CN115879984A - Network marketing method and system based on big data analysis - Google Patents
Network marketing method and system based on big data analysis Download PDFInfo
- Publication number
- CN115879984A CN115879984A CN202310194066.8A CN202310194066A CN115879984A CN 115879984 A CN115879984 A CN 115879984A CN 202310194066 A CN202310194066 A CN 202310194066A CN 115879984 A CN115879984 A CN 115879984A
- Authority
- CN
- China
- Prior art keywords
- health degree
- online
- evaluation
- customers
- clients
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000007405 data analysis Methods 0.000 title claims abstract description 24
- 230000036541 health Effects 0.000 claims abstract description 328
- 238000011156 evaluation Methods 0.000 claims description 157
- 238000004458 analytical method Methods 0.000 claims description 35
- 238000012937 correction Methods 0.000 claims description 22
- 238000001514 detection method Methods 0.000 claims description 17
- 230000000694 effects Effects 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 230000008520 organization Effects 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000012517 data analytics Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 13
- 239000002131 composite material Substances 0.000 description 9
- 238000012423 maintenance Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005111 flow chemistry technique Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
Images
Abstract
The invention belongs to the technical field of network marketing, and particularly relates to a network marketing method and system based on big data analysis. The invention evaluates the health degree grade and the loss risk of the online customers by detecting the comprehensive health degree scores of the online customers, can accurately grasp the weight proportion of each health degree index required by the customers, and can correspondingly optimize and adjust the online customer service system according to the weight proportion of the health degree indexes, so that the optimized online customer service system can meet the requirements of the online customers, thereby not only effectively reducing the loss rate of the online customers, but also finishing the continuous optimization of the online customer service system.
Description
Technical Field
The invention belongs to the technical field of network marketing, and particularly relates to a network marketing method and system based on big data analysis.
Background
Marketing based on big data is an important field of big data application, marketing based on big data needs to analyze and process big data of massive clients, the marketing process is to screen target clients based on tags and then send specified contents to the target clients in a proper mode, clients of service enterprises are not limited to off-line clients, more and more on-line clients are needed, the clients can be communicated or solve problems by contacting service personnel in real time through a mobile terminal without going out, and palm operation is completed through various APP software, which is very convenient and fast, so that the clients of some service enterprises are increased rapidly, and the service personnel can not spend the same time on each client, therefore, in the process of continuously marketing and developing new clients, the problem of old client loss can be continuously generated due to negligence of service personnel and novel marketing modes of other same-industry enterprises, while conventionally developed on-line service systems for marketing can replace service personnel to complete some simple requirements, but do not necessarily meet the requirements of developed clients, and therefore, developed clients are easy to lose due to dissatisfaction of service industries or competition of other clients.
In the marketing process, except for a marketing mode, the method is a crucial link for maintenance of new and old customers and the marketing process, especially in the service industry, aiming at new customers, as the new customers are not familiar with a service system, the loss risk is large, marketing personnel or service personnel spend a large amount of time for maintenance, and aiming at enterprise customers who have long-term cooperation, only a small amount of time is needed for repeated communication and flow processing, so the health degree of the online customers is a decisive condition for determining the service system of the online customers, the personnel cost can be greatly reduced through the online service process, and further the marketing cost can be reduced.
Disclosure of Invention
The invention aims to provide a network marketing method and a network marketing system based on big data analysis, which can evaluate the health degree of online customers through the analysis of a plurality of evaluation indexes, further can enable developed customers to obtain better maintenance in the continuous marketing process, and can reduce the subsequent cost aiming at the developed customers.
The technical scheme adopted by the invention is as follows:
a network marketing method based on big data analysis comprises the following steps:
acquiring all online customer information, and classifying the online customer information into team customers and individual customers according to the organization form of all the online customer information;
acquiring health degree evaluation indexes of a plurality of online clients from the online client information;
obtaining a grading interval of the health degree evaluation index, and converting the health degree evaluation index into standardized digital data according to the grading interval to obtain index scores of all online customers;
acquiring the weight ratio of all health degree evaluation indexes;
inputting all the weight ratios and the index scores into a health degree analysis model to obtain a health degree comprehensive score of the online customer;
acquiring a standard evaluation interval, and judging the health degree grade and the loss risk of the online customer by combining the health degree comprehensive score;
according to the health degree of the online client, an evaluation period is constructed, the loss amount of the online client in the evaluation period and the health degree grade of the corresponding online client are counted, and a health degree deviation report is obtained;
adjusting the weight proportion of the health degree evaluation indexes according to the health degree deviation report, inputting the weight proportion to a health degree analysis model, and recalculating the health degree grades of all the online clients to obtain a health degree correction report;
and correcting the loss risks of all the online clients according to the health degree correction report, rechecking the satisfaction of the loss risks and the health degree grades of all the online clients in the next evaluation period until the loss risks and the health degree grades of all the online clients correspond to each other, and determining a health degree analysis model in the evaluation period as a standard detection model.
In a preferred embodiment, the plurality of health evaluation indexes at least include customer activity, customer satisfaction, customer online time, customer feedback, and product module usage.
