Digital marketing effect analysis method and system based on big data

Abstract

The invention provides a digital marketing effect analysis method and system based on big data, and the method comprises the steps: obtaining browsing behavior data of a user for different marketing contents under different marketing channels, and integrating and storing the browsing behavior data; analyzing the browsing behavior data on the basis of the integration and storage results, determining progressive conversion rates of different marketing contents in each marketing stage under different marketing channels, performing correlation analysis on the progressive conversion rates of each marketing content in each marketing stage, and determining user conversion contributions under different marketing channels; and determining the return on investment of different marketing channels based on the user conversion contribution, and performing tabulation visualization display on the return on investment of different marketing channels. According to the method, the user can intuitively and effectively understand the marketing effects of different marketing channels, and meanwhile, the reliability and the accuracy of digital marketing effect analysis are improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a digital marketing effect analysis method and system based on big data. Background Art

[0002] At present, with the rapid development of Internet technology, digital marketing has become an important means for enterprises to promote products and services;

[0003] However, current digital marketing effectiveness evaluation faces numerous challenges. Traditional marketing effectiveness analysis often relies on simple metrics, such as click-through rate and conversion rate, lacking comprehensive data mining and in-depth analysis. Furthermore, the diversification of marketing channels leads to the isolation of data sources from different marketing channels. For example, social media data, website traffic data, and offline sales data cannot be effectively integrated, resulting in one-sided and inaccurate analysis of marketing effectiveness, wasting resources and unsatisfactory marketing results.

[0004] Therefore, in order to overcome the above-mentioned defects, the present invention provides a digital marketing effect analysis method and system based on big data. Summary of the Invention

[0005] The present invention provides a digital marketing effect analysis method and system based on big data, which is used to obtain users' browsing behavior data on different marketing contents in different marketing channels, and integrate and analyze the browsing behavior data, so as to accurately and effectively determine the progressive conversion rate of different marketing contents in each marketing stage under different marketing channels, thereby providing data support for data marketing effect evaluation. Secondly, the progressive conversion rate of each marketing content in each marketing stage is correlated and analyzed to determine the user conversion contribution of different marketing channels, and then the return on investment of different marketing channels is determined through the conversion contribution, so as to accurately and reliably determine the digital marketing effect of different marketing channels through the return on investment. Finally, the obtained return on investment is tabulated and visually displayed, so as to facilitate users to intuitively and effectively understand the marketing effects of different marketing channels, while improving the reliability and accuracy of digital marketing effect analysis.

[0006] The present invention provides a digital marketing effect analysis method based on big data, comprising:

[0007] Step 1: Obtain user browsing behavior data for different marketing content in different marketing channels, and integrate and store the browsing behavior data;

[0008] Step 2: Analyze browsing behavior data based on the integration and storage results to determine the progressive conversion rates of different marketing content at each marketing stage under different marketing channels. Also, conduct correlation analysis on the progressive conversion rates of each marketing content at each marketing stage to determine the user conversion contribution of different marketing channels.

[0009] Step 3: Determine the ROI of different marketing channels based on user conversion contribution, and tabulate and visualize the ROI of different marketing channels.

[0010] Preferably, a digital marketing effect analysis method based on big data, in step 1, obtaining user browsing behavior data for different marketing content in different marketing channels, includes:

[0011] Extract the interface configuration parameters of the databases in different marketing channels, and connect the data collection terminal with the databases of different marketing channels according to the interface configuration parameters;

[0012] Based on the user identity and the docking results, the browsing behavior data of different marketing contents in the database of different marketing channels are locked, and the locked browsing behavior data are retrieved.

[0013] Preferably, a digital marketing effect analysis method based on big data, browsing behavior data includes likes, comments, and sharing data on social media platforms, visit time, browsed pages, registration information data of corporate official websites, and sales time, sales volume, and customer information of offline sales terminals.

[0014] Preferably, a digital marketing effect analysis method based on big data, in step 1, integrating and storing browsing behavior data, includes:

[0015] Determine the integration standards for browsing behavior data, and classify browsing behavior data of different marketing content under different marketing channels in multiple dimensions based on the integration standards;

[0016] Based on the multi-dimensional classification results, a data set sequence is obtained, and cache space is allocated on the management terminal according to the composition of the data set sequence;

[0017] Store the data set sequence in the allocated buffer space.

