Big data user behavior analysis method based on edge calculation

Abstract

The invention discloses a big data user behavior analysis method based on edge computing, and relates to the technical field of big data analysis, and the method comprises the steps: collecting user behavior data, and carrying out the primary processing of the data; classifying the primarily processed data by using a built-in algorithm, constructing an evaluation model according to the type of the data, and evaluating the importance and real-time performance of the data; determining a data processing place by using an intelligent routing algorithm according to an evaluation result; according to a routing decision, distributing the data to a corresponding processing place; and synchronizing the data result processed by the edge device with the data result processed by the cloud. According to the method, the processing place of the data is dynamically determined according to the importance score of the data through the intelligent routing algorithm, reasonable allocation of resources is ensured, the probability of the processing place is calculated according to the intelligent routing algorithm, the processing place of the data is determined, the processing place of the data is flexibly determined, and the flexibility and adaptability of data processing are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of big data analysis, and in particular to a big data user behavior analysis method based on edge computing. Background Art

[0002] With the rapid development of information technology, big data analysis has become one of the key technologies for many industries to enhance their competitiveness, especially in the fields of the Internet and e-commerce. Through in-depth analysis of user behavior data, enterprises can better understand user needs. Traditional user behavior analysis methods mainly rely on centralized data centers for data processing and analysis. Due to problems such as long data transmission distances and network delays, it is difficult to meet the needs of real-time analysis. As the amount of data continues to increase, centralized processing methods are also facing pressure on computing resources and storage space, making it difficult to achieve efficient data processing.

[0003] In the field of big data analysis, most existing methods lack a comprehensive evaluation mechanism for data importance and real-time performance, and are unable to effectively distinguish different types of user behavior data, resulting in irrational resource allocation. Data routing algorithms mostly use static configurations and are unable to dynamically adapt to changes in the network environment, resulting in inflexible selection of data transmission paths. Edge computing solutions have a certain lag in data synchronization, and data consistency between edge devices and the cloud is difficult to ensure, affecting the accuracy and timeliness of data analysis. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a big data user behavior analysis method based on edge computing to solve the problems of data transmission delay, unreasonable resource allocation and data synchronization lag in big data user behavior analysis.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: In a first aspect, an embodiment of the present invention provides a big data user behavior analysis method based on edge computing, which includes collecting user behavior data and performing preliminary processing on the data; Use built-in algorithms to classify the data after preliminary processing, and build an evaluation model based on the type of data to evaluate the importance and real-time nature of the data; Based on the evaluation results, an intelligent routing algorithm is used to determine where the data is processed; Based on the routing decision, the data is assigned to the appropriate processing location; Synchronize the data results processed by the edge device with those processed by the cloud.

[0007] As a preferred solution of the big data user behavior analysis method based on edge computing described in the present invention, wherein: collecting user behavior data and preliminarily processing the data includes the following steps: Collect user behavior data on terminal devices, including clicks, browsing, and searches, and record the timestamp, event type, and event content data of user behavior events.

[0008] As a preferred solution of the big data user behavior analysis method based on edge computing described in the present invention, the collected data is preliminarily processed, including the following steps: The collected data is processed to remove null values, outliers, count the number of clicks, views and duplicate data records, and format them.

[0009] As a preferred solution of the big data user behavior analysis method based on edge computing described in the present invention, the built-in algorithm is used to classify the preliminarily processed data, including the following steps: Use built-in algorithms to classify processed data into high-value data and low-value data; Mark the user payment information in the processed data as high-value data; Mark the user browsing history in the processed data as low-value data.

[0010] As a preferred solution of the big data user behavior analysis method based on edge computing described in the present invention, wherein: constructing an evaluation model to evaluate the importance and real-time nature of the data includes the following steps: Extract timestamp, event type and event content features from the preliminarily processed data, select the extracted features to evaluate the importance and real-time nature of the data, and prioritize the data with high importance and real-time nature. Build an evaluation model, extract event type, event content and timestamp data from the original data, train the model, and evaluate the importance and real-time expression of the data: ; in, Score the importance of the evaluation data and, is the timestamp of the event, is the event type, For event content, is the reference timestamp, is the reference event type, For reference event content.

[0011] As a preferred solution of the big data user behavior analysis method based on edge computing described in the present invention, wherein: according to the evaluation results, an intelligent routing algorithm is used to determine the processing location of the data, including the following steps: The importance score of the evaluation data is obtained according to the evaluation model. When the importance score is obtained, the data needs to be processed immediately, and the intelligent routing algorithm is used to determine the processing location of the data. The expression is: ; in, the probability of assigning a processing location to the data, is the overall adjustment parameter, The weight of the timestamp, The importance weight of the event type, is the weight of the event content, is the standard deviation from the event content, is the nonlinear index of event content, is the standard deviation of the event type, is the standard deviation of the timestamps, is the nonlinear exponent of the timestamp; is the nonlinear index of event type, is a parameter for adjusting the importance score.

