WO2019196255A1 - 电销时间段的选取方法、装置、终端设备及介质 - Google Patents

电销时间段的选取方法、装置、终端设备及介质 Download PDF

Info

Publication number
WO2019196255A1
WO2019196255A1 PCT/CN2018/097455 CN2018097455W WO2019196255A1 WO 2019196255 A1 WO2019196255 A1 WO 2019196255A1 CN 2018097455 W CN2018097455 W CN 2018097455W WO 2019196255 A1 WO2019196255 A1 WO 2019196255A1
Authority
WO
WIPO (PCT)
Prior art keywords
time period
attribute
value
target
evaluation value
Prior art date
Legal status (The legal status 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 status listed.)
Ceased
Application number
PCT/CN2018/097455
Other languages
English (en)
French (fr)
Inventor
徐光飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen Co Ltd
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 Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Publication of WO2019196255A1 publication Critical patent/WO2019196255A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06QINFORMATION 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
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201Market modelling; Market analysis; Collecting market data
    • G06Q30/0202Market predictions or forecasting for commercial activities
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06QINFORMATION 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
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241Advertisements
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06QINFORMATION 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
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201Market modelling; Market analysis; Collecting market data
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06QINFORMATION 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
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241Advertisements
    • G06Q30/0242Determining effectiveness of advertisements