[0018] Preferably, a digital marketing effect analysis method based on big data, in step 2, analyzes browsing behavior data based on the integration and storage results, determines the progressive conversion rate of different marketing content in each marketing stage under different marketing channels, and performs correlation analysis on the progressive conversion rate of each marketing content in each marketing stage to determine the user conversion contribution under different marketing channels, including:

[0019] Obtain the entire digital marketing business process and divide it into stages based on node business characteristics;

[0020] Based on the stage division results, determine the business behavior characteristics of each stage according to industry implementation standards, and associate the business behavior characteristics with the stage division results;

[0021] Build a user behavior analysis model based on the correlation results, and analyze the browsing behavior data of different marketing content under different marketing channels based on the user behavior analysis model;

[0022] Based on the analysis results, the access characteristics of different users at each stage are determined, and the same object is tracked according to the execution logic between each stage based on the access characteristics;

[0023] Based on the tracking results of the same object, determine the changes in the group ratio of users between different stages, and based on the changes in group ratio, determine the progressive conversion rate of different marketing content in different marketing channels at each marketing stage;

[0024] Determine the digital marketing transfer ratio between adjacent stages based on the progressive conversion rate. At the same time, obtain the digital marketing weight of each stage and perform a weighted average of the digital marketing transfer ratios between adjacent stages based on the digital marketing weight.

[0025] Determine the user conversion contribution of different marketing channels based on the weighted average results.

[0026] Preferably, a digital marketing effectiveness analysis method based on big data, in step 3, determines the return on investment of different marketing channels based on user conversion contribution, and tabulates and visually displays the return on investment of different marketing channels, including:

[0027] Trace the user conversion contribution rate and determine the sub-user conversion rate of different marketing content under different marketing channels;

[0028] Obtain the marketing amount and marketing cost of different marketing content under different marketing channels, and convert the marketing amount based on the sub-user conversion rate to obtain the marketing conversion revenue of different marketing content under different marketing channels;

[0029] Convert marketing costs based on sub-user conversion rates to obtain target costs for different marketing content under different marketing channels;

[0030] The marketing conversion revenue and target cost of all the same marketing content under the same marketing channel are subtracted to obtain the marketing revenue of each marketing channel, and the corresponding return on investment is obtained based on the marketing revenue.

[0031] Preferably, a digital marketing effectiveness analysis method based on big data, in step 3, tabulating and visualizing the return on investment of different marketing channels, includes:

[0032] Convert the ROI of different marketing channels into charts to obtain corresponding visual display charts;

[0033] Visually display the visualization chart on the visualization terminal.

[0034] The present invention provides a digital marketing effect analysis system based on big data, comprising:

[0035] The data integration and storage module is used to obtain the browsing behavior data of users on different marketing contents in different marketing channels, and integrate and store the browsing behavior data;

[0036] The data analysis module is used to analyze browsing behavior data based on the integration and storage results, determine the progressive conversion rate of different marketing content at each marketing stage under different marketing channels, and conduct correlation analysis on the progressive conversion rate of each marketing content at each marketing stage to determine the user conversion contribution under different marketing channels;

[0037] The marketing effect determination module is used to determine the return on investment of different marketing channels based on user conversion contribution, and to tabulate and visualize the return on investment of different marketing channels.

[0038] Preferably, a digital marketing effect analysis system based on big data, a data integration and storage module, includes:

[0039] The interface docking unit is used to extract the interface configuration parameters of the databases in different marketing channels and connect the data collection terminal with the databases of different marketing channels according to the interface configuration parameters;

[0040] The data retrieval unit is used to lock the browsing behavior data of different marketing contents in the database of different marketing channels based on the user identity and the docking result, and to retrieve the locked browsing behavior data.

