WO2019196502A1 - 营销活动质量评估方法、服务器及计算机可读存储介质 - Google Patents

营销活动质量评估方法、服务器及计算机可读存储介质 Download PDF

Info

Publication number
WO2019196502A1
WO2019196502A1 PCT/CN2018/123580 CN2018123580W WO2019196502A1 WO 2019196502 A1 WO2019196502 A1 WO 2019196502A1 CN 2018123580 W CN2018123580 W CN 2018123580W WO 2019196502 A1 WO2019196502 A1 WO 2019196502A1
Authority
WO
WIPO (PCT)
Prior art keywords
activity
data
indicator
score
activities
Prior art date
Application number
PCT/CN2018/123580
Other languages
English (en)
French (fr)
Inventor
杨亮吉
陈旷雨
王思晶
Original Assignee
深圳壹账通智能科技有限公司
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 深圳壹账通智能科技有限公司 filed Critical 深圳壹账通智能科技有限公司
Publication of WO2019196502A1 publication Critical patent/WO2019196502A1/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
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0282—Rating or review of business operators or products
    • 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
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • 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
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0242—Determining effectiveness of advertisements

Definitions

  • the present application relates to the field of data analysis technologies, and in particular, to a marketing activity quality assessment method, a server, and a computer readable storage medium.
  • Internet marketing is a marketing method in which companies achieve marketing goals through online networks, computer communications, and digital interactive media.
  • Internet marketing has the characteristics of low cost, high efficiency, wide spread, good effect, and strong real-time performance.
  • the evaluation of Internet marketing activities faces many problems. For example, many qualitative indicators and hidden indicators require enterprise mining, while the input-output ratio, market size, and profit growth used by traditional marketing activities The indicators such as rate are obviously not enough, and how to automatically realize the historical vertical comparison of Internet marketing activities and the horizontal comparison in the same period is also an urgent need. Therefore, how to comprehensively evaluate the advantages and disadvantages of Internet marketing activities, and provide direction and ideas for future event optimization and new event planning has become a major problem that needs to be solved.
  • the present application proposes a marketing activity quality assessment method, a server, and a computer readable storage medium to solve the problem of how to comprehensively evaluate the merits of Internet marketing activities.
  • the present application proposes a marketing activity quality assessment method, the method comprising the steps of:
  • the activity data including the activity cost indicator, the customer indicator, the sales indicator, and the customer activity indicator;
  • the first formula is: Where Xi is the standardized activity data, and Yi is the value after Xi standardization. Representing the summation of multiple values to be normalized;
  • the pre-established activity quality assessment model processes the standardized activity data to obtain the activity quality score of the event and the activity quality score of other activities;
  • the growth data is obtained by subtracting the average of the period during which the event is held from the average of the month prior to the event.
  • the present application further provides a server, including a memory, a processor, and a marketing activity quality evaluation system stored on the memory and operable on the processor, the marketing activity quality evaluation system.
  • the steps of the marketing activity quality assessment method as described above are implemented when executed by the processor.
  • the present application further provides a computer readable storage medium storing a marketing activity quality evaluation system, the marketing activity quality evaluation system being executable by at least one processor, The step of causing the at least one processor to perform the marketing activity quality assessment method as described above.
  • the marketing activity quality evaluation method, the server and the computer readable storage medium proposed by the present application first acquire all activity data of the event and the history activity, delineate the storage space, and all the activities described. Data is stored in the storage space; secondly, the activity data is pre-processed; then, the pre-established activity quality assessment model processes the pre-processed activity data to obtain an activity quality score; and finally, in the bubble chart Show the effect of the event and compare the activities.
  • the advantages and disadvantages of Internet marketing activities can be comprehensively and comprehensively evaluated.
  • the historical vertical and horizontal comparison of Internet marketing activities can clearly compare activities.
  • the effects of various aspects are conducive to improving the efficiency of marketing activities, providing direction and ideas for future event optimization and new event planning, which is more convenient, faster and more accurate than the prior art.
  • 1 is a schematic diagram of an optional hardware architecture of the server of the present application.
  • FIG. 2 is a schematic diagram of a program module of a first embodiment of a marketing activity quality evaluation system of the present application
  • FIG. 3 is a schematic diagram of a program module of a second embodiment of the marketing activity quality evaluation system of the present application.
  • FIG. 4 is a schematic flow chart of a first embodiment of a method for evaluating a quality of a marketing activity of the present application
  • FIG. 5 is a schematic flow chart of a second embodiment of a method for evaluating a quality of a marketing activity of the present application
  • FIG. 6 is a schematic flow chart of a third embodiment of a method for evaluating a quality of marketing activities of the present application
  • FIG. 1 it is a schematic diagram of an optional hardware architecture of the server 1 of the present application.
  • the server 1 may include, but is not limited to, the memory 11, the processor 12, and the network interface 13 being communicably connected to each other through a system bus. It is pointed out that Figure 1 only shows the server 1 with the components 11-13, but it should be understood that not all illustrated components are required to be implemented, and more or fewer components may be implemented instead.
  • the server 1 may be a computing device such as a rack server, a blade server, a tower server, or a rack server.
  • the server 1 may be an independent server or a server cluster composed of multiple servers.
  • the memory 11 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (eg, SD or DX memory, etc.), a random access memory (RAM), a static Random access memory (SRAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), magnetic memory, magnetic disk, optical disk, and the like.
  • the memory 11 may be an internal storage unit of the server 1, such as a hard disk or memory of the server 1.
  • the memory 11 may also be an external storage device of the server 1, such as a plug-in hard disk equipped on the server 1, a smart memory card (SMC), and a secure digital (Secure) Digital, SD) cards, flash cards, etc.
  • the memory 11 can also include both the internal storage unit of the server 1 and its external storage device.
  • the memory 11 is generally used to store an operating system installed in the server 1 and various types of application software, such as program code of the marketing activity quality evaluation system 2. Further, the memory 11 can also be used to temporarily store various types of data that have been output or are to be output.
  • the processor 12 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments.
  • the processor 12 is typically used to control the overall operation of the server 1.
  • the processor 12 is configured to run program code or process data stored in the memory 11, such as running the marketing activity quality assessment system 2 and the like.
  • the network interface 13 may comprise a wireless network interface or a wired network interface, which is typically used to establish a communication connection between the server 1 and other electronic devices.
  • the present application proposes a marketing activity quality assessment system 2.
  • FIG. 2 it is a program module diagram of the first embodiment of the marketing activity quality assessment system 2 of the present application.
  • the marketing activity quality assessment system 2 includes a series of computer program instructions stored in the memory 11, and when the computer program instructions are executed by the processor 12, the quality of the marketing activities of the embodiments of the present application can be implemented. Evaluation operation.
  • the campaign quality assessment system 2 can be divided into one or more modules based on the particular operations implemented by the various portions of the computer program instructions. For example, in FIG. 3, the marketing activity quality assessment system 2 can be divided into a data acquisition module 21, a pre-processing module 22, a scoring module 23, and a display module 24. among them:
  • the data obtaining module 21 is configured to acquire all activity data of the current activity and other activities in the database.
  • other activities include activities held in conjunction with the event and events held in history.
  • the acquired activity data includes an activity cost indicator, a customer indicator, a sales indicator, and a customer activity indicator
  • the cost indicator includes a marketing resource cost, an internal channel promotion cost, an external channel promotion cost, a business development cost, and a customer.
  • the indicators include the number of registered persons, the number of accounts opened, the sales indicators include the number of purchases, the order quantity and sales volume, and the customer activity indicators include the number of customer logins and the number of logins.
