CN115271890A - Intelligent evaluation system for flow value of e-commerce platform - Google Patents
Intelligent evaluation system for flow value of e-commerce platform Download PDFInfo
- Publication number
- CN115271890A CN115271890A CN202211188022.6A CN202211188022A CN115271890A CN 115271890 A CN115271890 A CN 115271890A CN 202211188022 A CN202211188022 A CN 202211188022A CN 115271890 A CN115271890 A CN 115271890A
- Authority
- CN
- China
- Prior art keywords
- commerce platform
- index
- evaluation
- target
- distribution
- 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.)
- Granted
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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Educational Administration (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an intelligent evaluation system for the flow value of an e-commerce platform, which relates to the field of data processing and is characterized in that the intelligent evaluation system acquires the number of visitors, purchase conversion rate and platform operation cost of a target e-commerce platform in a preset time period; then, performing data operation to obtain an investment return rate ROI; meanwhile, carrying out multi-dimensional statistics on user behaviors of the target E-commerce platform to obtain the number, behaviors and quality index dimension statistical distribution; weighting and calculating fine grain dimension indexes in each statistical distribution in sequence, and calculating to obtain user participation scores in a preset time period; taking the user participation grade as an x axis of an abscissa and the investment return rate ROI as a y axis of an ordinate, and drawing a multi-channel flow value evaluation matrix diagram; and carrying out visual flow value evaluation on the target e-commerce platform. The method solves the technical problems that the value evaluation result of the e-commerce platform is single and the universality is poor.
Description
Technical Field
The invention relates to the field of data processing, in particular to an intelligent evaluation system for the flow value of an e-commerce platform.
Background
With the development of science and technology and the progress of the era, the living standard of people is continuously improved, the living pace is gradually accelerated, and more consumers are gradually used to online shopping; more and more enterprises open markets on the network and establish a network marketing e-commerce platform. In the operation process of the e-commerce platform, the sales performance of an enterprise is improved by improving the click rate and the purchase rate of a user entering a website; the higher the click rate of the user is, the higher the flow of the enterprise e-commerce platform is, which means that the enterprise sales performance is correspondingly improved. Therefore, the e-commerce platform traffic becomes an important index for enterprise operation health evaluation, and thus traffic statistics and analysis are particularly important for the healthy operation of the e-commerce platform.
However, in the prior art, when the traffic value of the e-commerce platform is evaluated, the traffic value is evaluated only by single user participation, and the return on investment of each channel in the e-commerce platform cannot be comprehensively referred, so that the obtained value evaluation result is single and the universality is poor.
Disclosure of Invention
The application provides an intelligent evaluation system for the e-commerce platform flow value, which is used for solving the technical problems that when the e-commerce platform is subjected to flow value evaluation, the flow value evaluation is carried out only by means of single user participation degree, the investment return rate of each channel in the e-commerce platform cannot be comprehensively referred to, the obtained value evaluation result is single, and the universality is lacked. The method achieves the technical effects of integrating the user participation and the return on investment of each operation channel in the e-commerce platform, and performing bidirectional index evaluation on the flow value of the e-commerce platform, so that the value evaluation result is accurate and universal.
In view of the above problems, the present application provides an intelligent evaluation system for the e-commerce platform traffic value.
In a first aspect, the embodiment of the application provides an intelligent evaluation method for the flow value of an e-commerce platform, which acquires the number of visitors, purchase conversion rate and platform operation cost of a target e-commerce platform in a preset time period; obtaining the investment return rate ROI of the target e-commerce platform by performing data operation on the visitor quantity, the purchase conversion rate and the platform operation cost; carrying out multi-dimensional statistics on the user behaviors of the target e-commerce platform in the preset time period to obtain quantity index dimension statistical distribution, behavior index dimension statistical distribution and quality index dimension statistical distribution; sequentially performing weighting and operation on each fine grain dimension index in each statistical distribution through the number index dimension statistical distribution, the behavior index dimension statistical distribution and the quality index dimension statistical distribution, and calculating to obtain a user participation score in the preset time period; drawing a multi-channel flow value evaluation matrix diagram of the target e-commerce platform by taking the user participation grade as an x axis of an abscissa and the investment return rate ROI as a y axis of an ordinate; and carrying out visual flow value evaluation on the target e-commerce platform based on the multi-channel flow value evaluation matrix diagram.