Definitions

  • the present application belongs to the field of data processing, and in particular, to a method, an apparatus, a terminal device, and a computer readable storage medium for selecting a time period of a sales period.
  • the customer reservation function has been set in the telephone sales systems of major enterprises.
  • the function is specifically: by making a short communication with each customer in advance, and recording the dialable time that the customer feedbacks, thereby generating a scheduled call task. Therefore, when a customer's dialable time arrives, the agent can confirm the customer as the target customer at the current moment, and make a telephone call to the target customer to perform accurate sales. Since the probability of the customer receiving the call is high during the time of dialing, there is a greater probability that the customer will be converted into the actual customer who purchased the product, thereby improving marketing efficiency and success rate.
  • the above reservation function can only be used to contact the customer before recording the customer's callable time. However, in most cases, the customer can report the call time is more random and less accurate. Due to the fact that during the entire sales process, the agent can only be in a passive state when contacting the customer, which greatly reduces the dialing efficiency.
  • the embodiment of the present application provides a method, a device, a terminal device, and a computer readable storage medium for selecting a time period of a power sale, so as to solve the problem that the agent in the prior art can only be in a passive state when contacting the client. This reduces the problem of dialing efficiency.
  • a first aspect of the embodiments of the present application provides a method for selecting a time period of a power sale, including:
  • the target customer is calculated at the time according to the evaluation value corresponding to each attribute and the weight value corresponding to each attribute value in the time period.
  • the probability of the call answering probability of the segment is calculated at the time according to the evaluation value corresponding to each attribute and the weight value corresponding to each attribute value in the time period.
  • a second aspect of the embodiments of the present application provides a device for selecting a time period of a power sale, the identification device comprising means for performing a method for selecting a time period of the power sale described in the first aspect.
  • a third aspect of the embodiments of the present application provides a terminal device, including a memory and a processor, where the computer stores computer readable instructions executable on the processor, the processor executing the computer
  • the step of selecting the method of selecting the time period of the electric pin as described in the first aspect is implemented when the command is read.
  • a fourth aspect of the embodiments of the present application provides a computer readable storage medium storing computer readable instructions, the computer readable instructions being executed by a processor to implement the first aspect as described in the first aspect The steps of the method of selecting the sales time period.
  • FIG. 1 is a flowchart for implementing a method for selecting a time period of a power sale provided by an embodiment of the present application
  • FIG. 2 is a flowchart of implementing a method for selecting a time period of a power sale according to another embodiment of the present application
  • FIG. 3 is a flowchart of implementing a method for selecting a time period of a power sale according to another embodiment of the present application
  • FIG. 4 is a structural block diagram of a device for selecting a time period of a power sale provided by an embodiment of the present application
  • FIG. 5 is a schematic diagram of a terminal device according to an embodiment of the present application.
  • FIG. 1 shows an implementation flow of a method for selecting a sales time period provided by an embodiment of the present application, where the method flow includes steps S101 to S106.
  • the specific implementation principles of each step are as follows:
  • S101 Acquire image data of the target customer.
  • the target customer is a customer to be promoted, and the callable time of the customer has not been determined yet.
  • the image data of the associated target customers can be extracted based on historical order records or questionnaire records, etc., to form a database for storing the image data of the respective target customers. Therefore, based on the database that is pre-docted, the image data of any target customers stored therein can be queried.
  • Image data includes, but is not limited to, personal information such as age, gender, occupation, hobbies, education, and residential address.
  • each personal information is marked according to the storage field value corresponding to each personal information in the data table of the database.
  • the image data of the obtained target customer A is ⁇ occupation: doctor ⁇ and ⁇ gender: female ⁇ .
  • S102 Extract various attributes included in the portrait data, and determine an evaluation value corresponding to each of the attributes according to the preset attribute evaluation value correspondence table.
  • the storage field value corresponding to the above personal information is an attribute in the portrait data.
  • the attribute included is "occupation"
  • the attribute included is "gender”.
  • the received attribute entry instruction multiple attributes collected in advance are acquired and stored in a preset data table.
  • the data table in which the respective attributes are stored is referred to as an attribute evaluation value correspondence table.
  • the evaluation value corresponding to the attribute is stored in a record to which each attribute belongs.
  • the evaluation value is used to indicate how much the attribute it corresponds to affects whether the customer answers the sales call. For example, after scientific statistical analysis, the telephone call-through rate of women's electricity sales is usually higher than that of men's electricity sales. Therefore, the attribute of gender has a certain impact on the result of the target customer receiving the power-selling call. For example, the telephone call completion rate of the target users whose academic qualifications are above the undergraduate level is usually greater than the sales call completion rate of the target users below the undergraduate degree. Therefore, the attribute of the education is to answer the sales call to the target customer. A result also played a certain role. Therefore, in order to measure the degree of influence of each attribute value, the evaluation value of each attribute is set in advance according to the evaluation value setting instruction issued by the manager.
  • the evaluation value W corresponding to the attribute is read one by one from the attribute evaluation value correspondence table.
  • Each of the above personal information in the portrait data is an attribute value.
  • the stored field value corresponding to the personal information is an attribute in the image data, so the portrait data has a corresponding attribute value for each attribute.
  • the attribute included is "professional", and the attribute value of the attribute "occupation” is "doctor”;
  • the above-mentioned portrait data ⁇ gender: female ⁇ it contains The attribute is "gender”, and the attribute of the attribute "gender” is "female”.
  • the attribute value of the attribute is read according to each attribute included in the image data.
  • S104 Determine a weight value corresponding to each attribute value in each preset time period according to a time period weight relationship table that is matched by each of the attribute values.
  • the weight values corresponding to the same attribute value are different in different time periods. Therefore, a time period weight relationship table is created for each attribute value in the image data for storing the weight value corresponding to each attribute value in the time period.
  • the weight value corresponding to the attribute value in each preset time period can be read and retrieved.
  • S105 calculating, for each of the time segments, the target customer according to the evaluation value corresponding to each attribute and the weight value corresponding to each attribute value in the time period. The value of the incoming call probability for this time period.
  • the current call answer probability value of the current target customer in the time period is calculated in each time period.
  • the calculating the call pickup probability value of the target client during the time period may be implemented by: for each of the time segments, respectively corresponding to each attribute
  • the evaluation value and the weight value corresponding to each of the attribute values in the time period are input into a preset calculation formula to obtain an incoming call probability value of the target customer during the time period, and the calculation formula includes :
  • the score n is the call answer probability value; the n is an identifier of the time period; the W i is the evaluation value corresponding to the attribute of the i-th item in the portrait data; S in is the weight value corresponding to the i-th attribute value in the portrait data, and the i is an integer greater than zero; the N is the total number of the attributes in the portrait data.
  • the call answer probability value of the target customer A in the time period 9:00-10:00 is to be calculated, and the image data of the target customer A includes: ⁇ gender: female ⁇ , ⁇ occupation: doctor ⁇ , ⁇ residence Land: China ⁇
  • the assessment values for “gender”, “occupation” and “residence” are W 1 , W 2 , W 3 respectively ; “female”, “doctor” and “China” at 9:00 -
  • S106 Determine the time period in which the call answering probability value is the highest, and determine the time period as the best selling time period of the target customer.
  • the value of the incoming call answering probability value is selected by comparing the value of each call answering probability value.
  • the time period corresponding to the call answer probability value is determined as the best selling time period of the target customer.
  • the target customer associated with the scheduled call is called, and after the call is made, the target customer is provided with product promotion service.
  • the target customer selection instruction issued by the sales agent when the target customer selection instruction issued by the sales agent is detected, if the current system time is not within the optimal sales time period of the target customer, a prompt message is sent to prompt the sales
  • the agent's time period is not the best sales time period of the current target customer, and the caller's probability value of the current time period and the best sales time period recommended by the display system are displayed in the prompt information, thereby ensuring the sales agent seat.
  • the personnel can accurately determine whether it is necessary to make a telephone call to the target customer, avoiding the harassment caused to the target customer and reducing the success rate of the sales.
  • the caller probability value of the target customer in each time period can be accurately predicted based on the personalized image data of the target customer.
  • the customer can have a greater possibility to answer the sales promotion when the sales agent performs the calling task within the optimal selling time period.
  • the telephone avoids the harassment of the customer during the busy time period, thus improving the marketing efficiency and improving the customer satisfaction; in the whole telephone sales process, the sales agent no longer needs to rely on the customer's subjective appointment time to contact the customer. Therefore, it also increases the initiative of the sales agent in the sales process.
  • FIG. 2 shows an implementation flow of a method for selecting a sales time period provided by another embodiment of the present application. As shown in FIG. 2, after the above S106, the method further includes:
  • S201 For each of the best selling time periods, count the total number of the target customers in the best selling time period.
  • the optimal sales time period of each target customer is output. Since the optimal sales time period is determined based on the respective time periods preset in the time period weight relationship table, the optimal sales time period of each target customer outputted above is only the preset time period. A time period in the middle. Therefore, based on each preset time period, it is determined whether the best sales time period of each target customer is the time period. If the best selling time period of a target customer is the time period, then the total number of target customers that are suitable for making the call is increased by one. And so on, until the total number of target customers in each time period is counted.
  • the value of the call answering probability value is sorted, and each target customer is sorted, so that the target customer with a large incoming call probability value is ranked before the target customer with a small incoming call probability value.
  • S203 Display the sorting result, so that the sales agent sequentially conducts telemarketing to each of the target customers based on the sorting result.
  • Displaying the ranking results of the plurality of target customers includes: generating a customer list including a plurality of target customers, the customer list includes a contact information of each target customer; and displaying the customer list in the sales seat Terminal interface.
  • a time period to which the system time belongs is determined according to the system time of the current time. After the time period is the best sales time period, after reading the customer list corresponding to the best sales time period, the customer list is displayed on the terminal interface of the sales agent seat.
  • the sales agent Based on the customer list displayed on the terminal interface of the sales agent seat and the contact information of each target customer in the customer list, the sales agent will conduct telemarketing to each of the target customers in turn during the time period.
  • displaying the sorting result of the multiple target clients may further include: displaying, in the terminal interface, a preset corresponding to each time period; and only when detecting that the control is selected, calling the corresponding control The time period matches the customer list to show the ranking results of each target customer during the best sales time period.
  • the output of the optimal sales time period of the plurality of target customers is realized; based on the optimal sales time period