  • the pre-processing module 22 is configured to perform pre-processing on the activity data to perform dimensionless processing on the activity data, so that the activity has dimensionless characteristics.
  • the pre-processing includes the steps of: calculating an average value of the activity data during an activity;
  • the growth data is obtained by subtracting the average of the period during which the event is held from the average of the month prior to the event.
  • the collected daily indicators are subtracted from the daily average value of the previous month of the activity, and the growth data is obtained, and the data is sorted according to the basis.
  • activity A should be held once a month. Take Activity A as an example.
  • the daily average R11 and R22 of the number of accounts opened this month and last month are based on the daily average value R11 of this month and the daily average value R22 of the previous month, and the growth data (R11-R22) of this month is compared with the average daily opening value of the previous month.
  • the method of calculating the growth data is as described above. The method is similar. I will not repeat them here.
  • the scoring module 23 is configured to process the activity data using a pre-established activity quality assessment model to obtain an activity quality score of the activity and an activity quality score of other activities.
  • the activity quality assessment model is mainly used to process the pre-processed activity data to obtain an activity quality score
  • the activity quality assessment model calculates the activity quality score includes: performing the activity growth data Sorting, calculating the activity quality score of the event and the activity quality score of other activities according to the sorted activity growth data.
  • the number of activities may be sorted according to different ranks according to different ranks, for example, the number of account opening data is sorted in descending order, and the sales volume increase data is in accordance with the largest to smallest. Sort in order.
  • the activity quality score of the activity and the activity quality score of other activities can be obtained by calculating the sorted activity growth data by a specific method.
  • the specific method may include performing data segmentation and corresponding to the sorted growth data.
  • the base score is formed into the basic score interval, for example, the aforementioned growth data is divided into one percentile points, and the corresponding score is 0.01 to 1 minute. For example, if the growth figures of the number of accounts for activity A, activity B, activity C, and activity D are 30, 20, 10, and 0, respectively, the percentiles corresponding to the numerical growth data of the account holder are 1, 0.75, respectively. 0.5, 0.25, corresponding to the score interval of 0.01 to 1, the corresponding base scores are 1, 0.75, 0.5, 0.25.
  • the percentile method to obtain the base score is to treat the same type of data in all activities as a percentile, for example, the number of accounts for multiple activities, the cost of business development for all activities, and all activities. After the percentile of the same type of data, it is necessary to match each percentile to the interval of [0.01, 1] to obtain the corresponding base score.
  • the specific method further includes determining different weights for different activity data. For example, according to the actual service scenario, the scoring weights are determined for the indicators participating in the scoring, each weight value is 0 to 1, and the weights are added to 1.
  • the steps of obtaining the weights of the indicators include:
  • the activity indicators are X1, X2, X3, ..., Xi, and assume that the values normalized to each indicator data are Y1, Y2, ..., Yi;
  • the step of obtaining the activity quality score further includes:
  • the activity quality score is obtained by the following formula:
  • the specific method further includes calculating the indicator base score by substituting the actual index value of each activity into each score interval, and multiplying the weight by the sum to obtain the comprehensive score.
  • the display module 24 compares the activity quality score of the current activity with the activity quality score of other activities, outputs an evaluation result of the activity according to the comparison result, and displays the activity of the activity on the bubble chart. Quality scores and activity quality scores for other activities.
  • the actual cost and important indicator value of the activity are collected (for example, one activity whose main purpose is to promote transaction volume, and the important indicator value is the transaction amount during the activity).
  • the activity scores, cost and important indicator values are marked as three output values on the bubble chart to visually compare the advantages and disadvantages between the activities at the same time; historical activities can also be introduced as a reference. It is also possible to fit an activity effect average line for each activity of the same period as a reference, and above and below the average line, it is higher than the average effect of the concurrent activities.
  • the marketing activity quality assessment system 2 can continuously update the quality sub-evaluation model to ensure that the evaluation effect is objective.
  • the new activity indicator values are included in all historical activities for sorting, and 100 percentiles are re-defined, and the interval values corresponding to each of the 0.01-1 individual scores. This standard can be presented to the event planner to quantitatively split the subsequent activity goals and properly control the activity process.
  • the marketing activity quality assessment system 2 includes a standardization module 25 in addition to the data acquisition module 21, the preprocessing module 22, the scoring module 23, and the display module 24 in the first embodiment.
  • the data obtaining module 21 is configured to acquire all activity data of the current activity and other activities in the database.
  • other activities include activities held in conjunction with the event and events held in history.
  • the acquired activity data includes an activity cost indicator, a customer indicator, a sales indicator, and a customer activity indicator
  • the cost indicator includes a marketing resource cost, an internal channel promotion cost, an external channel promotion cost, a business development cost, and a customer.
  • the indicators include the number of registered persons, the number of accounts opened, the sales indicators include the number of purchases, the order quantity and sales volume, and the customer activity indicators include the number of customer logins and the number of logins.
  • the pre-processing module 22 is configured to perform pre-processing on the activity data to perform dimensionless processing on the activity data, so that the activity has dimensionless characteristics.
  • the pre-processing includes the steps of: calculating an average value of the activity data during an activity;
  • the growth data is obtained by subtracting the average of the period during which the event is held from the average of the month prior to the event.
  • the collected daily indicators are subtracted from the daily average value of the previous month of the activity, and the growth data is obtained, and the data is sorted according to the basis.
  • activity A should be held once a month. Take Activity A as an example.
  • the daily average R11 and R22 of the number of accounts opened this month and last month are based on the daily average value R22 of the previous month and the daily average value R22 of the previous month.
  • the growth data (R11-R22) of this month is compared with the average daily value of the account opened last month.
  • the method of calculating the growth data is as described above. The method is similar. I will not repeat them here.
  • the scoring module 23 is configured to process the activity data using a pre-established activity quality assessment model to obtain an activity quality score of the activity and an activity quality score of other activities.
  • the activity quality assessment model is mainly used to process the pre-processed activity data to obtain an activity quality score
  • the functions of the activity quality assessment model include:
  • Performing data segmentation on the input data and corresponding to the basic score interval to form a base score for example, dividing the growth data R11-R22 into one hundred points, and correspondingly the base score is 0.01 to 1 minute;
  • the scoring weights are determined for the indicators participating in the scoring, each weight value is 0 to 1, and the weights are added to 1;
  • the display module 24 is configured to compare the activity quality score of the current activity with the activity quality score of other activities, output an evaluation result of the activity according to the comparison result, and display the activity on the bubble chart. Activity quality scores and activity quality scores for other activities.
  • the actual cost and important indicator value of the activity are collected (for example, one main purpose is to promote the activity of the transaction volume, and the important indicator value is the transaction amount during the activity period).
  • the activity scores, cost and important indicator values are marked as three output values on the bubble chart to visually compare the advantages and disadvantages between the activities at the same time; historical activities can also be introduced as a reference. It is also possible to fit an activity effect average line for each activity of the same period as a reference, and above and below the average line, it is higher than the average effect of the concurrent activities.
  • the marketing activity quality assessment system 2 can continuously update the quality sub-evaluation model to ensure that the evaluation effect is objective.
