧急度值；
    若在坐席员任务池中检测到有回访任务的紧急度值小于或等于预设的紧急度阈值，获取与回访任务的紧急度值对应的操作失败参数，将回访任务加入坐席员任务池队列中的优先任务池队列；
    获取加入优先任务池队列中回访任务的客户端信息，将客户端信息作为预 先构建的客户优质度模型的输入，获取与客户端信息对应的客户优质等级值；
    根据客户端信息对应的客户优质等级值，将客户端信息对应的回访任务分配至对应服务等级的坐席员终端。
  17. 根据权利要求16所述的存储介质，其特征在于，所述操作失败参数包括：操作类型对应值、操作次数、操作时间；
    所述紧急度计算模型为：
    Tp＝INT[(k 1Ptt+k 2Pn+k 3Pt)*Ip]；
    其中，Ptt表示任务操作类型对应值，Pn表示操作次数，Pt表示操作时间，Ip表示坐席服务器的调度粒度，Tp表示与操作失败参数对应的紧急度值，k 1、k 2、k 3分别表示第一调节系数、第二调节系数、第三调节系数，INT[]表示取整函数。
  18. 根据权利要求16所述的存储介质，其特征在于，所述客户端信息包括：终端机型对应值、用户所处地理位置信息对应值、终端使用时间段；
    所述客户优质度模型为：
    Figure PCTCN2018085269-appb-100004
    其中，P 1表示终端机型对应值记、P 2表示用户所处地理位置信息对应值、P 3表示终端使用时间段，k 4、k 5、k 6分别表示第四调节系数、第五调节系数、第六调节系数，QL表示客户优质等级值。
  19. 根据权利要求17所述的存储介质，其特征在于，所述获取客户端所反馈的操作失败参数，包括：
    根据操作类型、及预设的操作类型值对应表，获取任务操作类型对应值；
    根据系统当前时间与用户初次操作时间的时间间隔，获取操作时间；
    根据在操作时间内对指定虚拟操作按钮的点击次数，获取操作次数。
  20. 根据权利要求16所述的存储介质，其特征在于，所述坐席员任务池队列包括普通任务池队列，及优先任务池队列；所述普通任务池队列中的回访任务按紧急度值进行升序排列；所述优先任务池队列中的回访任务按紧急度值进行升序排列。
PCT/CN2018/085269 2018-02-12 2018-05-02 回访方法、装置、计算机设备及存储介质 WO2019153545A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810145747.4A CN108288167B (zh) 2018-02-12 2018-02-12 回访方法、装置、计算机设备及存储介质
CN201810145747.4 2018-02-12

Publications (1)

Publication Number Publication Date
WO2019153545A1 true WO2019153545A1 (zh) 2019-08-15

Family

ID=62832670

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/085269 WO2019153545A1 (zh) 2018-02-12 2018-05-02 回访方法、装置、计算机设备及存储介质

Country Status (2)

Country Link
CN (1) CN108288167B (zh)
WO (1) WO2019153545A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110648060A (zh) * 2019-09-19 2020-01-03 达疆网络科技(上海)有限公司 一种自动给客服分配任务的方法
CN112150118A (zh) * 2020-09-30 2020-12-29 惠州市善居电子商务有限公司 回访客户记录监测方法、装置、计算机设备和存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102012015893A1 (de) * 2012-08-10 2014-02-13 BSH Bosch und Siemens Hausgeräte GmbH Übermittlung einer Information betreffend ein Haushaltsgerät
CN105228139A (zh) * 2014-06-05 2016-01-06 阿里巴巴集团控股有限公司 一种基于智能设备的呼叫处理方法、装置及设备
CN106200451A (zh) * 2015-05-27 2016-12-07 宁波吉德家电科技有限公司 一种家电故障采集处理系统
CN106330570A (zh) * 2016-09-27 2017-01-11 三星电子（中国）研发中心 设备客户端、移动客户端和设备故障诊断系统

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104731649A (zh) * 2015-04-21 2015-06-24 中国建设银行股份有限公司 一种多任务处理方法及装置
CN105719010A (zh) * 2015-07-24 2016-06-29 北京小度信息科技有限公司 配送任务的处理方法及装置
CN107274471B (zh) * 2017-06-15 2020-10-09 深圳市彬讯科技有限公司 一种基于实时离线渲染并行的多优先级队列调度系统
CN107360336A (zh) * 2017-06-28 2017-11-17 上海航动科技有限公司 一种基于语音服务的智能派单系统及方法
CN107665401B (zh) * 2017-09-15 2020-06-26 平安科技（深圳）有限公司 一种任务分配方法、终端及计算机可读存储介质

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102012015893A1 (de) * 2012-08-10 2014-02-13 BSH Bosch und Siemens Hausgeräte GmbH Übermittlung einer Information betreffend ein Haushaltsgerät
CN105228139A (zh) * 2014-06-05 2016-01-06 阿里巴巴集团控股有限公司 一种基于智能设备的呼叫处理方法、装置及设备
CN106200451A (zh) * 2015-05-27 2016-12-07 宁波吉德家电科技有限公司 一种家电故障采集处理系统
CN106330570A (zh) * 2016-09-27 2017-01-11 三星电子（中国）研发中心 设备客户端、移动客户端和设备故障诊断系统

Also Published As

Publication number Publication date
CN108288167B (zh) 2019-11-08
CN108288167A (zh) 2018-07-17

Similar Documents

Publication Publication Date Title
KR102409347B1 (ko) 정책 기반 자원 관리 및 할당 시스템
CN110612545B (zh) 自学习自适应路由系统
US10756911B2 (en) Cost estimation on a cloud-computing platform
US8606905B1 (en) Automated determination of system scalability and scalability constraint factors
US9223672B1 (en) Method and system for providing error repair status data to an application user
US9742684B1 (en) Adaptive service scaling
WO2019061998A1 (zh) 断点智能分流方法、电子装置及计算机可读存储介质
WO2019153545A1 (zh) 回访方法、装置、计算机设备及存储介质
US20180268343A1 (en) Virtual dialogue crowdsourcing
WO2019200759A1 (zh) 坐席信息处理方法、装置及计算机可读存储介质
US20200133443A1 (en) Cognitive contact assistance with dynamically generated contact lists for messages
CN107786627B (zh) 资源处理系统和方法
US9210265B2 (en) Exploring multiple contact channels to determine potential for reaching customers
US20170293877A1 (en) Identifying Professional Incentive Goal Progress and Contacts for Achieving Goal
KR20190094096A (ko) 문서 정보 입력 방법, 장치, 서버, 그리고 저장 매체
US20170147962A1 (en) Method and system for assigning service requests
US20200118058A1 (en) Real-time workflow tracking
JP7006408B2 (ja) 利用料決定プログラム、利用料決定方法、及び情報処理装置
US20200382447A1 (en) Chatbot information processing
WO2019196243A1 (zh) 坐席协办任务管理方法、装置、计算机设备及存储介质
Rosen et al. Mapping global mobile performance trends with Mobilyzer and MobiPerf
US10282732B2 (en) Analysis of customer feedback for applications executing on distributed computational systems
US20130091065A1 (en) Automatic spike licensing
US20170041283A1 (en) Prioritizing and handling of messages across multiple communication systems
US20170075705A1 (en) Optimizing computer systems by adjusting computer resource usage

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18905454

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 16/11/2020)

122 Ep: pct application non-entry in european phase

Ref document number: 18905454

Country of ref document: EP

Kind code of ref document: A1