  • the size of each target customer is sorted and displayed, so that the sales agent can perform the sales operation in turn according to the order of the customers. Since the target customers with the previous ranking have greater possibility to be converted into the transaction customers within the same time period, they are sold to each target customer according to the order, ensuring that the sales agents can complete their tasks in the shortest possible time. Achieve scalar quantity and improve marketing efficiency.
  • the best selling time period of the target customer can be determined and changed after the telemarket agent conducts telemarketing to each target customer.
  • the method further includes:
  • S301 Acquire a satisfaction degree and a satisfaction influence factor of the target customer after receiving the power call.
  • the satisfaction is measured numerically. For example, the number “2" indicates very satisfactory, the number “1” indicates satisfaction, the number “-1” indicates general, and the number “-2" indicates dissatisfaction.
  • a voice prompt message will be sent to prompt the target customer who answers the call to make satisfaction with the service process of the sales agent and the feedback of the satisfaction factor; or, when starting the telemarketing, according to the electricity
  • the feedback from the current target customers collected by the sales agent is the satisfaction of the target customer and the satisfaction factor of the satisfaction.
  • the satisfaction impact factor refers to the reason/cause that affects the satisfaction of the current sales
  • the satisfaction impact factor is any of the above-mentioned preset attributes and/or attribute values.
  • the satisfaction of the target customer feedback is low, and the reason for the low satisfaction is that “I am a doctor.
  • the time period that the agent dials is a busy time period, which affects the work”. Therefore, when the target customer feedbacks the satisfaction factor You can select the attribute "occupation" as the influencing factor;
  • the satisfaction impact factor obtained as the occupation attribute If the customer feedback says that the current time period is not suitable due to occupational problems; when the agent feedback satisfaction, the “weight” of the time period corresponding to the “professional” attribute may be selected as the influencing factor. Similarly, if the sales call is successful and the satisfaction of the target customer is high, the satisfaction impact factor feedback from the customer is also received.
  • S302 Determine an evaluation value and/or a weight value associated with the satisfaction impact factor.
  • the satisfaction impact factor when the satisfaction impact factor includes any of the preset attributes, the evaluation value corresponding to the attribute is read according to the correspondence between each attribute and the evaluation value, and the evaluation value is the same as the above.
  • the satisfaction affects the estimated value associated with the factor.
  • the satisfaction impact factor includes any preset attribute value, according to the feedback time period of the satisfaction influence factor, the weight value corresponding to the attribute value in the feedback time period is read, and the weight value is satisfied with the above The weight value associated with the degree impact factor.
  • the optimal sales time period of the target customer output based on the above S106 is accurate. If the satisfaction degree is less than the preset threshold, it indicates that the optimal sales time period does not match the actual one. Therefore, the determined evaluation value and/or the weight value need to be decreased; if the satisfaction degree is greater than or equal to the preset threshold, The optimal time period for the sale is in line with the actual situation, so the determined evaluation value and/or weight value can be increased.
  • the adjusted evaluation value is:
  • W 0 is the evaluation value before adjustment
  • k is the satisfaction level fed back by the target customer
  • c is the preset parameter
  • the adjusted weight value is:
  • S 0 is the weight value before adjustment
  • k is the satisfaction level fed back by the target customer
  • C is the preset parameter. It should be noted that c and C here may be the same or different.
  • the satisfaction result of the target customer and the corresponding satisfaction factor of the satisfaction are obtained by collecting the result of the power-selling call of the agent, and the evaluation value corresponding to the customer image data is adjusted according to the feedback result. And/or the weight value, forming a closed-loop management and self-learning process of dynamically adjusting the evaluation value and the weight value, so that the next time a target customer having the same portrait data is encountered, the calculation can be based on the adjusted evaluation value and/or the weight value.
  • the target customer's best sales time period improves the calculation accuracy of the best sales time period.
  • a single sales task corresponding to each target customer in the time period is generated.
  • the sales agent dials the call of a target customer
  • the execution status of the sales task corresponding to the target customer is switched to the dialed state.
  • Target customer Change the best sales time period of each target customer to the next time period of the best sales time period. For example, if the best selling time period of the target customer A is 9:00-10:00, but at the end of the time period of 9:00-10:00, the execution status of the sales task corresponding to the target customer A In the unexecuted state, the target customer A's best sales time period is changed to 10:00-11:00 to generate and display the target customer A again during the current time period of 10:00-11:00. Corresponding to a sales task. Thereby, the time period transfer of the power sales task is realized.
  • the transferred power will be transferred after displaying the ranking result of the target customer in the optimal sales time period.
  • the sales task is placed before the sales task of the target customer who was originally ranked first, so that the sales agent can limit the processing of the sales tasks that have not been processed in the previous period.
  • the number of power sales tasks in an optimal sales time period is ensured.
  • the best processing can be performed in the next time period as much as possible, so that the actual processing time of the sales task does not deviate greatly from the optimal sales time. Paragraph, it also raised the possibility of successful sales of electricity to a certain extent.
  • FIG. 4 is a structural block diagram of the apparatus for selecting the sales time period provided by the embodiment of the present application. For the convenience of explanation, only the parts related to the present embodiment are shown.
  • the apparatus includes:
  • the image data obtaining unit 41 is configured to acquire image data of the target client.
  • the attribute extraction unit 42 is configured to extract various attributes included in the image data, and determine an evaluation value corresponding to each of the attributes according to the preset attribute evaluation value correspondence table.
  • the attribute value reading unit 43 is configured to read an attribute value of each attribute of the image data.
  • the weight value determining unit 44 is configured to determine, according to the time period weight relationship table that each of the attribute values respectively match, a weight value corresponding to each of the attribute values in each preset time period.
  • the answer probability value calculation unit 45 is configured to, for each of the time segments, the weight value corresponding to each of the evaluation values corresponding to each attribute and each attribute value in the time period. And calculating a call answer probability value of the target customer during the time period.
  • the sales time period determining unit 46 is configured to determine the time period in which the call answering probability value is the highest, and determine the time period as the best selling time period of the target customer.
  • the device for selecting the sales time period further includes: a statistics unit, configured to count, for each of the optimal sales time periods, a total number of the target customers in the optimal sales time period. And a sorting unit, configured to: when the total number of the target customers is greater than a preset threshold, sort the respective target customers in the optimal sales time period according to the order of the call answering probability values. And a display unit, configured to display the sorting result, so that the sales agent sequentially conducts telemarketing to each of the target customers based on the sorting result.
  • a statistics unit configured to count, for each of the optimal sales time periods, a total number of the target customers in the optimal sales time period.
  • a sorting unit configured to: when the total number of the target customers is greater than a preset threshold, sort the respective target customers in the optimal sales time period according to the order of the call answering probability values.
  • a display unit configured to display the sorting result, so that the sales agent sequentially conducts telemarketing to each of the target customers based on the sorting
  • the device for selecting the sales time period further includes: a first acquiring unit, configured to acquire a satisfaction degree and a satisfaction influence factor of the target customer after receiving the power call. a determining unit for determining an evaluation value and/or a weight value associated with the satisfaction impact factor. And an adjusting unit, configured to adjust the determined evaluation value and/or the weight value based on the satisfaction degree, and update the corresponding relationship between the attribute evaluation values according to the adjusted evaluation value and/or the weight value Table and the time period weight relationship table.
  • a first acquiring unit configured to acquire a satisfaction degree and a satisfaction influence factor of the target customer after receiving the power call.
  • a determining unit for determining an evaluation value and/or a weight value associated with the satisfaction impact factor.
  • an adjusting unit configured to adjust the determined evaluation value and/or the weight value based on the satisfaction degree, and update the corresponding relationship between the attribute evaluation values according to the adjusted evaluation value and/or the weight value Table and the time period weight relationship table.
  • the device for selecting the sales time period further includes:
  • a second obtaining unit configured to acquire a total number of dialed calls of the target customer at the end of the best selling time period.
  • a change unit configured to determine, if the total number of the target customers dialed is less than the total number of the target customers in the optimal time period, determine each of the target customers that have not completed the task, and each of the targets The customer's best selling time period is changed to the next time period of the best selling time period.
  • the answer probability value calculation unit 45 includes:
  • the input subunit is configured to input, to each of the time segments, the evaluation value corresponding to each attribute and the weight value corresponding to each attribute value in the time period into a preset a calculation formula to obtain a call answer probability value of the target customer during the time period, the calculation formula includes:
  • the score n is the call answer probability value; the n is an identifier of the time period; the W i is the evaluation value corresponding to the attribute of the i-th item in the portrait data; S in is the weight value corresponding to the i-th attribute value in the portrait data, and the i is an integer greater than zero; the N is the total number of the attributes in the portrait data.
  • FIG. 5 is a schematic diagram of a terminal device according to an embodiment of the present application.
  • the terminal device 5 of this embodiment includes a processor 50 and a memory 51 in which computer readable instructions 52, such as a sales time period, executable on the processor 50 are stored. Selection process.
  • the processor 50 executes the computer readable instructions 52 to implement the steps in the foregoing method for selecting the various charging time periods, such as steps 101 to 106 shown in FIG.
  • the processor 50 when executing the computer readable instructions 52, implements the functions of the various modules/units in the various apparatus embodiments described above, such as the functions of the units 41-46 shown in FIG.
  • the computer readable instructions 52 may be partitioned into one or more modules/units that are stored in the memory 51 and executed by the processor 50, To complete this application.
  • the one or more modules/units may be a series of computer readable instruction segments capable of performing a particular function, the instruction segments being used to describe the execution of the computer readable instructions 52 in the terminal device 5.
  • the terminal device 5 may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server.
  • the terminal device may include, but is not limited to, the processor 50 and the memory 51. It will be understood by those skilled in the art that FIG. 5 is only an example of the terminal device 5, does not constitute a limitation of the terminal device 5, may include more or less components than the illustrated, or combine some components, or different components.
  • the terminal device may further include an input/output device, a network access device, a bus, and the like.
  • the processor 50 may be a central processing unit (CPU), or may be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc.
  • the general purpose processor may be a microprocessor or the processor or any conventional processor or the like.
  • the memory 51 may be an internal storage unit of the terminal device 5, such as a hard disk or a memory of the terminal device 5.
  • the memory 51 may also be an external storage device of the terminal device 5, such as a plug-in hard disk equipped on the terminal device 5, a smart memory card (SMC), and a secure digital (SD). Card, flash card, etc. Further, the memory 51 may also include both an internal storage unit of the terminal device 5 and an external storage device.
  • the memory 51 is configured to store the computer readable instructions and other programs and data required by the terminal device.
  • the memory 51 can also be used to temporarily store data that has been output or is about to be output.
  • the integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium.
  • a computer readable storage medium A number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present application.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like, which can store program codes. .

