Merchant cashier data monitoring management system based on data analysis

Abstract

The invention discloses a merchant cashier data monitoring and management system based on data analysis, and particularly relates to the technical field of data analysis, trade data and customer information of a merchant are collected, the collected trade data and customer information are packaged through an API interface, the packaged trade data and customer information are submitted to a block chain through an intelligent contract, historical trade data are extracted from the block chain, and the historical trade data are stored in a database; data cleaning is carried out, the data is stored in a data warehouse, data analysis is supported, the total consumption amount, consumption frequency and purchase frequency indexes of each customer are calculated according to the purchase history of the customers, analysis results are synthesized, customer portraits are established, and the customer portraits and historical purchase data are acquired based on the customer portraits and the historical purchase data. According to the method, personalized commodity recommendation is generated by adopting a collaborative filtering algorithm, a recommendation result is fed back to a block chain, and based on real-time transaction data on the block chain, an abnormal transaction monitoring standard is set, and when an abnormal condition is found, an early warning is sent to a merchant to remind the merchant to pay attention.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and more specifically, to a merchant cashier data monitoring and management system based on data analysis. Background Art

[0002] In today's business environment, data analysis plays an increasingly important role, especially in the retail and catering industries. The challenge facing merchants is not only how to increase sales, but also how to effectively manage and monitor cash register data. With the popularity of electronic payments, merchants accumulate a large amount of transaction data every day. These data contain rich information and can provide merchants with deep insights and help business decisions.

[0003] Traditional cashier management often relies on manual records and simple financial statements, which cannot reflect the actual business conditions of merchants in a timely manner. This not only easily leads to omissions and errors in data, but also makes merchants slow to respond to market changes. Therefore, it is particularly important to build a merchant cashier data monitoring and management system based on data analysis. The system can monitor and analyze cashier data in real time, help merchants grasp business dynamics, and discover potential problems. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a merchant cashier data monitoring and management system based on data analysis to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above-mentioned purpose, the present invention provides the following technical solution: a merchant cashier data monitoring and management system based on data analysis, comprising a data collection module, a data analysis module, a commodity recommendation module, and an early warning module;

[0006] The data collection module is used to collect merchant transaction data and customer information, and submit the collected transaction data to the blockchain through the API interface via a smart contract;

[0007] The data analysis module extracts historical transaction data from the blockchain, establishes a data warehouse to support data analysis, and creates customer portraits based on the customer's purchase history;

[0008] The product recommendation module generates personalized product recommendations based on customer portraits and historical purchase data using a collaborative filtering algorithm, and feeds the recommendation results back to the blockchain;

[0009] The early warning module sets monitoring standards for abnormal transactions based on real-time transaction data on the blockchain. When an abnormal situation is found, an early warning is issued to the merchant to remind the merchant to pay attention.

[0010] In a preferred embodiment, the data collection module is used to collect merchant transaction data and customer information, and submit the collected transaction data to the blockchain through the API interface through the smart contract to ensure the data is tamper-proof and transparent. The specific steps are as follows:

[0011] Step A1, data collection: collect customer information through customer registration membership cards, including customer ID, gender, age, and contact information, install and configure code scanning equipment, obtain product ID and price information, and record transaction time, transaction amount, product ID, customer ID, and payment method information in the cash register system. After the customer completes the payment at the merchant, a transaction receipt is generated for the customer to view and verify, and the collected transaction data and customer information are packaged through the API interface, and the data is submitted to the blockchain using smart contracts;

[0012] Step A2, data check: Format verification of collected transaction data and customer information to ensure that the data types and formats of all fields meet expectations, check whether there are duplicate transaction records and customer information to avoid submitting duplicate data on the blockchain, generate data summaries, and provide a unique identifier for transaction data submitted to the blockchain to ensure data integrity.