[0041] Preferably, a digital marketing effect analysis system based on big data, browsing behavior data includes likes, comments, and sharing data on social media platforms, visit time, browsed pages, registration information data of corporate official websites, and sales time, sales volume, and customer information of offline sales terminals.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] By obtaining users' browsing behavior data on different marketing content under different marketing channels, and integrating and analyzing the browsing behavior data, we can accurately and effectively determine the progressive conversion rates of different marketing content in each marketing stage under different marketing channels, providing data support for data marketing effect evaluation. Secondly, we conduct correlation analysis on the progressive conversion rates of each marketing content in each marketing stage to determine the user conversion contribution of different marketing channels, and then determine the return on investment of different marketing channels through conversion contribution, and accurately and reliably determine the digital marketing effect of different marketing channels through return on investment. Finally, the obtained return on investment is tabulated and visualized, which facilitates users to intuitively and effectively understand the marketing effects of different marketing channels, while improving the reliability and accuracy of digital marketing effect analysis.

[0044] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be achieved and obtained through the structures specifically pointed out in this application document.

[0045] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0047] Figure 1 This is a flow chart of a digital marketing effect analysis method based on big data in an embodiment of the present invention;

[0048] Figure 2 This is a flowchart of step 1 in a digital marketing effect analysis method based on big data in an embodiment of the present invention;

[0049] Figure 3 This is a structural diagram of a digital marketing effect analysis system based on big data in an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0051] In one embodiment, a digital marketing effectiveness analysis method based on big data includes:

[0052] Step 1: Obtain user browsing behavior data for different marketing content in different marketing channels, and integrate and store the browsing behavior data;

[0053] Step 2: Analyze browsing behavior data based on the integration and storage results to determine the progressive conversion rates of different marketing content at each marketing stage under different marketing channels. Also, conduct correlation analysis on the progressive conversion rates of each marketing content at each marketing stage to determine the user conversion contribution of different marketing channels.

[0054] Step 3: Determine the ROI of different marketing channels based on user conversion contribution, and tabulate and visualize the ROI of different marketing channels.

[0055] In this embodiment, different marketing channels refer to platforms or websites where digital content needs to be published or promoted, such as social platforms, corporate websites, and e-commerce service platforms.

[0056] In this embodiment, different marketing contents refer to digital information that needs to be promoted, such as product details or technical services.

[0057] In this embodiment, browsing behavior data refers to data such as users' clicks on different marketing content through different marketing channels and browsing time, etc., specifically including likes, comments, and sharing data on social media platforms, visit time, browsed pages, registration information data of the company's official website, and sales time, sales volume, and customer information of offline sales terminals.

[0058] In this embodiment, the marketing stage refers to all stages from the user's understanding to the purchase of marketing content through the marketing channel, such as the awareness stage, the interest stage, the decision stage, and the purchase stage.

[0059] In this embodiment, the progressive conversion rate refers to the transmission effect between each marketing stage, for example, it can be the probability or proportion of users entering the interest stage through the awareness stage and the probability or proportion of users entering the decision stage through the interest stage.

[0060] In this embodiment, user conversion contribution refers to the promotion of different marketing contents by different marketing channels, that is, the purchase or order placement of different marketing contents by users through different marketing channels.

[0061] In this embodiment, the return on investment refers to the user conversion contribution under different marketing channels, that is, determined by the number of acquired user groups, marketing costs and marketing benefits of different marketing channels.

[0062] In this embodiment, tabulation visualization refers to making corresponding visualization tables of the return on investment of different marketing channels, thereby realizing the display of the return on investment of different marketing channels, for example, generating a line chart or a bar chart for visualization.

[0063] The working principle and beneficial effects of the above technical solution are: by obtaining the browsing behavior data of users on different marketing contents under different marketing channels, and integrating and analyzing the browsing behavior data, the progressive conversion rate of different marketing contents in each marketing stage under different marketing channels can be accurately and effectively determined, providing data support for data marketing effect evaluation; secondly, the progressive conversion rate of each marketing content in each marketing stage is correlated and analyzed to determine the user conversion contribution of different marketing channels, and then the return on investment of different marketing channels is determined through the conversion contribution, and the digital marketing effect of different marketing channels is accurately and reliably determined through the return on investment; finally, the obtained return on investment is tabulated and visually displayed, so that users can intuitively and effectively understand the marketing effects of different marketing channels, while improving the reliability and accuracy of digital marketing effect analysis.