Landscapes

  • Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Telephonic Communication Services (AREA)

Abstract

本方案提供了一种电销时间段的选取方法、装置、终端设备及介质,适用于数据处理领域,该方法包括:获取目标客户的画像数据;提取画像数据所包含的各项属性,分别确定与每一项属性对应的评估值;读取画像数据中各项属性的属性值;确定出各项属性值分别在各个预设的时间段内所对应的权重值;对每一时间段,根据各项属性所分别对应的评估值以及该时间段内各项属性值所分别对应的权重值,计算目标客户在该时间段的来电接听概率值;确定出来电接听概率值最高的时间段,并将该时间段确定为目标客户的最佳电销时间段。本方案提高了营销效率以及提高了客户满意度;电销坐席不再需要依赖于客户主观化的预约时间来联系客户,因而也提高了推销的主动性。

Description

电销时间段的选取方法、装置、终端设备及介质
本申请要求于2018年04月09日提交中国专利局、申请号为201810311216.8、发明名称为“电销时间段的选取方法、终端设备及介质”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
本申请属于数据处理领域,尤其涉及一种电销时间段的选取方法、装置、终端设备及计算机可读存储介质。
背景技术
为了避免电销的坐席人员只能随机地打出大量客户电话,凭借运气地去给各个客户推销产品,目前,各大企业的电话销售系统中,均已设置了客户预约功能。该功能具体为:通过预先与各个客户进行短暂沟通,记录客户所反馈的可拨打时间,从而生成预约拨打任务。因此,当某一客户的可拨打时间到达时,坐席人员便能将该客户确认为当前时刻的目标客户,向该目标客户进行电话拨打以执行精准的销售。由于可拨打时间内,客户接听电话的概率较高,因此,能够有更大的概率令客户转化为购买产品的实际成交客户,从而提高了营销效率以及成功率。
上述预约功能只能先联系客户后再记录客户的可拨打时间,然而,大多情况下,客户所反馈的可拨打时间都较为随意,准确度较低。由于整个电销过程中,坐席人员在联系客户时只能处于被动的状态,故大大降低了拨打效率。
技术问题
有鉴于此,本申请实施例提供了一种电销时间段的选取方法、装置、终端设备及计算机可读存储介质,以解决现有技术中坐席人员在联系客户时只能处于被动的状态,从而降低了拨打效率的问题。
技术解决方案
本申请实施例的第一方面提供了一种电销时间段的选取方法,包括:
获取目标客户的画像数据;
提取所述画像数据所包含的各项属性,并根据预设的属性评估值对应关系表,分别确定与每一项所述属性对应的评估值;
读取所述画像数据中各项所述属性的属性值;
根据每一所述属性值所分别匹配的时间段权重关系表,确定出各项所述属性值分别在各个预设的时间段内所对应的权重值;
对每一所述时间段,根据各项所述属性所分别对应的所述评估值以及该时间段内各项所述属性值所分别对应的所述权重值,计算所述目标客户在该时间段的来电接听概率值;
确定出所述来电接听概率值最高的所述时间段,并将该时间段确定为所述目标客户的最佳电销时间段。
本申请实施例的第二方面提供了一种电销时间段的选取装置,所述识别装置包括用于执行上述第一方面所述的电销时间段的选取方法的单元。
本申请实施例的第三方面提供了一种终端设备,包括存储器以及处理器,所述存储器中存储有可在所述处理器上运行的计算机可读指令,所述处理器执行所述计算机可读指令时实现如第一方面所述的电销时间段的选取方法的步骤。
本申请实施例的第四方面提供了一种计算机可读存储介质,所述计算机可读存储介质存储有计算机可读指令,所述计算机可读指令被处理器执行时实现如第一方面所述的电销时间段的选取方法的步骤。
有益效果
本申请实施例中,通过预先设置属性评估值对应关系表以及时间段权重关系表,可基于目标客户个性化的画像数据来准确地预测出目标客户在各个时间段内的来电接听概率值。通过将来电接听概率值最高的时间段作为目标客户的最佳电销时间段,保证了电销坐席在该最佳电销时间段内执行拨打任务时,客户能够具有较大的可能性接听推销电话,避免了在客户忙碌时间段对其造成骚扰,故提高了营销效率以及提高了客户满意度;整个电话销售过程中,电销坐席不再需要依赖于客户主观化的预约时间来联系客户,因而也提高了电销坐席在推销过程中的主动性。
附图说明
图1是本申请实施例提供的电销时间段的选取方法的实现流程图;
图2是本申请另一实施例提供的电销时间段的选取方法的实现流程图;
图3是本申请又一实施例提供的电销时间段的选取方法的实现流程图;
图4是本申请实施例提供的电销时间段的选取装置的结构框图;
图5是本申请实施例提供的终端设备的示意图。
本发明的实施方式
为了说明本申请所述的技术方案,下面通过具体实施例来进行说明。
图1示出了本申请实施例提供的电销时间段的选取方法的实现流程,该方法流程包括步骤S101至S106。各步骤的具体实现原理如下:
S101:获取目标客户的画像数据。
本申请实施例中,目标客户为待推销客户,且客户的可拨打时间尚未确定。在外部的各个业务平台中,根据历史订单记录或调查问卷记录等,可提取出关联的各个目标客户的画像数据,以形成用于存储各个目标客户的画像数据的数据库。因此,基于预先对接的该数据库,可查询出其所存储的任一目标客户的画像数据。画像数据包括但不限于年龄、性别、职业、兴趣爱好、学历、居住地址等个人信息。
其中,在获取上述的每一项画像数据时,根据数据库的数据表中,每一项个人信息所对应的存储字段值,对各项个人信息进行标记。例如,获取得到的目标客户A的画像数据为{职业:医生}以及{性别:女}等。
S102:提取所述画像数据所包含的各项属性,并根据预设的属性评估值对应关系表,分别确定与每一项所述属性对应的评估值。
上述个人信息所对应的存储字段值为画像数据中的属性。例如,对于上述画像数据{职业:医生},其所包含的属性为“职业”;对于上述画像数据{性别:女},其所包含的属性为“性别”。
本申请实施例中,根据接收到的属性录入指令,获取预先收集得到的多个属性,并将其存入预设的数据表。其中,为了区别于本申请中的其他各个数据表,将上述存储有各个属性的数据表称为属性评估值对应关系表。
在每一属性所属的一条记录中,存储该属性所对应的评估值。评估值用于表示其所对应的属性对客户是否接听推销电话所起到的影响程度大小。例如,经过科学统计分析可得,女性的电销电话接通率通常会大于男性的电销电话接通率,因此,性别这一属性对目标客户接听电销电话这一结果起到了一定的影响作用;再例如,学历在本科以上的目标用户的电销电话接通率通常会大于学历在本科以下的目标用户的电销电话接通率,故学历这一属性对目标客户接听电销电话这一结果也起到了一定的影响作用。因此,为了衡量各个属性值所产生的影响程度大小,预先根据管理人员所发出的评估值设置指令来设置各个属性的评估值。
本申请实施例中,提取出目标客户的画像数据中的各项属性后,对于其中的每一属性,从上述属性评估值对应关系表中,逐一读取该属性所对应的评估值W。
S103:读取所述画像数据中各项所述属性的属性值。
画像数据中的每一项上述个人信息即属性值。根据上分析可知,个人信息所对应的存储字段值为画像数据中的属性,故画像数据在每一属性上存在对应的属性值。例如,对于上述画像数据{职业:医生},其所包含的属性为“职业”,“职业”这一属性的属性值为“医生”;对于上述画像数据{性别:女},其所包含的属性为“性别”,“性别”这一属性的属性值为“女”。
本申请实施例中,根据上述画像数据中所包含的每一项属性,读取出该属性的属性值。
S104:根据每一所述属性值所分别匹配的时间段权重关系表,确定出各项所述属性值分别在各个预设的时间段内所对应的权重值。
对于不同的属性值,其在不同的时间段对目标客户是否接听电销电话这一结果所起到的影响作用是不同的。例如,在中国时间13:00-14:00这一时间段,若目标客户在居住地这一属性上的属性值为美国,则目标客户在该时间段内基本不会愿意接听电销电话,因此,该属性值对目标客户是否接听电销电话这一结果所起到的影响作用较大;而若目标客户在居住地这一属性上的属性值为中国,则其属性值对目标客户是否接听电销电话这一结果所起到的影响作用较小。与上述评估值类似,对于属性值这一维度,以权重值来衡量属性值对电销电话接听概率的影响程度。
本申请实施例中,在不同的时间段内,同一属性值所对应的权重值不同。因此,为上述画像数据中的每一属性值创建一个时间段权重关系表,用于存储每一属性值在该时间段内所对应的权重值。
示例性地,以“女”和“男”这两个属性值为例,与“女”这一属性值所匹配的时间段权重关系表如表1所示,与“男”这一属性值所匹配的时间段权重关系表如表2所示:
Figure PCTCN2018097455-appb-000001
可见,根据每一属性值所匹配的时间段权重关系表,可读取出该属性值在每一预设的时间段内所对应的权重值。