In a preferred embodiment, the step of obtaining a classification section of the health degree evaluation index, and converting the health degree evaluation index into standardized numerical data according to the classification section to obtain index scores of all online customers includes:
acquiring health degree evaluation indexes of all online clients and a plurality of grading intervals of the health degree evaluation indexes;
constructing a plurality of index scores according to the number of the grading intervals, wherein the value range of the index scores is 1-100;
and comparing all the health degree evaluation indexes with the edge threshold of the grading interval one by one to obtain the index scores corresponding to all the online customers.
In a preferred embodiment, the step of inputting all the weight ratios and the index scores into the health degree analysis model to obtain a health degree comprehensive score of the online customer includes:
acquiring the weight ratio of all the health degree evaluation indexes and the index scores of all the online customers;
acquiring an objective function from the health degree analysis model;
and inputting the weight ratio and the index score into a target function together to obtain a comprehensive score of the health degree of all online customers, and sequencing all online customers from high to low according to the value of the comprehensive score.
In a preferred embodiment, the step of obtaining a standard evaluation interval and determining the health level and the loss risk of the online customer by combining the health comprehensive score includes:
obtaining a critical threshold value of a standard evaluation interval;
determining the health degree grade according to the standard evaluation interval;
comparing all the comprehensive health degree scores with a critical threshold value one by one to obtain the health degree grade of the client on the corresponding line;
and judging the loss risk of the corresponding online customer according to the health degree grade, wherein the lower the health degree grade is, the higher the loss risk of the online customer is.
In a preferred embodiment, the step of counting the loss of the online clients in the evaluation period and obtaining the health deviation report corresponding to the health grade of the online clients comprises:
acquiring the health degree grade of the lost customer in the evaluation period and the corresponding loss risk;
acquiring the total amount of lost customers under each health degree grade, and inputting the total amount into a health degree deviation model to obtain the health degree deviation of the lost customers;
and acquiring all the health degree deviation quantities, and summarizing the health degree deviation quantities into a health degree deviation report.
In a preferred embodiment, the step of adjusting the weight ratio of the health degree evaluation index according to the health degree deviation report includes:
all online clients inconsistent with the loss risk are obtained from the health degree deviation report and are calibrated as clients to be evaluated;
enumerating all health degree evaluation indexes of the clients to be evaluated;
arranging the index scores of the clients to be evaluated in a sequence from high to low;
and acquiring health degree evaluation indexes corresponding to the index scores, and adjusting the weight ratio of the corresponding health degree evaluation indexes according to the loss risk.
In a preferred embodiment, the step of correcting the churn risk of all online customers according to the health degree correction report and rechecking the churn risk and health degree level satisfaction of all online customers in the next evaluation period comprises:
acquiring the health degree grades and the loss risks of all online clients in an evaluation period in real time;
inputting the health degree grades and the loss risks of all online customers into a correction model for correction, and determining the weight ratio of each health degree evaluation index;
if the loss risk of the online clients does not correspond to the health degree grade in the next evaluation period, continuously adjusting the weight ratio of each health degree evaluation index, and recalculating the health degree grades and the loss risks of all the online clients;
and if the loss risk of all online customers in the next evaluation period corresponds to the health degree grade, determining the health degree analysis model in the evaluation period as a standard detection model.
The invention also provides a network marketing system based on big data analysis, which is applied to the network marketing method based on big data analysis, and comprises the following steps:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring all online customer information and classifying the online customer information into team customers and individual customers according to the organization forms of all the online customer information;
a second obtaining module, configured to obtain health degree evaluation indexes of a plurality of online clients from the online client information;
the data conversion module is used for acquiring a grading interval of the health degree evaluation index, and converting the health degree evaluation index into standardized digital data according to the grading interval to obtain index scores of all online customers;
the third acquisition module is used for acquiring the weight proportion of all the health degree evaluation indexes;
the health degree analysis module is used for inputting all the weight ratios and the index scores into a health degree analysis model to obtain a health degree comprehensive score of the online customer;
the judging module is used for acquiring a standard evaluation interval and judging the health degree grade and the loss risk of the online customer by combining the health degree comprehensive score;
the evaluation module is used for adjusting the weight proportion of the health degree evaluation indexes according to the health degree deviation report, inputting the weight proportion to a health degree analysis model, recalculating the health degree grades of all the online clients and obtaining a health degree correction report;
and the rechecking module is used for correcting the loss risks of all the online clients according to the health degree correction report, rechecking the loss risks and the health degree grades of all the online clients in the next evaluation period until the loss risks and the health degree grades of all the online clients correspond to each other, and determining the health degree analysis model in the evaluation period as a standard detection model.
And, a network marketing detection terminal based on big data analysis, including:
at least one processor;
and a memory communicatively coupled to the at least one processor;
wherein the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the big data analytics-based network marketing method described above.