[0012] As a preferred solution of the big data user behavior analysis method based on edge computing described in the present invention, the data is distributed to the corresponding processing location according to the intelligent routing decision, including the following steps: The probability of processing location is calculated based on the intelligent routing algorithm to determine the processing location of the data; A probability threshold is set based on the probability of the processing location. When the probability of uploading to the cloud is greater than the set probability threshold, it means that the data is of high importance and should be uploaded to the cloud for processing; When the probability of uploading to the cloud is less than the set probability threshold, it means that the data is of low importance and should be processed at the edge device.

[0013] As a preferred solution of the big data user behavior analysis method based on edge computing described in the present invention, wherein: synchronizing the data results processed by the edge device to the cloud processing results includes the following steps: Use a database to record the flow of each piece of data, including the processing location to which the data is assigned and the timestamp information of the processing; Check the data consistency between edge devices and the cloud to ensure there is no duplicate data; Regularly upload the data results processed by the edge device to the cloud, synchronize the edge device data results to the cloud server, and update the processing location in the database.

[0014] In a second aspect, an embodiment of the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the big data user behavior analysis method based on edge computing as described in the first aspect of the present invention is implemented.

[0015] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the big data user behavior analysis method based on edge computing as described in the first aspect of the present invention.

[0016] The beneficial effects of the present invention are as follows: by collecting the behavior data of users on terminal devices, removing null values, abnormal values ​​and duplicate data records, the integrity and accuracy of the data are ensured; the data is classified through a built-in algorithm to distinguish between high-value data and low-value data, so that resource allocation is more reasonable, high-value data is processed first, and the efficiency and accuracy of data processing are improved; an evaluation model is constructed to evaluate the importance of data from timestamps, event types and event content, thereby ensuring the accuracy and timeliness of data processing; an intelligent routing algorithm dynamically determines the processing location of the data according to the importance score of the data, thereby ensuring the reasonable allocation of resources; the probability of the processing location is calculated according to the intelligent routing algorithm, the processing location of the data is determined, and the processing location of the data is flexibly determined, thereby ensuring the flexibility and adaptability of data processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0018] Figure 1 This is a flow chart of the big data user behavior analysis method based on edge computing in Example 1.

[0019] Figure 2 This is a flowchart of processing location allocation for the big data user behavior analysis method based on edge computing in Example 1. DETAILED DESCRIPTION

[0020] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0021] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0022] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0023] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a big data user behavior analysis method based on edge computing, comprising the following steps: S1. Collect user behavior data and perform preliminary processing on the data, including the following steps: Collect user behavior data on terminal devices, including clicks, browsing and searches, and record the timestamp, event type and event content data of user behavior events. Furthermore, the specific pages, links or buttons clicked by users, as well as the time of click, the pages viewed by users, the browsing time, dwell time and scrolling position, and the user's search keywords, search time, number of search result pages and clicked search results are recorded; Accurately record the time of occurrence of each behavioral event, ensure the time series characteristics of the data, clearly mark the type of each behavioral event, and record the specific content of each behavioral event in detail.

[0024] S2. Perform preliminary processing on the collected data, including the following steps: Furthermore, by removing null values ​​and outliers, the integrity of the data is ensured, avoiding analysis errors caused by missing or outlier data; Count clicks and views, generate frequency distribution, provide detailed statistical information on user behavior, and improve data accuracy; Removing duplicate data records ensures data consistency and avoids the impact of duplicate data on analysis results; Formatting converts data into a unified format to facilitate subsequent processing and analysis, thereby improving the analyzability of the data.

[0025] S3. Use the built-in algorithm to classify the preliminarily processed data, including the following steps: Use built-in algorithms to classify processed data into high-value data and low-value data; Mark the user payment information in the processed data as high-value data; Mark the user browsing history in the processed data as low-value data; Furthermore, by dividing data into high-value and low-value data, high-value data can be processed and analyzed first, resource allocation can be optimized, and user payment information can be marked as high-value data, highlighting the importance of this data in business analysis and decision-making, which will help companies better understand user consumption behavior and market trends. User browsing history can be marked as low-value data, reducing the processing burden of low-value data, avoiding the impact of data noise on analysis results, and improving data purity.