S105:对每一所述时间段,根据各项所述属性所分别对应的所述评估值以及该时间段内各项所述属性值所分别对应的所述权重值,计算所述目标客户在该时间段的来电接听概率值。
本申请实施例中,分别以各个时间段为单位,计算当前的一个目标客户在该时间段内的来电接听概率值。一个时间段的来电接听概率值越高,则电销坐席在该时间段内拨打给该目标客户时,该目标客户愿意接受电话推销的可能性越大。
根据目标客户的画像数据所包含的各项属性值所分别对应的权重值,以及,根据目标 客户的画像数据所包含的各项属性所分别对应的评估值,计算目标客户在一时间段内的来电接听概率值。
作为本申请的一个实施例,上述计算所述目标客户在该时间段的来电接听概率值,可通过以下步骤来实现:对每一所述时间段,将各项所述属性所分别对应的所述评估值以及该时间段内各项所述属性值所分别对应的所述权重值输入预设的计算公式,以得到所述目标客户在该时间段的来电接听概率值,所述计算公式包括:
Figure PCTCN2018097455-appb-000002
其中,所述Score n为所述来电接听概率值;所述n为所述时间段的标识符;所述W i为所述画像数据中第i项属性所对应的所述评估值;所述S in为所述画像数据中第i项属性值所对应的所述权重值,且所述i为大于零的整数;所述N为所述画像数据中所述属性的总数。
通过上述公式,可计算出每一时间段对应的一个来电接听概率值。
示例性地,若要计算目标客户A在时间段9:00-10:00内的来电接听概率值,且目标客户A的画像数据包括:{性别:女}、{职业:医生}、{居住地:中国},“性别”、“职业”以及“居住地”所分别对应的评估值为W 1、W 2、W 3;“女”、“医生”以及“中国”在时间段9:00-10:00内所分别对应的权重值为S 1、S 2、S 3;则基于上述公式所计算出的来电接听概率值为Score=W 1S 1+W 2S 2+W 3S 3
S106:确定出所述来电接听概率值最高的所述时间段,并将该时间段确定为所述目标客户的最佳电销时间段。
本申请实施例中,在计算出同一目标客户分别在各个时间段的来电接听概率值后,通过比较各个来电接听概率值的数值大小,选取出数值最大的来电接听概率值。将该来电接听概率值所对应的时间段确定为该目标客户的最佳电销时间段。
作为本申请的一个实施示例,在确定出每一目标客户的最佳电销时间段后,生成该最佳电销时间段对应的一个预约拨打任务,以提示电销坐席人员在预设的该最佳电销时间段内,向该预约拨打任务所关联的目标客户进行电话拨打操作,并在电话拨通后,为目标客户提供产品推销服务。
作为本申请的一个实施示例,当检测到电销坐席人员所发出的目标客户选取指令时,若当前系统时间不在该目标客户的最佳电销时间段内,则发出提示信息,以提示电销坐席人员该时间段并非当前目标客户的最佳电销时间段,并在提示信息中显示当前时间段的来电接听概率值以及显示系统推荐的最佳电销时间段,由此保证了电销坐席人员能够准确地确定是否需要给目标客户进行电话拨打操作,避免了对目标客户所造成的骚扰以及降低电销成功率。
本申请实施例中,通过预先设置属性评估值对应关系表以及时间段权重关系表,可基于目标客户个性化的画像数据来准确地预测出目标客户在各个时间段内的来电接听概率值。通过将来电接听概率值最高的时间段作为目标客户的最佳电销时间段,保证了电销坐席在该最佳电销时间段内执行拨打任务时,客户能够具有较大的可能性接听推销电话,避免了在客户忙碌时间段对其造成骚扰,故提高了营销效率以及提高了客户满意度;整个电话销售过程中,电销坐席不再需要依赖于客户主观化的预约时间来联系客户,因而也提高了电销坐席在推销过程中的主动性。
作为本申请的另一个实施例,图2示出了本申请另一实施例提供的电销时间段的选取方法的实现流程。如图2所示,在上述S106之后,还包括:
S201:对每一所述最佳电销时间段,统计该最佳电销时间段内所述目标客户的总数。
对于预先读取的多个目标客户的画像数据,对每一个目标客户的画像数据执行上述步骤S101至S106后,输出各个目标客户的最佳电销时间段。由于最佳电销时间段基于时间段权重关系表中所预设的各个时间段来确定得出,故上述输出的各个目标客户的最佳电销时间段也仅会是预设的各个时间段中的一个时间段。因此,以预设的每一个时间段为基础,判断每一目标客户的最佳电销时间段是否为该时间段。若某一目标客户的最佳电销时间段为该时间段,则将该时段段适宜拨打电话的目标客户的总数加一。如此类推,直至各个时间段的目标客户总数统计完成。
S202:当所述目标客户的总数大于预设阈值时,根据所述来电接听概率值的高低顺序,对该最佳电销时间段内的各个所述目标客户进行排序。
本申请实施例中,对于每一个最佳电销时间段,若该时间段内所统计得到的目标客户的总数大于预设阈值,则基于其所对应的各个目标客户的来电接听概率值,按照来电接听概率值的数值大小,对各个目标客户进行排序,使得来电接听概率值较大的目标客户排在来电接听概率值较小的目标客户之前。
S203:展示排序结果,以使电销坐席基于所述排序结果依次对各个所述目标客户进行电话推销。
将上述多个目标客户的排序结果进行展示,具体包括:生成包含多个目标客户的排列顺序的客户名单,客户名单中包含每一目标客户的联系方式;将该客户名单显示于电销坐席的终端界面。
进一步地,在上述排序结果展示方式中,根据当前时刻的系统时间,确定系统时间所属的一个时间段。以该时间段为最佳电销时间段,读取该最佳电销时间段所对应的客户名单后,再将客户名单显示于电销坐席的终端界面。
基于显示于电销坐席的终端界面的客户名单以及客户名单中每一目标客户的联系方式,电销坐席将在该时间段内,依次对其中的每一个目标客户进行电话推销。
进一步地,将上述多个目标客户的排序结果进行展示,还可以包括:在终端界面展示预设的各个时间段所分别对应的控件;仅在检测到控件被选取时,才调用与该控件对应的时间段相匹配的客户名单,以展示该最佳电销时间段内各个目标客户的排序结果。
本申请实施例中,通过利用上述电销时间段的运算逻辑来处理多个目标客户的画像数据,实现了多个目标客户的最佳电销时间段的输出;基于最佳电销时间段的大小来对各个目标客户进行排序并展示,使得电销坐席能够依照客户的排列顺序来依次执行电销操作。由于同一时间段内,排序在前的目标客户具有更大的可能性转化为成交客户,因而根据排序来向各个目标客户推销,保证了电销坐席能够在尽可能短的时间内完成自身的任务达标量,提高营销效率。
在一种应用场景中,可以在电销坐席对每一目标客户进行电话推销后,对该目标客户的最佳电销时间段进行确定及更改。具体地,如图3所示,作为本申请的又一个实施例,在上述S106之后,还包括:
S301:获取所述目标客户在接听电销来电后所反馈的满意度以及满意度影响因子。
本申请实施例中,满意度以数值的方式衡量。例如,数字“2”表示非常满意,数字“1”表示满意,数字“-1”表示一般,数字“-2”表示不满意。在电销拨打销售电话后,将发出语音提示信息,以提示接听电话的目标客户对电销坐席的服务过程进行满意度以及满意度影响因子的反馈;或者,在开始执行电话推销时,根据电销坐席所收集的当前的目标客户所反馈的意见,得到目标客户所实时反馈的满意度以及满意度影响因子。其中,满意度影响因子是指,影响本次电销满意度的理由/原因,满意度影响因子为上述预设的任一属性和/或属性值。例如,目标客户反馈的满意度较低,导致满意度低的理由是,“本人是医生,坐席拨打过来的时间段是繁忙时间段,影响工作”,因此,目标客户在反馈满意度影响因子时,可以选取“职业”这一属性作为该影响因素;
获取得到的满意度影响因子为职业这一属性。若客户反馈说因职业问题,当前时间段不合适;则坐席反馈满意度时,可以选取“职业”属性对应的时间段的的“权重”作为该影响因素。同理,若本次电销电话拨打成功,且目标客客户所反馈的满意度较高,则同样接收客户所反馈的满意度影响因子。
S302:确定与所述满意度影响因子关联的评估值和/或权重值。
本申请实施例中,当满意度影响因子包括预设的任一属性时,根据上述每一属性及评估值的对应关系,读取出与该属性对应的评估值,则该评估值为与上述该满意度影响因子关 联的评估值。当满意度影响因子包括预设的任一属性值时,根据满意度影响因子的反馈时间段,读取该属性值在反馈时间段内所对应的权重值,则该权重值为与上述该满意度影响因子关联的权重值。
S303:基于所述满意度,对确定出的所述评估值和/或权重值进行调整,并根据调整后的所述评估值和/或权重值,更新所述属性评估值对应关系表以及所述时间段权重关系表。
本申请实施例中,根据目标客户所反馈的满意度高低,可获知基于上述S106所输出的该目标客户的最佳电销时间段是否准确。若满足度小于预设阈值,则表示上述最佳电销时间段与实际不符,因此,需要将确定出的评估值和/或权重值降低;若满足度大于或等于预设阈值,则表示上述最佳电销时间段与实际情况较为吻合,因此,可将确定出的评估值和/或权重值调高。