The invention has the technical effects that:
in the process of network marketing, the invention evaluates the health degree grade and loss risk of the on-line customers by detecting the health degree comprehensive scores of the on-line customers aiming at the developed on-line customers, and can accurately grasp the weight proportion of each health degree index required by the customers, and the on-line customer service system can be correspondingly optimized and adjusted according to the weight proportion of the health degree indexes, thereby adjusting the marketing strategy, so that the optimized on-line customer service system can meet the requirements of the on-line customers, and further the loss rate of the on-line customers can be effectively reduced.
Drawings
FIG. 1 is a schematic flow chart of a method provided by an embodiment of the present invention;
fig. 2 is a schematic diagram of system modules provided by the embodiment of the invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced otherwise than as specifically described herein, and it will be appreciated by those skilled in the art that the present invention may be practiced without departing from the spirit and scope of the present invention and that the present invention is not limited by the specific embodiments disclosed below.
Furthermore, the references herein to "one embodiment" or "an embodiment" refer to a particular feature, structure, or characteristic that may be included in at least one implementation of the present invention. The appearances of the phrase "in one preferred embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
Referring to fig. 1 and fig. 2, the present invention provides a network marketing method based on big data analysis, including:
s1, obtaining all online customer information, and classifying the online customer information into team customers and individual customers according to the organization form of all online customer information;
s2, obtaining health degree evaluation indexes of a plurality of online clients from online client information, wherein the health degree evaluation indexes at least comprise client activity, client satisfaction, client online time, client feedback and product module utilization rate;
s3, obtaining a grading interval of the health degree evaluation index, and converting the health degree evaluation index into standardized digital data according to the grading interval to obtain index scores of all online customers;
s4, acquiring the weight ratio of all health degree evaluation indexes;
s5, inputting all the weight ratios and the index scores into a health degree analysis model to obtain a health degree comprehensive score of the online customer;
s6, acquiring a standard evaluation interval, and judging the health degree grade and the loss risk of the online customer by combining with the comprehensive score of the health degree;
s7, establishing an evaluation period according to the health degree of the online customer, and counting the loss amount of the online customer in the evaluation period and the health degree grade of the corresponding online customer to obtain a health degree deviation report;
s8, adjusting the weight proportion of the health degree evaluation indexes according to the health degree deviation report, inputting the weight proportion to a health degree analysis model, recalculating the health degree grades of all online clients, and obtaining a health degree correction report;
and S9, correcting the loss risks of all online clients according to the health degree correction report, rechecking the loss risks and health degree grade satisfaction of all online clients in the next evaluation period until the loss risks and health degree grades of all online clients correspond to each other, and determining the health degree analysis model in the evaluation period as a standard detection model.
As described in the above steps S1-S9, for the enterprise providing online service, besides realizing revenue in marketing new customers, the stability of online customers is also the main condition for realizing revenue, so it is necessary for detecting the health degree of the online customer service system, in this embodiment, online customers are first classified into team customers and individual customers, and then relevant health degree evaluation indexes are formulated according to the enterprise service, where the health degree evaluation indexes at least include customer activity, customer satisfaction, customer online time, customer feedback and product module usage rate, where the customer activity, customer online time and product module usage rate can all be evaluated by the online customer usage time, and the customer satisfaction and customer feedback can be obtained by random questionnaire or full questionnaire, in order to embody the health degree grade of the online customer conveniently, the embodiment sets corresponding grading intervals aiming at different health degree evaluation indexes so as to convert the health degree evaluation indexes into standardized digital data, and it is clear that when the health degree grade of the online customer is evaluated, the grading intervals of each health degree evaluation index are set to be the same, the index scores of all online customers can be obtained based on the grading intervals, then the service experience of service personnel in an enterprise is counted to set the weight proportion of each health degree evaluation index, the weight proportion is input into a health degree analysis model, so that the comprehensive health degree score of the online customer can be obtained, the health degree grade of the online customer is evaluated according to the corresponding evaluation interval, and the health degree grade and the loss risk of the online customer are in an inverse proportion relation, that is, the higher the health degree grade of the online customer is, the lower the loss risk is, in order to ensure the accuracy of the data, the corresponding evaluation period is constructed subsequently, the loss amount of the online customer in the rating period is collected, and the corresponding health degree grade and loss risk are analyzed to judge whether the lost customer meets the relationship between the preset health degree grade and loss risk, if the loss amount is not met, the weight proportion of the determined health degree evaluation index is not preferable, the weight proportion of each health degree evaluation index needs to be readjusted, so that a standard detection model meeting the health degree of the online customer can be gradually obtained by repeating the steps, and then the accurate health degree of the online customer can be obtained by detecting the index score of each health degree evaluation index of the online customer, so that the technical scheme provided by the embodiment can continuously perfect the detection result of the health degree of the online customer, for example, the online customer is classified into three gradients according to the comprehensive health score, the first gradient is a healthy customer, the second gradient is a sub-healthy customer, the third gradient is a risk customer, when the proportion of the healthy customer is set to 95%, the corresponding online customer service system is in a healthy state, when the proportion of the online customer health class to the healthy gradient is lower than 95%, the online customer service system needs to be optimized, when the optimization is specific, the online customer service system can be discussed through the feedback result of the online customer, the service staff submits opinions to optimize, the actual operation condition of the enterprise needs to be set, no clear limitation is performed, but when the proportion of the online customer health class to the healthy gradient is lower than 95%, enterprise managers can be reminded through generating alarm information, and the comprehensive health degree scores mentioned here are obtained based on the standard detection model, so that accurate data support can be provided for enterprises.