[0026] S4. Construct an evaluation model to evaluate the importance and real-time nature of the data, including the following steps: Extract timestamp, event type and event content features from the preliminarily processed data, select the extracted features to evaluate the importance and real-time nature of the data, and prioritize the data with high importance and real-time nature. Build an evaluation model, extract event type, event content and timestamp data from the original data, train the model, and evaluate the importance and real-time expression of the data: ; in, Score the importance of the evaluation data and, is the timestamp of the event, is the event type, For event content, is the reference timestamp, is the reference event type, For reference event content; Furthermore, the timestamp of each event is extracted from the data to evaluate the real-time nature of the data, the type of each event, click, browse, search, etc., is extracted from the data to evaluate the nature of the event, and the content of each event is extracted from the data to evaluate the specific information of the event; Using the timestamp and the reference timestamp, calculate the importance score, the formula Partially ensures that the closer the time is to the reference timestamp, the higher the importance score is, ensuring that data with high importance is processed first; The importance score of the event type is calculated using the event type and the reference event type. This partly ensures that the closer the event type is to the reference event type, the higher the importance score is, ensuring that critical events are prioritized; The importance score of the event content is calculated using the event content and the reference event content. This part ensures that the closer the event content is to the reference event content, the higher the importance score is, ensuring that important data of specific information is processed first.

[0027] S5. Based on the evaluation results, use the intelligent routing algorithm to determine the data processing location, including the following steps: The importance score of the evaluation data is obtained according to the evaluation model. When the importance score is obtained, the data needs to be processed immediately, and the intelligent routing algorithm is used to determine the processing location of the data. The expression is: ; in, the probability of assigning a processing location to the data, is the overall adjustment parameter, The weight of the timestamp, The importance weight of the event type, is the weight of the event content, is the standard deviation from the event content, is the nonlinear index of event content, is the standard deviation of the event type, is the standard deviation of the timestamps, is the nonlinear exponent of the timestamp; is the nonlinear index of event type, To adjust the parameters of importance scoring; Furthermore, the timestamp of the impact item , ensuring that high-real-time data is processed first, improving the system's response speed and user experience; Influence items by event type , ensuring that data of key event types are processed first, improving the pertinence and effectiveness of data processing; Influence items of event content , ensuring that important data of specific information is processed first, improving the precision and accuracy of data processing; By adjusting the parameters of the importance score , ensuring that data with high importance scores are processed first, further optimizing resource allocation; By adjusting the overall parameters, the weights of various influencing factors can be flexibly adjusted to ensure the adaptability of the intelligent routing algorithm.

[0028] S6. Allocate data to corresponding processing locations according to intelligent routing decisions, including the following steps: The probability of processing location is calculated based on the intelligent routing algorithm to determine the processing location of the data; A probability threshold is set based on the probability of the processing location. When the probability of uploading to the cloud is greater than the set probability threshold, it means that the data is of high importance and should be uploaded to the cloud for processing; When the probability of uploading to the cloud is less than the set probability threshold, it means that the data is of low importance and should be processed on the edge device. Furthermore, by setting probability thresholds and reasonably allocating data processing locations, high-importance data can be uploaded to the cloud for processing, ensuring efficient use of resources and avoiding resource waste; Highly important data is uploaded to the cloud for processing first, ensuring the real-time and accuracy of the data, improving response speed and user experience; Processing low-importance data on edge devices reduces the load on the cloud, reduces the energy consumption and operation and maintenance costs of data centers, and improves overall performance.

[0029] S7, synchronizing the data results processed by the edge device to the cloud processing results, including the following steps: Use a database to record the flow of each piece of data, including the processing location to which the data is assigned and the timestamp information of the processing; Check the data consistency between edge devices and the cloud to ensure there is no duplicate data; Regularly upload the data results processed by the edge device to the cloud, synchronize the edge device data results to the cloud server, and update the processing location in the database. Furthermore, by using a database to record the flow of each piece of data, the integrity and traceability of the data are ensured, providing support for subsequent data analysis and auditing. Check the data consistency between edge devices and the cloud to ensure there is no duplicate data, avoid duplication and omission of data processing, and improve data accuracy and reliability; Regularly upload the data processed by edge devices to the cloud to ensure the real-time and consistency of data, improve response speed and user experience; By updating the processing location in the database, the accuracy of the data processing location information is ensured, and the management and scheduling of resources are optimized.

[0030] This embodiment also provides a computer device, which is suitable for the big data user behavior analysis method based on edge computing, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the big data user behavior analysis method based on edge computing proposed in the above embodiment. The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0031] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for implementing big data user behavior analysis based on edge computing proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, disk or optical disk.