示例性地,若需要对上述S402所确定出的评估值进行调整,则调整后的评估值为:
W=W 0+k*c
其中,W 0为调整前的评估值,k为目标客户所反馈的满意度,c为预设参数。
若需要对上述S402所确定出的权重值进行调整,则调整后的权重值为:
S=S 0*(1+k*C)
其中,S 0为调整前的权重值,k为目标客户所反馈的满意度,C为预设参数。需要注意的是,这里的c和C可以相同,也可以不同。
本申请实施例中,通过收集电销坐席每次拨打电销电话的结果,获取目标客户所反馈的满意度以及对应的满意度影响因子,并根据反馈结果来调整客户画像数据所对应的评估值和/或权重值,形成闭环管理和自学习动态调整评估值、权重值的过程,使得下次遇到具有相同画像数据的目标客户时,能够基于调整后的评估值和/或权重值来计算该目标客户的最佳电销时间段,提高了最佳电销时间段的计算准确率。
优选地,在当前时刻所属的一个时间段内,生成该时间段内各个目标客户所分别对应的一个电销任务。当电销坐席拨打一目标客户的电话后,将该目标客户所对应的电销任务的执行状态切换为已拨打状态。将当前时间段的目标客户拨打总数加一。由于上述各个时间段为预先设定的时间区间,因此,若检测到当前时刻所属的时间段与上一时刻所属的时间段不同,则可确定上一时间段结束。在每一时间段结束时,统计出该时间段内目标客户拨打总数。
若统计得到的目标客户拨打总数小于该时间段内所展示的目标客户的总数,则确定出未完成拨打任务的各个目标客户,即,确定出执行状态为未执行状态的各个电销任务所对应的目标客户。将其中各个目标客户的最佳电销时间段变更为该最佳电销时间段的下一时间段。例如,若目标客户A的最佳电销时间段为9:00-10:00,但在9:00-10:00这一时间段结束时, 目标客户A所对应的电销任务的执行状态为未执行状态,则将目标客户A的最佳电销时间段更改为10:00-11:00,以在当前10:00-11:00这一时间段内,再次生成并展示目标客户A所对应的一个电销任务。由此,实现了电销任务的时间段转移。
优选地,若在任一最佳电销时间段内,检测上一时间段内所转移的电销任务,则在展示该最佳电销时间段的目标客户的排序结果后,将转移的该电销任务置于原本排于第一位的目标客户的电销任务之前,使得电销坐席能够有限处理上一时间段所未处理完成的电销任务。
本申请实施例中,通过确定出未执行完成的电销任务,将其转移至下一时间段并将其排序于最前位置,保证了在一最佳电销时间段内的电销任务数目较为集中时,即使电销任务无法处理完毕所有电销任务,也能尽可能地在下一时间段内进行优选处理,使得该电销任务的实际处理时间并不会较大地偏离其最佳电销时间段,故也在一定程度上提高了电销成功的可能性。
应理解,上述实施例中各步骤的序号的大小并不意味着执行顺序的先后,各过程的执行顺序应以其功能和内在逻辑确定,而不应对本申请实施例的实施过程构成任何限定。
对应于上文实施例所述的电销时间段的选取方法,图4示出了本申请实施例提供的电销时间段的选取装置的结构框图。为了便于说明,仅示出了与本实施例相关的部分。
参照图4,该装置包括:
画像数据获取单元41,用于获取目标客户的画像数据。
属性提取单元42,用于提取所述画像数据所包含的各项属性,并根据预设的属性评估值对应关系表,分别确定与每一项所述属性对应的评估值。
属性值读取单元43,用于读取所述画像数据中各项所述属性的属性值。
权重值确定单元44,用于根据每一所述属性值所分别匹配的时间段权重关系表,确定出各项所述属性值分别在各个预设的时间段内所对应的权重值。
接听概率值计算单元45,用于对每一所述时间段,根据各项所述属性所分别对应的所述评估值以及该时间段内各项所述属性值所分别对应的所述权重值,计算所述目标客户在该时间段的来电接听概率值。
电销时间段确定单元46,用于确定出所述来电接听概率值最高的所述时间段,并将该时间段确定为所述目标客户的最佳电销时间段。
可选地,上述电销时间段的选取装置还包括:统计单元,用于对每一所述最佳电销时间段,统计该最佳电销时间段内所述目标客户的总数。排序单元,用于当所述目标客户的总数大于预设阈值时,根据所述来电接听概率值的高低顺序,对该最佳电销时间段内的各个所述目标客户进行排序。展示单元,用于展示排序结果,以使电销坐席基于所述排序结果依次 对各个所述目标客户进行电话推销。
可选地,上述电销时间段的选取装置还包括:第一获取单元,用于获取所述目标客户在接听电销来电后所反馈的满意度以及满意度影响因子。确定单元,用于确定与所述满意度影响因子关联的评估值和/或权重值。调整单元,用于基于所述满意度,对确定出的所述评估值和/或权重值进行调整,并根据调整后的所述评估值和/或权重值,更新所述属性评估值对应关系表以及所述时间段权重关系表。
可选地,上述电销时间段的选取装置还包括:
第二获取单元,用于在所述最佳电销时间段结束时,获取目标客户拨打总数。
变更单元,用于若所述目标客户拨打总数小于所述最佳电销时间段内所述目标客户的总数,则确定出未完成拨打任务的各个所述目标客户,并将其中各个所述目标客户的所述最佳电销时间段变更为所述最佳电销时间段的下一所述时间段。
可选地,所述接听概率值计算单元45包括:
输入子单元,用于对每一所述时间段,将各项所述属性所分别对应的所述评估值以及该时间段内各项所述属性值所分别对应的所述权重值输入预设的计算公式,以得到所述目标客户在该时间段的来电接听概率值,所述计算公式包括:
Figure PCTCN2018097455-appb-000003
其中,所述Score n为所述来电接听概率值;所述n为所述时间段的标识符;所述W i为所述画像数据中第i项属性所对应的所述评估值;所述S in为所述画像数据中第i项属性值所对应的所述权重值,且所述i为大于零的整数;所述N为所述画像数据中所述属性的总数。
图5是本申请一实施例提供的终端设备的示意图。如图5所示,该实施例的终端设备5包括:处理器50以及存储器51,所述存储器51中存储有可在所述处理器50上运行的计算机可读指令52,例如电销时间段的选取程序。所述处理器50执行所述计算机可读指令52时实现上述各个电销时间段的选取方法实施例中的步骤,例如图1所示的步骤101至106。或者,所述处理器50执行所述计算机可读指令52时实现上述各装置实施例中各模块/单元的功能,例如图4所示单元41至46的功能。
示例性的,所述计算机可读指令52可以被分割成一个或多个模块/单元,所述一个或者多个模块/单元被存储在所述存储器51中,并由所述处理器50执行,以完成本申请。所述一个或多个模块/单元可以是能够完成特定功能的一系列计算机可读指令段,该指令段用于描述所述计算机可读指令52在所述终端设备5中的执行过程。
所述终端设备5可以是桌上型计算机、笔记本、掌上电脑及云端服务器等计算设备。 所述终端设备可包括,但不仅限于处理器50和存储器51。本领域技术人员可以理解,图5仅仅是终端设备5的示例,并不构成对终端设备5的限定,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,例如所述终端设备还可以包括输入输出设备、网络接入设备、总线等。
所称处理器50可以是中央处理单元(Central Processing Unit,CPU),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。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。
所述存储器51可以是所述终端设备5的内部存储单元,例如终端设备5的硬盘或内存。所述存储器51也可以是所述终端设备5的外部存储设备,例如所述终端设备5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,所述存储器51还可以既包括所述终端设备5的内部存储单元也包括外部存储设备。所述存储器51用于存储所述计算机可读指令以及所述终端设备所需的其他程序和数据。所述存储器51还可以用于暂时地存储已经输出或者将要输出的数据。
另外,在本申请各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质中,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random Access Memory,RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述,以上实施例仅用以说明本申请的技术方案,而非对其限制;尽管参照前述实施例对本申请进行了详细的说明,本领域的普通技术人员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分技术特征进行等同替换;而这些修改或者替换,并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围。