Based on the above, in the process of network marketing, aiming at developed online customers, the health degree grade and the loss risk of the online customers are evaluated by adopting a mode of detecting the health degree comprehensive scores of the online customers, so that the weight proportion of each health degree index required by the customers can be accurately grasped, and the online customer service system can be correspondingly optimized and adjusted according to the weight proportion of the health degree indexes, thereby adjusting the marketing strategy, so that the optimized online customer service system can meet the requirements of the online customers, further not only can the loss rate of the online customers be effectively reduced, but also the continuous optimization of the online customer service system can be completed.
In a preferred embodiment, the step of obtaining a classification interval of the health degree evaluation index, and converting the health degree evaluation index into standardized digital data according to the classification interval to obtain index scores of all online customers includes:
s301, acquiring health degree evaluation indexes of all online clients and a plurality of grading intervals of the health degree evaluation indexes;
s302, constructing a plurality of index scores according to the number of the grading intervals, wherein the value range of the index scores is 1-100;
and S303, comparing all the health degree evaluation indexes with the edge threshold value of the grading interval one by one to obtain the index scores corresponding to all online customers.
As described in the above steps S301 to S303, the number of the grading intervals of the multiple health degree evaluation indexes mentioned above may be inconsistent, but all online clients participating in the evaluation need to be evaluated based on the grading intervals, that is, the evaluation conditions of each online client are consistent, in this embodiment, the value range of the index score is set to be 1 to 100, and may be set according to specific situations, for example, 1 to 10, and so on, which is not described herein in too much detail, and taking the online duration (unit: minute) of the online client as an example, five grading intervals are set, respectively: (0, 200], (200, 400], (400, 600], (600, 800], (800, 1000], and the corresponding index scores are determined to be 20, 40, 60, 80, 100 in sequence, then the online time duration of the online client corresponds to the index score of (0, 200) being 20, the index score corresponding to (200, 400) being 40, the index score corresponding to (400, 600) being 60, the index score corresponding to (600, 800) being 80, and the index score corresponding to (800, 1000) being 100.
In a preferred embodiment, the step of inputting all the weight ratios and the index score into the health degree analysis model to obtain a comprehensive health degree score of the online customer comprises:
s501, acquiring the weight ratio of all health degree evaluation indexes and the index scores of all online customers;
s502, obtaining a target function from the health degree analysis model;
and S503, inputting the weight ratio and the index score into the objective function together to obtain a comprehensive score of the health degree of all online customers, and sequencing all online customers from high to low according to the value of the comprehensive score.
As described in the above steps S501 to S503, the objective function in the health degree analysis model is:
wherein Q represents a composite score for on-line customer health, n represents the total number of health evaluation indicators, and/or>
Represents the weight ratio of the health evaluation index in the interval 1-n, and/or>
The index scores of the online customers in the interval 1-n are shown, and based on the index scores, the comprehensive health score of the online customers participating in the evaluation can be obtained. />
In a preferred embodiment, the step of obtaining the standard evaluation interval and determining the health level and the loss risk of the online customer by combining the health comprehensive score comprises:
s601, obtaining a critical threshold value of a standard evaluation interval;
s602, determining the health degree grade according to the standard evaluation interval;
s603, comparing the comprehensive scores of all health degrees with a critical threshold one by one to obtain the health degree grade of the client on the corresponding line;
and S604, judging the loss risk of the corresponding online customer according to the health degree grade, wherein the lower the health degree grade is, the higher the loss risk of the online customer is.
As described in steps S601 to S604, after the health degree composite score of the online client is obtained, the health degree composite score is compared with the critical threshold of the standard evaluation interval, so that the evaluation interval of the health degree composite score can be determined, and accordingly, the health degree grade of the online client can be determined, where the evaluation interval is preset, for example, when the evaluation interval is set to (0, 20], (20, 40], (40, 60], (60, 80], (80, 100), and when the health degree composite score is set to (0, 20), the health degree grade of the online client is determined to be 1, and when the health degree composite score is set to (20, 40), the health degree grade of the online client is determined to be 2, when the health degree composite score is set to (40, 60), the health degree grade of the online client is determined to be 3, when the health degree composite score is set to (60, 80), the health degree grade of the online client is determined to be 4, when the health degree composite score is set to be (80, 100), the health grade of the online client is determined to be 5, and the corresponding risk of the online client is determined to be a loss, and the corresponding to be a low risk of the online client is determined to be a loss.
In a preferred embodiment, the step of statistically evaluating the amount of loss of the online customer within the period of the evaluation and obtaining a report of the deviation of health from the health rating of the online customer comprises:
s701, acquiring the health degree grade of the loss client in the evaluation period and the corresponding loss risk;
s702, acquiring the total amount of lost customers under each health degree grade, and inputting the total amount into a health degree deviation model to obtain the health degree deviation of the lost customers;
and S703, acquiring all health degree deviation quantities, and summarizing the health degree deviation quantities into a health degree deviation report.