In a second aspect, an embodiment of the present application provides an intelligent evaluation system for e-commerce platform traffic value, where the system includes: the data acquisition module is used for acquiring the number of visitors, the purchase conversion rate and the platform operation cost of the target e-commerce platform in a preset time period; the data operation module is used for performing data operation on the number of the visitors, the purchase conversion rate and the platform operation cost to obtain the return on investment rate ROI of the target E-commerce platform; the dimension statistical module is used for carrying out multi-dimensional statistics on the user behaviors of the target e-commerce platform in the preset time period to obtain quantity index dimension statistical distribution, behavior index dimension statistical distribution and quality index dimension statistical distribution; the weighting calculation module is used for sequentially weighting and calculating fine grain dimension indexes in each statistical distribution through the number index dimension statistical distribution, the behavior index dimension statistical distribution and the quality index dimension statistical distribution, and calculating user participation scores in the preset time period; the matrix drawing module is used for drawing a multi-channel flow value evaluation matrix chart of the target e-commerce platform by taking the user participation grade as an x axis of an abscissa and the investment return rate ROI as a y axis of an ordinate; and the value evaluation module is used for carrying out visual flow value evaluation on the target e-commerce platform based on the multi-channel flow value evaluation matrix diagram.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
the method comprises the steps of collecting the number of visitors, the purchase conversion rate and the platform operation cost of a target e-commerce platform in a preset time period; then, performing data operation to obtain an investment return rate ROI; meanwhile, carrying out multi-dimensional statistics on user behaviors of the target e-commerce platform to obtain the number, behavior and quality index dimension statistical distribution; weighting and calculating fine grain dimension indexes in each statistical distribution in sequence to calculate user participation scores in a preset time period; taking the user participation grade as an x axis of an abscissa and the investment return rate ROI as a y axis of an ordinate, and drawing a multi-channel flow value evaluation matrix diagram; and carrying out visual flow value evaluation on the target e-commerce platform. The method and the device solve the technical problems that when the e-commerce platform is subjected to flow value evaluation, the flow value evaluation is carried out only by means of single user participation, the investment return rate of each channel in the e-commerce platform cannot be comprehensively referred, and the obtained value evaluation result is single and lacks universality. The method achieves the technical effects of integrating the user participation and the return on investment of each operation channel in the e-commerce platform, and performing bidirectional index evaluation on the flow value of the e-commerce platform, so that the value evaluation result is accurate and universal.
Drawings
Fig. 1 is a schematic flow chart of an intelligent evaluation method for flow value of an e-commerce platform provided in the present application;
fig. 2 is a schematic flow chart illustrating the process of sequentially performing weighting and operation on each fine-grain dimension index in each statistical distribution in the intelligent evaluation method for the flow value of the e-commerce platform provided by the present application;
fig. 3 is a schematic flow chart illustrating the process of obtaining the user engagement score in the intelligent evaluation method for the e-commerce platform traffic value provided in the present application;
fig. 4 is a schematic flow chart illustrating a multi-channel flow value evaluation matrix chart of the target e-commerce platform in the intelligent evaluation method for the e-commerce platform flow value provided in the present application;
fig. 5 is a schematic structural diagram of an intelligent evaluation system for flow value of an e-commerce platform according to the present application.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The application provides an intelligent evaluation system for the flow value of an e-commerce platform, which is characterized in that the number of visitors, purchase conversion rate and platform operation cost of a target e-commerce platform in a preset time period are collected; then, performing data operation to obtain an investment return rate ROI; meanwhile, carrying out multi-dimensional statistics on user behaviors of the target e-commerce platform to obtain the number, behavior and quality index dimension statistical distribution; weighting and calculating fine grain dimension indexes in each statistical distribution in sequence, and calculating to obtain user participation scores in a preset time period; taking the user participation grade as an x axis of an abscissa and the investment return rate ROI as a y axis of an ordinate, and drawing a multi-channel flow value evaluation matrix diagram; and carrying out visual flow value evaluation on the target E-commerce platform.
Example one
As shown in fig. 1, the present application provides an intelligent evaluation method for the flow value of an e-commerce platform, the method includes:
step S100: acquiring the number of visitors, purchase conversion rate and platform operation cost of a target e-commerce platform in a preset time period;
step S200: obtaining the investment return rate ROI of the target e-commerce platform by performing data operation on the visitor quantity, the purchase conversion rate and the platform operation cost;
further, step S200 includes:
step S210: using the formula: calculating the cost of the channel and the ROI = (visitor number conversion rate passenger unit price), and calculating the return on investment rate ROI of the target e-commerce platform;
the ROI is the return on investment of the target e-commerce platform, the number of visitors is the number of visitors of the target e-commerce platform in the preset time period, the conversion rate is the conversion rate of whether goods of a user are purchased or not on the target e-commerce platform, the customer price is the unit price of the goods purchased by the user on the target e-commerce platform, and the channel cost reflects the multi-channel consumption cost of the goods for flow promotion on the target e-commerce platform.
Specifically, the intelligent evaluation method for the e-commerce platform flow value performs two-way index evaluation on the e-commerce platform flow value by integrating two indexes, namely user participation and return on investment of each operation channel in the e-commerce platform, so that the value evaluation result is accurate and universal. The enterprise electronic commerce platform is a management environment which establishes a virtual network space for carrying out business activities on the Internet and ensures the smooth operation of business; the system is an important place for coordinating and integrating information flow, cargo flow and fund flow in order, relevance and high-efficiency flow. Enterprises and merchants can make full use of shared resources such as network infrastructure, payment platform, security platform, management platform and the like provided by the electronic commerce platform to effectively develop their own commercial activities at low cost. The target e-commerce platform is understood to be any goods marketing platform with online transaction property, such as Taobao, jingdong, etc., which are not specifically set herein.