[0064] In one embodiment, a digital marketing effect analysis method based on big data, such as Figure 2 As shown, in step 1, the user's browsing behavior data for different marketing content in different marketing channels is obtained, including:

[0065] Step 101: extracting interface configuration parameters of databases in different marketing channels, and connecting the data collection terminal with the databases of different marketing channels according to the interface configuration parameters;

[0066] Access the backends of different marketing channels and determine the interface configuration parameters of the corresponding database based on the access results, where the interface configuration parameters are the type of database interface and the communication requirements for data communication;

[0067] Adapt the communication interface of the data collection terminal based on the interface configuration parameters, and connect the data collection terminal to the databases of different marketing channels after successful adaptation;

[0068] Step 102: Based on the user identity and the docking result, the browsing behavior data of different marketing contents in the database of different marketing channels is locked, and the locked browsing behavior data is retrieved;

[0069] Extract address information from data stored in databases of different marketing channels, and determine access terminal information for different browsing behavior data based on the address information extraction results;

[0070] The user's target terminal is determined based on the user identity, and the correspondence between the browsing behavior data and the user identity is determined based on the target terminal and access terminal information. The browsing behavior data of different marketing contents in the database of different marketing channels are locked based on the correspondence.

[0071] In one embodiment, a digital marketing effectiveness analysis method based on big data includes integrating and storing browsing behavior data in step 1, including:

[0072] Determine the integration standards for browsing behavior data, and classify browsing behavior data of different marketing content under different marketing channels in multiple dimensions based on the integration standards, including:

[0073] Acquire an integration standard for browsing behavior data based on the management terminal, parse the integration standard, and determine a limited subject item in the integration standard, wherein the subject item is a user identity identifier;

[0074] Extracting data attribution features of browsing behavior data for different marketing content under different marketing channels, and determining the attribution objects of different browsing behavior data based on the data attribution features, wherein the attribution features are the data source of the browsing behavior data, and the attribution object is the user ID determined based on the data source;

[0075] Matching the attribution object with the user identity identifier, and based on the matching result, aggregating the browsing behavior data of the same user under different marketing channels to obtain a data set sequence, wherein the data set sequence is the sum of all browsing behavior data of each user under different marketing channels;

[0076] Based on the multi-dimensional classification results, a data set sequence is obtained, and cache space is allocated on the management terminal according to the composition of the data set sequence, specifically including:

[0077] Determining the byte amount of each data set in the data set sequence and in the data set, and allocating buffer space for each data set in the management terminal according to the byte amount;

[0078] Store the data set sequence in the allocated buffer space.

[0079] In one embodiment, a digital marketing effectiveness analysis method based on big data includes analyzing browsing behavior data based on the integration and storage results in step 2 to determine the progressive conversion rates of different marketing content at each marketing stage under different marketing channels, and performing correlation analysis on the progressive conversion rates of each marketing content at each marketing stage to determine the user conversion contribution under different marketing channels, including:

[0080] Obtain the entire digital marketing business process and divide it into stages based on node business characteristics. The entire business process refers to all aspects of digital marketing, and node business characteristics refer to the business type and characteristics of each aspect.

[0081] Based on the stage division results, determine the business behavior characteristics of each stage according to the industry implementation standards, and associate the business behavior characteristics with the stage division results. The industry implementation standards are known in advance, and the business behavior characteristics are the business conditions and business content of each stage.

[0082] Build a user behavior analysis model based on the correlation results, and analyze the browsing behavior data of different marketing content under different marketing channels based on the user behavior analysis model;

[0083] Based on the analysis results, the access characteristics of different users at each stage are determined. Based on the access characteristics, the same object is tracked according to the execution logic between each stage. The access characteristics are the type of digital marketing content viewed, the length of browsing time, and the number of clicks by users at each stage. The same object tracking is to track the access characteristics of the same user at different stages.