[0032] In summary, the present invention collects user behavior data on terminal devices, removes null values, abnormal values ​​and duplicate data records, thereby ensuring the integrity and accuracy of the data; classifies the data through a built-in algorithm, distinguishes between high-value data and low-value data, makes resource allocation more reasonable, prioritizes high-value data, improves the efficiency and accuracy of data processing, constructs an evaluation model, evaluates the importance of data from timestamps, event types and event content, thereby ensuring the accuracy and timeliness of data processing; an intelligent routing algorithm dynamically determines the processing location of the data according to the importance score of the data, thereby ensuring the reasonable allocation of resources; the probability of the processing location is calculated according to the intelligent routing algorithm, the processing location of the data is determined, and the processing location of the data is flexibly determined, thereby ensuring the flexibility and adaptability of data processing.

[0033] Example 2, referring to Table 1, is the second example of the present invention. In order to further verify the technical solution of the present invention, experimental simulation data of a big data user behavior analysis method based on edge computing is provided.

[0034] During the trial, we collected behavioral data from 1,000 users over a month, including click, browse, and search events, and recorded the timestamp, event type, and event content of each event. The experiment used 10 edge devices and 1 cloud server. The edge devices used high-performance embedded computing devices, and the cloud server used a high-configuration server. Use Python programming language and Pandas library to preprocess data, including removing null values, outliers, counting clicks and views, removing duplicate data records, and formatting; During the trial, the user's behavior data on the terminal device is collected through the API interface, and the collected data is pre-processed; Use built-in algorithms to classify the initially processed data into high-value data and low-value data; Mark user payment information as high-value data and user browsing history as low-value data; Extract timestamp, event type and event content features from the preliminarily processed data.

[0035] The extracted features are selected to evaluate the importance and real-time nature of the data.

[0036] Build an evaluation model, extract event type, event content and timestamp data from the original data, train the model, and evaluate the importance of the data. The expression of the evaluation model is: ; in, Score the importance of the evaluation data and, is the timestamp of the event, is the event type, For event content, is the reference timestamp, is the reference event type, For reference event content; The importance score of the evaluation data is obtained based on the evaluation model, and the intelligent routing algorithm is used to determine the data processing location, expression, ; in, the probability of assigning a processing location to the data, is the overall adjustment parameter, The weight of the timestamp, The importance weight of the event type, is the weight of the event content, is the standard deviation from the event content, is the nonlinear index of event content, is the standard deviation of the event type, is the standard deviation of the timestamps, is the nonlinear exponent of the timestamp; is the nonlinear index of event type, is a parameter for adjusting the importance score.

[0037] Use a database to record the flow of each piece of data, including the processing location to which the data is assigned and the timestamp information of the processing; Regularly upload the data results processed by the edge device to the cloud, synchronize the edge device data results to the cloud server, and update the processing location in the database; Check the data consistency between edge devices and the cloud to ensure there is no duplicate data; The details are shown in Table 1 below: Table 1 Experimental record table As can be seen from the table, there are large differences in the number of clicks and views of different users. For example, user A has 120 clicks and 350 views, while user D has 100 clicks and 250 views, which reflects the user's activity level and interest preferences on the website; Data processing time refers to the time required from data collection to data processing completion. The table shows that the average data processing time for all users is 1.8 seconds. This shows that the method of the present invention performs well in data processing efficiency and can complete the processing of a large amount of data in a relatively short time; In particular, user D has the shortest data processing time, which is only 1.5 seconds. This is due to the efficient processing capability of edge computing. Compared with the existing technology, the traditional centralized processing method often requires all data to be uploaded to the cloud for processing, resulting in a longer data processing time. The present invention significantly shortens the data processing time by uploading high-value data to the cloud first and processing low-value data on the edge device. Data transmission delay refers to the time required from data generation to data processing completion. The table shows that the average data transmission delay of all users is 134 milliseconds, which indicates that the method of the present invention performs well in data transmission delay and can realize real-time data processing; User D has the lowest data transmission delay of only 110 milliseconds, thanks to the optimization of the intelligent routing algorithm. Compared with the existing technology, the traditional centralized processing method requires all data to be uploaded to the cloud, resulting in higher data transmission delay. The present invention uses an intelligent routing algorithm to upload high-importance data to the cloud first, and processes low-value data on edge devices, significantly reducing data transmission delay; By uploading high-value data to the cloud and processing low-value data on edge devices, the present invention effectively reduces the load on the cloud. In the experiment, the load on the cloud was reduced by about 30%, and the load on the edge device increased by about 20%, which shows that the present invention is more efficient in resource utilization and avoids resource waste; Compared with the existing technology, the traditional centralized processing method often leads to excessive cloud load, affecting the overall performance of the system. The present invention uses an intelligent routing algorithm to reasonably allocate data processing locations and ensure efficient use of resources. By using a database to record the flow of each piece of data, including the processing location to which the data is assigned and the timestamp information of the processing, the present invention ensures the consistency and integrity of the data. In the experiment, no duplicate data was found and the data synchronization process was smooth; Compared with the prior art, the traditional centralized processing method is prone to data loss and duplication due to frequent data transmission. The present invention ensures the consistency and integrity of data through a data synchronization mechanism and improves the efficiency of data management.