  • the new activity indicator values are included in all historical activities for sorting, and 100 percentiles are re-defined, and the interval values corresponding to each of the 0.01-1 individual scores. This standard can be presented to the event planner to quantitatively split the subsequent activity goals and properly control the activity process.
  • the embodiment further includes a standardization module 25 with respect to the first embodiment.
  • the normalization module 25 is configured to perform dimensionless processing on the activity data based on the first formula.
  • the common standardized dimensionless processing method includes the threshold method and the proportion. Law and standardization law, etc.
  • the first formula for preprocessing the activity data by the specific gravity method and using the specific gravity method to perform dimensionless processing on the activity is:
  • Step b is to perform dimensionless processing on each data for different characteristics of different types of data units, for example, the cost unit is a unit, the unit of the customer index is a number, and the number of units of the sales indicator is a number, etc., To avoid distortion due to different units in the calculation, it is necessary to standardize the data without dimensioning.
  • the present application also proposes a method for evaluating the quality of marketing activities.
  • FIG. 4 it is a schematic flowchart of the first embodiment of the quality assessment method for marketing activities of the present application.
  • the order of execution of the steps in the flowchart shown in FIG. 4 may be changed according to different requirements, and some steps may be omitted.
  • step S110 all activity data of the event and other activities in the database are acquired.
  • the acquired activity data includes an activity cost indicator, a customer indicator, a sales indicator, and a customer activity indicator
  • the cost indicator includes a marketing resource cost, an internal channel promotion cost, an external channel promotion cost, a business development cost, and a customer.
  • the indicators include the number of registered persons, the number of accounts opened, the sales indicators include the number of purchases, the order quantity and sales volume, and the customer activity indicators include the number of customer logins and the number of logins.
  • Step S120 preprocessing the activity data to standardize the activity data.
  • the collected daily indicators are subtracted from the daily average value of the previous month of the activity, and the growth data is obtained, and the data is sorted according to the basis.
  • activity A should be held once a month. Take Activity A as an example.
  • the daily average values R11 and R22 of the number of accounts opened this month and last month are based on the daily average value R22 of the previous month and the daily average value R22 of the previous month, and the growth data R11-R22 of this month is compared with the average daily opening value of the previous month.
  • the method of calculating the growth data is as described above. The method is similar. I will not repeat them here.
  • Step S130 the pre-established activity quality assessment model processes the activity data to obtain an activity quality score of the activity and an activity quality score of the other activities.
  • the activity quality assessment model can be composed of three aspects: data segmentation, determination of indicator weights, and score output.
  • the scoring weights are determined for the indicators participating in the scoring, each weight value is 0 to 1, and the weights of ownership are added to 1.
  • Score output Substitute the actual indicator value of each activity into each score interval to calculate the indicator base score, and multiply by the weight to get the comprehensive score.
  • the steps of obtaining the weights of the indicators include:
  • the activity indicators are X1, X2, X3, ..., Xi, and assume that the values normalized to each indicator data are Y1, Y2, ..., Yi;
  • the step of obtaining the activity quality score further includes:
  • the activity quality score is obtained by the following formula:
  • the activity quality assessment model may also be a three-layer structure model established based on the analytic hierarchy process, the activity quality assessment model includes three layers, the first layer is the activity quality effect, and the second layer is the cost indicator, and the customer is obtained.
  • the number of people, the number of accounts opened, the sales indicators include the number of purchases, order volume and sales volume.
  • the customer activity indicators include the number of customer logins and the number of logins.
  • Step S140 comparing the activity quality score of the current activity with the activity quality score of other activities, outputting the evaluation result of the activity according to the comparison result, and displaying the activity quality score of the activity on the bubble chart and Activity quality scores for other activities.
  • the actual cost and important indicator value of the activity are collected (for example, one main purpose is to promote the activity of the transaction volume, and the important indicator value is the transaction amount during the activity period).
  • the activity scores, cost and important indicator values are marked as three output values on the bubble chart to visually compare the advantages and disadvantages between the activities at the same time; historical activities can also be introduced as a reference. It is also possible to fit an activity effect average line for each activity of the same period as a reference, and above and below the average line, it is higher than the average effect of the concurrent activities.
  • step S210 of the marketing activity quality evaluation method, S230-S250 is similar to the steps S110-S140 of the first embodiment, except that the method further includes step S220.
  • the method includes the following steps:
  • step S210 all activity data of the event and other activities in the database are obtained.
  • Step S220 performing dimensionless processing on the activity data based on the first formula.
  • the common standardized dimensionless processing method includes the threshold method and the proportion. Law and standardization law, etc.
  • the first formula for preprocessing the activity data by the specific gravity method and using the specific gravity method to perform dimensionless processing on the activity is:
  • Step b is to perform dimensionless processing on each data for different characteristics of different types of data units, for example, the cost unit is a unit, the unit of the customer index is a number, and the number of units of the sales indicator is a number, etc., To avoid distortion due to different units in the calculation, it is necessary to standardize the data without dimensioning.
  • Step S230 preprocessing the activity data.
  • Step S240 the pre-established activity quality assessment model processes the activity data to obtain an activity quality score of the activity and an activity quality score of other activities.
  • Step S250 comparing the activity quality score of the current activity with the activity quality score of other activities, outputting the evaluation result of the activity according to the comparison result, and displaying the activity quality score of the activity on the bubble chart and Activity quality scores for other activities.
  • step S130 of the marketing activity quality assessment method and the activity quality assessment model in step S240 of the second embodiment to score the activity data includes the following steps:
  • step S310 the data is segmented.
  • the interval of each quantile point is corresponding to 0.01 to 1 minute.
  • step S320 the indicator weight is determined.
  • the scoring weights are determined for the indicators participating in the scoring, each weight value is 0 to 1, and the weights of ownership are added to 1.
  • the steps of obtaining the weights of the indicators include:
  • the activity indicators are X1, X2, X3, ..., Xi, and assume that the values normalized to each indicator data are Y1, Y2, ..., Yi;
  • step S330 the scores of the respective indicators are obtained by the following formula:
  • the activity quality score is obtained by the following formula:
  • the score is calculated and the score is output.
  • the marketing activity quality evaluation method, the server and the computer readable storage medium proposed by the present application first acquire all activity data of the event and the history activity, delineate the storage space, and all the activities described. Data is stored in the storage space; secondly, the activity data is pre-processed; then, the pre-established activity quality assessment model processes the pre-processed activity data to obtain an activity quality score; and finally, in the bubble chart Show the effect of the event and compare the activities.
  • the advantages and disadvantages of Internet marketing activities can be comprehensively and comprehensively evaluated.
  • the historical vertical and horizontal comparison of Internet marketing activities can clearly compare activities.
  • the effects of various aspects are conducive to improving the efficiency of marketing activities, providing direction and ideas for future event optimization and new event planning, which is more convenient, faster and more accurate than the prior art.
  • the foregoing embodiment method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be through hardware, but in many cases, the former is better.
  • Implementation Based on such understanding, the technical solution of the present application, which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM, disk,
  • the optical disc includes a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the methods described in various embodiments of the present application.