[0084] Based on the tracking results of the same object, determine the changes in the group ratio of users between different stages, and based on the changes in group ratio, determine the progressive conversion rate of different marketing content in different marketing channels at each marketing stage. The change in group ratio refers to the change in the number of users between different stages, that is, the change in the number of user groups;

[0085] Determine the digital marketing transfer ratio between adjacent stages based on the progressive conversion rate. Simultaneously, obtain the digital marketing weight of each stage and perform a weighted average of the digital marketing transfer ratios between adjacent stages based on the digital marketing weights. The digital marketing transfer ratio represents the user group conversion status between adjacent stages determined based on the progressive conversion rate, such as the transfer effect from the interest stage to the understanding stage, specifically the user conversion volume. The digital marketing weight represents the importance of digital marketing at different stages.

[0086] Determine the user conversion contribution of different marketing channels based on the weighted average results.

[0087] To further improve digital marketing effectiveness and ensure the adaptability of marketing content to user groups, an embodiment is proposed, a digital marketing effectiveness analysis method based on big data. After tracking the same object based on access characteristics and the execution logic between each stage, the method includes:

[0088] Based on the tracking results of the same subject, we determine the same subject's attention to different marketing content at different stages. At the same time, we extract the performance characteristics of the same marketing content at different stages under different marketing channels. The performance characteristics are the presentation forms of marketing content at different stages and the basic situation of digital marketing.

[0089] Associating attention with the performance characteristics of marketing content with the same marketing content, and based on the association results of the same marketing content, determining the change in the same subject's access behavior characteristics towards the marketing content at different stages, where the change in access behavior characteristics refers to the user's viewing time and number of shares of the marketing content at different stages;

[0090] Based on the change in access behavior characteristics, the marketing content conversion rate of the same marketing content at different stages is obtained. At the same time, the user group composition of each marketing content at different stages is determined, and the determined user group composition is divided into group hierarchies. The group hierarchies are divided into different age groups according to age groups.

[0091] Extract key behavioral information from the performance characteristics of marketing content at different stages, determine the corresponding marketing style, and then associate the marketing style, marketing content conversion rate, and group level division results with the same marketing content. Key behavioral information refers to the copywriting and video types of marketing content at different stages, and the main association is to associate the marketing style, marketing content conversion rate, and group level division results corresponding to the same marketing content;

[0092] Determine the marketing effect of each marketing content under each marketing channel based on the subject association results, and sort the marketing effects of each marketing content under each marketing channel in descending order;

[0093] Adaptively deploy each marketing content in each marketing channel based on the return on investment of each marketing content in descending order. Adaptive deployment involves displaying marketing content with a return on investment below a preset threshold in marketing channels with a return on investment above the preset threshold.

[0094] Complete dynamic optimization and adjustment of marketing content based on adaptive allocation results.

[0095] In one embodiment, a method for analyzing digital marketing effectiveness based on big data includes determining the return on investment (ROI) of different marketing channels based on user conversion contributions in step 3, and tabulating and visualizing the ROI of different marketing channels, including:

[0096] Trace the user conversion contribution rate and determine the sub-user conversion rate of different marketing content under different marketing channels;

[0097] Obtain the marketing amount and marketing cost of different marketing content under different marketing channels, and convert the marketing amount based on the sub-user conversion rate to obtain the marketing conversion revenue of different marketing content under different marketing channels;

[0098] Convert marketing costs based on sub-user conversion rates to obtain target costs for different marketing content under different marketing channels;

[0099] The marketing conversion revenue and target cost of all the same marketing content under the same marketing channel are subtracted to obtain the marketing revenue of each marketing channel, and the corresponding return on investment is obtained based on the marketing revenue.