In addition, when the flow value of the e-commerce platform is evaluated, a certain time period is required in the goods transaction process, so that data acquisition needs to be performed through the certain time period, and the time period required in the goods transaction process and the later settlement process of the platform can be understood within the preset time period. The visitor number is the number of the users accessing the E-commerce platform, and can reflect the flow scale of the users; the purchase conversion rate is the process that the user has interactive behavior and browsing record on the access platform and purchases the interactively browsed goods, and the conversion rate reflects the conversion condition; the platform operation cost is the cost spent on the flow promotion of goods to be sold by the platform in the earlier stage. Further, the formula can be utilized: and calculating the ROI (number of visitors, conversion rate and passenger unit price)/channel cost to obtain the investment return rate ROI of the target E-commerce platform. Wherein, ROI refers to the return on investment of a flow channel, namely the commodity sales amount brought by buying amount in a certain channel and putting in one piece of money. The ROI is a very important index, and can simultaneously reflect three factors of user traffic size, user conversion and user income. Meanwhile, the visitor number is the visitor number of the target e-commerce platform in the preset time period, the conversion rate is the conversion rate of whether the goods of the user are purchased or not on the target e-commerce platform, the customer price is the price of the goods purchased by the user on the target e-commerce platform, and the channel cost reflects the multi-channel consumption cost of the goods for flow promotion on the target e-commerce platform.
Step S300: carrying out multi-dimensional statistics on the user behaviors of the target e-commerce platform in the preset time period to obtain quantity index dimension statistical distribution, behavior index dimension statistical distribution and quality index dimension statistical distribution;
step S400: sequentially performing weighting and operation on each fine grain dimension index in each statistical distribution through the number index dimension statistical distribution, the behavior index dimension statistical distribution and the quality index dimension statistical distribution, and calculating to obtain a user participation score in the preset time period;
further, as shown in fig. 2, step S400 includes:
step S410: performing multi-fine-granularity splitting on the statistical distribution of the behavior index dimension to obtain a multi-behavior fine-granularity index;
step S420: performing multi-fine-granularity resolution on the quality index dimension statistical distribution to obtain multi-quality fine-granularity indexes;
step S430: drawing a behavior characteristic radar chart based on the multi-behavior fine granularity index, and drawing a quality characteristic radar chart based on the multi-quality fine granularity index;
step S440: marking the number index dimension statistical distribution as a primary index U1, the behavior index dimension statistical distribution as a primary index U2 and the quality index dimension statistical distribution as a primary index U3;
step S450: and respectively carrying out weight distribution on the primary indexes U1, the primary indexes U2 and the primary indexes U3 by using weight distribution channels to obtain corresponding primary weights Q1, Q2 and Q3.
Further, as shown in fig. 3, step S400 further includes step S460:
step S461: performing data distribution analysis of the multi-behavior fine-grained indexes on the behavior characteristic radar chart to obtain multi-behavior fine-grained data distribution;
step S462: performing weight distribution on the multi-row fine-grained data distribution to obtain Q21, Q22, Q23 to Q2n under the weight distribution of the primary weight Q2;
step S463: performing data distribution analysis of the multi-quality fine-grained indexes on the quality characteristic radar map to obtain multi-quality fine-grained data distribution;
step S464: performing weight distribution on the multi-quality fine-grained data distribution to obtain Q31, Q32, Q33 and Q3n under the weight distribution of the primary weight Q3;
step S465: and performing weight summation operation on the user behavior acquisition data of the target e-commerce platform by using the primary weight Q1, Q21, Q22, Q23 to Q2n under the weight distribution of the primary weight Q2 and Q31, Q32, Q33 to Q3n under the weight distribution of the primary weight Q3 to obtain the user participation score.
Specifically, after the return on investment ROI of the e-commerce platform is obtained, the user engagement score of the e-commerce platform needs to be calculated. The user participation reflects the behavior of the user on the e-commerce platform, and can be classified into a quantity index, a behavior index and a quality index, wherein the quantity index dimension statistical distribution reflects the statistical distribution corresponding to the quantity index, the behavior index dimension statistical distribution reflects the statistical distribution corresponding to the behavior index, and the quality index dimension statistical distribution reflects the statistical distribution corresponding to the quality index. The quantity index reflects the number of access users of the platform and the access times of a single user; the behavior indexes comprise a series of operations of sharing, collecting, adding a shopping cart, searching keywords, submitting orders, paying, completing transactions, evaluating and the like of a certain user based on the E-commerce platform; the quality indexes comprise fine-grained indexes such as arrival rate, hop rate, page stay time, browsing depth, access frequency, previous access time and retention rate of a certain user to common indexes based on the E-commerce platform, the indexes reflect the participation of the user from different aspects and need to be combined together, the hop rate is the common index for measuring the retention of the user, the higher the hop rate is, the more serious the user loss is, but if the user enters a page, the content in the page is very interesting, the stay time is long, but if the user does not enter the next operation, the page background displays the user to jump out, at the moment, if the user is measured by the hop rate, an error conclusion of losing the user is generated, and if the page stay time index is combined, the evaluation result is more objective. Based on the above, the indexes should be put together to form a comprehensive index engage, i.e. user participation, reflecting the sum of user behaviors, and used for measuring the interaction degree of the visitor and the platform.
From the above, the quantity index, the behavior index and the quality index all have more fine-grained dimension indexes, that is, the quality index includes various fine-grained indexes such as the arrival rate, the hop rate, the page retention time, the browsing depth, the access frequency, the time from the last access and the retention rate of a certain user to the common indexes based on the e-commerce platform. And weighting and calculating the fine particle dimension indexes in the statistical distributions to obtain the user participation grade in the preset time period, wherein the user participation grade comprehensively reflects the participation grade result of the user on the e-commerce platform.