Landscapes

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

Abstract

本申请公开了一种营销活动质量评估方法，该方法包括：获取本次活动及数据库中其他活动的所有活动数据，对所述活动数据进行预处理，预先建立的活动质量评估模型对所述活动数据进行处理从而得到本次活动的活动质量评分及其他活动的活动质量评分，在气泡图上展示活动效果，进行活动间的对比。本申请还提供一种服务器及计算机可读存储介质。本申请提供的营销活动质量评估方法、服务器及计算机可读存储介质能够清楚地对比活动在各方面的效果，从而有利于提高营销活动的效率，为以后的活动优化、新活动策划提供方向和思路。

Description

营销活动质量评估方法、服务器及计算机可读存储介质
本申请要求于2018年4月13日提交中国专利局，申请号为201810331128.4、发明名称为“营销活动质量评估方法、服务器及计算机可读存储介质”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
本申请涉及数据分析技术领域，尤其涉及一种营销活动质量评估方法、服务器及计算机可读存储介质。
背景技术
随着互联网技术的蓬勃发展，不论是新型的互联网企业还是大多数的传统实体企业，开展互联网营销都是所有企业未来生存和发展的必要手段。互联网营销是指企业借助于联机网络、计算机通信和数字交互式媒体实现营销目标的一种营销方式。互联网营销具有成本低、效率高、传播广、效果好、实时性强等特性。但是，相对于传统营销活动来说，互联网营销活动的评估却面临很多问题，比如许多定性的指标、隐性的指标需要企业挖掘，而传统营销活动使用的投入产出比、市场规模、利润增长率等指标显然不够用，且如何自动实现互联网营销活动的历史纵向对比和同期横向对比也是一个迫切的需求。因此，如何综合地评估互联网营销活动的优劣，为以后的活动优化、新活动策划提供方向和思路成了当前一大急需解决的问题。
发明内容
有鉴于此，本申请提出一种营销活动质量评估方法、服务器及计算机可读存储介质，以解决如何综合评估互联网营销活动优劣的问题。
首先，为实现上述目的，本申请提出一种营销活动质量评估方法，该方法包括步骤：
获取本次活动及数据库中其他活动的活动数据，所述活动数据包括活动的成本指标、获客指标、销售指标及客户活跃指标；
基于第一公式对所述活动数据进行无量纲处理以对所述活动数据标准化，所述第一公式为：
Figure PCTCN2018123580-appb-000001
其中，Xi为标准化的所述活动数据，Yi为Xi标准化之后的值，
Figure PCTCN2018123580-appb-000002
表示多个待标准化值的求和；
预先建立的活动质量评估模型对标准化后的所述活动数据进行处理从而得到本次活动的活动质量评分及其他活动的活动质量评分；及
将所述本次活动的活动质量评分与其他活动的活动质量评分进行比较，根据比较结果输出所述活动的评估结果，并在气泡图上展示所述本次活动的活动质量评分与其他活动的活动质量评分。
计算所述活动举办前一个月的各项数据平均值；及
将所述活动举办期间的平均值与是所述活动举办前一个月的平均值相减获得增长数据。
此外，为实现上述目的，本申请还提供一种服务器，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营销活动质量评估***，所述营销活动质量评估***被所述处理器执行时实现如上述的营销活动质量评估方法的步骤。
进一步地，为实现上述目的，本申请还提供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营销活动质量评估***，所述营销活动质量评估***可被至少一个处理器执行，以使所述至少一个处理器执行如上述的营销活动质量评估方法的步骤。
相较于现有技术，本申请所提出的营销活动质量评估方法、服务器及计算机可读存储介质，首先获取本次活动及历史记录活动的所有活动数据，划定存储空间，将所述所有活动数据保存于所述存储空间；其次，对所述活动数据进行预处理；然后，预先建立的活动质量评估模型对预处理后的所述活动数据进行处理从而得到活动质量评分；最后，在气泡图上展示活动效果，进行活动间的对比。采用本申请所提出的营销活动质量评估方法、服务器及计算机可读存储介质可以全面、综合地评估互联网营销活动的优劣，对互联网营销活动的历史纵向和横向进行对比分析可以清楚地对比活动在各方面的效果，从而有利于提高营销活动的效率，为以后的活动优化、新活动策划提供方向和思路，相较于现有技术，更加方便、快捷、准确。
附图说明
图1是本申请服务器一可选的硬件架构的示意图；
图2是本申请营销活动质量评估***第一实施例的程序模块示意图；
图3是本申请营销活动质量评估***第二实施例的程序模块示意图；
图4是本申请营销活动质量评估方法第一实施例的流程示意图；
图5是本申请营销活动质量评估方法第二实施例的流程示意图；
图6是本申请营销活动质量评估方法第三实施例的流程示意图；
本申请目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。
具体实施方式
为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请进行进一步详细说明。应当理解，此处所描述的具体实施例仅用以解释本申请，并不用于限定本申请。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。
需要说明的是，在本申请中涉及“第一”、“第二”等的描述仅用于描述目的， 而不能理解为指示或暗示其相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征可以明示或者隐含地包括至少一个该特征。另外，各个实施例之间的技术方案可以相互结合，但是必须是以本领域普通技术人员能够实现为基础，当技术方案的结合出现相互矛盾或无法实现时应当认为这种技术方案的结合不存在，也不在本申请要求的保护范围之内。
参阅图1所示，是本申请服务器1一可选的硬件架构的示意图。
本实施例中，所述服务器1可包括，但不仅限于，可通过***总线相互通信连接存储器11、处理器12、网络接口13。需要指出的是，图1仅示出了具有组件11-13的服务器1，但是应理解的是，并不要求实施所有示出的组件，可以替代的实施更多或者更少的组件。
其中，所述服务器1可以是机架式服务器、刀片式服务器、塔式服务器或机柜式服务器等计算设备，该服务器1可以是独立的服务器，也可以是多个服务器所组成的服务器集群。
所述存储器11至少包括一种类型的可读存储介质，所述可读存储介质包括闪存、硬盘、多媒体卡、卡型存储器(例如，SD或DX存储器等)、随机访问存储器(RAM)、静态随机访问存储器(SRAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、可编程只读存储器(PROM)、磁性存储器、磁盘、光盘等。在一些实施例中，所述存储器11可以是所述服务器1的内部存储单元，例如该服务器1的硬盘或内存。在另一些实施例中，所述存储器11也可以是所述服务器1的外部存储设备，例如该服务器1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。当然，所述存储器11还可以既包括所述服务器1的内部存储单元也包括其外部存储设备。本实施例中，所述存储器11通常用于存储安装于所述服务器1的操作***和各类应用软件，例如营销活动质量评估***2的程序代码等。此外，所述存储器11还可以用于暂时地存储已经输出或者将要输出的各类数据。
所述处理器12在一些实施例中可以是中央处理器(Central Processing Unit，CPU)、控制器、微控制器、微处理器、或其他数据处理芯片。该处理器12通常用于控制所述服务器1的总体操作。本实施例中，所述处理器12用于运行所述存储器11中存储的程序代码或者处理数据，例如运行所述的营销活动质量评估***2等。
所述网络接口13可包括无线网络接口或有线网络接口，该网络接口13通常用于在所述服务器1与其他电子设备之间建立通信连接。
至此，己经详细介绍了本申请相关设备的硬件结构和功能。下面，将基于上述介绍提出本申请的各个实施例。
首先，本申请提出一种营销活动质量评估***2。
参阅图2所示，是本申请营销活动质量评估***2第一实施例的程序模块图。
本实施例中，所述营销活动质量评估***2包括一系列的存储于存储器11上的计算机程序指令，当该计算机程序指令被处理器12执行时，可以实现本申请各实施例的营销活动质量评估操作。在一些实施例中，基于该计算机程序指令各部分所实现的特定的操作，营销活动质量评估***2可以被划分为一个或多个模块。例如，在图3中，所述营销活动质量评估***2可以被分割成数据获取模块21、预处理模块22、评分模块23及显示模块24。其中：
所述数据获取模块21，用于获取本次活动及数据库中其他活动的所有活动数据。