[0013] In a preferred embodiment, the data analysis module extracts historical transaction data from the blockchain, establishes a data warehouse to support data analysis, and establishes a customer profile based on the customer's purchase history. The specific steps are as follows:

[0014] Step B1, data extraction: extract historical transaction data from the blockchain through the API interface, including customer ID, transaction time, transaction amount, and product ID information, and perform data cleaning to store the data in the data warehouse;

[0015] Step B2, building a customer portrait: Aggregate transaction data according to customer ID, calculate the total consumption amount, consumption frequency and purchase number indicators of each customer, comprehensively analyze the results, extract transaction behavior characteristics and preference characteristics, and build a customer portrait, further including the following steps:

[0016] Step B201, data analysis: Aggregate transaction data according to customer ID to calculate the total consumption amount, consumption frequency and purchase number indicators of each customer. The specific calculation formula for the total consumption amount is: Among them, M i is the total consumption amount of customer i, A ij is the amount of customer i's transaction in the αth transaction, and n is the total number of transactions of customer i. The specific calculation formula for the consumption frequency is: Among them, F i is the consumption frequency of customer i, N iis the number of purchases by customer i, and T is the number of days the customer is active. The specific calculation formula for the number of purchases is: Among them, N i is the number of purchases by customer i, m is the total number of transaction records of customer i during the analysis period, i,j is the identifier of customer i in the αth transaction. If the customer has made a purchase in the αth transaction, it is counted as 1, otherwise it is counted as 0;

[0017] Step B202, feature extraction: extract the characteristics of each customer, including transaction behavior characteristics and preference characteristics. The transaction behavior characteristics include the average transaction amount, the maximum single transaction amount of customer i, and the minimum single purchase amount The specific calculation formula for the average transaction amount is: Q i represents the average amount of money spent by customer i in each transaction, M i is the total consumption amount of customer i, N i is the number of purchases by customer i; the preference characteristics include hot product preferences and hot product IDs. The number of times customer i purchases products is sorted to obtain the hot product IDs. The above indicators are combined to construct a comprehensive customer portrait. The mathematical expression is: Among them, V i is a comprehensive portrait of customer i, M i is the total consumption amount of customer i, F i is the consumption frequency of customer i, N i is the number of purchases by customer i, and are the maximum and minimum single transaction amounts of customer i, Q i is the average spending amount of customer i, H i is the popular product ID of customer i.

[0018] In a preferred embodiment, the product recommendation module generates personalized product recommendations based on customer portraits and historical purchase data using a collaborative filtering algorithm, and feeds the recommendation results back to the blockchain. The specific steps are as follows:

[0019] Step C1, calculate user similarity: use the features in the customer portrait to calculate the similarity between customers. The specific calculation formula is as follows:

[0020]

[0021] Among them, sim(V i ,V j ) is the similarity between customer i and customer j, V i and V jare the comprehensive portraits of customer i and customer j, M i and M j are the total consumption amounts of customers i and j, respectively, and F i and F j are the consumption frequencies of customer i and customer j, respectively, and N i and N j are the purchase times of customer i and customer j respectively, and are the maximum and minimum single transaction amounts of customer i, respectively. and are the maximum and minimum single transaction amounts of customer j, Q i and Q j are the average spending amounts of customer i and customer j respectively;

[0022] Step C2, generate recommended products: by calculating the similarity between users, predict the score of customer i for the unpurchased products. The prediction score formula is: Among them, L(i) is the set of customers similar to customer i, R[j] is the real rating of customer j for the product, sim(V i ,V j ) is the similarity between customer i and customer j, R[i][j] is the rating of customer i for the unpurchased product;

[0023] The highest-rated items are selected for recommendation based on the predicted scores, and the recommendation results are recorded on the blockchain to ensure data security and transparency.

[0024] In a preferred embodiment, the early warning module sets monitoring standards for abnormal transactions based on real-time transaction data on the blockchain. When an abnormal situation is found, an early warning is issued to the merchant to remind the merchant to pay attention. The specific steps are as follows:

[0025] Step D1: Extract real-time transaction data from the blockchain, including transaction amount, transaction time, transaction type, and customer ID. Compare the real-time transaction data with the customer's historical data, calculate the abnormality of the consumption amount and frequency characteristics, and score the abnormality of each transaction. The abnormality of the consumption amount is The abnormal degree of the consumption frequency is Among them, Z A is the abnormal score of the consumption amount, A k is the consumption amount of the kth transaction, μ A is the historical average consumption amount, σ A is the standard deviation of historical consumption amount; Z F is the abnormal score of consumption frequency, F k is the consumption frequency of the kth transaction, μ Fis the historical average consumption frequency, σ F is the standard deviation of historical consumption frequency;