Specifically, when the fine-grained dimension indexes are weighted, multi-fine-grained division can be performed on the behavior index dimension statistical distribution, and multi-behavior fine-grained indexes can be obtained, wherein the multi-behavior fine-grained indexes cover fine-grained indexes such as sharing, collection, shopping cart addition, keyword search, order submission, payment, transaction completion, evaluation and the like. And meanwhile, carrying out multi-fine-granularity splitting on the quality index dimension statistical distribution to obtain multi-quality fine-granularity indexes, wherein the multi-quality fine-granularity indexes cover fine-granularity indexes such as arrival rate, hop rate, page dwell time, browsing depth, access frequency, last access time and retention rate. Furthermore, a behavior characteristic radar chart may be drawn based on the multi-behavior fine-grained index, and a quality characteristic radar chart may be drawn based on the multi-quality fine-grained index, where the behavior characteristic radar chart reflects actual behavior data distribution of each behavior fine-grained index, and the quality characteristic radar chart reflects actual quality data distribution of each quality fine-grained index.
Before weighting each fine-grained index, the quantity index, the behavior index and the quality index of the upper level can be weighted. Specifically, the quantity index dimension statistical distribution flag may be a first-level index U1, the behavior index dimension statistical distribution flag may be a first-level index U2, the quality index dimension statistical distribution flag may be a first-level index U3, the first-level index U1, the first-level index U2, and the first-level index U3 are parallel first-level indexes, and further, weight distribution channels are used to respectively perform weight distribution on the first-level index U1, the first-level index U2, and the first-level index U3, so as to obtain a corresponding first-level weight Q1, a corresponding first-level weight Q2, and a corresponding first-level weight Q3. The weight distribution channel comprises three weight distribution sub-channels, and corresponding first-level weight Q1, first-level weight Q2 and first-level weight Q3 can be obtained by inputting first-level index U1 into a first sub-channel, first-level index U2 into a second sub-channel and first-level index U3 into a third sub-channel respectively and performing weight distribution training, wherein the first-level weight Q1 reflects the influence weight proportion of the quantity index to the user participation, the first-level weight Q2 reflects the influence weight proportion of the behavior index to the user participation, and the first-level weight Q3 reflects the influence weight proportion of the quality index to the user participation.
After the number index, the behavior index and the quality index of the previous level are weighted, fine weighting can be carried out on each fine-grained index under each level of the first level index. Specifically, firstly, data distribution analysis of multiple behavior fine-grained indexes can be performed on the behavior feature radar map, and multiple behavior fine-grained data distribution can be obtained, wherein the multiple behavior fine-grained data distribution reflects actual distribution of sharing data, collecting data, shopping cart adding data, keyword searching data, order submitting data, payment data, transaction completing data, evaluation data and the like of a user on the behavior feature radar map, and effective weight conversion can be performed on the distance distribution by traversing distances from the actual fine-grained feature distribution data to a radar map center point, so that Q21, Q22, Q23 and Q2n under the weight distribution of the first-level weight Q2 can be obtained, exemplarily, Q21 can represent influence weight proportion of the sharing index of the user on user participation. By analogy, data distribution analysis of the multi-quality fine-grained indexes can be performed on the quality feature radar map, and multi-quality fine-grained data distribution can be obtained, wherein the multi-quality fine-grained data distribution reflects actual distribution of user arrival rate data, jump-out rate data, page stay time data, browsing depth data, access frequency data, time data from last access, retention rate data and the like on the quality feature radar map, and effective weight conversion can be performed on distance distribution by traversing distances of the actual fine-grained feature distribution data from a radar map center point, so that Q31, Q32, Q33 and Q3n under the weight distribution of the first-level weight Q3 are obtained, and exemplarily, Q31 can represent influence weight proportion of the user arrival rate indexes on user participation. Finally, the user behavior acquisition data of the target e-commerce platform is subjected to weight addition operation by using the primary weight Q1, Q21, Q22, Q23 to Q2n under the weight distribution of the primary weight Q2 and Q31, Q32, Q33 to Q3n under the weight distribution of the primary weight Q3 to obtain the user participation grade, and the user participation grade can be used for comprehensively obtaining the user participation degree of the e-commerce platform.
Step S500: drawing a multi-channel flow value evaluation matrix diagram of the target e-commerce platform by taking the user participation grade as an x axis of an abscissa and the investment return rate ROI as a y axis of an ordinate;
step S600: and carrying out visual flow value evaluation on the target e-commerce platform based on the multi-channel flow value evaluation matrix diagram.
Further, as shown in fig. 4, step S500 includes:
step S510: presetting a grading boundary value according to the user participation grade;
step S520: presetting a ROI graded boundary value according to the ROI;
step S530: on the basis of the grading boundary value and the ROI grading boundary value, performing quadrant division on the multi-channel flow value evaluation matrix graph to obtain a first evaluation quadrant, a second evaluation quadrant, a third evaluation quadrant and a fourth evaluation quadrant respectively, wherein the first evaluation quadrant covers high-level value flow, and the third evaluation quadrant covers low-level value flow;
step S540: attribution analysis is carried out on the high-grade value flow covered in the first evaluation quadrant, and multi-channel contribution value in the first evaluation quadrant can be obtained;
step S550: and optimizing the value of the multi-channel contribution in the third evaluation quadrant by using the multi-channel contribution value.