具体地，为了比较这次本次活动与其他活动的效果，获取本次活动及其他活动的活动数据，其他活动包括与本次活动同时举办的活动及历史上举办的活动。
具体地，获取的活动数据包括活动的的成本指标、获客指标、销售指标及客户活跃指标，其中，成本指标包括营销资源成本、内部渠道推广成本、外部渠道推广成本、业务开发成本，获客指标包括注册人数、开户人数，销售指标包括购买人数、订单量和销量，客户活跃指标包括客户登录次数、登录人数。
所述预处理模块22，用于对所述活动数据进行预处理，以对所述活动数据进行无量纲的处理，使得所述活动具备无量纲的特性。
具体地，所述的预处理包括步骤：计算所述活动数据在活动期间的平均值；
计算所述活动举办前一个月的各项数据平均值；及
将所述活动举办期间的平均值与是所述活动举办前一个月的平均值相减获得增长数据。
具体地，将收集到的各个指标在活动期间的日均值与活动前一个月的日均值相减，得到增长数据，并对数据按照进行排序。例如，活动A每一个月要举办一次，以活动A开户人数为例，获取活动A本次活动举办后本月的开户人数R1及上个月活动开户人数R2，以R1及R2为基数分别求得本月以及上月开户人数的日均值R11、R22，以本月日均值R11及上月日均值R22为基数求得本月相对于上月开户日均值的增长数据(R11-R22)。进一步地，对于不同的活动A及活动B来说，只要他们举办的目的相同，比如说，都是以增加营业额、订单量、开户数等为目标，那么他们计算增长数据的方法就和前述的方法类似。在此不再赘述。
所述评分模块23，用于使用预先建立的活动质量评估模型对所述活动数据进行处理从而得到本次活动的活动质量评分及其他活动的活动质量评分。
具体地，所述活动质量评估模型主要用于对预处理后的所述活动数据进行处理从而得到活动质量评分，所述活动质量评估模型计算活动质量评分的步骤包括：将所述活动增长数据进行排序，根据排序后的所述活动增长数据 计算本次活动的活动质量评分及其他活动的活动质量评分。
具体地，可对所述活动数根据不同列别按照从大到小的顺序进行排序，例如将开户人数增长数据按照从大到小的顺序进行排序，将销售量增长数据按照从大到小的顺序进行排序。
通过特定方法对排序后的活动增长数据进行计算可以得到本次活动的活动质量评分及其他活动的活动质量评分，具体地，特定方法可以包括可对分类排序后的增长数据进行数据切分并对应到基础得分区间形成基础得分，例如，将前述的增长数据切分成一百分位点，并对应为基础得分0.01～1分。举例而言，若活动A、活动B、活动C及活动D的开户人数的增长数据分别为30、20、10、0，则对于开户人数值增长数据对应的百分位数分别为1、0.75、0.5、0.25，对应到0.01～1的分数区间其对应的基础得分分别为1、0.75、0.5、0.25。需要说明的是，采用百分位数法获得基础得分是将所有活动中的同类型数据进行百分位数的处理，例如，多个活动的开户人数，所有活动的业务开发成本，获取所有活动中同类型数据的百分位数之后，需要将各百分位数对应到[0.01,1]的区间以获得对应的基础得分。
具体地，特定方法还包括对不同的活动数据确定不同的权重，举例而言，按照实际业务场景，对参与评分的指标确定打分权重，各权重值为0～1，所有权重相加为1。
具体地，各指标权重的获取步骤包括：
获取各指标标准化后的活动数据，例如活动指标为X1，X2，X3，…，Xi，假设对各指标数据标准化后的值为Y1，Y2，…，Yi；
求各指标的信息熵:根据信息论中信息熵的定义,一组数据的信息熵:
E i＝-ln(n) -1∑p ilnp i，其中，P i＝Y i/∑Y i
确定各指标的权重:根据信息熵的计算公式,计算出各个指标的信息熵为E1，E2，…，Ek，权重为：Wi＝(1-Ei)/(k-∑Ei)，i＝1，2，…，k。
具体地，获得所述活动质量得分的步骤还包括：
通过以下公式获得各个指标的得分：
Pi＝Yi*Wi，i＝1,2,…，16
通过以下公式获得所述活动质量得分：
Figure PCTCN2018123580-appb-000003
具体地，特定方法还包括将各活动的实际指标值代入各个得分区间算出指标基础得分，再乘以权重加总得到综合得分。
所述显示模块24，将所述本次活动的活动质量评分与其他活动的活动质量评分进行比较，根据比较结果输出所述活动的评估结果，并在气泡图上展示所述本次活动的活动质量评分与其他活动的活动质量评分。
具体地，在得到活动综合得分之后，收集活动实际发生的成本和重要指标值(比如一个主要目的是促进交易量的活动，重要指标值就是活动期间交 易金额)。将活动分、成本和重要指标值作为三个输出值标记在气泡图上，直观地比较同时期各个活动之间的优劣之处；也可引入历史活动作为参考。并可以就同时期的各个活动拟合一条活动效果平均线作为参考，在平均线的上下就表示是否高于同期活动的平均效果。
进一步地，所述营销活动质量评估***2还可以不断迭代更新质量分评估模型，以保证评估效果客观。
具体地，将新的活动指标值纳入到历史所有活动当中进行排序，重新划定100个百分位数，以及各个0.01～1各个分值对应的区间值。可以将此标准展示给活动策划人，以便定量地拆分以后的活动目标，合理把控活动流程。
参阅图3所示，是本申请营销活动质量评估***2第二实施例的程序模块图。本实施例中，所述的营销活动质量评估***2除了包括第一实施例中的所述数据获取模块21、预处理模块22、评分模块23及显示模块24之外，还包括标准化模块25。
所述数据获取模块21，用于获取本次活动及数据库中其他活动的所有活动数据。
具体地，为了比较这次本次活动与其他活动的效果，获取本次活动及其他活动的活动数据，其他活动包括与本次活动同时举办的活动及历史上举办的活动。
具体地，获取的活动数据包括活动的的成本指标、获客指标、销售指标及客户活跃指标，其中，成本指标包括营销资源成本、内部渠道推广成本、外部渠道推广成本、业务开发成本，获客指标包括注册人数、开户人数，销售指标包括购买人数、订单量和销量，客户活跃指标包括客户登录次数、登录人数。
所述预处理模块22，用于对所述活动数据进行预处理，以对所述活动数据进行无量纲的处理，使得所述活动具备无量纲的特性。
具体地，所述的预处理包括步骤：计算所述活动数据在活动期间的平均值；
计算所述活动举办前一个月的各项数据平均值；及
将所述活动举办期间的平均值与是所述活动举办前一个月的平均值相减获得增长数据。
具体地，将收集到的各个指标在活动期间的日均值与活动前一个月的日均值相减，得到增长数据，并对数据按照进行排序。例如，活动A每一个月要举办一次，以活动A开户人数为例，获取活动A本次活动举办后本月的开户人数R1及上个月活动开户人数R2，以R1及R2为基数分别求得本月以及上月开户人数的日均值R11、R22，以本月日均值R11级上月日均值R22为基数求得本月相对于上月开户日均值的增长数据(R11-R22)。进一步地，对于不同的活动A及活动B来说，只要他们举办的目的相同，比如说，都是以增加营业额、订单量、开户数等为目标，那么他们计算增长数据的方法就和前述的方法类似。 在此不再赘述。
所述评分模块23，用于使用预先建立的活动质量评估模型对所述活动数据进行处理从而得到本次活动的活动质量评分及其他活动的活动质量评分。
具体地，所述活动质量评估模型主要用于对预处理后的所述活动数据进行处理从而得到活动质量评分，所述活动质量评估模型的功能包括：
对输入数据进行数据切分并对应到基础得分区间形成基础得分，例如，将增长数据R11-R22切分成一百分为点，并对应为基础得分0.01～1分；
对不同的活动数据确定不同的权重，举例而言，按照实际业务场景，对参与评分的指标确定打分权重，各权重值为0～1，所有权重相加为1；
将各活动的实际指标值代入各个得分区间算出指标基础得分，再乘以权重加总得到综合得分。
所述显示模块24，用于将所述本次活动的活动质量评分与其他活动的活动质量评分进行比较，根据比较结果输出所述活动的评估结果，并在气泡图上展示所述本次活动的活动质量评分与其他活动的活动质量评分。
具体地，在得到活动综合得分之后，收集活动实际发生的成本和重要指标值(比如一个主要目的是促进交易量的活动，重要指标值就是活动期间交易金额)。将活动分、成本和重要指标值作为三个输出值标记在气泡图上，直观地比较同时期各个活动之间的优劣之处；也可引入历史活动作为参考。并可以就同时期的各个活动拟合一条活动效果平均线作为参考，在平均线的上下就表示是否高于同期活动的平均效果。
进一步地，所述营销活动质量评估***2还可以不断迭代更新质量分评估模型，以保证评估效果客观。
具体地，将新的活动指标值纳入到历史所有活动当中进行排序，重新划定100个百分位数，以及各个0.01～1各个分值对应的区间值。可以将此标准展示给活动策划人，以便定量地拆分以后的活动目标，合理把控活动流程。
本实施例与第一实施例的区别在于，本实施例相对于第一实施例还包括标准化模块25。
所述标准化模块25，用于基于第一公式对所述活动数据进行无量纲处理。