[0026] Step D2: Combine the abnormal scores of consumption amount and frequency to calculate the comprehensive abnormal score. Set the warning standard as ξ according to the comprehensive abnormal score. 综 >ξ, it is judged as an abnormal transaction, and a warning message including transaction ID, amount, time, and customer ID information is generated. The comprehensive abnormality score is: Z 综 =λZ A +γZ F , where Z 综 is the comprehensive anomaly score, λ and γ are weight parameters, and Z F is the abnormal score of consumption frequency, Z A is the abnormality score of the consumption amount.

[0027] The beneficial effects of the present invention are as follows: collecting the transaction data and customer information of merchants, and packaging the collected transaction data and customer information through an API interface, submitting them to the blockchain through a smart contract, extracting historical transaction data from the blockchain, and performing data cleaning to store the data in a data warehouse to support data analysis, and calculating the total consumption amount, consumption frequency and purchase times of each customer based on the customer's purchase history, comprehensively analyzing the results, establishing a customer portrait, and using a collaborative filtering algorithm to generate personalized product recommendations based on the customer portrait and historical purchase data, which can enhance the customer's shopping experience, and feeding back the recommendation results to the blockchain, setting monitoring standards for abnormal transactions based on real-time transaction data on the blockchain, and issuing an early warning to the merchant when an abnormal situation is found, and ensuring the immutability and transparency of the data by recording the relevant information of each transaction on the blockchain, and recommending related products based on real-time sales data and customer purchase behavior, thereby promoting sales growth. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0030] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0031] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0032] Example 1

[0033] This embodiment provides Figure 1 A merchant cashier data monitoring and management system based on data analysis is shown, which specifically includes a data collection module, a data analysis module, a commodity recommendation module, and an early warning module;

[0034] The data collection module is used to collect merchant transaction data and customer information, and submit the collected transaction data to the blockchain through the API interface via a smart contract;

[0035] The data analysis module extracts historical transaction data from the blockchain, establishes a data warehouse to support data analysis, and creates customer portraits based on the customer's purchase history;

[0036] The product recommendation module generates personalized product recommendations based on customer portraits and historical purchase data using a collaborative filtering algorithm, and feeds the recommendation results back to the blockchain;

[0037] The early warning module sets monitoring standards for abnormal transactions based on real-time transaction data on the blockchain. When an abnormal situation is found, an early warning is issued to the merchant to remind the merchant to pay attention.

[0038] In this embodiment, the data collection module specifically needs to be explained. The data collection module is used to collect the merchant's transaction data and customer information, and submit the collected transaction data to the blockchain through the API interface through the smart contract to ensure that all transaction data and customer information records are tamper-proof, providing a reliable data foundation for the merchant. The specific steps are as follows:

[0039] Step A1, data collection: collect customer information, including customer ID, gender, age, and contact information, through customer registration membership cards, install and configure code scanning equipment, obtain product ID and price information, and record transaction time, transaction amount, product ID, customer ID, and payment method information in the cash register system. After the customer completes the payment at the merchant, a transaction receipt is generated for the customer to view and verify, and the collected transaction data and customer information are packaged through the API interface, and the data is submitted to the blockchain using a smart contract. The smart contract is an automatically executed contract deployed on the blockchain, in which the contract terms are directly written into the code and run on the blockchain. Once the preset conditions are met, it will be automatically executed;

[0040] Step A2, data check: Format verification of collected transaction data and customer information to ensure that the data types and formats of all fields meet expectations, check whether there are duplicate transaction records and customer information to avoid submitting duplicate data on the blockchain, generate data summaries, and provide a unique identifier for transaction data submitted to the blockchain to ensure data integrity.