[0100] In one embodiment, a digital marketing effectiveness analysis method based on big data includes tabulating and visualizing the return on investment of different marketing channels in step 3, including:

[0101] Convert the ROI of different marketing channels into charts to obtain corresponding visual display charts, including:

[0102] Obtain the return on investment (ROI) for different marketing channels and determine the target value corresponding to the ROI;

[0103] Retrieving a plurality of different categories of visualization chart templates from a visualization chart library, and determining basic data requirements for each category of visualization chart template, wherein the basic data requirements are requirements of the visualization chart template on the data format;

[0104] Convert and import target values corresponding to the return on investment based on basic data requirements, and generate corresponding visual display charts based on the conversion and import results;

[0105] Visually display the visualization chart on the visualization terminal, including:

[0106] Receiving a visualization request from a visualization terminal, parsing the visualization request, and determining an intended category for a visualization display chart, wherein the intended category is a type of chart that the user expects to see;

[0107] When there is an intention category, the visualization display chart corresponding to the intention category is visualized on the visualization terminal;

[0108] When there is no intention category, the visualization display chart of each category is sequentially visualized on the visualization terminal for a preset time period.

[0109] In one embodiment, a digital marketing effect analysis system based on big data, such as Figure 3 Shown, including:

[0110] The data integration and storage module is used to obtain the browsing behavior data of users on different marketing contents in different marketing channels, and integrate and store the browsing behavior data;

[0111] The data analysis module is used to analyze browsing behavior data based on the integration and storage results, determine the progressive conversion rate of different marketing content at each marketing stage under different marketing channels, and conduct correlation analysis on the progressive conversion rate of each marketing content at each marketing stage to determine the user conversion contribution under different marketing channels;

[0112] The marketing effect determination module is used to determine the return on investment of different marketing channels based on user conversion contribution, and to tabulate and visualize the return on investment of different marketing channels.

[0113] In one embodiment, a digital marketing effectiveness analysis system based on big data, including a data integration and storage module, includes:

[0114] The interface docking unit is used to extract the interface configuration parameters of the databases in different marketing channels and connect the data collection terminal with the databases of different marketing channels according to the interface configuration parameters;

[0115] Access the backends of different marketing channels and determine the interface configuration parameters of the corresponding database based on the access results, where the interface configuration parameters are the type of database interface and the communication requirements for data communication;

[0116] Adapt the communication interface of the data collection terminal based on the interface configuration parameters, and connect the data collection terminal to the databases of different marketing channels after successful adaptation;

[0117] A data retrieval unit is used to lock browsing behavior data of different marketing contents in databases of different marketing channels based on user identity and docking results, and retrieve the locked browsing behavior data;

[0118] The user's target terminal is determined based on the user identity, and the correspondence between the browsing behavior data and the user identity is determined based on the target terminal and access terminal information. The browsing behavior data of different marketing contents in the database of different marketing channels are locked based on the correspondence.

[0119] In one embodiment, a digital marketing effectiveness analysis system based on big data includes browsing behavior data including likes, comments, and sharing data on social media platforms, visit time, browsed pages, and registration information data on corporate official websites, and sales time, sales volume, and customer information at offline sales terminals.

[0120] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A digital marketing effect analysis method based on big data, characterized in that: include: Step 1: Obtain user browsing behavior data for different marketing content in different marketing channels, and integrate and store the browsing behavior data; Step 2: Analyze browsing behavior data based on the integration and storage results to determine the progressive conversion rates of different marketing content at each marketing stage under different marketing channels. Also, conduct correlation analysis on the progressive conversion rates of each marketing content at each marketing stage to determine the user conversion contribution of different marketing channels. Step 3: Determine the ROI of different marketing channels based on user conversion contribution, and tabulate and visualize the ROI of different marketing channels.

2. The digital marketing effect analysis method based on big data according to claim 1, characterized in that: In step 1, obtain user browsing behavior data for different marketing content in different marketing channels, including: Extract the interface configuration parameters of the databases in different marketing channels, and connect the data collection terminal with the databases of different marketing channels according to the interface configuration parameters; Based on the user identity and the docking results, the browsing behavior data of different marketing contents in the database of different marketing channels are locked, and the locked browsing behavior data are retrieved.

3. The digital marketing effect analysis method based on big data according to claim 1, characterized in that: Browsing behavior data includes likes, comments, and sharing data on social media platforms, visit time, browsed pages, registration information data of corporate official websites, and sales time, sales volume, and customer information of offline sales terminals.