Specifically, after obtaining the user participation and the return on investment of each operation channel in the e-commerce platform, bidirectional index evaluation can be performed on the flow value of the e-commerce platform, specifically, a multi-channel flow value evaluation matrix diagram of the target e-commerce platform can be drawn by using the user participation score as an x axis of abscissa and the return on investment ROI as a y axis of ordinate, and the multi-channel flow value evaluation matrix diagram reflects the position distribution promoted by each channel in the e-commerce platform under the influence of the dual indexes of the user participation and the return on investment.
Further, a rating boundary value may be preset according to the user engagement score, a rating boundary value may be preset according to the return on investment ROI, wherein the rating boundary value may be understood as a median distribution in the user engagement score, and the ROI rating boundary value may be understood as a median distribution in the return on investment ROI, and the multi-channel traffic value evaluation matrix map may be quadrant-divided based on the rating boundary value and the ROI rating boundary value to obtain a first evaluation quadrant, a second evaluation quadrant, a third evaluation quadrant, and a fourth evaluation quadrant, respectively, wherein the first evaluation quadrant is located at the upper right corner of the matrix map, the second evaluation quadrant is located at the upper left corner of the matrix map, the third evaluation quadrant is located at the lower left corner of the matrix map, and the fourth evaluation quadrant is located at the lower right corner of the matrix map. Since the first evaluation quadrant reflects the distribution of the promotion channels with higher user participation scores and higher return on investment, the first evaluation quadrant covers high-grade value traffic, and conversely, since the third evaluation quadrant reflects the distribution of the promotion channels with lower user participation scores and lower return on investment, the third evaluation quadrant covers low-grade value traffic.
Performing a visual traffic value assessment on the target e-commerce platform based on the multi-channel traffic value assessment matrix map. In particular, attribution analysis may be performed by the high-value traffic covered in the first evaluation quadrant. Generally, due to analysis, it is literally a cause for an event or an action, and it is simply a cause and effect analysis to guess which cause the action is. Specifically, the corresponding attribution analysis model can be selected for data analysis according to the actual high-quality value flow, and is not specifically subdivided here. For example, due to the attribution analysis, it can be known that the cost of a certain promotion channel in the e-commerce platform is too high, or the customer price is too low, which results in a low-value flow rate evaluation result for the e-commerce platform, and the channel entries can be further split to see whether all fine-dimension entry data are represented, and the entry with poor data representation is optimized and the business negotiation adjustment is performed to adjust the delivery price, and the delivery of the well-represented entry is continued. The multi-channel contribution value reflects the operation and sale means of the promotion channel corresponding to the high-flow value evaluation result, and the multi-channel contribution value can be utilized to optimize the value of the multi-channel contribution in the third evaluation quadrant. Therefore, the visual flow value evaluation of the target e-commerce platform is realized. The method and the device achieve bidirectional index evaluation on the flow value of the E-commerce platform, and simultaneously optimize the value of a popularization channel corresponding to a low flow value evaluation result.
To sum up, the intelligent evaluation method for the flow value of the e-commerce platform provided by the embodiment of the application has the following technical effects:
1. the method comprises the steps of collecting the number of visitors, purchase conversion rate and platform operation cost of a target e-commerce platform in a preset time period; then, performing data operation to obtain an investment return rate ROI; meanwhile, carrying out multi-dimensional statistics on user behaviors of the target E-commerce platform to obtain the number, behaviors and quality index dimension statistical distribution; weighting and calculating fine grain dimension indexes in each statistical distribution in sequence to calculate user participation scores in a preset time period; taking the user participation grade as an x axis of an abscissa and the investment return rate ROI as a y axis of an ordinate, and drawing a multi-channel flow value evaluation matrix diagram; and carrying out visual flow value evaluation on the target E-commerce platform. The method and the device solve the technical problems that when the e-commerce platform is subjected to flow value evaluation, the flow value evaluation is carried out only by means of single user participation, the investment return rate of each channel in the e-commerce platform cannot be comprehensively referred, and the obtained value evaluation result is single and lacks universality. The method achieves the technical effects of integrating the user participation and the return on investment of each operation channel in the e-commerce platform, and performing two-way index evaluation on the flow value of the e-commerce platform, so that the value evaluation result is more accurate and has universality.
2. Attribution analysis is carried out on the high-grade value flow covered in the first evaluation quadrant, the multi-channel contribution value in the first evaluation quadrant can be obtained, and then value optimization is carried out on the multi-channel contribution in the third evaluation quadrant by utilizing the multi-channel contribution value. And the value optimization of the promotion channel corresponding to the low flow value evaluation result is realized by using the operation and sale means of the promotion channel corresponding to the high flow value evaluation result.
Example two
Based on the same inventive concept as the intelligent evaluation method for the e-commerce platform flow value in the foregoing embodiment, as shown in fig. 5, the present application provides an intelligent evaluation system for the e-commerce platform flow value, the system includes:
the data acquisition module is used for acquiring the number of visitors, the purchase conversion rate and the platform operation cost of the target e-commerce platform in a preset time period;
the data operation module is used for performing data operation on the number of the visitors, the purchase conversion rate and the platform operation cost to obtain the return on investment rate ROI of the target e-commerce platform;
the dimension statistical module is used for carrying out multi-dimensional statistics on the user behaviors of the target e-commerce platform in the preset time period to obtain quantity index dimension statistical distribution, behavior index dimension statistical distribution and quality index dimension statistical distribution;
the weighting calculation module is used for sequentially weighting and calculating fine grain dimension indexes in each statistical distribution through the number index dimension statistical distribution, the behavior index dimension statistical distribution and the quality index dimension statistical distribution, and calculating user participation scores in the preset time period;
the matrix drawing module is used for drawing a multi-channel flow value evaluation matrix diagram of the target e-commerce platform by taking the user participation grade as an x axis of a horizontal coordinate and the ROI as a y axis of a vertical coordinate;
and the value evaluation module is used for carrying out visual flow value evaluation on the target e-commerce platform based on the multi-channel flow value evaluation matrix diagram.