具体地，由于所述活动数据的性质不同、计量单位不同，因此无法直接输入模型进行计算分析，所以需要对提取的原始数据进行标准化无量纲处理，常见的标准化无量纲处理方法包括阈值法、比重法和标准化法等。
采用比重法对所述活动数据进行预处理，采用比重法对所述活动进行无量纲处理的的第一公式为：
Figure PCTCN2018123580-appb-000004
其中，Yi为Xi标准化之后的值，
Figure PCTCN2018123580-appb-000005
表示多个待标准化值的求和。步骤b的作用在于，针对不同类型的数据单位不同的特点，对各数据进行无量纲处理，例如成本单位是元，获客指标单位是个数，销售指标中购买人数单位为个数等等，为了避免计算时因为单位不同结果失真，有必要先对数据进行标准化无量纲处理。
此外，本申请还提出一种营销活动质量评估方法。
参阅图4所示，是本申请营销活动质量评估方法第一实施例的流程示意图。在本实施例中，根据不同的需求，图4所示的流程图中的步骤的执行顺序可以改变，某些步骤可以省略。
步骤S110，获取本次活动及数据库中其他活动的所有活动数据。
具体地，获取的活动数据包括活动的的成本指标、获客指标、销售指标及客户活跃指标，其中，成本指标包括营销资源成本、内部渠道推广成本、外部渠道推广成本、业务开发成本，获客指标包括注册人数、开户人数，销售指标包括购买人数、订单量和销量，客户活跃指标包括客户登录次数、登录人数。
步骤S120，对所述活动数据进行预处理，以对所述活动数据标准化。
具体地，将收集到的各个指标在活动期间的日均值与活动前一个月的日均值相减，得到增长数据，并对数据按照进行排序。例如，活动A每一个月要举办一次，以活动A开户人数为例，获取活动A本次活动举办后本月的开户人数R1及上个月活动开户人数R2，以R1及R2为基数分别求得本月以及上月开户人数的日均值R11、R22，以本月日均值R11级上月日均值R22为基数求得本月相对于上月开户日均值的增长数据R11-R22。进一步地，对于不同的活动A及活动B来说，只要他们举办的目的相同，比如说，都是以增加营业额、订单量、开户数等为目标，那么他们计算增长数据的方法就和前述的方法类似。在此不再赘述。
步骤S130，预先建立的活动质量评估模型对所述活动数据进行处理从而得到本次活动的活动质量评分及其他活动的活动质量评分。
具体地，活动质量评估模型可由三个方面组成：数据切分、确定指标权重和得分输出。
数据切分：通过将前续步骤已经排序好的各个指标值切分成100个分位点，将各个分位点的区间对应到0.01～1分。
确定权重：按照实际业务场景，对参与评分的指标确定打分权重，各权重值为0～1，所有权重相加为1。
得分输出：将各活动的实际指标值代入各个得分区间算出指标基础得分，再乘以权重加总得到综合得分。
具体地，各指标权重的获取步骤包括：
获取各指标标准化后的活动数据，例如活动指标为X1，X2，X3，…，Xi，假设对各指标数据标准化后的值为Y1，Y2，…，Yi；
求各指标的信息熵:根据信息论中信息熵的定义,一组数据的信息熵:E i＝-ln(n) -1∑p ilnp i，其中，P i＝Y i/∑Y i
确定各指标的权重:根据信息熵的计算公式,计算出各个指标的信息熵为E1，E2，…，Ek，权重为：Wi＝(1-Ei)/(k-∑Ei)，i＝1，2，…，k。
具体地，获得所述活动质量得分的步骤还包括：
通过以下公式获得各个指标的得分：
Pi＝Yi*Wi，i＝1,2,…，16
通过以下公式获得所述活动质量得分：
Figure PCTCN2018123580-appb-000006
具体地，所述活动质量评估模型还可以是基于层次分析法建立的三层结构模型，所述活动质量评估模型包括三层，第一层为活动质量效果，第二层为成本指标、获客指标、销售指标及客户活跃指标，第三层为第二层个指标的具体指标，其中，成本指标包括营销资源成本、内部渠道推广成本、外部渠道推广成本、业务开发成本，获客指标包括注册人数、开户人数，销售指标包括购买人数、订单量和销量，客户活跃指标包括客户登录次数、登录人数。
步骤S140，将所述本次活动的活动质量评分与其他活动的活动质量评分进行比较，根据比较结果输出所述活动的评估结果，并在气泡图上展示所述本次活动的活动质量评分与其他活动的活动质量评分。
具体地，在得到活动综合得分之后，收集活动实际发生的成本和重要指标值(比如一个主要目的是促进交易量的活动，重要指标值就是活动期间交易金额)。将活动分、成本和重要指标值作为三个输出值标记在气泡图上，直观地比较同时期各个活动之间的优劣之处；也可引入历史活动作为参考。并可以就同时期的各个活动拟合一条活动效果平均线作为参考，在平均线的上下就表示是否高于同期活动的平均效果。
如图5所示，是本申请营销活动质量评估方法的第二实施例的流程示意图。本实施例中，所述营销活动质量评估方法的步骤S210，S230-S250与第一实施例的步骤S110-S140相类似，区别在于该方法还包括步骤S220。
该方法包括以下步骤：
步骤S210，获取本次活动及数据库中其他活动的所有活动数据。
步骤S220，基于第一公式对所述活动数据进行无量纲处理。
具体地，由于所述活动数据的性质不同、计量单位不同，因此无法直接输入模型进行计算分析，所以需要对提取的原始数据进行标准化无量纲处理，常见的标准化无量纲处理方法包括阈值法、比重法和标准化法等。
采用比重法对所述活动数据进行预处理，采用比重法对所述活动进行无量纲处理的的第一公式为：
Figure PCTCN2018123580-appb-000007
其中，Yi为Xi标准化之后的值，
Figure PCTCN2018123580-appb-000008
表示多个待标准化值的求和。步骤b的作用在于，针对不同类型的数据单位不同的特点，对各数据进行无量纲处理，例如成本单位是元，获客指标单位是个数，销售指标中购买人数单位为个数等等，为了避免计算时因为单位不同结果失真，有必要先对数据进行标准化无量纲处理。
步骤S230，对所述活动数据进行预处理。
步骤S240，预先建立的活动质量评估模型对所述活动数据进行处理从而得到本次活动的活动质量评分及其他活动的活动质量评分。
步骤S250，将所述本次活动的活动质量评分与其他活动的活动质量评分进行比较，根据比较结果输出所述活动的评估结果，并在气泡图上展示所述本次活动的活动质量评分与其他活动的活动质量评分。
如图6所示，是本申请营销活动质量评估方法的第三实施例的流程示意图。本实施例中，所述营销活动质量评估方法的步骤S130与第二实施例的步骤S240中所述活动质量评估模型对所述活动数据进行评分包括以下步骤：
步骤S310，数据切分。
具体地，通过将前续步骤已经排序好的各个指标值切分成100个分位点，将各个分位点的区间对应到0.01～1分。
步骤S320，确定指标权重。
具体地，按照实际业务场景，对参与评分的指标确定打分权重，各权重值为0～1，所有权重相加为1。
具体地，各指标权重的获取步骤包括：
获取各指标标准化后的活动数据，例如活动指标为X1，X2，X3，…，Xi，假设对各指标数据标准化后的值为Y1，Y2，…，Yi；
求各指标的信息熵:根据信息论中信息熵的定义,一组数据的信息熵:
E i＝-ln(n) -1∑p ilnp i，其中，P i＝Y i/∑Y i
确定各指标的权重:根据信息熵的计算公式,计算出各个指标的信息熵为E1，E2，…，Ek，权重为：Wi＝(1-Ei)/(k-∑Ei)，i＝1，2，…，k。
步骤S330，通过以下公式获得各个指标的得分：
Pi＝Yi*Wi，i＝1,2,…，16
通过以下公式获得所述活动质量得分：
Figure PCTCN2018123580-appb-000009
计算得分并将所述得分输出。
相较于现有技术，本申请所提出的营销活动质量评估方法、服务器及计算机可读存储介质，首先获取本次活动及历史记录活动的所有活动数据，划定存储空间，将所述所有活动数据保存于所述存储空间；其次，对所述活动数据进行预处理；然后，预先建立的活动质量评估模型对预处理后的所述活动数据进行处理从而得到活动质量评分；最后，在气泡图上展示活动效果，进行活动间的对比。采用本申请所提出的营销活动质量评估方法、服务器及计算机可读存储介质可以全面、综合地评估互联网营销活动的优劣，对互联网营销活动的历史纵向和横向进行对比分析可以清楚地对比活动在各方面的效果，从而有利于提高营销活动的效率，为以后的活动优化、新活动策划提 供方向和思路，相较于现有技术，更加方便、快捷、准确。
上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。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(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，空调器，或者网络设备等)执行本申请各个实施例所述的方法。
以上仅为本申请的优选实施例，并非因此限制本申请的专利范围，凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本申请的专利保护范围内。