As described in the above steps S701 to S703, after the lost customers in the evaluation period are counted, the health degree evaluation indexes of the lost customers are input into the health degree analysis model, so as to calculate the health degree comprehensive score of the lost customers, and accordingly, the health degree grades and the loss risks of the lost customers can be determined, and then the standard loss rates under different loss risks are obtained, for example, the loss rate of the risky customers is set to 70%, the loss rate of the sub-healthy customers is set to 20%, and the loss rate of the healthy customers is set to 5%, if the risky customers, the sub-healthy customers, and the healthy customers with the loss rates greater than the standard loss rate exist, that is, the weight ratio of the used health degree evaluation indexes has an error, and then the health degree deviation of the lost customers is calculated based on the health degree deviation model, wherein the standard function of the health degree deviation model is:
wherein P represents a health degree deviation amount,
represents the initial amount, based on the risk client, the sub-healthy client and the healthy client involved in the evaluation>
Indicates the remaining amount of at-risk clients, sub-healthy clients, and healthy clients who participate in the evaluation>
Indicating standard attrition rates for risk customers, sub-healthy customers, and healthy customers.
In a preferred embodiment, the step of adjusting the weight ratio of the health degree evaluation index according to the health degree deviation report includes:
s801, acquiring all online clients inconsistent with the loss risk from the health deviation report, and calibrating the online clients as clients to be evaluated;
s802, enumerating health degree evaluation indexes of all clients to be evaluated;
s803, arranging the index scores of the clients to be evaluated in a sequence from high to low;
s804, obtaining the health degree evaluation indexes corresponding to the scores of all indexes, and adjusting the weight ratio of the corresponding health degree evaluation indexes according to the loss risk.
As described in the above steps S801 to S804, after the health deviation report is obtained, the online customers exceeding the standard loss rate are extracted from the health deviation report and are calibrated as the customers to be evaluated, in the present embodiment, the health evaluation indexes of the customers to be evaluated are listed first, and then the health evaluation indexes of the customers to be evaluated are analyzed one by one, for example, the index scores of the customer online time length, the customer activity and the product module usage rate of a large number of customers to be evaluated are all 80, and the index scores of the customer satisfaction and the customer feedback are all 40, and the customers are all determined as sub-healthy customers, and the loss rate exceeds 20%, so that the weight ratio of the online time length, the customer activity and the product module usage rate of the online customers can be properly reduced, and the weight ratio of the customer satisfaction and the customer feedback is increased, which needs to be determined according to the discussion of the internal service staff of the enterprise, and is not clearly limited herein.
In a preferred embodiment, the step of calibrating the churning risk of all online customers according to the health degree calibration report and rechecking the churning risk and health degree level satisfaction of all online customers in the next evaluation period comprises:
s901, acquiring the health degree grades and the loss risks of all online customers in an evaluation period in real time;
s902, inputting the health degree grades and the loss risks of all online customers into a correction model for correction, and determining the weight ratio of each health degree evaluation index;
s903, if the loss risk of the online clients does not correspond to the health degree grade in the next evaluation period, continuously adjusting the weight ratio of each health degree evaluation index, and recalculating the health degree grades and the loss risks of all the online clients;
and S904, if the loss risk of all online customers in the next evaluation period corresponds to the health degree grade, determining the health degree analysis model in the evaluation period as a standard detection model.
As described in the above steps S901 to S904, after the weight ratios of the adjusted health degree evaluation indexes are obtained, the adjusted health degree evaluation indexes are input into the health degree analysis model again, the health degree comprehensive scores of all online customers in the current rating period are calculated, the loss risk and the health degree grade of all online customers are counted, then the health degree grades and the loss risks of the online customers in the next rating period are collected continuously, whether the loss risks of all online customers correspond to the health degree grades is judged, finally, the standard detection model is determined according to the judgment result, or the health degree grades and the loss risks of all online customers are recalculated.
The invention also provides a network marketing system based on big data analysis, which is applied to the network marketing method based on big data analysis, and comprises the following steps:
the first acquisition module is used for acquiring all online customer information and classifying the online customer information into team customers and individual customers according to the organization form of all the online customer information;
the second acquisition module is used for acquiring the health degree evaluation indexes of a plurality of online clients from the online client information;
the data conversion module is used for acquiring a grading interval of the health degree evaluation index, converting the health degree evaluation index into standardized digital data according to the grading interval and obtaining index scores of all online customers;
the third acquisition module is used for acquiring the weight ratio of all the health degree evaluation indexes;
the health degree analysis module is used for inputting all the weight ratios and the index scores into the health degree analysis model to obtain the comprehensive health degree score of the online customer;
the judging module is used for acquiring a standard evaluation interval and judging the health degree grade and the loss risk of the online customer by combining the health degree comprehensive score;
the evaluation module is used for adjusting the weight proportion of the health degree evaluation indexes according to the health degree deviation report, inputting the weight proportion into the health degree analysis model, recalculating the health degree grades of all online clients and obtaining a health degree correction report;
and the rechecking module is used for correcting the loss risks of all online clients according to the health degree correction report, rechecking the loss risks and health degree grades of all online clients in the next evaluation period until the loss risks and health degree grades of all online clients correspond to each other, and determining the health degree analysis model in the evaluation period as a standard detection model.