4. The digital marketing effect analysis method based on big data according to claim 1, characterized in that: In step 1, the browsing behavior data is integrated and stored, including: Determine the integration standards for browsing behavior data, and classify browsing behavior data of different marketing content under different marketing channels in multiple dimensions based on the integration standards; Based on the multi-dimensional classification results, a data set sequence is obtained, and cache space is allocated on the management terminal according to the composition of the data set sequence; Store the data set sequence in the allocated buffer space.

5. The digital marketing effect analysis method based on big data according to claim 1, characterized in that: In step 2, based on the integration and storage results, the browsing behavior data is analyzed to determine the progressive conversion rates of different marketing content at each marketing stage under different marketing channels. Correlation analysis is then performed on the progressive conversion rates of each marketing content at each marketing stage to determine the user conversion contribution of different marketing channels, including: Obtain the entire digital marketing business process and divide it into stages based on node business characteristics; Based on the stage division results, determine the business behavior characteristics of each stage according to industry implementation standards, and associate the business behavior characteristics with the stage division results; Build a user behavior analysis model based on the correlation results, and analyze the browsing behavior data of different marketing content under different marketing channels based on the user behavior analysis model; Based on the analysis results, the access characteristics of different users at each stage are determined, and the same object is tracked according to the execution logic between each stage based on the access characteristics; Based on the tracking results of the same object, determine the changes in the group ratio of users between different stages, and based on the changes in group ratio, determine the progressive conversion rate of different marketing content in different marketing channels at each marketing stage; Determine the digital marketing transfer ratio between adjacent stages based on the progressive conversion rate. At the same time, obtain the digital marketing weight of each stage and perform a weighted average of the digital marketing transfer ratios between adjacent stages based on the digital marketing weight. Determine the user conversion contribution of different marketing channels based on the weighted average results.

6. The digital marketing effect analysis method based on big data according to claim 1, characterized in that: In step 3, the ROI of different marketing channels is determined based on user conversion contributions, and the ROI of different marketing channels is tabulated and visualized, including: Trace the user conversion contribution rate and determine the sub-user conversion rate of different marketing content under different marketing channels; Obtain the marketing amount and marketing cost of different marketing content under different marketing channels, and convert the marketing amount based on the sub-user conversion rate to obtain the marketing conversion revenue of different marketing content under different marketing channels; Convert marketing costs based on sub-user conversion rates to obtain target costs for different marketing content under different marketing channels; The marketing conversion revenue and target cost of all the same marketing content under the same marketing channel are subtracted to obtain the marketing revenue of each marketing channel, and the corresponding return on investment is obtained based on the marketing revenue.

7. The digital marketing effect analysis method based on big data according to claim 1, characterized in that: In step 3, the ROI of different marketing channels is tabulated and visualized, including: Convert the ROI of different marketing channels into charts to obtain corresponding visual display charts; Visually display the visualization chart on the visualization terminal.

8. A digital marketing effect analysis system based on big data, characterized by: include: The data integration and storage module is used to obtain the browsing behavior data of users on different marketing contents in different marketing channels, and integrate and store the browsing behavior data; The data analysis module is used to analyze browsing behavior data based on the integration and storage results, determine the progressive conversion rate of different marketing content at each marketing stage under different marketing channels, and conduct correlation analysis on the progressive conversion rate of each marketing content at each marketing stage to determine the user conversion contribution under different marketing channels; The marketing effect determination module is used to determine the return on investment of different marketing channels based on user conversion contribution, and to tabulate and visualize the return on investment of different marketing channels.

9. The digital marketing effect analysis system based on big data according to claim 8, characterized in that: Data integration and storage modules, including: The interface docking unit is used to extract the interface configuration parameters of the databases in different marketing channels and connect the data collection terminal with the databases of different marketing channels according to the interface configuration parameters; The data retrieval unit is used to lock the browsing behavior data of different marketing contents in the database of different marketing channels based on the user identity and the docking result, and to retrieve the locked browsing behavior data.

10. The digital marketing effect analysis system based on big data according to claim 8, characterized in that: Browsing behavior data includes likes, comments, and sharing data on social media platforms, visit time, browsed pages, registration information data of corporate official websites, and sales time, sales volume, and customer information of offline sales terminals.

Images