Further, the system comprises:
a rate of return calculation unit to use the formula: ROI = (visitor number. Conversion rate. Passenger unit price)/channel cost, and the investment return rate ROI of the target e-commerce platform is obtained through calculation;
the ROI is the return on investment of the target e-commerce platform, the number of visitors is the number of visitors of the target e-commerce platform in the preset time period, the conversion rate is the conversion rate of whether goods of a user are purchased or not on the target e-commerce platform, the customer price is the unit price of the goods purchased by the user on the target e-commerce platform, and the channel cost reflects the multi-channel consumption cost of the goods for flow promotion on the target e-commerce platform.
Further, the system comprises:
the behavior index multi-fine-granularity splitting unit is used for carrying out multi-fine-granularity splitting on the dimension statistical distribution of the behavior index to obtain a multi-behavior fine-granularity index;
the quality index multi-fine-granularity splitting unit is used for performing multi-fine-granularity splitting on the quality index dimension statistical distribution to obtain a multi-quality fine-granularity index;
and the characteristic radar chart drawing unit is used for drawing a behavior characteristic radar chart based on the multi-behavior fine-grained index and drawing a quality characteristic radar chart based on the multi-quality fine-grained index.
Further, the system comprises:
the index dimension marking unit is used for marking the number index dimension statistical distribution as a primary index U1, the behavior index dimension statistical distribution as a primary index U2 and the quality index dimension statistical distribution as a primary index U3;
and the index weight distribution unit is used for respectively carrying out weight distribution on the first-level index U1, the first-level index U2 and the first-level index U3 by using a weight distribution channel to obtain a corresponding first-level weight Q1, a corresponding first-level weight Q2 and a corresponding first-level weight Q3.
Further, the system comprises:
the behavior data distribution analysis unit is used for carrying out data distribution analysis on the multi-behavior fine-grained indexes on the behavior characteristic radar map to obtain multi-behavior fine-grained data distribution;
a behavior fine-grained weight distribution unit, configured to perform weight distribution on the multi-behavior fine-grained data distribution to obtain Q21, Q22, Q23, through Q2n under the weight distribution of the primary weight Q2;
the quality data distribution analysis unit is used for carrying out data distribution analysis on the multi-quality fine-grained indexes on the quality characteristic radar map to obtain multi-quality fine-grained data distribution;
a quality fine-grained weight distribution unit, configured to perform weight distribution on the multi-quality fine-grained data distribution to obtain Q31, Q32, Q33, through Q3n under the weight distribution of the primary weight Q3;
and the weight adding and calculating unit is used for performing weight adding and calculating on the user behavior acquisition data of the target e-commerce platform by using the primary weight Q1, Q21, Q22, Q23 to Q2n under the weight distribution of the primary weight Q2 and Q31, Q32, Q33 to Q3n under the weight distribution of the primary weight Q3 to obtain the user participation degree score.
Further, the system comprises:
the grading boundary value presetting unit is used for presetting a grading boundary value according to the grading of the user participation degree;
the ROI graded boundary value presetting unit is used for presetting an ROI graded boundary value according to the investment return rate ROI;
and the matrix quadrant division unit is used for carrying out quadrant division on the multi-channel flow value evaluation matrix graph based on the grading boundary value and the ROI grading boundary value to respectively obtain a first evaluation quadrant, a second evaluation quadrant, a third evaluation quadrant and a fourth evaluation quadrant, wherein the first evaluation quadrant covers high-level value flow, and the third evaluation quadrant covers low-level value flow.
Further, the system comprises:
the attribution analysis unit is used for carrying out attribution analysis on the high-grade value flow covered in the first evaluation quadrant to obtain the multi-channel contribution value in the first evaluation quadrant;
and the value optimization unit is used for optimizing the value of the multi-channel contribution in the third evaluation quadrant by utilizing the multi-channel contribution value.
For a specific working process of the module disclosed in the above embodiment of the present application, reference may be made to the content of the corresponding method embodiment, which is not described herein again.
Those skilled in the art can make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. An intelligent evaluation system for the flow value of an e-commerce platform, the system comprising:
the data acquisition module is used for acquiring the number of visitors, purchase conversion rate and platform operation cost of the target e-commerce platform in a preset time period;
the data operation module is used for performing data operation on the number of the visitors, the purchase conversion rate and the platform operation cost to obtain the return on investment rate ROI of the target e-commerce platform;
the dimension statistical module is used for carrying out multi-dimensional statistics on the user behaviors of the target e-commerce platform in the preset time period to obtain quantity index dimension statistical distribution, behavior index dimension statistical distribution and quality index dimension statistical distribution;
the weighting calculation module is used for sequentially weighting and calculating fine grain dimension indexes in each statistical distribution through the number index dimension statistical distribution, the behavior index dimension statistical distribution and the quality index dimension statistical distribution, and calculating user participation scores in the preset time period;
the matrix drawing module is used for drawing a multi-channel flow value evaluation matrix chart of the target e-commerce platform by taking the user participation grade as an x axis of an abscissa and the investment return rate ROI as a y axis of an ordinate;
and the value evaluation module is used for carrying out visual flow value evaluation on the target e-commerce platform based on the multi-channel flow value evaluation matrix diagram.