Claims (20)

  1. 一种电销时间段的选取方法,其特征在于,包括:
    获取目标客户的画像数据;
    提取所述画像数据所包含的各项属性,并根据预设的属性评估值对应关系表,分别确定与每一项所述属性对应的评估值;
    读取所述画像数据中各项所述属性的属性值;
    根据每一所述属性值所分别匹配的时间段权重关系表,确定出各项所述属性值分别在各个预设的时间段内所对应的权重值;
    对每一所述时间段,根据各项所述属性所分别对应的所述评估值以及该时间段内各项所述属性值所分别对应的所述权重值,计算所述目标客户在该时间段的来电接听概率值;
    确定出所述来电接听概率值最高的所述时间段,并将该时间段确定为所述目标客户的最佳电销时间段。
  2. 如权利要求1所述的电销时间段的选取方法,其特征在于,还包括:
    对每一所述最佳电销时间段,统计该最佳电销时间段内所述目标客户的总数;
    当所述目标客户的总数大于预设阈值时,根据所述来电接听概率值的高低顺序,对该最佳电销时间段内的各个所述目标客户进行排序;
    展示排序结果,以使电销坐席基于所述排序结果依次对各个所述目标客户进行电话推销。
  3. 如权利要求1或2所述的电销时间段的选取方法,其特征在于,还包括:
    获取所述目标客户在接听电销来电后所反馈的满意度以及满意度影响因子;
    确定与所述满意度影响因子关联的评估值和/或权重值;
    基于所述满意度,对确定出的所述评估值和/或权重值进行调整,并根据调整后的所述评估值和/或权重值,更新所述属性评估值对应关系表以及所述时间段权重关系表。
  4. 如权利要求2所述的电销时间段的选取方法,其特征在于,还包括:
    在所述最佳电销时间段结束时,获取目标客户拨打总数;
    若所述目标客户拨打总数小于所述最佳电销时间段内所述目标客户的总数,则确定出未完成拨打任务的各个所述目标客户,并将其中各个所述目标客户的所述最佳电销时间段变更为所述最佳电销时间段的下一所述时间段。
  5. 如权利要求1所述的电销时间段的选取方法,其特征在于,所述对每一所述时间段,根据各项所述属性所分别对应的所述评估值以及该时间段内各项所述属性值所分别对应的 所述权重值,计算所述目标客户在该时间段的来电接听概率值,包括:
    对每一所述时间段,将各项所述属性所分别对应的所述评估值以及该时间段内各项所述属性值所分别对应的所述权重值输入预设的计算公式,以得到所述目标客户在该时间段的来电接听概率值,所述计算公式包括:
    Figure PCTCN2018097455-appb-100001
    其中,所述Score n为所述来电接听概率值;所述n为所述时间段的标识符;所述W i为所述画像数据中第i项属性所对应的所述评估值;所述S in为所述画像数据中第i项属性值所对应的所述权重值,且所述i为大于零的整数;所述N为所述画像数据中所述属性的总数。
  6. 一种电销时间段的选取装置,其特征在于,包括:
    画像数据获取单元,用于获取目标客户的画像数据;
    属性提取单元,用于提取所述画像数据所包含的各项属性,并根据预设的属性评估值对应关系表,分别确定与每一项所述属性对应的评估值;
    属性值读取单元,用于读取所述画像数据中各项所述属性的属性值;
    权重值确定单元,用于根据每一所述属性值所分别匹配的时间段权重关系表,确定出各项所述属性值分别在各个预设的时间段内所对应的权重值;
    接听概率值计算单元,用于对每一所述时间段,根据各项所述属性所分别对应的所述评估值以及该时间段内各项所述属性值所分别对应的所述权重值,计算所述目标客户在该时间段的来电接听概率值;
    电销时间段确定单元,用于确定出所述来电接听概率值最高的所述时间段,并将该时间段确定为所述目标客户的最佳电销时间段。
  7. 根据权利要求6所述的电销时间段的选取装置,其特征在于,还包括:
    统计单元,用于对每一所述最佳电销时间段,统计该最佳电销时间段内所述目标客户的总数;
    排序单元,用于当所述目标客户的总数大于预设阈值时,根据所述来电接听概率值的高低顺序,对该最佳电销时间段内的各个所述目标客户进行排序;
    展示单元,用于展示排序结果,以使电销坐席基于所述排序结果依次对各个所述目标客户进行电话推销。
  8. 根据权利要求6或7所述的电销时间段的选取装置,其特征在于,还包括:
    第一获取单元,用于获取所述目标客户在接听电销来电后所反馈的满意度以及满意度 影响因子;
    确定单元,用于确定与所述满意度影响因子关联的评估值和/或权重值;
    调整单元,用于基于所述满意度,对确定出的所述评估值和/或权重值进行调整,并根据调整后的所述评估值和/或权重值,更新所述属性评估值对应关系表以及所述时间段权重关系表。
  9. 根据权利要求7所述的电销时间段的选取装置,其特征在于,还包括:
    第二获取单元,用于在所述最佳电销时间段结束时,获取目标客户拨打总数;
    变更单元,用于若所述目标客户拨打总数小于所述最佳电销时间段内所述目标客户的总数,则确定出未完成拨打任务的各个所述目标客户,并将其中各个所述目标客户的所述最佳电销时间段变更为所述最佳电销时间段的下一所述时间段。
  10. 根据权利要求6所述的电销时间段的选取装置,其特征在于,还包括:
    输入子单元,用于对每一所述时间段,将各项所述属性所分别对应的所述评估值以及该时间段内各项所述属性值所分别对应的所述权重值输入预设的计算公式,以得到所述目标客户在该时间段的来电接听概率值,所述计算公式包括:
    Figure PCTCN2018097455-appb-100002
    其中,所述Score n为所述来电接听概率值;所述n为所述时间段的标识符;所述W i为所述画像数据中第i项属性所对应的所述评估值;所述S in为所述画像数据中第i项属性值所对应的所述权重值,且所述i为大于零的整数;所述N为所述画像数据中所述属性的总数。
  11. 一种终端设备,其特征在于,包括存储器以及处理器,所述存储器中存储有可在所述处理器上运行的计算机可读指令,所述处理器执行所述计算机可读指令时实现如下步骤:
    获取目标客户的画像数据;
    提取所述画像数据所包含的各项属性,并根据预设的属性评估值对应关系表,分别确定与每一项所述属性对应的评估值;
    读取所述画像数据中各项所述属性的属性值;
    根据每一所述属性值所分别匹配的时间段权重关系表,确定出各项所述属性值分别在各个预设的时间段内所对应的权重值;
    对每一所述时间段,根据各项所述属性所分别对应的所述评估值以及该时间段内各项所述属性值所分别对应的所述权重值,计算所述目标客户在该时间段的来电接听概率值;
    确定出所述来电接听概率值最高的所述时间段,并将该时间段确定为所述目标客户的 最佳电销时间段。
  12. 根据权利要求11所述的终端设备,其特征在于,所述处理器执行所述计算机可读指令时还实现如下步骤:
    对每一所述最佳电销时间段,统计该最佳电销时间段内所述目标客户的总数;
    当所述目标客户的总数大于预设阈值时,根据所述来电接听概率值的高低顺序,对该最佳电销时间段内的各个所述目标客户进行排序;
    展示排序结果,以使电销坐席基于所述排序结果依次对各个所述目标客户进行电话推销。
  13. 根据权利要求11或12所述的终端设备,其特征在于,所述处理器执行所述计算机可读指令时还实现如下步骤:
    获取所述目标客户在接听电销来电后所反馈的满意度以及满意度影响因子;
    确定与所述满意度影响因子关联的评估值和/或权重值;
    基于所述满意度,对确定出的所述评估值和/或权重值进行调整,并根据调整后的所述评估值和/或权重值,更新所述属性评估值对应关系表以及所述时间段权重关系表。
  14. 根据权利要求12所述的终端设备,其特征在于,所述处理器执行所述计算机可读指令时还实现如下步骤:
    在所述最佳电销时间段结束时,获取目标客户拨打总数;
    若所述目标客户拨打总数小于所述最佳电销时间段内所述目标客户的总数,则确定出未完成拨打任务的各个所述目标客户,并将其中各个所述目标客户的所述最佳电销时间段变更为所述最佳电销时间段的下一所述时间段。
  15. 根据权利要求11所述的终端设备,其特征在于,所述对每一所述时间段,根据各项所述属性所分别对应的所述评估值以及该时间段内各项所述属性值所分别对应的所述权重值,计算所述目标客户在该时间段的来电接听概率值,包括:
    对每一所述时间段,将各项所述属性所分别对应的所述评估值以及该时间段内各项所述属性值所分别对应的所述权重值输入预设的计算公式,以得到所述目标客户在该时间段的来电接听概率值,所述计算公式包括:
    Figure PCTCN2018097455-appb-100003
    其中,所述Score n为所述来电接听概率值;所述n为所述时间段的标识符;所述W i为所述画像数据中第i项属性所对应的所述评估值;所述S in为所述画像数据中第i项属性值所 对应的所述权重值,且所述i为大于零的整数;所述N为所述画像数据中所述属性的总数。
  16. 一种计算机可读存储介质,所述计算机可读存储介质存储有计算机可读指令,其特征在于,所述计算机可读指令被至少一个处理器执行时实现如下步骤:
    获取目标客户的画像数据;
    提取所述画像数据所包含的各项属性,并根据预设的属性评估值对应关系表,分别确定与每一项所述属性对应的评估值;
    读取所述画像数据中各项所述属性的属性值;
    根据每一所述属性值所分别匹配的时间段权重关系表,确定出各项所述属性值分别在各个预设的时间段内所对应的权重值;
    对每一所述时间段,根据各项所述属性所分别对应的所述评估值以及该时间段内各项所述属性值所分别对应的所述权重值,计算所述目标客户在该时间段的来电接听概率值;
    确定出所述来电接听概率值最高的所述时间段,并将该时间段确定为所述目标客户的最佳电销时间段。
  17. 根据权利要求16所述的计算机可读存储介质,其特征在于,所述计算机可读指令被至少一个处理器执行时还实现如下步骤:
    对每一所述最佳电销时间段,统计该最佳电销时间段内所述目标客户的总数;
    当所述目标客户的总数大于预设阈值时,根据所述来电接听概率值的高低顺序,对该最佳电销时间段内的各个所述目标客户进行排序;
    展示排序结果,以使电销坐席基于所述排序结果依次对各个所述目标客户进行电话推销。
  18. 根据权利要求16或17所述的计算机可读存储介质,其特征在于,所述计算机可读指令被至少一个处理器执行时还实现如下步骤:
    获取所述目标客户在接听电销来电后所反馈的满意度以及满意度影响因子;
    确定与所述满意度影响因子关联的评估值和/或权重值;
    基于所述满意度,对确定出的所述评估值和/或权重值进行调整,并根据调整后的所述评估值和/或权重值,更新所述属性评估值对应关系表以及所述时间段权重关系表。
  19. 根据权利要求17所述的计算机可读存储介质,其特征在于,所述计算机可读指令被至少一个处理器执行时还实现如下步骤:
    在所述最佳电销时间段结束时,获取目标客户拨打总数;
    若所述目标客户拨打总数小于所述最佳电销时间段内所述目标客户的总数,则确定出未完成拨打任务的各个所述目标客户,并将其中各个所述目标客户的所述最佳电销时间段变 更为所述最佳电销时间段的下一所述时间段。
  20. 根据权利要求16所述的计算机可读存储介质,其特征在于,所述对每一所述时间段,根据各项所述属性所分别对应的所述评估值以及该时间段内各项所述属性值所分别对应的所述权重值,计算所述目标客户在该时间段的来电接听概率值,包括:
    对每一所述时间段,将各项所述属性所分别对应的所述评估值以及该时间段内各项所述属性值所分别对应的所述权重值输入预设的计算公式,以得到所述目标客户在该时间段的来电接听概率值,所述计算公式包括:
    Figure PCTCN2018097455-appb-100004
    其中,所述Score n为所述来电接听概率值;所述n为所述时间段的标识符;所述W i为所述画像数据中第i项属性所对应的所述评估值;所述S in为所述画像数据中第i项属性值所对应的所述权重值,且所述i为大于零的整数;所述N为所述画像数据中所述属性的总数。
PCT/CN2018/097455 2018-04-09 2018-07-27 电销时间段的选取方法、装置、终端设备及介质 Ceased WO2019196255A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810311216.8 2018-04-09
CN201810311216.8A CN108711067A (zh) 2018-04-09 2018-04-09 电销时间段的选取方法、终端设备及介质