Claims (20)

  1. 一种营销活动质量评估方法，应用于服务器，其特征在于，所述方法包括步骤：
    获取本次活动及数据库中其他活动的活动数据，所述活动数据包括活动的成本指标、获客指标、销售指标及客户活跃指标；
    基于第一公式对所述活动数据进行无量纲处理以对所述活动数据标准化，所述第一公式为：
    Figure PCTCN2018123580-appb-100001
    i＝1,2,…，16，其中，Xi为标准化的所述活动数据，Yi为Xi标准化之后的值，
    Figure PCTCN2018123580-appb-100002
    表示多个待标准化值的求和；
    预先建立的活动质量评估模型对标准化后的所述活动数据进行处理从而得到本次活动的活动质量评分及其他活动的活动质量评分；及
    将所述本次活动的活动质量评分与其他活动的活动质量评分进行比较，根据比较结果输出所述活动的评估结果，并在气泡图上展示所述本次活动的活动质量评分与其他活动的活动质量评分。
  2. 如权利要求1所述的营销活动质量评估方法，其特征在于，所述成本指标包括营销资源成本、内部渠道推广成本、外部渠道推广成本、业务开发成本，所述获客指标包括注册人数、开户人数，销售指标包括购买人数、订单量和销量，所述客户活跃指标包括客户登录次数、登录人数。
  3. 如权利要求2所述的营销活动质量评估方法，其特征在于，步骤“预先建立的活动质量评估模型对标准化后的所述活动数据进行处理从而得到本次活动的活动质量评分及其他活动的活动质量评分”包括：
    计算举办活动后的活动增长数据；及
    根据所述活动增长数据计算本次活动的活动质量评分及其他活动的活动质量评分。
  4. 如权利要求3所述的营销活动质量评估方法，其特征在于，计算所述活动增长数据包括步骤：
    计算所述活动数据在活动期间的平均值；
    计算所述活动举办前一个月的各项数据平均值；及
    将所述活动举办期间的平均值与是所述活动举办前一个月的平均值相减获得所述增长数据。
  5. 如权利要求4所述的营销活动质量评估方法，其特征在于，将所述增长数据中的同类增长数据进行从大到小的排序。
  6. 如权利要求5所述的营销活动质量评估方法，其特征在于，计算本次活动的活动质量评分及其他活动的活动质量评分包括以下步骤：
    数据切分，将所述同类增长数据切分为100个分位点以获得所述同类增长数据的百分位数，将所述同类增长数据的各百分位数对应到[0.01，1]的分数，将对应的分数作为基础得分；
    确定指标权重，采用信息熵法得到所述指标的权重；及
    将所述基础得分乘以所述权重得到单项得分，将各个所述单项得分加总得到本次活动的活动质量评分及其他活动的活动质量评分。
  7. 如权利要求6所述的营销活动质量评估方法，其特征在于，所述指标权重的获取步骤包括：
    获取各指标标准化后的活动数据，其中活动指标为X1，X2，X3…Xi，对各指标数据标准化后的值为Y1，Y2…Yi；
    根据第二公式求各指标的信息熵，所述第二公式为：
    E i＝-ln(n) -1∑p ilnp i，其中，P i＝Y i/∑Y i；及
    根据第三公式确定各指标的权重，所述第三公式为：
    Wi＝(1-Ei)/(k-∑Ei)，i＝1，2，…，k。
  8. 一种服务器，其特征在于，所述服务器包括存储器、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营销活动质量评估***，所述营销活动质量评估***被所述处理器执行时实现如下步骤：
    获取本次活动及数据库中其他活动的活动数据，所述活动数据包括活动的成本指标、获客指标、销售指标及客户活跃指标；
    基于第一公式对所述活动数据进行无量纲处理以对所述活动数据标准化，所述第一公式为：
    Figure PCTCN2018123580-appb-100003
    i＝1,2,…，16，其中，Xi为标准化的所述活动数据，Yi为Xi标准化之后的值，
    Figure PCTCN2018123580-appb-100004
    表示多个待标准化值的求和；
    预先建立的活动质量评估模型对标准化后的所述活动数据进行处理从而得到本次活动的活动质量评分及其他活动的活动质量评分；及
    将所述本次活动的活动质量评分与其他活动的活动质量评分进行比较，根据比较结果输出所述活动的评估结果，并在气泡图上展示所述本次活动的活动质量评分与其他活动的活动质量评分。
  9. 如权利要求8所述的服务器，其特征在于，所述成本指标包括营销资源成本、内部渠道推广成本、外部渠道推广成本、业务开发成本，所述获客指标包括注册人数、开户人数，销售指标包括购买人数、订单量和销量，所述客户活跃指标包括客户登录次数、登录人数。
  10. 如权利要求9所述的服务器，其特征在于，步骤“预先建立的活动质量评估模型对标准化后的所述活动数据进行处理从而得到本次活动的活动质量评分及其他活动的活动质量评分”包括：
    计算举办活动后的活动增长数据；及
    根据所述活动增长数据计算本次活动的活动质量评分及其他活动的活动质量评分。
  11. 如权利要求10所述的服务器，其特征在于，计算所述活动增长数据包括步骤：
    计算所述活动数据在活动期间的平均值；
    计算所述活动举办前一个月的各项数据平均值；及
    将所述活动举办期间的平均值与是所述活动举办前一个月的平均值相减 获得所述增长数据。
  12. 如权利要求11所述的服务器，其特征在于，将所述增长数据中的同类增长数据进行从大到小的排序。
  13. 如权利要求12所述的服务器，其特征在于，计算本次活动的活动质量评分及其他活动的活动质量评分包括以下步骤：
    数据切分，将所述同类增长数据切分为100个分位点以获得所述同类增长数据的百分位数，将所述同类增长数据的各百分位数对应到[0.01，1]的分数，将对应的分数作为基础得分；
    确定指标权重，采用信息熵法得到所述指标的权重；及
    将所述基础得分乘以所述权重得到单项得分，将各个所述单项得分加总得到本次活动的活动质量评分及其他活动的活动质量评分。
  14. 如权利要求13所述的服务器，其特征在于，所述指标权重的获取步骤包括：
    获取各指标标准化后的活动数据，其中活动指标为X1，X2，X3…Xi，对各指标数据标准化后的值为Y1，Y2…Yi；
    根据第二公式求各指标的信息熵，所述第二公式为：
    E i＝-ln(n) -1∑p ilnp i，其中，P i＝Y i/∑Y i；及
    根据第三公式确定各指标的权重，所述第三公式为：
    Wi＝(1-Ei)/(k-∑Ei)，i＝1，2，…，k。
  15. 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营销活动质量评估***，所述营销活动质量评估***可被至少一个处理器执行，以使所述至少一个处理器执行如下步骤：
    获取本次活动及数据库中其他活动的活动数据，所述活动数据包括活动的成本指标、获客指标、销售指标及客户活跃指标；
    基于第一公式对所述活动数据进行无量纲处理以对所述活动数据标准化，所述第一公式为：
    Figure PCTCN2018123580-appb-100005
    i＝1,2,…，16，其中，Xi为标准化的所述活动数据，Yi为Xi标准化之后的值，
    Figure PCTCN2018123580-appb-100006
    表示多个待标准化值的求和；
    预先建立的活动质量评估模型对标准化后的所述活动数据进行处理从而得到本次活动的活动质量评分及其他活动的活动质量评分；及
    将所述本次活动的活动质量评分与其他活动的活动质量评分进行比较，根据比较结果输出所述活动的评估结果，并在气泡图上展示所述本次活动的活动质量评分与其他活动的活动质量评分。
  16. 如权利要求15所述的计算机可读存储介质，其特征在于，所述成本指标包括营销资源成本、内部渠道推广成本、外部渠道推广成本、业务开发成本，所述获客指标包括注册人数、开户人数，销售指标包括购买人数、订单量和销量，所述客户活跃指标包括客户登录次数、登录人数。
  17. 如权利要求16所述的计算机可读存储介质，其特征在于，步骤“预先建立的活动质量评估模型对标准化后的所述活动数据进行处理从而得到本 次活动的活动质量评分及其他活动的活动质量评分”包括：
    计算举办活动后的活动增长数据；及
    根据所述活动增长数据计算本次活动的活动质量评分及其他活动的活动质量评分。
  18. 如权利要求17所述的计算机可读存储介质，其特征在于，计算所述活动增长数据包括步骤：
    计算所述活动数据在活动期间的平均值；
    计算所述活动举办前一个月的各项数据平均值；及
    将所述活动举办期间的平均值与是所述活动举办前一个月的平均值相减获得所述增长数据。
  19. 如权利要求18所述的计算机可读存储介质，其特征在于，将所述增长数据中的同类增长数据进行从大到小的排序；
    所述计算本次活动的活动质量评分及其他活动的活动质量评分包括以下步骤：
    数据切分，将所述同类增长数据切分为100个分位点以获得所述同类增长数据的百分位数，将所述同类增长数据的各百分位数对应到[0.01，1]的分数，将对应的分数作为基础得分；
    确定指标权重，采用信息熵法得到所述指标的权重；及
    将所述基础得分乘以所述权重得到单项得分，将各个所述单项得分加总得到本次活动的活动质量评分及其他活动的活动质量评分。
  20. 如权利要求19所述的计算机可读存储介质，其特征在于，所述指标权重的获取步骤包括：
    获取各指标标准化后的活动数据，其中活动指标为X1，X2，X3…Xi，对各指标数据标准化后的值为Y1，Y2…Yi；
    根据第二公式求各指标的信息熵，所述第二公式为：
    E i＝-ln(n) -1∑p ilnp i，其中，P i＝Y i/∑Y i；及
    根据第三公式确定各指标的权重，所述第三公式为：
    Wi＝(1-Ei)/(k-∑Ei)，i＝1，2，…，k。
PCT/CN2018/123580 2018-04-13 2018-12-25 营销活动质量评估方法、服务器及计算机可读存储介质 WO2019196502A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810331128.4 2018-04-13
CN201810331128.4A CN108805603A (zh) 2018-04-13 2018-04-13 营销活动质量评估方法、服务器及计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2019196502A1 true WO2019196502A1 (zh) 2019-10-17