2. The system of claim 1, wherein the data operation module comprises:
a rate of return calculation unit for using the formula: calculating the cost of the channel and the ROI = (visitor number conversion rate passenger unit price), and calculating the return on investment rate ROI of the target e-commerce platform;
the ROI is the return on investment of the target e-commerce platform, the number of visitors is the number of visitors of the target e-commerce platform in the preset time period, the conversion rate is the conversion rate of whether goods of a user are purchased or not on the target e-commerce platform, the customer price is the unit price of the goods purchased by the user on the target e-commerce platform, and the channel cost reflects the multi-channel consumption cost of the goods for flow promotion on the target e-commerce platform.
3. The system of claim 1, wherein the empowerment computation module comprises:
the behavior index multi-fine-granularity splitting unit is used for carrying out multi-fine-granularity splitting on the dimension statistical distribution of the behavior index to obtain a multi-behavior fine-granularity index;
the quality index multi-fine-granularity splitting unit is used for performing multi-fine-granularity splitting on the quality index dimension statistical distribution to obtain a multi-quality fine-granularity index;
and the characteristic radar chart drawing unit is used for drawing a behavior characteristic radar chart based on the multi-behavior fine-grained index and drawing a quality characteristic radar chart based on the multi-quality fine-grained index.
4. The system of claim 3, wherein the system comprises:
the index dimension marking unit is used for marking the number index dimension statistical distribution as a primary index U1, the behavior index dimension statistical distribution as a primary index U2 and the quality index dimension statistical distribution as a primary index U3;
and the index weight distribution unit is used for respectively carrying out weight distribution on the first-level index U1, the first-level index U2 and the first-level index U3 by using a weight distribution channel to obtain a corresponding first-level weight Q1, a corresponding first-level weight Q2 and a corresponding first-level weight Q3.
5. The system of claim 4, wherein the system comprises:
the behavior data distribution analysis unit is used for carrying out data distribution analysis on the multi-behavior fine-grained indexes on the behavior characteristic radar map to obtain multi-behavior fine-grained data distribution;
a behavior fine-grained weight distribution unit, configured to perform weight distribution on the multi-behavior fine-grained data distribution to obtain Q21, Q22, Q23, through Q2n under the weight distribution of the primary weight Q2;
the quality data distribution analysis unit is used for carrying out data distribution analysis on the multi-quality fine-grained indexes on the quality characteristic radar map to obtain multi-quality fine-grained data distribution;
a quality fine-grained weight distribution unit, configured to obtain Q31, Q32, Q33, through Q3n under the weight distribution of the primary weight Q3 by performing weight distribution on the multi-quality fine-grained data distribution;
and the weight adding and calculating unit is used for performing weight adding and calculating on the user behavior acquisition data of the target e-commerce platform by using the primary weight Q1, Q21, Q22, Q23 to Q2n under the weight distribution of the primary weight Q2 and Q31, Q32, Q33 to Q3n under the weight distribution of the primary weight Q3 to obtain the user participation degree score.
6. The system of claim 1, wherein the matrix drawing module comprises:
the grading boundary value presetting unit is used for presetting a grading boundary value according to the grading of the user participation degree;
the ROI graded boundary value presetting unit is used for presetting an ROI graded boundary value according to the investment return rate ROI;
and the matrix quadrant division unit is used for carrying out quadrant division on the multi-channel flow value evaluation matrix diagram based on the grading boundary value and the ROI grading boundary value to respectively obtain a first evaluation quadrant, a second evaluation quadrant, a third evaluation quadrant and a fourth evaluation quadrant, wherein the first evaluation quadrant covers high-level value flow, and the third evaluation quadrant covers low-level value flow.
7. The system of claim 6, wherein the system comprises:
the attribution analysis unit is used for carrying out attribution analysis on the high-grade value flow covered in the first evaluation quadrant to obtain the multi-channel contribution value in the first evaluation quadrant;
and the value optimization unit is used for optimizing the value of the multi-channel contribution in the third evaluation quadrant by utilizing the multi-channel contribution value.