Publications (1)

Publication Number Publication Date
WO2019196255A1 true WO2019196255A1 (zh) 2019-10-17

Family

ID=63867093

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/097455 Ceased WO2019196255A1 (zh) 2018-04-09 2018-07-27 电销时间段的选取方法、装置、终端设备及介质

Country Status (2)

Country Link
CN (1) CN108711067A (zh)
WO (1) WO2019196255A1 (zh)

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109600522A (zh) * 2018-12-10 2019-04-09 中国银行股份有限公司 一种外呼控制方法及装置
CN111435482A (zh) * 2019-01-14 2020-07-21 顺丰科技有限公司 一种外呼模型的构建方法、外呼方法、装置和存储介质
CN110428263A (zh) * 2019-06-19 2019-11-08 平安科技(深圳)有限公司 客户预判方法、装置、终端及存储介质
CN110706036B (zh) * 2019-10-08 2022-09-16 上海莉莉丝科技股份有限公司 评估广告的多个新素材的方法、装置、存储介质和系统
CN111935362B (zh) * 2020-08-07 2021-07-16 北京新唐思创教育科技有限公司 通话数据处理方法、装置、电子设备及计算机存储介质
CN112132597A (zh) * 2020-09-30 2020-12-25 深圳前海微众银行股份有限公司 数据处理方法、装置、设备及存储介质
CN112422755B (zh) * 2020-11-19 2021-10-15 中国联合网络通信集团有限公司 电话拨打方法、装置及存储介质
CN113256070A (zh) * 2021-04-26 2021-08-13 北京淇瑀信息科技有限公司 基于电销转化率的承接线路分配方法、装置及电子设备
CN113450124B (zh) * 2021-06-24 2024-06-25 江苏百应信息技术有限公司 基于用户行为的外呼方法、装置、电子设备及介质
CN114154727B (zh) * 2021-12-07 2024-07-09 深圳前海微众银行股份有限公司 一种信息处理方法及装置、存储介质
CN114240630A (zh) * 2021-12-21 2022-03-25 中国建设银行股份有限公司 数据处理方法、装置、电子设备、介质及程序产品

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100287242A1 (en) * 2009-05-07 2010-11-11 Gopesh Kumar Method for Providing a Conference System Allowing Advisors to Offer Conference Sessions to Clients
CN105761112A (zh) * 2016-02-23 2016-07-13 国元证券股份有限公司 一种证券融资融券和资管目标客户的挖掘方法
CN106971321A (zh) * 2017-04-06 2017-07-21 百度在线网络技术(北京)有限公司 营销信息推送方法、装置、设备以及存储介质
CN107590688A (zh) * 2017-08-24 2018-01-16 平安科技(深圳)有限公司 目标客户的识别方法及终端设备
CN107688967A (zh) * 2017-08-24 2018-02-13 平安科技(深圳)有限公司 客户购买意向的预测方法及终端设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100287242A1 (en) * 2009-05-07 2010-11-11 Gopesh Kumar Method for Providing a Conference System Allowing Advisors to Offer Conference Sessions to Clients
CN105761112A (zh) * 2016-02-23 2016-07-13 国元证券股份有限公司 一种证券融资融券和资管目标客户的挖掘方法
CN106971321A (zh) * 2017-04-06 2017-07-21 百度在线网络技术(北京)有限公司 营销信息推送方法、装置、设备以及存储介质
CN107590688A (zh) * 2017-08-24 2018-01-16 平安科技(深圳)有限公司 目标客户的识别方法及终端设备
CN107688967A (zh) * 2017-08-24 2018-02-13 平安科技(深圳)有限公司 客户购买意向的预测方法及终端设备

Also Published As

Publication number Publication date
CN108711067A (zh) 2018-10-26

Similar Documents

Publication Publication Date Title
WO2019196255A1 (zh) 电销时间段的选取方法、装置、终端设备及介质
CN107833056B (zh) 一种客户反馈信息的处理方法及其终端
CN108615119B (zh) 一种异常用户的识别方法及设备
CN106355391B (zh) 一种业务处理方法及装置
CN104103113A (zh) 排队服务器以及排队方法
TW201813364A (zh) 調整業務語音播放順序的方法及設備
WO2019037202A1 (zh) 目标客户的识别方法、装置、电子设备及介质
CN109472312B (zh) 应用程序评估方法、装置、计算机设备及存储介质
CN113591444A (zh) 一种信息填写方法、装置及电子设备
CN109600344A (zh) 识别风险群体的方法、装置及电子设备
WO2019232821A1 (zh) 风控数据处理方法、装置、计算机设备及存储介质
CN110796348A (zh) 一种满意度调查的方法和装置
CN111598162A (zh) 一种黄牛风险监测方法、终端设备和存储介质
CN111142746A (zh) 一种系统配额计算方法和装置
CN109858900B (zh) 一种支付信息推送方法、装置及终端设备
WO2021042541A1 (zh) 新零售模式下的商品导购方法、装置、设备及存储介质
CN110941639B (zh) 数据处理、数据查询方法、装置以及设备
US20210185000A1 (en) Dynamic Email Content Engine
CN107330709B (zh) 确定目标对象的方法及装置
CN106133779B (zh) 电子商务企业订单接受算法控制方法和装置
US20180211199A1 (en) Decision engine for generating interfaces to simulate and optimize employee scheduling in work locations
CN111291957A (zh) 生成客服调度信息的方法及装置、电子设备、存储介质
CN108876548A (zh) 一种云产品推荐方法及装置
CN113283814A (zh) 业务处理效率确定方法、装置、电子设备及可读存储介质
CN110232590B (zh) 一种方案的生成方法及设备

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: 18914272

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 1205A DATED 22.01.2021)

122 Ep: pct application non-entry in european phase

Ref document number: 18914272

Country of ref document: EP

Kind code of ref document: A1