[0041] In this embodiment, the data analysis module specifically needs to be explained. The data analysis module extracts historical transaction data from the blockchain, establishes a data warehouse to support data analysis, and establishes customer portraits based on the customer's purchase history to help merchants provide customized services and products based on the actual needs of customers. The specific steps are as follows:

[0042] Step B1, data extraction: extract historical transaction data from the blockchain through the API interface, including customer ID, transaction time, transaction amount, and product ID information, and perform data cleaning to store the data in the data warehouse;

[0043] Step B2, building a customer portrait: Aggregate transaction data according to customer ID, calculate the total consumption amount, consumption frequency and purchase number indicators of each customer, comprehensively analyze the results, extract transaction behavior characteristics and preference characteristics, and build a customer portrait, further including the following steps:

[0044] Step B201, data analysis: Aggregate transaction data according to customer ID to calculate the total consumption amount, consumption frequency and purchase number indicators of each customer. The specific calculation formula for the total consumption amount is: Among them, M iis the total consumption amount of customer i, A ij is the amount of customer i's transaction in the αth transaction, and n is the total number of transactions of customer i. The specific calculation formula for the consumption frequency is: Among them, F i is the consumption frequency of customer i, N i is the number of purchases by customer i, and T is the number of days the customer is active. The specific calculation formula for the number of purchases is: Among them, N i is the number of purchases by customer i, m is the total number of transaction records of customer i during the analysis period, i,j is the identifier of customer i in the αth transaction. If the customer has made a purchase in the αth transaction, it is counted as 1, otherwise it is counted as 0;

[0045] Step B202, feature extraction: extract the characteristics of each customer, including transaction behavior characteristics and preference characteristics. The transaction behavior characteristics include the average transaction amount, the maximum single transaction amount of customer i, and the minimum single purchase amount The specific calculation formula for the average transaction amount is: Q i represents the average amount of money spent by customer i in each transaction, M i is the total consumption amount of customer i, N i is the number of purchases by customer i; the preference characteristics include hot product preferences and hot product IDs. The number of times customer i purchases products is sorted to obtain the hot product IDs. The above indicators are combined to construct a comprehensive customer portrait. The mathematical expression is: Among them, V i is a comprehensive portrait of customer i, M i is the total consumption amount of customer i, F i is the consumption frequency of customer i, N i is the number of purchases by customer i, and are the maximum and minimum single transaction amounts of customer i, Q i is the average spending amount of customer i, H i It is the popular product ID of customer i. Through data analysis, merchants can have a more comprehensive understanding of customer's spending power and habits, provide customers with personalized product recommendations, and increase customer satisfaction and willingness to buy.

[0046] In this embodiment, the product recommendation module specifically needs to be explained. The product recommendation module uses a collaborative filtering algorithm to generate personalized product recommendations based on customer portraits and historical purchase data, and feeds the recommendation results back to the blockchain to ensure that all interactive data is recorded in real time and reduce the risk of data leakage. The specific steps are as follows:

[0047] Step C1, calculate user similarity: use the features in the customer portrait to calculate the similarity between customers. The specific calculation formula is as follows:

[0048]

[0049] Among them, sim(V i ,V j ) is the similarity between customer i and customer j, V i and V j are the comprehensive portraits of customer i and customer j, M i and M j are the total consumption amounts of customers i and j, respectively, and F i and F j are the consumption frequencies of customer i and customer j, respectively, and N i and N j are the purchase times of customer i and customer j respectively, and are the maximum and minimum single transaction amounts of customer i, respectively. and are the maximum and minimum single transaction amounts of customer j, Q i and Q j are the average spending amounts of customer i and customer j respectively;

[0050] Step C2, generate recommended products: by calculating the similarity between users, predict the score of customer i for the unpurchased products. The score of customer i for the unpurchased products is: Among them, L(i) is the set of customers similar to customer i, R[j] is the real rating of customer j for the product, sim(V i ,V j ) is the similarity between customer i and customer j, R[i][j] is the rating of customer i for the unpurchased product;

[0051] The products with the highest scores are selected for recommendation based on the predicted scores, and the recommendation results are recorded on the blockchain. By utilizing the transparency and real-time data flow of the blockchain, it is possible to respond quickly to changes in market demand.