As described above, in the process of developing influence, the online customer information in the enterprise is collected into the data factory, and the online customer health degree is evaluated in the manner described above, the online customers in the data factory may also be divided into multiple groups, and simultaneously detected, and finally, multiple groups of results may be comprehensively analyzed, and of course, to ensure that the comprehensive health degree score of the online customer can be finally output, text data or experience data of the service staff inside the enterprise needs to be converted into standardized digital data by the data conversion module, and after the comprehensive health degree score is obtained, the evaluation module can be used to output the health degree grade and loss risk of the online customer.
And, a network marketing detection terminal based on big data analysis, including:
at least one processor;
and a memory communicatively coupled to the at least one processor;
wherein the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the above-mentioned big data analytics-based network marketing method.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of another identical element in a process, apparatus, article, or method comprising the element.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and amendments can be made without departing from the principle of the present invention, and these modifications and amendments should also be considered as the protection scope of the present invention. Structures, devices, and methods of operation not specifically described or illustrated herein are not specifically illustrated or described, but are instead contemplated to be practiced in the art by those skilled in the art.
Claims (10)
1. A network marketing method based on big data analysis is characterized in that: the method comprises the following steps:
acquiring all online customer information, and classifying the online customer information into team customers and individual customers according to the organization form of all the online customer information;
acquiring health degree evaluation indexes of a plurality of online clients from the online client information;
obtaining a grading interval of the health degree evaluation index, and converting the health degree evaluation index into standardized digital data according to the grading interval to obtain index scores of all online customers;
acquiring the weight ratio of all health degree evaluation indexes;
inputting all the weight ratios and the index scores into a health degree analysis model to obtain a health degree comprehensive score of the online customer;
acquiring a standard evaluation interval, and judging the health degree grade and the loss risk of the online customer by combining the health degree comprehensive score;
according to the health degree of the online client, an evaluation period is constructed, the loss amount of the online client in the evaluation period and the health degree grade of the corresponding online client are counted, and a health degree deviation report is obtained;
adjusting the weight proportion of the health degree evaluation indexes according to the health degree deviation report, inputting the weight proportion to a health degree analysis model, and recalculating the health degree grades of all the online clients to obtain a health degree correction report;
and correcting the loss risks of all the online clients according to the health degree correction report, rechecking the satisfaction of the loss risks and the health degree grades of all the online clients in the next evaluation period until the loss risks and the health degree grades of all the online clients correspond to each other, and determining a health degree analysis model in the evaluation period as a standard detection model.
2. The big data analysis-based network marketing method according to claim 1, wherein: the plurality of health degree evaluation indexes at least comprise customer activity, customer satisfaction, customer online time, customer feedback and product module utilization rate.
3. The big data analysis-based network marketing method according to claim 1, wherein: the step of obtaining the grading interval of the health degree evaluation index, converting the health degree evaluation index into standardized digital data according to the grading interval, and obtaining the index scores of all online customers comprises the following steps:
acquiring health degree evaluation indexes of all online clients and a plurality of grading intervals of the health degree evaluation indexes;
constructing a plurality of index scores according to the number of the grading intervals, wherein the value range of the index scores is 1-100;
and comparing all the health degree evaluation indexes with the edge threshold of the grading interval one by one to obtain the index scores corresponding to all the online customers.
4. The big data analysis-based network marketing method according to claim 3, wherein: the step of inputting all the weight ratios and the index scores into a health degree analysis model to obtain a comprehensive health degree score of the online customer includes:
acquiring the weight ratio of all the health degree evaluation indexes and the index scores of all the online customers;
acquiring an objective function from the health degree analysis model;
and inputting the weight ratio and the index score into a target function together to obtain a comprehensive score of the health degree of all online customers, and sequencing all online customers from high to low according to the value of the comprehensive score.
5. The big data analysis-based network marketing method according to claim 4, wherein: acquiring a standard evaluation interval, and determining the health degree grade and the loss risk of the online customer by combining the health degree comprehensive score, wherein the steps comprise:
obtaining a critical threshold value of a standard evaluation interval;
determining the health degree grade according to the standard evaluation interval;
comparing all the comprehensive health degree scores with a critical threshold value one by one to obtain the health degree grade of the client on the corresponding line;
and judging the loss risk of the corresponding online customer according to the health degree grade, wherein the lower the health degree grade is, the higher the loss risk of the online customer is.
6. The big data analysis-based network marketing method according to claim 5, wherein: the step of counting the loss of the online clients in the evaluation period and the health degree grade of the corresponding online clients to obtain a health degree deviation report comprises the following steps:
acquiring the health degree grade of the loss client in the evaluation period and the corresponding loss risk;
acquiring the total amount of lost customers under each health degree grade, and inputting the total amount into a health degree deviation model to obtain the health degree deviation of the lost customers;
and acquiring all the health degree deviation quantities, and summarizing the health degree deviation quantities into a health degree deviation report.