Family

ID=64094252

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/123580 WO2019196502A1 (zh) 2018-04-13 2018-12-25 营销活动质量评估方法、服务器及计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN108805603A (zh)
WO (1) WO2019196502A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108805603A (zh) * 2018-04-13 2018-11-13 深圳壹账通智能科技有限公司 营销活动质量评估方法、服务器及计算机可读存储介质
CN115496545B (zh) * 2022-11-17 2023-04-07 北京名洋数字科技股份有限公司 线上展会数据分析方法、***及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20110100030A (ko) * 2010-03-03 2011-09-09 주식회사 이든앤앨리스마케팅 마케팅 효과측정 시스템, 방법 및 그 프로그램이 기록된 기록매체
CN106600007A (zh) * 2016-11-29 2017-04-26 上海亿账通互联网科技有限公司 活动质量评估方法及装置
CN106716472A (zh) * 2014-07-23 2017-05-24 通讯数字频道集团私人有限公司 用于运行营销活动的计算机实现方法和***
CN108805603A (zh) * 2018-04-13 2018-11-13 深圳壹账通智能科技有限公司 营销活动质量评估方法、服务器及计算机可读存储介质

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5429859B2 (ja) * 2009-04-28 2014-02-26 Ｋｄｄｉ株式会社 通信サービスのキャンペーン評価システム
US20160180383A1 (en) * 2014-12-23 2016-06-23 Teradata Us, Inc. Automatic customer attribute snapshot for predictive analysis
CN107403344A (zh) * 2017-08-03 2017-11-28 浙江极赢信息技术有限公司 一种互联网活动效果的分析方法及装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20110100030A (ko) * 2010-03-03 2011-09-09 주식회사 이든앤앨리스마케팅 마케팅 효과측정 시스템, 방법 및 그 프로그램이 기록된 기록매체
CN106716472A (zh) * 2014-07-23 2017-05-24 通讯数字频道集团私人有限公司 用于运行营销活动的计算机实现方法和***
CN106600007A (zh) * 2016-11-29 2017-04-26 上海亿账通互联网科技有限公司 活动质量评估方法及装置
CN108805603A (zh) * 2018-04-13 2018-11-13 深圳壹账通智能科技有限公司 营销活动质量评估方法、服务器及计算机可读存储介质

Also Published As

Publication number Publication date
CN108805603A (zh) 2018-11-13

Similar Documents

Publication Publication Date Title
WO2021174944A1 (zh) 基于目标对象活跃度的消息推送方法及相关设备
CN110837931A (zh) 客户流失预测方法、装置及存储介质
WO2018145586A1 (zh) 信用评分方法及服务器
CN109118094B (zh) 一种基于信用体系的企业服务应用***
CN115545516A (zh) 一种基于流程引擎的绩效数据处理方法、装置及***
WO2019196502A1 (zh) 营销活动质量评估方法、服务器及计算机可读存储介质
TW201503029A (zh) 計算企業拖欠帳款機率之技術
CN115545886A (zh) 逾期风险识别方法、装置、设备及存储介质
CN110197316B (zh) 运营数据的处理方法、装置、计算机可读介质及电子设备
CN117788115A (zh) 一种物品需求信息确定方法、装置、设备及存储介质
CN112950359A (zh) 一种用户识别方法和装置
CN117593115A (zh) 信贷风险评估模型的特征值确定方法、装置、设备和介质
CN111815435A (zh) 一种群体风险特征的可视化方法、装置、设备及存储介质
CN114398562B (zh) 一种店铺数据管理方法、装置、设备及存储介质
CN110717653A (zh) 风险识别方法及装置和电子设备
CN115034659A (zh) 一种数据源评估方法、装置、电子设备及存储介质
CN114298825A (zh) 还款积极度评估方法及装置
CN115619245A (zh) 一种基于数据降维方法的画像构建和分类方法及***
CN114626940A (zh) 数据分析方法、装置及电子设备
WO2021129368A1 (zh) 一种客户类型的确定方法及装置
CN110245775B (zh) 用户收支数据的分析方法、装置及计算机设备
CN113435746A (zh) 用户工作量的评分方法、装置、电子设备及存储介质
CN110852392A (zh) 一种用户分群方法、装置、设备和介质
TWI657393B (zh) 行銷客群預測系統及其方法
CN116166501B (zh) 一种日志校验方法、装置、电子设备及存储介质

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: 18914125

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 12/02/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 18914125

Country of ref document: EP

Kind code of ref document: A1