[0052] In this embodiment, the early warning module specifically needs to be explained. The early warning module sets monitoring standards for abnormal transactions based on real-time transaction data on the blockchain. When an abnormal situation is found, an early warning is issued to the merchant to remind the merchant to pay attention, which can reduce the risk of customers in the transaction process and improve the customer experience. The specific steps are as follows:

[0053] Step D1: Extract real-time transaction data from the blockchain, including transaction amount, transaction time, transaction type, and customer ID. Compare the real-time transaction data with the customer's historical data, calculate the abnormality of the consumption amount and frequency characteristics, and score the abnormality of each transaction. The abnormality of the consumption amount is The abnormal degree of the consumption frequency is Among them, Z A is the abnormal score of the consumption amount, A k is the consumption amount of the kth transaction, μ A is the historical average consumption amount, σ A is the standard deviation of historical consumption amount; Z F is the abnormal score of consumption frequency, F k is the consumption frequency of the kth transaction, μ F is the historical average consumption frequency, σ F is the standard deviation of historical consumption frequency;

[0054] Step D2: Combine the abnormal scores of consumption amount and frequency to calculate the comprehensive abnormal score. Set the warning standard as ξ according to the comprehensive abnormal score. 综 >ξ, it is judged as an abnormal transaction, and a warning message including transaction ID, amount, time, and customer ID information is generated. The comprehensive abnormality score is: Z 综 =λZ A +γZ F , where Z 综 is the comprehensive anomaly score, λ and γ are weight parameters, and Z F is the abnormal score of consumption frequency, Z A is the abnormality score of the consumption amount.

[0055] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0056] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0057] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0058] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0059] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0060] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0061] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A merchant cashier data monitoring and management system based on data analysis, characterized by: It includes data collection module, data analysis module, product recommendation module, and early warning module; The data collection module is used to collect merchant transaction data and customer information, and submit the collected transaction data to the blockchain through the API interface via a smart contract; The data analysis module extracts historical transaction data from the blockchain, establishes a data warehouse to support data analysis, and creates customer portraits based on the customer's purchase history; The product recommendation module generates personalized product recommendations based on customer portraits and historical purchase data using a collaborative filtering algorithm, and feeds the recommendation results back to the blockchain; The early warning module sets monitoring standards for abnormal transactions based on real-time transaction data on the blockchain. When an abnormal situation is found, an early warning is issued to the merchant to remind the merchant to pay attention.

2. A merchant cashier data monitoring and management system based on data analysis according to claim 1, characterized in that: The data collection module is used to collect merchant transaction data and customer information, and submit the collected transaction data to the blockchain through the API interface through the smart contract. The specific steps are as follows: Step A1, data collection: collect customer information through customer registration membership cards, including customer ID, gender, age, and contact information, install and configure code scanning equipment, obtain product ID and price information, and record transaction time, transaction amount, product ID, customer ID, and payment method information in the cash register system. After the customer completes the payment at the merchant, a transaction receipt is generated for the customer to view and verify, and the collected transaction data and customer information are packaged through the API interface, and the data is submitted to the blockchain using smart contracts; Step A2, data check: Verify the format of the collected transaction data and customer information, check whether there are duplicate transaction records and customer information, and generate a data summary to provide a unique identifier for the transaction data submitted to the blockchain to ensure data integrity.

3. A merchant cashier data monitoring and management system based on data analysis according to claim 1, characterized in that: The data analysis module extracts historical transaction data from the blockchain, establishes a data warehouse to support data analysis, and creates a customer profile based on the customer's purchase history. The specific steps are as follows: Step B1, data extraction: extract historical transaction data from the blockchain through the API interface, including customer ID, transaction time, transaction amount, and product ID information, and perform data cleaning to store the data in the data warehouse; Step B2: Construct customer portrait: Aggregate transaction data based on customer ID, calculate the total consumption amount, consumption frequency and purchase number indicators of each customer, comprehensively analyze the results, extract transaction behavior characteristics and preference characteristics, and construct customer portrait. The mathematical expression is: Among them, V i is a comprehensive portrait of customer i, M i is the total consumption amount of customer i, F i is the consumption frequency of customer i, N i is the number of purchases by customer i, and are the maximum and minimum single transaction amounts of customer i, Q i is the average spending amount of customer i, H i is the popular product ID of customer i.