7. The big data analysis-based network marketing method according to claim 6, wherein: the step of adjusting the weight proportion of the health degree evaluation index according to the health degree deviation report includes:
acquiring all online clients inconsistent with the loss risk from the health degree deviation report, and calibrating the online clients as clients to be evaluated;
listing all health degree evaluation indexes of the clients to be evaluated;
arranging the index scores of the clients to be evaluated in a sequence from high to low;
and acquiring health degree evaluation indexes corresponding to the index scores, and adjusting the weight ratio of the corresponding health degree evaluation indexes according to the loss risk.
8. The big-data-analysis-based network marketing method according to claim 7, wherein: the step of correcting the loss risk of all the online clients according to the health degree correction report until the loss risk and the health degree grade of all the online clients meet a correction model, and determining the correction model as a standard detection model comprises the following steps:
acquiring the health degree grades and the loss risks of all online customers in an evaluation period in real time;
inputting the health degree grades and the loss risks of all online customers into a correction model for correction, and determining the weight ratio of each health degree evaluation index;
if the loss risk of the online clients does not correspond to the health degree grade in the next evaluation period, continuously adjusting the weight ratio of each health degree evaluation index, and recalculating the health degree grades and the loss risks of all online clients;
and if the loss risk of all online clients in the next evaluation period corresponds to the health degree grade, determining the health degree analysis model in the evaluation period as a standard detection model.
9. A big data analysis-based network marketing system applied to the big data analysis-based network marketing method of any one of claims 1 to 8, wherein: the method comprises the following steps:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring all online customer information and classifying the online customer information into team customers and individual customers according to the organization form of all the online customer information;
a second obtaining module, configured to obtain health degree evaluation indexes of a plurality of online clients from the online client information;
the data conversion module is used for acquiring a grading interval of the health degree evaluation index, and converting the health degree evaluation index into standardized digital data according to the grading interval to obtain index scores of all online customers;
the third acquisition module is used for acquiring the weight ratio of all the health degree evaluation indexes;
the health degree analysis module is used for inputting all the weight ratios and the index scores into a health degree analysis model to obtain a health degree comprehensive score of the online customer;
the judging module is used for acquiring a standard evaluation interval and judging the health degree grade and the loss risk of the online customer by combining the health degree comprehensive score;
the evaluation module is used for adjusting the weight proportion of the health degree evaluation indexes according to the health degree deviation report, inputting the weight proportion to a health degree analysis model, recalculating the health degree grades of all the online clients and obtaining a health degree correction report;
and the rechecking module is used for correcting the loss risks of all the online clients according to the health degree correction report, rechecking the loss risks and the health degree grades of all the online clients in the next evaluation period until the loss risks and the health degree grades of all the online clients correspond to each other, and determining the health degree analysis model in the evaluation period as a standard detection model.
10. A network marketing detection terminal based on big data analysis is characterized in that: the method comprises the following steps:
at least one processor;
and a memory communicatively coupled to the at least one processor;
wherein the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the big data analytics-based network marketing method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310194066.8A CN115879984A (en) | 2023-03-03 | 2023-03-03 | Network marketing method and system based on big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310194066.8A CN115879984A (en) | 2023-03-03 | 2023-03-03 | Network marketing method and system based on big data analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115879984A true CN115879984A (en) | 2023-03-31 |
Family
ID=85761851
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310194066.8A Pending CN115879984A (en) | 2023-03-03 | 2023-03-03 | Network marketing method and system based on big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115879984A (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022800A (en) * | 2016-05-16 | 2016-10-12 | 北京百分点信息科技有限公司 | User feature data processing method and device |
| CN106202216A (en) * | 2016-03-23 | 2016-12-07 | 四川长虹电器股份有限公司 | A kind of data processing method and data handling system |
| CN107292659A (en) * | 2017-05-20 | 2017-10-24 | 深圳市前海安测信息技术有限公司 | Health service topsis system and method based on concern amount and consumption number of times |
| WO2019104868A1 (en) * | 2017-11-30 | 2019-06-06 | 平安科技（深圳）有限公司 | Client risk level determining method, device and equipment, and readable storage medium |
