Intelligent marketing analysis and decision-making method based on customer full life cycle data

Abstract

The invention discloses an intelligent marketing analysis and decision-making method based on customer full life cycle data, and the method comprises the steps: S1, collecting a plurality of types of heterogeneous data source information of a customer, and cleaning the plurality of types of heterogeneous data source information; s2, establishing a data lake warehouse, and storing the cleaned heterogeneous data source information into the data lake warehouse; and S3, loading and analyzing the data in the customer data lake warehouse according to different business requirements to obtain a corresponding data analysis result. According to the method, the consistency and integrity of data are ensured through data cleaning; real-time processing and analysis of large-scale data are realized, the requirements of enterprises on real-time data processing are met, and the data processing efficiency is improved; various multi-dimensional analysis tools and personalized marketing support are provided, enterprises are helped to deeply understand customer demands and behaviors, precise marketing is achieved, and the marketing effect is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent marketing analysis and customer data management, and in particular to an intelligent marketing analysis and decision-making method based on customer full life cycle data. Background Art

[0002] In many companies, marketers tend to use customer relationship management systems to collect, associate and analyze all relevant customer data, including contact information, interaction information with corporate sales representatives, historical purchase records, service requests, assets and quotes / proposals, etc. Users can then access this data and understand the latest developments at each touch point, and create a complete customer profile based on this, thereby building a strong customer relationship.

[0003] In the existing technologies for customer data management and marketing systems, there are data silos and differences between systems with different functions, which makes it impossible to effectively integrate and uniformly analyze data; and traditional data management platforms cannot effectively cope with the storage and processing needs of such massive data, resulting in low data processing efficiency and slow response speed. At the same time, traditional customer data management systems often rely on manual input and data improvement, resulting in problems with the accuracy and update speed of customer data. Some data may be delayed and unable to reflect the latest situation of customers in a timely manner, affecting the comprehensive understanding and accurate analysis of customers. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent marketing analysis and decision-making method based on customer life cycle data. The present invention aims to solve the problems of data silos and differences between different functional systems in customer data management and marketing systems, the inability to effectively integrate and uniformly analyze data, and the low accuracy and update speed of customer data.

[0005] To achieve the above object, the present invention is implemented through the following technical solutions:

[0006] The present invention provides an intelligent marketing analysis and decision-making method based on customer life cycle data, the method comprising:

[0007] Step S1: Collecting several types of heterogeneous data source information from customers, and cleaning the several types of heterogeneous data source information;

[0008] Step S2: Establish a data lake warehouse, and store the cleaned information of the heterogeneous data sources in the data lake warehouse;

[0009] Step S3: Load and analyze the data in the customer data lake warehouse according to different business needs to obtain corresponding data analysis results.

[0010] Preferably, the collection of several types of heterogeneous data source information includes: formulating a predetermined event, and after the user's operation behavior on the client triggers the predetermined event, the corresponding heterogeneous data source information is pushed to the server through the client.

[0011] Preferably, the several types of heterogeneous data source information include: any one of order data, user data, behavior data, tracking logs, and third-party anonymized data, or any combination thereof.

[0012] Preferably, cleaning the information of several types of heterogeneous data sources includes:

[0013] By normalizing data fields, converting several types of heterogeneous data source messages into distributed message flow platform messages for data transmission;

[0014] Performing field mapping, that is, parsing data according to predetermined rules and the standard of the distributed message flow platform to obtain parsed data;

[0015] A cleaning logic is formulated, and according to the cleaning logic, the parsed data is converted into expected data, where the expected data is information of the several types of heterogeneous data sources after cleaning.

[0016] Preferably, converting several types of heterogeneous data source messages into distributed message flow platform messages for data transmission also includes: formulating different calculation types according to different business timeliness requirements or actual enterprise resources.

[0017] Preferably, the different calculation types include: scheduled calculation and real-time calculation.

[0018] Preferably, the data in the customer data lake warehouse is loaded and analyzed according to different business requirements to obtain corresponding data analysis results, which specifically includes:

[0019] According to different business requirements, different architectures are used to load and analyze the data in the data lake warehouse to obtain data analysis results;

[0020] The data analysis results are transmitted to different analysis tools through the unified data export service for different marketing analysis and decision-making.

[0021] Preferably, the data analysis results include: any one or any combination of consumption index calculation, user profiling, behavior analysis and data aggregation statistics.

[0022] Preferably, the different analysis tools include: any one or any combination of visualization reports, terminal devices or marketing systems.

[0023] Preferably, the different architectures include: a computing engine in a distributed file system or an analytical database in a massively parallel processing architecture.

[0024] Compared with the prior art, the present invention has the following beneficial effects:

[0025] The present invention ensures the consistency and integrity of data through data cleaning; realizes real-time processing and analysis of large-scale data, meets the needs of enterprises for real-time data processing, and improves data processing efficiency; provides a variety of analysis tools and personalized marketing support to help enterprises understand customer needs and behaviors, realize precision marketing, and improve marketing effectiveness; solves the problems of data islands and differences between different functional systems, the inability to effectively integrate and uniformly analyze data, and the low accuracy and update speed of customer data. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for the description. Obviously, the drawings described below are an embodiment of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work:

[0027] Figure 1 A schematic diagram of a complete processing system architecture of an intelligent marketing analysis and decision-making method based on customer life cycle data provided by an embodiment of the present invention;

[0028] Figure 2 A flowchart of cleaning information of several heterogeneous data sources provided by an embodiment of the present invention;

[0029] Figure 3 A flowchart for cleaning information of several heterogeneous data sources using different calculation types provided by an embodiment of the present invention;

[0030] Figure 4 A schematic diagram of a process for loading and analyzing data in a data lake provided by an embodiment of the present invention;

[0031] Figure 5 A schematic diagram of a specific data processing flow in a car rental business provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0032] The following is combined with Figure 1-5The intelligent marketing analysis and decision-making method based on customer life cycle data proposed in the present invention is further described in detail with specific implementation methods. According to the following description, the advantages and features of the present invention will be clearer. It should be noted that the drawings are in a very simplified form and use non-precise proportions, which are only used to conveniently and clearly assist in explaining the purpose of the implementation methods of the present invention. In order to make the purposes, features and advantages of the present invention more obvious and easy to understand, please refer to the drawings. It should be noted that the structures, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification for people familiar with this technology to understand and read, and are not used to limit the limiting conditions for the implementation of the present invention, so they have no technical substantive significance. Any structural modification, change in proportional relationship or adjustment of size, without affecting the effects that can be produced by the present invention and the purposes that can be achieved, should still fall within the scope of the technical content disclosed by the present invention.

[0033] refer to Figure 1 As shown, this embodiment provides an intelligent marketing analysis and decision-making method based on customer life cycle data, and the method includes the following steps:

[0034] Step S1: Collect several kinds of heterogeneous data source information from customers, clean several kinds of said heterogeneous data source information, and the collection of several kinds of heterogeneous data source information includes: formulating a predetermined event, and after the user's operation behavior on the client triggers the predetermined event, the corresponding said heterogeneous data source information is pushed to the server through the client. When formulating a predetermined event, you can formulate event rules to protect customer privacy. Under the premise of following the principle of customer consent and respecting customer privacy, you can fully control customer data and minimize the burden of data isolation. At the same time, by complying with existing and emerging data privacy regulations and industry standards, establish customer trust and ensure data security and compliance. Several kinds of said heterogeneous data source information include: any one or any combination of order data, user data, behavior data, tracking logs, and third-party anonymized data.

[0035] refer to Figure 2 As shown, cleaning of several types of heterogeneous data source information includes: by normalizing data fields, converting several types of heterogeneous data source messages into distributed message flow platform messages for data transmission. In this embodiment, the distributed message flow platform messages are Kafka messages; performing field mapping, that is, parsing data according to predetermined rules and the standards of the distributed message flow platform to obtain parsed data; formulating cleaning logic, and converting the parsed data into expected data according to the cleaning logic. The expected data is the cleaned heterogeneous data source information.

[0036] refer to Figure 3As shown, converting several types of heterogeneous data source messages into distributed message flow platform messages for data transmission also includes: formulating different calculation types according to different business timeliness requirements or actual enterprise resources, and the different calculation types include: scheduled calculation and real-time calculation.

[0037] Step S2: Establish a data lake warehouse, and store the cleaned information of the heterogeneous data sources in the data lake warehouse.

[0038] Step S3: Load and analyze the data in the customer data lake warehouse according to different business needs to obtain corresponding data analysis results, which specifically includes: Figure 4 As shown, according to different business needs, different architectures are used to load and analyze the data in the data lake warehouse to obtain data analysis results. The different architectures include: a computing engine in a distributed file system or an analytical database in a massively parallel processing architecture. The computing engine in the distributed file system is the mainstream Flink computing engine or Spark computing engine in the Hadoop (distributed file system) ecosystem. The analytical database in the massively parallel processing architecture is the analytical database Doris of the MPP (Massively Parallel Processing) architecture. The data analysis results include: any one or any combination of consumption indicator calculation, user portrait, behavior analysis and data aggregation statistics; the data analysis results are transmitted to different analysis tools through a unified data export service for different marketing analysis and decision-making. The different analysis tools include: any one or any combination of visual reports, terminal devices or marketing systems.

[0039] The above method uniformly collects and cleans data to ensure the accuracy and completeness of the data, establishes a customer data lake warehouse, provides quasi-real-time analysis capabilities, and provides business decision makers with multi-dimensional analysis assistance capabilities. Through a unified customer data lake warehouse, the source data is gradually processed to form a 360-degree customer portrait across all channels, including customer basic information, behavioral preferences, purchase history and other multi-dimensional information, providing companies with accurate customer analysis and marketing strategy support; supports user-defined queries and report generation: provides business decision makers with multi-dimensional analysis assistance capabilities, allowing users to customize queries and generate reports according to needs, thereby improving the flexibility and efficiency of data analysis.

[0040] Thanks to the powerful Hadoop ecosystem, Hadoop ecosystem components can easily achieve global user association analysis and calculation and quasi-real-time user reach, which is difficult to achieve in traditional customer data management and marketing businesses. Figure 5As shown, the following takes the real-time analysis of the user's operation behavior in the car rental process and then infers the content that the user is interested in as an example to introduce the scene landing application. The method is as follows:

[0041] Data requirements: To realize the function of data requirements, it is necessary to ensure that the relevant data can be reported through the corresponding terminal application. In this scenario, it is assumed that after the user browses the quotation list page in the App, browses the quotation details page more than four times within 15 minutes, and returns to the car model quotation list page, it can be preliminarily inferred that the user may be more concerned about the price of different car models. After hitting this rule, we can optimize some business solutions, such as issuing some coupons to users to promote user order rates.

[0042] Data collection: By recording user operations on clients such as apps and mini-programs, in order to avoid collecting user sensitive personal information, we only need to record two events: the user browsed the car model quotation list page and the quotation details page at a certain point in time. Each event will be pushed to the server application in real time after it is triggered. The server can add custom logic to format the data and then forward it to a dedicated message queue channel (such as Kafka, RabbitMq and other mainstream message queue services).

[0043] Data cleaning and processing: The tracking events collected by the client will be consumed by the Flink computing engine. By writing Flink Job task code to consume messages sent by message queues such as Kafka for logical processing, in the specific Job code, we can complete the data aggregation results we want according to the above business rules.

[0044] Since Flink Job can be used as a consumer terminal of mainstream consumer queue services to support direct mass consumption of messages, with the help of high-performance, high-concurrency message queue services such as Kafka, data processing speed can be achieved in milliseconds. After the embedding event is sent from the client, it can be received and processed in milliseconds.

[0045] In this process, we need to use a time window function to maintain the behavior events of each user in the last 15 minutes and sort them by time. Every time a new event is generated by a user, all events in this time window are read and tested according to our expected rules to determine whether there are events that meet our expectations.

[0046] Data application: Once an expected event occurs within a specified time window, we can push the result to interested applications such as a coupon distribution system. After receiving the message, the application system can issue coupons to users and notify them to collect them in the form of SMS or email. If the system can provide instant messaging capabilities, it can also directly reach users who are using the App, making the user experience more friendly and timely.

[0047] In this process, mainstream computing engines such as Flink / Spark can be used to process bounded or unbounded data streams very quickly and easily. The amount of data is no longer a bottleneck, and the data analysis process can be easily accelerated by improving hardware resources. The entire process component is plug-in-based, and applications can be flexibly selected and replaced according to the company's respective technical preferences.

[0048] In summary, the intelligent marketing analysis and decision-making method based on customer life cycle data provided in this embodiment improves marketing efficiency through intelligent analysis and precision marketing support, reduces marketing costs and increases sales revenue by providing comprehensive and precise customer service and marketing support, ensures data consistency and integrity through data cleaning, normalization and standardization, and effectively solves the problem of low data quality in traditional customer data management systems. Real-time data processing capabilities enable real-time processing and analysis of large-scale data, meet the needs of enterprises for real-time data processing, and improve data processing efficiency; provide a variety of multi-dimensional analysis tools and personalized marketing support to help enterprises deeply understand customer needs and behaviors, achieve precision marketing, and improve marketing effectiveness. It solves the problems of data silos and differences between different functional systems, the inability to effectively integrate and uniformly analyze data, and the low accuracy and update speed of customer data.

[0049] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0050] It should be noted that the devices and methods disclosed in the embodiments of this article can also be implemented in other ways. The device implementation described above is only schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of this article. In this regard, each box in the flowchart or block diagram can represent a part of a module, program or code, and the module, program segment or part of the code contains one or more executable instructions for implementing the specified logical function, and the module, program segment or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented by a dedicated hardware-based system for performing a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0051] Although the content of the present invention has been described in detail through the above preferred embodiments, it should be appreciated that the above description should not be considered as a limitation of the present invention. After reading the above content, it will be apparent to those skilled in the art that various modifications and substitutions of the present invention will occur. Therefore, the protection scope of the present invention should be limited by the appended claims.

Claims

1. An intelligent marketing analysis and decision-making method based on customer life cycle data, characterized in that: The method comprises: Step S1: Collecting several types of heterogeneous data source information from customers, and cleaning the several types of heterogeneous data source information; Step S2: Establish a data lake warehouse, and store the cleaned information of the heterogeneous data sources in the data lake warehouse; Step S3: Load and analyze the data in the customer data lake warehouse according to different business needs to obtain corresponding data analysis results.

2. The intelligent marketing analysis and decision-making method based on customer life cycle data according to claim 1, characterized in that: The collection of several types of heterogeneous data source information includes: formulating a predetermined event, and after the user's operation behavior on the client triggers the predetermined event, the corresponding heterogeneous data source information is pushed to the server through the client.

3. The intelligent marketing analysis and decision-making method based on customer life cycle data according to claim 1, characterized in that: The several types of heterogeneous data source information include: any one or any combination of order data, user data, behavior data, tracking logs, and third-party anonymized data.

4. The intelligent marketing analysis and decision-making method based on customer life cycle data according to claim 1, characterized in that: Cleaning the information of several heterogeneous data sources includes: By normalizing data fields, converting several types of heterogeneous data source messages into distributed message flow platform messages for data transmission; Performing field mapping, that is, parsing data according to predetermined rules and the standard of the distributed message flow platform to obtain parsed data; A cleaning logic is formulated, and according to the cleaning logic, the parsed data is converted into expected data, where the expected data is information of the several types of heterogeneous data sources after cleaning.

5. The intelligent marketing analysis and decision-making method based on customer life cycle data according to claim 4, characterized in that: Converting several types of heterogeneous data source messages into distributed message flow platform messages for data transmission also includes: formulating different calculation types according to different business timeliness requirements or actual enterprise resources.

6. The intelligent marketing analysis and decision-making method based on customer life cycle data according to claim 5, characterized in that: The different calculation types include: scheduled calculation and real-time calculation.

7. The intelligent marketing analysis and decision-making method based on customer life cycle data according to claim 1, characterized in that: The data in the customer data lake warehouse is loaded and analyzed according to different business requirements to obtain corresponding data analysis results, which specifically includes: According to different business requirements, different architectures are used to load and analyze the data in the data lake warehouse to obtain data analysis results; The data analysis results are transmitted to different analysis tools through the unified data export service for different marketing analysis and decision-making.

8. The intelligent marketing analysis and decision-making method based on customer life cycle data according to claim 7, characterized in that: The data analysis results include: any one or any combination of consumption index calculation, user profiling, behavior analysis and data aggregation statistics.

9. The intelligent marketing analysis and decision-making method based on customer life cycle data according to claim 7, characterized in that: The different analysis tools include: any one or any combination of visual reports, terminal devices or marketing systems.

10. The intelligent marketing analysis and decision-making method based on customer life cycle data according to claim 7, characterized in that: The different architectures include: a computing engine in a distributed file system or an analytical database in a massively parallel processing architecture.

Images