4. A merchant cashier data monitoring and management system based on data analysis according to claim 3, characterized in that: The step B2 of constructing the customer portrait further includes the following steps: Step B201, data analysis: Aggregate transaction data according to customer ID to calculate the total consumption amount, consumption frequency and purchase number indicators of each customer. The specific calculation formula for the total consumption amount is: Among them, M i is the total consumption amount of customer i, A ij is the amount of customer i's transaction in the αth transaction, and n is the total number of transactions of customer i. The specific calculation formula for the consumption frequency is: Among them, F i is the consumption frequency of customer i, N i is the number of purchases by customer i, and T is the number of days the customer is active. The specific calculation formula for the number of purchases is: Among them, N i is the number of purchases by customer i, m is the total number of transaction records of customer i during the analysis period, i,j is the identifier of customer i in the αth transaction; Step B202, feature extraction: extract the characteristics of each customer, including transaction behavior characteristics and preference characteristics. The transaction behavior characteristics include the average transaction amount, the maximum single transaction amount of customer i, and the minimum single purchase amount The specific calculation formula for the average transaction amount is: Q i represents the average amount of money spent by customer i in each transaction, M i is the total consumption amount of customer i, N i is the number of purchases by customer i; the preference characteristics include hot product preferences and hot product IDs. The number of times customer i purchases products is sorted to obtain the hot product IDs. The above indicators are combined to construct a comprehensive customer portrait.

5. The merchant cashier data monitoring and management system based on data analysis according to claim 1, characterized in that: The product recommendation module uses collaborative filtering algorithm to generate personalized product recommendations based on customer portraits and historical purchase data, and feeds the recommendation results back to the blockchain. The specific steps are as follows: Step C1, calculate user similarity: use the features in the customer portrait to calculate the similarity between customers. The specific calculation formula is as follows: Among them, sim(V i ,V j ) is the similarity between customer i and customer j, V i and V j are the comprehensive portraits of customer i and customer j, M i and M j are the total consumption amounts of customers i and j, respectively, and F i and F j are the consumption frequencies of customer i and customer j, respectively, N i and N j are the purchase times of customer i and customer j respectively, and are the maximum and minimum single transaction amounts of customer i, respectively. and are the maximum and minimum single transaction amounts of customer j, Q i and Q j are the average spending amounts of customer i and customer j respectively; Step C2, generate recommended products: by calculating the similarity between users, predict the rating of customer i for the unpurchased products, select the highest-rated products for recommendation based on the predicted ratings, and record the recommendation results on the blockchain to ensure data security and transparency.

6. The merchant cashier data monitoring and management system based on data analysis according to claim 1, characterized in that: In step C2, the specific calculation formula for customer i's rating of the unpurchased product is: Among them, L(i) is the set of customers similar to customer i, R[j] is the real rating of customer j for the product, sim(V i ,V j ) is the similarity between customer i and customer j, and R[i][j] is the rating given by customer i to the unpurchased product.

7. The merchant cashier data monitoring and management system based on data analysis according to claim 1, characterized in that: The early warning module sets monitoring standards for abnormal transactions based on real-time transaction data on the blockchain. When an abnormal situation is found, an early warning is issued to the merchant to remind the merchant to pay attention. The specific steps are as follows: Step D1: Extract real-time transaction data from the blockchain, including transaction amount, transaction time, transaction type, and customer ID. Compare the real-time transaction data with the customer's historical data, calculate the abnormality of the consumption amount and frequency characteristics, and score the abnormality of each transaction. The abnormality of the consumption amount is The abnormal degree of the consumption frequency is Among them, Z A is the abnormal score of the consumption amount, A k is the consumption amount of the kth transaction, μ A is the historical average consumption amount, σ A is the standard deviation of historical consumption amount; Z F is the abnormal score of consumption frequency, F k is the consumption frequency of the kth transaction, μ F is the historical average consumption frequency, σ F is the standard deviation of historical consumption frequency; Step D2: Combine the abnormal scores of consumption amount and frequency to calculate the comprehensive abnormal score. Set the warning standard as ξ according to the comprehensive abnormal score. 综 >ξ, it is judged as an abnormal transaction, and a warning message including transaction ID, amount, time, and customer ID information is generated. The comprehensive abnormality score is: Z 综 =λZ A +γZ F , where Z 综 is the comprehensive anomaly score, λ and γ are weight parameters, and Z F is the abnormal score of consumption frequency, Z A is the abnormality score of the consumption amount.

Images