| CN110245958A (en) * | 2019-01-14 | 2019-09-17 | 北京纷扬科技有限责任公司 | A kind of client intelligent scoring method and system based on crm system |
| CN110443678A (en) * | 2019-07-05 | 2019-11-12 | 亳州市青年电商产业园运营管理有限公司 | A kind of electric business information interaction system remotely controlled and method |
| CN110766481A (en) * | 2019-11-04 | 2020-02-07 | 泰康保险集团股份有限公司 | Client data processing method and device, electronic equipment and computer readable medium |
| CN110837931A (en) * | 2019-11-08 | 2020-02-25 | 中国农业银行股份有限公司 | Customer churn prediction method, device and storage medium |
| CN113298353A (en) * | 2021-04-28 | 2021-08-24 | 上海淇玥信息技术有限公司 | Resource adjusting method, device and system based on user survival model |
| CN113554448A (en) * | 2020-04-23 | 2021-10-26 | 支付宝实验室(新加坡)有限公司 | User loss prediction method and device and electronic equipment |
| CN114219668A (en) * | 2021-12-20 | 2022-03-22 | 盖小睿 | Method for improving loyalty of car insurance customers through big data accurate marketing |
| CN114298547A (en) * | 2021-12-28 | 2022-04-08 | 中电金信软件有限公司 | User loyalty scoring method, device, equipment and readable storage medium |
-
2023
- 2023-03-03 CN CN202310194066.8A patent/CN115879984A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106202216A (en) * | 2016-03-23 | 2016-12-07 | 四川长虹电器股份有限公司 | A kind of data processing method and data handling system |
| CN106022800A (en) * | 2016-05-16 | 2016-10-12 | 北京百分点信息科技有限公司 | User feature data processing method and device |
| CN107292659A (en) * | 2017-05-20 | 2017-10-24 | 深圳市前海安测信息技术有限公司 | Health service topsis system and method based on concern amount and consumption number of times |
| WO2019104868A1 (en) * | 2017-11-30 | 2019-06-06 | 平安科技（深圳）有限公司 | Client risk level determining method, device and equipment, and readable storage medium |
| CN110245958A (en) * | 2019-01-14 | 2019-09-17 | 北京纷扬科技有限责任公司 | A kind of client intelligent scoring method and system based on crm system |
| CN110443678A (en) * | 2019-07-05 | 2019-11-12 | 亳州市青年电商产业园运营管理有限公司 | A kind of electric business information interaction system remotely controlled and method |
| CN110766481A (en) * | 2019-11-04 | 2020-02-07 | 泰康保险集团股份有限公司 | Client data processing method and device, electronic equipment and computer readable medium |
| CN110837931A (en) * | 2019-11-08 | 2020-02-25 | 中国农业银行股份有限公司 | Customer churn prediction method, device and storage medium |
| CN113554448A (en) * | 2020-04-23 | 2021-10-26 | 支付宝实验室(新加坡)有限公司 | User loss prediction method and device and electronic equipment |
| CN113298353A (en) * | 2021-04-28 | 2021-08-24 | 上海淇玥信息技术有限公司 | Resource adjusting method, device and system based on user survival model |
| CN114219668A (en) * | 2021-12-20 | 2022-03-22 | 盖小睿 | Method for improving loyalty of car insurance customers through big data accurate marketing |
| CN114298547A (en) * | 2021-12-28 | 2022-04-08 | 中电金信软件有限公司 | User loyalty scoring method, device, equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106951984B (en) | Dynamic analysis and prediction method and device for system health degree | |
| Jacobs | Alternative methods to examine hospital efficiency: data envelopment analysis and stochastic frontier analysis | |
| Hajdu et al. | Sensitivity analysis in PERT networks: Does activity duration distribution matter? | |
| CN106682768B (en) | A kind of Forecasting Methodology, system, terminal and the server of answer fraction | |
| CN110196814B (en) | Software quality evaluation method | |
| CN106886481B (en) | Static analysis and prediction method and device for system health degree | |
| Apeland et al. | Risk based maintenance optimization: foundational issues | |
| CN116051037B (en) | Project progress supervision system based on data analysis | |
| CN103971023A (en) | Automatic quality evaluating system and method in research and development process | |
| CN115018384A (en) | Building site security risk assessment method and system | |
| Shores et al. | Pulling back the curtain: Intra-district school spending inequality and its correlates | |
| CN115098829A (en) | Online carbon emission analysis method based on multi-source metering data | |
| CN102468997A (en) | Method for assessing stability of safety index system of multidimension network | |
| Sower | Statistical process control for managers | |
| CN115879984A (en) | Network marketing method and system based on big data analysis | |
| CN106250993A (en) | A kind of measurement equipment metering cycle method of adjustment based on warship maintenance section | |
| RU2470352C1 (en) | Statistical process control method (versions) | |
| Kosgodagan et al. | Expert judgment in life-cycle degradation and maintenance modelling for steel bridges | |
| CN114638499A (en) | Public cultural efficiency assessment method based on hesitation fuzzy four-stage DEA | |
| Ramani et al. | Accounting for nonlinearity in the MCDM approach for a transportation planning application | |
| CN110766248A (en) | Workshop human factor reliability evaluation method based on SHEL and interval intuition fuzzy evaluation | |
| CN113962558A (en) | Industrial internet platform evaluation method and system based on production data management | |
| CN110363374A (en) | A kind of quantitative analysis method of substandard product influence factor | |
| RU99231U1 (en) | EQUIPMENT ASSESSMENT SYSTEM FOR EQUIPMENT | |
| Neil et al. | Benchmarking in pathology: development of a benchmarking complexity unit and associated key performance indicators |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230331 |
|
| RJ01 | Rejection of invention patent application after publication |