[0038] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A big data user behavior analysis method based on edge computing, characterized by: include, Collect user behavior data and perform preliminary processing on the data; Use built-in algorithms to classify the data after preliminary processing, and build an evaluation model based on the type of data to evaluate the importance and real-time nature of the data; Based on the evaluation results, an intelligent routing algorithm is used to determine where the data is processed; Based on the routing decision, the data is assigned to the appropriate processing location; Synchronize the data results processed by the edge device with those processed by the cloud.

2. The big data user behavior analysis method based on edge computing according to claim 1, characterized in that: Collect user behavior data and perform preliminary processing on the data, including the following steps: Collect user behavior data on terminal devices, including clicks, browsing, and searches, and record the timestamp, event type, and event content data of user behavior events.

3. The big data user behavior analysis method based on edge computing as claimed in claim 2, characterized in that: Conduct preliminary processing of the collected data. The following steps are included: The collected data is processed to remove null values, outliers, count the number of clicks, views and duplicate data records, and format them.

4. The big data user behavior analysis method based on edge computing as claimed in claim 3, characterized in that: Use built-in algorithms to classify the preliminarily processed data, including the following steps, Use built-in algorithms to classify processed data into high-value data and low-value data; Mark the user payment information in the processed data as high-value data; Mark the user browsing history in the processed data as low-value data.

5. The big data user behavior analysis method based on edge computing according to claim 4, characterized in that: Constructing an evaluation model to evaluate the importance and real-time nature of data includes the following steps: Extract timestamp, event type and event content features from the preliminarily processed data, select the extracted features to evaluate the importance and real-time nature of the data, and prioritize the data with high importance and real-time nature. Build an evaluation model, extract event type, event content and timestamp data from the original data, train the model, and evaluate the importance and real-time expression of the data: ； in, Score the importance of the evaluation data and, is the timestamp of the event, is the event type, For event content, is the reference timestamp, is the reference event type, For reference event content.

6. The big data user behavior analysis method based on edge computing according to claim 5, characterized in that: Based on the evaluation results, an intelligent routing algorithm is used to determine the data processing location, including the following steps: The importance score of the evaluation data is obtained according to the evaluation model. When the importance score is obtained, the data needs to be processed immediately, and the intelligent routing algorithm is used to determine the processing location of the data. The expression is: ； in, the probability of assigning a processing location to the data, is the overall adjustment parameter, The weight of the timestamp, The importance weight of the event type, is the weight of the event content, is the standard deviation from the event content, is the nonlinear index of event content, is the standard deviation of the event type, is the standard deviation of the timestamps, is the nonlinear exponent of the timestamp; is the nonlinear index of event type, is a parameter for adjusting the importance score.

7. The big data user behavior analysis method based on edge computing according to claim 6, characterized in that: According to the intelligent routing decision, the data is allocated to the corresponding processing location, including the following steps, The probability of processing location is calculated based on the intelligent routing algorithm to determine the processing location of the data; A probability threshold is set based on the probability of the processing location. When the probability of uploading to the cloud is greater than the set probability threshold, it means that the data is of high importance and should be uploaded to the cloud for processing; When the probability of uploading to the cloud is less than the set probability threshold, it means that the data is of low importance and should be processed at the edge device.

8. The big data user behavior analysis method based on edge computing according to claim 7, characterized in that: Synchronizing the data processed by the edge device to the cloud processing results includes the following steps: Use a database to record the flow of each piece of data, including the processing location to which the data is assigned and the timestamp information of the processing; Check the data consistency between edge devices and the cloud to ensure there is no duplicate data; Regularly upload the data results processed by the edge device to the cloud, synchronize the edge device data results to the cloud server, and update the processing location in the database.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the big data user behavior analysis method based on edge computing are implemented in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the big data user behavior analysis method based on edge computing are implemented in any one of claims 1 to 8.

Images