8. An intelligent evaluation method for the flow value of an e-commerce platform is characterized by comprising the following steps:
the method comprises the steps of collecting the number of visitors, purchase conversion rate and platform operation cost of a target e-commerce platform in a preset time period;
obtaining the investment return rate ROI of the target e-commerce platform by performing data operation on the visitor quantity, the purchase conversion rate and the platform operation cost;
carrying out multi-dimensional statistics on the user behaviors of the target e-commerce platform in the preset time period to obtain quantity index dimension statistical distribution, behavior index dimension statistical distribution and quality index dimension statistical distribution;
sequentially performing weighting and operation on each fine grain dimension index in each statistical distribution through the number index dimension statistical distribution, the behavior index dimension statistical distribution and the quality index dimension statistical distribution, and calculating to obtain a user participation score in the preset time period;
drawing a multi-channel flow value evaluation matrix diagram of the target e-commerce platform by taking the user participation grade as an x axis of an abscissa and the investment return rate ROI as a y axis of an ordinate;
and performing visual flow value evaluation on the target e-commerce platform based on the multi-channel flow value evaluation matrix diagram.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211188022.6A CN115271890B (en) | 2022-09-28 | 2022-09-28 | Intelligent evaluation system for flow value of e-commerce platform |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211188022.6A CN115271890B (en) | 2022-09-28 | 2022-09-28 | Intelligent evaluation system for flow value of e-commerce platform |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115271890A true CN115271890A (en) | 2022-11-01 |
CN115271890B CN115271890B (en) | 2023-04-07 |
Family
ID=83756741
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211188022.6A Active CN115271890B (en) | 2022-09-28 | 2022-09-28 | Intelligent evaluation system for flow value of e-commerce platform |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115271890B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108280599A (en) * | 2018-03-08 | 2018-07-13 | 国网湖北省电力有限公司经济技术研究院 | A kind of agriculture distribution input and output appraisal procedure based on public service value models |
CN109583722A (en) * | 2018-11-16 | 2019-04-05 | 北京奇虎科技有限公司 | A kind of channel data analysis system and method |
CN110232597A (en) * | 2019-06-14 | 2019-09-13 | 苏州开心盒子软件有限公司 | Appraisal procedure, device, equipment and the storage medium of advertising channel |
CN112085332A (en) * | 2020-08-06 | 2020-12-15 | 微民保险代理有限公司 | Data processing method, data processing device, computer equipment and storage medium |
CN114781861A (en) * | 2022-04-20 | 2022-07-22 | 国网浙江省电力有限公司 | Power demand response assessment method and system based on improved radar mapping method |
CN114862173A (en) * | 2022-04-28 | 2022-08-05 | 北京爱笔科技有限公司 | Shop data processing method and device, computer equipment and storage medium |
-
2022
- 2022-09-28 CN CN202211188022.6A patent/CN115271890B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108280599A (en) * | 2018-03-08 | 2018-07-13 | 国网湖北省电力有限公司经济技术研究院 | A kind of agriculture distribution input and output appraisal procedure based on public service value models |
CN109583722A (en) * | 2018-11-16 | 2019-04-05 | 北京奇虎科技有限公司 | A kind of channel data analysis system and method |
CN110232597A (en) * | 2019-06-14 | 2019-09-13 | 苏州开心盒子软件有限公司 | Appraisal procedure, device, equipment and the storage medium of advertising channel |
CN112085332A (en) * | 2020-08-06 | 2020-12-15 | 微民保险代理有限公司 | Data processing method, data processing device, computer equipment and storage medium |
CN114781861A (en) * | 2022-04-20 | 2022-07-22 | 国网浙江省电力有限公司 | Power demand response assessment method and system based on improved radar mapping method |
CN114862173A (en) * | 2022-04-28 | 2022-08-05 | 北京爱笔科技有限公司 | Shop data processing method and device, computer equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN115271890B (en) | 2023-04-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Valarezo et al. | Drivers and barriers to cross-border e-commerce: Evidence from Spanish individual behavior | |
US20180322175A1 (en) | Methods and systems for analyzing entity performance | |
US20180292959A1 (en) | Systems and methods for analyzing performance of an entity | |
Chatterjee et al. | Are tradeoffs inherent in diversification moves? A simultaneous model for type of diversification and mode of expansion decisions | |
EP2884441A1 (en) | Methods and systems for analyzing entity performance | |
Yin et al. | The effects of China’s cross-border e-commerce on its exports: a comparative analysis of goods and services trade | |
CN103827906A (en) | Method and system for selection, filtering or presentation of available sales outlets | |
KR20070002741A (en) | Method and system for decideing advertising fee | |
US20080201247A1 (en) | Method, system and computer-readable media for evaluation or selection of real estate appraisers | |
CN107886241B (en) | Resource analysis method, device, medium, and electronic apparatus | |
US20200410518A1 (en) | Machine learning engine for demand-based pricing | |
Venkatesan et al. | Understanding the confluence of retailer characteristics, market characteristics and online pricing strategies | |
CN110838022A (en) | Advertisement price adjusting method and device, electronic equipment and computer readable medium | |
Han | The analysis on Chinese e-commerce tax losses based on the perspective of information asymmetry | |
JP2016091075A (en) | Information processing device, information processing method, and program | |
Bertola et al. | Dealer pricing of consumer credit | |
CN115271890B (en) | Intelligent evaluation system for flow value of e-commerce platform | |
CN109544299B (en) | Buyer identity rating method, device and storage medium based on transaction guarantee platform | |
CN116308599A (en) | Financial product intelligent recommendation method and device based on product tags and customer tags | |
MacEachern | Measuring the added value of library and information services: the New Zealand approach | |
CN113254778B (en) | ASIN group keyword recommendation method based on Amazon platform | |
KR101565924B1 (en) | Method of Calculating the mall's premium | |
US20020123961A1 (en) | Computerized retail lease program selection systems and methods | |
Chodak | Measuring the Impact of E-Commerce on the Economy | |
Duch-Brown et al. | Evaluating the impact of market integration-Banning online trade restrictions in the EU portable PC market |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |