Special number quality risk management and control system and method for brand franchise gas station

Abstract

The invention discloses a data quality risk management and control system and method special for a brand joining gas station, and belongs to the technical field of gas station safety management and control, and the system comprises a basic data acquisition module which comprises historical refueling data, risk type data and real-time refueling data; the historical refueling data comprises historical inventory data and historical sales detail data; the risk type data comprises M management and control risks; the real-time refueling data comprises real-time inventory data and real-time sales detail data; the data analysis module analyzes the historical refueling data, the historical sales detail data and the risk type data to establish relevance among the historical refueling data, the historical sales detail data and the risk type data; and the management and control output module analyzes the real-time refueling data, the real-time sales detail data and the relevance to output risk type data existing in each brand franchise gas station at present. According to the method, whether the management and control risk exists in each brand franchise gas station or not and which type of management and control risk exists can be quickly and accurately analyzed.

Description

Technical Field

[0001] The present invention belongs to the technical field of gas station safety management and control, and specifically relates to a data quality risk management and control system and method dedicated to brand franchise gas stations. Background Art

[0002] In modern society, gas stations play a vital role. They are places that provide fuel for various motor vehicles, and they mainly sell oil products such as gasoline, diesel, and motor oil. With the rapid economic growth and the improvement of people's living standards, the number of cars and other motor vehicles has shown an explosive growth trend. This phenomenon has directly led to the vigorous development of the gas station industry, and both the number of brands and the scale of gas stations are constantly expanding. However, with the increase in the number of gas stations, various brands and models of oil products have appeared on the market, each with unique quality and performance characteristics. Due to the differences in quality and performance of these oil products, their cost-effectiveness is also different, which provides consumers with more choices, but also provides some gas stations with opportunities to engage in improper business practices.

[0003] Among many gas stations, some well-known brands usually adopt a franchise business model in order to expand their market share and maintain the quality standards of their products. This model allows other operators to use their brands and trademarks in exchange for certain franchise fees and management fees. However, in the actual operation process, this franchise model also exposes some problems and defects. For example, in order to pursue higher profits, some franchise gas stations may adopt improper means, such as adding water to the oil depot or injecting other low-value brands of oil to reduce costs. In addition, in order to avoid regulatory risks, some gas stations may deliberately cut off the inventory detection system or tamper with the sales data transmission system to cover up their illegal behavior. Some gas stations also seek personal gain by stealing oil, changing oil or withholding consumer rights.

[0004] In view of the above problems, in order to ensure that brand franchise gas stations can operate legally and in compliance with regulations and protect the legitimate rights and interests of consumers, it is particularly important to develop a set of data quality risk control systems and methods specifically for brand franchise gas stations. Such a system and method can effectively monitor and manage the operation process of gas stations, ensure that the quality and quantity of oil products meet the standards, prevent illegal activities, and thus maintain the healthy development of the entire industry and the vital interests of consumers. Summary of the invention

[0005] In order to solve the technical problems existing in the known technology, the present invention provides a data quality risk control system and method dedicated to brand franchise gas stations. Through the correlation between refueling data and risk type data, it is possible to quickly and accurately analyze whether each brand franchise gas station has a control risk and what type of control risk exists.

[0006] The first object of the present invention is to provide a digital quality risk management system dedicated to brand franchise gas stations, including:

[0007] A basic data acquisition module, wherein the basic data includes historical refueling data, risk type data and real-time refueling data; the historical refueling data includes historical inventory data and historical sales detail data of each brand franchised gas station within a historical period; the risk type data includes M types of management and control risks; the real-time refueling data includes real-time inventory data and real-time sales detail data of each brand franchised gas station; M is a natural number greater than 1;

[0008] The data analysis module establishes the correlation between historical refueling data and risk type data by analyzing historical refueling data, historical sales detail data and risk type data;

[0009] The management and control output module outputs the risk type data of each brand franchised gas station by analyzing the real-time refueling data, real-time sales detail data and correlation.

[0010] Preferably, the basic data acquisition module detects the inventory data of each brand franchised gas station in real time through a liquid level meter system, and acquires the sales details data of each brand franchised gas station in real time through an Internet of Things gas station management system.

[0011] Preferably, the management and control risks include: inventory data missing risk, sales data missing risk, unauthorized oil intake risk, abnormal loss and spill risk, failure to install waterproof filter element, quality risk of unloading and sending at the same time, and quality risk of overdue storage of oil products.

[0012] Preferably, the association includes the following logical judgment:

[0013] When the inventory data of a franchised gas station is lost within a period of time, there is a risk of missing inventory data. Otherwise, there is no risk of missing inventory data.

[0014] If the sales data of a brand franchised gas station is not lost within a period of time, there is no risk of sales data loss. Otherwise, the following threshold judgment is entered: If the sales data of a brand franchised gas station is lost within a period of time, the inventory data within the period is calculated to obtain the tank inventory data L1 before the sales details are lost and the tank inventory data L2 after the sales details are lost. The change range between L1 and L2 is calculated. If the change range exceeds the risk control threshold X, there is a risk of sales data loss; if the change range does not exceed the threshold X, there is no risk of sales data loss.

[0015] When a franchised gas station privately introduces oil without permission, there is a risk of private oil imports. Otherwise, there is no risk of private oil imports. Specifically: first, establish a corresponding relationship between gas stations and purchase data. According to the contract, the oil products purchased by the franchised gas station must be supplied by the brand's oil depot. Every day, the brand's oil depot automatically counts the delivery volume L3 of the gas station through the gas station code and oil type data. The actual purchase data of the gas station every day is automatically calculated by the system through historical inventory details L4. When the delivery volume L3 is less than the actual receipt volume L4 of the gas station, the threshold is clarified according to the brand's management agreement, and there is a risk of private oil imports by the franchised gas station.

[0016] Abnormal loss and surplus risk: Calculate monthly loss by product type, the inventory at the beginning of the month is L5, the cumulative shipment of this product from the brand's oil depot to the oil depot is L6, the cumulative sales volume of the gas station during the cycle is L7, and the inventory at the end of the month is L8. Calculate the monthly loss S; S = L5 + L6 - L7 - L8. Define the threshold according to the brand's management agreement. When S exceeds the threshold, there is an "abnormal loss and surplus" risk;

[0017] Failure to install waterproof filter cartridges and quality risks of unloading and shipping: Actively identify sales behaviors during the gas station receiving process, match waterproof filter cartridge information with brand franchise stations that have sales behaviors during the gas station purchase process, and issue risk reminders for not installing waterproof filter cartridges for brand gas stations without valid waterproof filter cartridge information;

[0018] Quality risk of overdue storage of oil products: According to the management agreement of the brand, the storage time thresholds of different types of oil products are clearly defined. Through analysis of detailed inventory data, the oil filling behavior of the oil tank is identified. The first oil filling time is marked as T1, and the second oil filling time is marked as T2. If the time interval between T1 and T2 exceeds the time threshold agreed by the brand, quality inspection information is matched. If there is no quality inspection information, or the quality inspection results do not meet the quality standards set by the brand, there is a risk of overdue storage.

[0019] Preferably, the correlation is completed by a neural network model. First, the historical refueling data, historical sales detail data and risk type data are preprocessed to remove non-objective data generated by human factors; then, according to the chronological order, the preprocessed historical refueling data, historical sales detail data and risk type data are divided into data groups (X t , Y t ), where X t represents the historical refueling data at time t, Y t Represents the historical sales details at time t, Z t represents the risk type data at time t; finally, the data group (X t , Y t , Z t ) is divided into a training set and a test set, and the neural network model is imported for training to obtain a trained neural network model.

[0020] Preferably, it also includes a portrait module, which draws an inventory level curve based on real-time inventory data and draws a theoretical inventory curve based on inventory data, purchase data and sales detail data.

[0021] The second object of the present invention is to provide a data quality risk control method dedicated to brand franchise gas stations, comprising the following steps:

[0022] S1. Obtain basic data, including historical refueling data, risk type data and real-time refueling data; the historical refueling data includes historical inventory data and historical sales details data of each brand franchised gas station within a historical period; the risk type data includes M types of management and control risks; the real-time refueling data includes real-time inventory data and real-time sales details data of each brand franchised gas station; M is a natural number greater than 1;

[0023] S2. Data analysis: by analyzing historical refueling data, historical sales detail data and risk type data, the correlation between historical refueling data and risk type data is established;

[0024] S3. Management and control output: by analyzing the real-time refueling data, real-time sales detail data and correlation, output the risk type data of each brand franchised gas station.

[0025] Preferably, in S1, the inventory data of each brand franchised gas station is detected in real time through the liquid level meter system, and the sales details data of each brand franchised gas station is obtained in real time through the Internet of Things gas station management system; the management and control risks include: inventory data missing risk, sales data missing risk, unauthorized oil entry risk, abnormal loss and spill risk, failure to install waterproof filter element, quality risk of unloading and sending at the same time, and quality risk of overdue storage of oil products.

[0026] Preferably, the association includes the following logical judgment:

[0027] When the inventory data of a franchised gas station is lost within a period of time, there is a risk of missing inventory data. Otherwise, there is no risk of missing inventory data.

[0028] If the sales data of a brand franchised gas station is not lost within a period of time, there is no risk of sales data loss. Otherwise, the following threshold judgment is entered: If the sales data of a brand franchised gas station is lost within a period of time, the inventory data within the period is calculated to obtain the tank inventory data L1 before the sales details are lost and the tank inventory data L2 after the sales details are lost. The change range between L1 and L2 is calculated. If the change range exceeds the risk control threshold X, there is a risk of sales data loss; if the change range does not exceed the threshold X, there is no risk of sales data loss.

[0029] When a franchised gas station privately introduces oil without permission, there is a risk of private oil imports. Otherwise, there is no risk of private oil imports. Specifically: first, establish a corresponding relationship between gas stations and purchase data. According to the contract, the oil products purchased by the franchised gas station must be supplied by the brand's oil depot. Every day, the brand's oil depot automatically counts the delivery volume L3 of the gas station through the gas station code and oil type data. The actual purchase data of the gas station every day is automatically calculated by the system through historical inventory details L4. When the delivery volume L3 is less than the actual receipt volume L4 of the gas station, the threshold is clarified according to the brand's management agreement, and there is a risk of private oil imports by the franchised gas station.

[0030] Abnormal loss and surplus risk: Calculate monthly loss by product type, the inventory at the beginning of the month is L5, the cumulative shipment of this product from the brand's oil depot to the oil depot is L6, the cumulative sales volume of the gas station during the cycle is L7, and the inventory at the end of the month is L8. Calculate the monthly loss S; S = L5 + L6 - L7 - L8. Define the threshold according to the brand's management agreement. When S exceeds the threshold, there is an "abnormal loss and surplus" risk;

[0031] Failure to install waterproof filter cartridges and quality risks of unloading and shipping: Actively identify sales behaviors during the gas station receiving process, match waterproof filter cartridge information with brand franchise stations that have sales behaviors during the gas station purchase process, and issue risk reminders for not installing waterproof filter cartridges for brand gas stations without valid waterproof filter cartridge information;

[0032] Quality risk of overdue storage of oil products: According to the management agreement of the brand, the storage time thresholds of different types of oil products are clearly defined. Through analysis of detailed inventory data, the oil filling behavior of the oil tank is identified. The first oil filling time is marked as T1, and the second oil filling time is marked as T2. If the time interval between T1 and T2 exceeds the time threshold agreed by the brand, quality inspection information is matched. If there is no quality inspection information, or the quality inspection results do not meet the quality standards set by the brand, there is a risk of overdue storage.

[0033] Preferably, the correlation is completed by a neural network model. First, the historical refueling data, historical sales detail data and risk type data are preprocessed to remove non-objective data generated by human factors; then, according to the chronological order, the preprocessed historical refueling data, historical sales detail data and risk type data are divided into data groups (X t , Y t ), where X t represents the historical refueling data at time t, Y t Represents the historical sales details at time t, Z t represents the risk type data at time t; finally, the data group (X t , Y t , Z t ) is divided into a training set and a test set, and the neural network model is imported for training to obtain a trained neural network model.

[0034] The advantages and positive effects of the present invention are:

[0035] The core of the present invention is to collect and organize a large amount of historical refueling data, historical sales detail data and risk type data, so as to deeply analyze the internal relationship between these data. Through the comprehensive analysis of these historical data, the present invention successfully reveals the correlation between historical refueling data, historical sales detail data and risk type data. Based on this correlation, the present invention further combines real-time refueling data and real-time sales detail data to effectively predict and evaluate the management and control risks of brand franchise gas stations.

[0036] Specifically, the present invention first collects a large amount of historical refueling data from multiple gas stations, which records in detail the key information of each gas station, such as the amount of refueling, refueling time, customer information, etc. At the same time, the present invention also obtains historical sales details data, which includes detailed information such as the sales records, product types, sales amounts, etc. of the gas station. In addition, the present invention also integrates different types of risk data, such as equipment failures, safety accidents, financial risks, etc., which help to fully understand the various risks that gas stations may face.

[0037] Through in-depth analysis of these historical data, the present invention reveals the inherent connection between refueling data, sales data and risk types. For example, certain specific sales patterns may be highly correlated with the risk of equipment failure, or certain peak refueling hours may be more prone to safety accidents. Based on these findings, the present invention has established a comprehensive analysis model that can apply the correlation in historical data to the analysis of real-time data.

[0038] Finally, the present invention uses the established correlation model, combined with real-time refueling data and real-time sales detail data, to monitor and evaluate the risk level of brand franchise gas stations in real time. This real-time risk assessment and control mechanism enables gas stations to take timely measures to prevent and respond to various potential risks. Therefore, the present invention can not only ensure the safe operation of brand franchise gas stations, but also effectively protect the legitimate rights and interests of consumers and avoid losses caused by risk events. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 is a structural block diagram of a preferred embodiment of the present invention;

[0040] Figure 2 A flowchart of a preferred embodiment of the present invention;

[0041] Figure 3 A flowchart of constructing a neural network model in a preferred embodiment of the present invention;

[0042] Figure 4 This is an example diagram of identifying the oil inlet start point in a preferred embodiment of the present invention;

[0043] Figure 5 It is an inventory data interruption risk map in a preferred embodiment of the present invention;

[0044] Figure 6 This is an example diagram of the risk of sales data interruption in a preferred embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to further understand the content, features and effects of the present invention, the following embodiments are listed and described in detail with reference to the accompanying drawings:

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the technical solutions in the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] First embodiment:

[0048] See also Figures 1 to 6, a data quality risk control system dedicated to brand franchise gas stations, including: basic data acquisition module, data analysis module and control output module; among which:

[0049] In this system, the basic data acquisition module plays a vital role. It is responsible for collecting and organizing various key data to ensure the efficient operation of the entire system. Specifically, the basic data includes historical refueling data, risk type data, and real-time refueling data. Historical refueling data covers the detailed inventory records and sales details of each brand franchised gas station in the past period of time. These data are essential for analyzing the operating conditions and historical trends of gas stations. Risk type data includes a variety of risk factors that may affect the operation of gas stations, such as M types of management and control risks, where M is a natural number greater than 1, representing the number of risk types that the system can identify and handle. Real-time refueling data includes the current inventory status and sales details of each brand franchised gas station. The real-time nature of these data ensures that the system can respond to market changes and operating conditions in a timely manner.

[0050] In order to ensure the accuracy and completeness of the data, the basic data acquisition module monitors the inventory data of each brand franchised gas station in real time through the liquid level meter system, and obtains the sales details data of each brand franchised gas station in real time through the Internet of Things gas station management system. In order to prevent data loss, these two systems need to remain online 24 hours a day, 7 days a week to ensure the continuity and reliability of the data. In this embodiment, the management and control risks mainly include the risk of missing inventory data, the risk of missing sales data, the risk of unauthorized oil entry, the risk of abnormal loss and overflow, the risk of not installing a waterproof filter, the risk of unloading and sending quality, and the risk of overdue storage of oil quality. The identification and processing of these risk factors are crucial to ensuring the normal operation of gas stations.

[0051] The data analysis module is one of the core parts of this system. It establishes the correlation between historical refueling data and risk type data through in-depth analysis of historical refueling data, historical sales details data and risk type data. In order to ensure the accuracy of the management and control results, the data analysis module needs to establish a reasonable and accurate correlation. This correlation can be achieved through two means: logical correlation and neural network correlation. Specifically, logical correlation is to obtain the analysis results through a series of logical judgments. For example:

[0052] When the inventory data of a franchised gas station is lost within a period of time, there is a risk of missing inventory data. Otherwise, there is no risk of missing inventory data.

[0053] When the sales details data of a brand franchised gas station is lost within a period of time, there is a risk of missing sales data. Otherwise, there is no risk of missing sales data; (for example, in the case of periodic sales details data loss, the inventory data of the period is calculated, the tank inventory data before the sales details are lost is L1, and the tank inventory data after the sales details are lost is L2. The range of changes between L1 and L2 is calculated. If the risk control threshold X is exceeded, for example, the flow rate of the gas station is 50L / min and the refueling time is half a minute, the control threshold is set to 25L. If the threshold is exceeded, X<L2-L1, there is a risk of missing sales data; if the threshold is not exceeded, there is no risk of missing sales data);

[0054] When a franchised gas station privately introduces oil without permission, there is a risk of private oil imports. Otherwise, there is no risk of private oil imports. Specifically: first, establish a corresponding relationship between gas stations and purchase data. According to the contract, the oil products purchased by the franchised gas station must be supplied by the brand's oil depot. Every day, the brand's oil depot automatically counts the delivery volume L3 of the gas station through the gas station code and oil type data. The actual purchase data of the gas station every day is automatically calculated by the system through historical inventory details L4. When the delivery volume L3 is less than the actual receipt volume L4 of the gas station, the threshold is clarified according to the brand's management agreement, and there is a risk of private oil imports by the franchised gas station.

[0055] Abnormal loss and surplus risk: Calculate monthly loss by product, the inventory at the beginning of the month is L5, the cumulative shipment of this product from the brand's oil depot to the oil depot is L6, the cumulative sales volume of the gas station during the cycle is L7, and the inventory at the end of the month is L8, and calculate the monthly loss S. S = L5 + L6-L7-L8, and the threshold can be clarified according to the management agreement of the brand. If S exceeds the threshold, there will be an "abnormal loss and surplus" risk reminder.

[0056] Failure to install waterproof filter cartridges and quality risks of unloading and shipping: Actively identify sales behaviors during the gas station receiving process, match waterproof filter cartridge information with brand franchise stations that have sales behaviors during the gas station purchase process, and issue risk reminders for not installing waterproof filter cartridges for brand gas stations without valid waterproof filter cartridge information;

[0057] Quality risk of over-storage of oil products: According to the management agreement of the brand, the storage time thresholds of different types of oil products are clearly defined. Through analysis of detailed inventory data, the oil filling behavior of the oil tank is identified. The first oil filling time is marked as T1, and the second oil filling time is marked as T2. When the time interval between T1 and T2 exceeds the time threshold agreed by the brand, quality inspection information is matched. If there is no quality inspection information, or the quality inspection results do not meet the quality standards set by the brand (the standard shall not be lower than the national standard requirements), there is a risk of over-storage.

[0058] Neural network correlation uses neural network technology to obtain analysis results. First, the historical refueling data, historical sales details data and risk type data are preprocessed to eliminate non-objective data generated by human factors. Then, according to the chronological order, the preprocessed data is divided into different data groups (X t , Y t , Z t ), where X t represents the historical refueling data at time t, Y t Represents the historical sales details at time t, Z t Represents the risk type data at time t. Finally, these data groups are divided into training sets and test sets, and they are imported into the neural network model for training, thereby obtaining a trained neural network model.

[0059] The management and control output module outputs the risk type data of each brand franchised gas station by analyzing the real-time refueling data, real-time sales detail data and the aforementioned correlation. In order to conduct more intuitive and effective management and control, the system also includes a portrait module. This module draws an inventory level curve based on real-time inventory data to help managers intuitively understand inventory changes. At the same time, the portrait module also draws a theoretical inventory curve based on inventory data, purchase data and sales detail data to further help managers analyze and predict the operating status of gas stations. Through these curves, managers can more clearly understand the operating status of gas stations and promptly discover and deal with potential risks and problems.

[0060] Second embodiment:

[0061] See also Figure 2 , a data quality risk control method dedicated to brand franchise gas stations, including the following steps:

[0062] S1. First of all, this application needs to obtain a series of basic data, including historical refueling data, risk type data and real-time refueling data. Historical refueling data covers the historical inventory data and historical sales details data of each brand franchised gas station in the past period of time. These data can help this application understand the operation and sales trends of each gas station. Risk type data includes a variety of management and control risks. Specifically, there are M different risk types, where M is a natural number greater than 1. Real-time refueling data includes the current real-time inventory data and real-time sales details data of each brand franchised gas station. In order to ensure the accuracy of the data, this application uses a liquid level meter system to monitor the inventory status of each brand franchised gas station in real time, and uses the Internet of Things gas station management system to obtain the sales details data of each brand franchised gas station in real time. The management and control risks mainly include the risk of missing inventory data, the risk of missing sales data, the risk of unauthorized oil entry, the risk of abnormal loss and overflow, the risk of not installing a waterproof filter, the quality risk of unloading and sending at the same time, and the quality risk of overdue storage of oil products;

[0063] S2. Next, the application needs to conduct an in-depth analysis of the historical refueling data and risk type data obtained. Through this analysis, the application can establish the correlation between the historical refueling data and the risk type data. This correlation can be divided into two types: logical correlation and neural network correlation. In terms of logical correlation, the application can identify potential risks through a series of logical judgments. For example,

[0064] When the inventory data of a franchised gas station is lost within a period of time, there is a risk of missing inventory data. Otherwise, there is no risk of missing inventory data.

[0065] When the sales details data of a brand franchised gas station is lost within a period of time, there is a risk of missing sales data. Otherwise, there is no risk of missing sales data; (for example, in the case of periodic sales details data loss, the inventory data of the period is calculated, the tank inventory data before the sales details are lost is L1, and the tank inventory data after the sales details are lost is L2. The range of changes between L1 and L2 is calculated. If the risk control threshold X is exceeded, for example, the flow rate of the gas station is 50L / min and the refueling time is half a minute, the control threshold is set to 25L. If the threshold is exceeded, X<L2-L1, there is a risk of missing sales data; if the threshold is not exceeded, there is no risk of missing sales data);

[0066] When a franchised gas station privately introduces oil without permission, there is a risk of private oil imports. Otherwise, there is no risk of private oil imports. Specifically: first, establish a corresponding relationship between gas stations and purchase data. According to the contract, the oil products purchased by the franchised gas station must be supplied by the brand's oil depot. Every day, the brand's oil depot automatically counts the delivery volume L3 of the gas station through the gas station code and oil type data. The actual purchase data of the gas station every day is automatically calculated by the system through historical inventory details L4. When the delivery volume L3 is less than the actual receipt volume L4 of the gas station, the threshold is clarified according to the brand's management agreement, and there is a risk of private oil imports by the franchised gas station.

[0067] Abnormal loss and surplus risk: Calculate monthly loss by product, the inventory at the beginning of the month is L5, the cumulative shipment of this product from the brand's oil depot to the oil depot is L6, the cumulative sales volume of the gas station during the cycle is L7, and the inventory at the end of the month is L8, and calculate the monthly loss S. S = L5 + L6-L7-L8, and the threshold can be clarified according to the management agreement of the brand. If S exceeds the threshold, there will be an "abnormal loss and surplus" risk reminder.

[0068] Failure to install waterproof filter cartridges and quality risks of unloading and shipping: Actively identify sales behaviors during the gas station receiving process, match waterproof filter cartridge information with brand franchise stations that have sales behaviors during the gas station purchase process, and issue risk reminders for not installing waterproof filter cartridges for brand gas stations without valid waterproof filter cartridge information;

[0069] Quality risk of over-storage of oil products: According to the management agreement of the brand, the storage time thresholds of different types of oil products are clearly defined. Through analysis of detailed inventory data, the oil filling behavior of the oil tank is identified. The first oil filling time is marked as T1, and the second oil filling time is marked as T2. When the time interval between T1 and T2 exceeds the time threshold agreed by the brand, quality inspection information is matched. If there is no quality inspection information, or the quality inspection results do not meet the quality standards set by the brand (the standard shall not be lower than the national standard requirements), there is a risk of over-storage.

[0070] See also Figure 3 First, the application needs to pre-process the historical refueling data, historical sales details data and risk type data to eliminate non-objective data generated by human factors. Then, the application divides the pre-processed data into different data groups (X t , Y t , Zt), where X t represents the historical refueling data at time t, Y t represents the historical sales details at time t, and Z tRepresents the risk type data at time t. Finally, the present application divides these data groups into training sets and test sets, and imports them into the neural network model for training, thereby obtaining a trained neural network model.

[0071] S3. Finally, through comprehensive analysis of the above correlations and real-time refueling data, this application can output the risk type data of each brand of franchised gas stations. This step is crucial because it can help this application to promptly discover and respond to various potential risks, thereby ensuring the normal operation of gas stations and the accuracy of data. In this way, this application can effectively manage risks at each gas station and ensure the stability and security of the entire refueling network.

[0072] The following is a detailed example of risk supervision in the purchase process:

[0073] See also Figure 4 , oil intake calculation logic

[0074] S1: Get inventory files, parse them and store them in the order of collection time;

[0075] S2: Get the starting point of inventory analysis;

[0076] S3: According to the starting inventory point time, take all subsequent inventory points within the date of the inventory point and arrange them in chronological order into K1, K2, K3...Kn;

[0077] S4: Calculate in a loop, take two inventory points at a certain time interval, and calculate the inventory difference ΔK;

[0078] S5: Set a threshold (adjustable). If ΔK is greater than the threshold, it is considered that the inventory point is already in the process of oil intake; if ΔK is less than the threshold, continue to judge the next inventory point until the condition is met;

[0079] S6: Take the minimum value between K1 and Kn as the oil inlet starting point inventory, and the corresponding time point is the oil inlet time point;

[0080] S7: After the oil inlet starting point is confirmed in S6, the oil inlet starting point Kmin is accurately calculated with this point as the starting point;

[0081] S8: loop through the inventory difference ΔK sets in order to find the turning point of the liquid level drop;

[0082] S9: Calculate the cumulative number of negative trends in inventory Σn (i.e., only outflows and no inflows, continuous negative trends accumulate) based on the ΔK set, and identify the oil inflow end point Kmax;

[0083] S10: Take the sales records of the tank corresponding to the oil inlet starting point S6 and the oil inlet ending point S9, and accumulate them to get L, where L is the sales data of the tank while unloading and sending, Kmax-Kmin+L is the oil inlet volume of this batch, and the time points corresponding to Kmin and Kmax are the start and end time points of oil inlet.

[0084] S11: The time point corresponding to Kmax is used as the starting point for the next batch of oil inlet, and the next round of oil inlet judgment calculation and analysis is entered.

[0085] This application is aimed at checking the consistency of the waterproof filter installation details for oil tanks that are shipped while unloading. For oil tanks that are shipped while unloading without waterproof filters installed, a reminder of "no waterproof filter installed, shipping while unloading, quality risk" is issued.

[0086] This application also reminds you of the quality risks of overdue storage of oil products, specifically:

[0087] If the ethanol gasoline tank exceeds 60 days and the clean gasoline + diesel tank exceeds 90 days, if there is no purchase, an "overdue storage" risk reminder is required. The overdue storage tank needs to be inspected for quality, and can only be sold after the quality inspection results are qualified. After entering the LIMS system order number, the "overdue storage" risk reminder label will be removed, and the next 60 days / 90 days risk reminder will continue.

[0088] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When the use is implemented in whole or in part in the form of a computer program product, the computer program product includes one or more computer instructions. When the computer program instructions are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL) or wireless (e.g., infrared, wireless, microwave, etc.) mode) to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk SolidState Disk (SSD)), etc.

[0089] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Any simple modification, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention are within the scope of the technical solution of the present invention.

Claims

1. A data quality risk control system dedicated to brand franchise gas stations, characterized by: include: A basic data acquisition module, wherein the basic data includes historical refueling data, risk type data and real-time refueling data; The historical refueling data includes the historical inventory data and historical sales details data of each brand franchised gas station within a historical period; the risk type data includes M types of management and control risks; the real-time refueling data includes the real-time inventory data and real-time sales details data of each brand franchised gas station; M is a natural number greater than 1; The data analysis module establishes the correlation between historical refueling data and risk type data by analyzing historical refueling data, historical sales detail data and risk type data; The management and control output module outputs the risk type data of each brand franchised gas station by analyzing the real-time refueling data, real-time sales detail data and correlation.

2. The data quality risk control system for brand franchise gas stations according to claim 1 is characterized in that: The basic data acquisition module detects the inventory data of each brand franchised gas station in real time through the liquid level meter system, and acquires the sales details data of each brand franchised gas station in real time through the Internet of Things gas station management system.

3. The data quality risk control system for brand franchise gas stations according to claim 1 is characterized in that: The management and control risks include: inventory data missing risk, sales data missing risk, unauthorized oil intake risk, abnormal loss and spill risk, failure to install waterproof filters, quality risk of unloading and shipping at the same time, and quality risk of overdue oil storage.

4. The data quality risk control system for brand franchise gas stations according to claim 3 is characterized in that: The association includes the following logical judgments: When the inventory data of a franchised gas station is lost within a period of time, there is a risk of missing inventory data. Otherwise, there is no risk of missing inventory data. If the sales data of a brand franchised gas station is not lost within a period of time, there is no risk of sales data loss. Otherwise, the following threshold judgment is entered: If the sales data of a brand franchised gas station is lost within a period of time, the inventory data within the period is calculated to obtain the tank inventory data L1 before the sales details are lost and the tank inventory data L2 after the sales details are lost. The change range between L1 and L2 is calculated. If the change range exceeds the risk control threshold X, there is a risk of sales data loss; if the change range does not exceed the threshold X, there is no risk of sales data loss. When a franchised gas station privately introduces oil without permission, there is a risk of private oil imports. Otherwise, there is no risk of private oil imports. Specifically: first, establish a corresponding relationship between gas stations and purchase data. According to the contract, the oil products purchased by the franchised gas station must be supplied by the brand's oil depot. Every day, the brand's oil depot automatically counts the delivery volume L3 of the gas station through the gas station code and oil type data. The actual purchase data of the gas station every day is automatically calculated by the system through historical inventory details L4. When the delivery volume L3 is less than the actual receipt volume L4 of the gas station, the threshold is clarified according to the brand's management agreement, and there is a risk of private oil imports by the franchised gas station. Abnormal loss or surplus risk: Calculate monthly loss by product, the inventory at the beginning of the month is L5, the cumulative shipment of this product from the brand's oil depot to the oil depot is L6, the cumulative sales volume of the gas station during the cycle is L7, the inventory at the end of the month is L8, and the monthly loss S is calculated; S = L5 + L6 - L7 - L8. The threshold is defined according to the management agreement of the brand. When S exceeds the threshold, there is an "abnormal loss or surplus" risk; Failure to install waterproof filter cartridges and quality risks of unloading and shipping: Actively identify sales behaviors during the gas station receiving process, match waterproof filter cartridge information with brand franchise stations that have sales behaviors during the gas station purchase process, and issue risk reminders for not installing waterproof filter cartridges for brand gas stations without valid waterproof filter cartridge information; Quality risk of overdue storage of oil products: According to the management agreement of the brand, the storage time thresholds of different types of oil products are clearly defined. Through analysis of detailed inventory data, the oil filling behavior of the oil tank is identified. The first oil filling time is marked as T1, and the second oil filling time is marked as T2. If the time interval between T1 and T2 exceeds the time threshold agreed by the brand, quality inspection information is matched. If there is no quality inspection information, or the quality inspection results do not meet the quality standards set by the brand, there is a risk of overdue storage.

5. The data quality risk control system for brand franchise gas stations according to claim 3 is characterized in that: The correlation is completed by a neural network model. First, the historical refueling data, historical sales detail data and risk type data are preprocessed to eliminate non-objective data generated by human factors; then, according to the chronological order, the preprocessed historical refueling data, historical sales detail data and risk type data are divided into data groups (X t , Y t ), where X t represents the historical refueling data at time t, Y t Represents the historical sales details at time t, Z t represents the risk type data at time t; finally, the data group (X t , Y t , Z t ) is divided into a training set and a test set, and the neural network model is imported for training to obtain a trained neural network model.

6. The data quality risk control system for brand franchise gas stations according to claim 1 is characterized in that: It also includes a portrait module, which draws the inventory level curve based on the real-time inventory data, and draws the theoretical inventory curve based on the inventory data, purchase data and sales detail data.

7. A data quality risk control method for brand franchise gas stations, characterized in that: The steps include: S1. Obtain basic data, including historical refueling data, risk type data and real-time refueling data; the historical refueling data includes historical inventory data and historical sales details data of each brand franchised gas station within a historical period; the risk type data includes M types of management and control risks; the real-time refueling data includes real-time inventory data and real-time sales details data of each brand franchised gas station; M is a natural number greater than 1; S2. Data analysis: by analyzing historical refueling data, historical sales detail data and risk type data, the correlation between historical refueling data and risk type data is established; S3. Management and control output: by analyzing the real-time refueling data, real-time sales detail data and correlation, output the risk type data of each brand franchised gas station.

8. The data quality risk control method for brand franchise gas stations according to claim 7 is characterized in that: In S1, the inventory data of each brand of franchised gas stations is detected in real time through the liquid level meter system, and the sales details data of each brand of franchised gas stations is obtained in real time through the Internet of Things gas station management system; the management and control risks include: inventory data missing risk, sales data missing risk, unauthorized oil entry risk, abnormal loss and spill risk, failure to install waterproof filters, quality risks of unloading and sending at the same time, and quality risks of overdue storage of oil products.

9. The method for data quality risk control dedicated to brand franchise gas stations according to claim 8 is characterized in that: The association includes the following logical judgments: When the inventory data of a franchised gas station is lost within a period of time, there is a risk of missing inventory data. Otherwise, there is no risk of missing inventory data. If the sales data of a brand franchised gas station is not lost within a period of time, there is no risk of sales data loss. Otherwise, the following threshold judgment is entered: If the sales data of a brand franchised gas station is lost within a period of time, the inventory data within the period is calculated to obtain the tank inventory data L1 before the sales details are lost and the tank inventory data L2 after the sales details are lost. The change range between L1 and L2 is calculated. If the change range exceeds the risk control threshold X, there is a risk of sales data loss; if the change range does not exceed the threshold X, there is no risk of sales data loss. When a franchised gas station privately introduces oil without permission, there is a risk of private oil imports. Otherwise, there is no risk of private oil imports. Specifically: first, establish a corresponding relationship between gas stations and purchase data. According to the contract, the oil products purchased by the franchised gas station must be supplied by the brand's oil depot. Every day, the brand's oil depot automatically counts the delivery volume L3 of the gas station through the gas station code and oil type data. The actual purchase data of the gas station every day is automatically calculated by the system through historical inventory details L4. When the delivery volume L3 is less than the actual receipt volume L4 of the gas station, the threshold is clarified according to the brand's management agreement, and there is a risk of private oil imports by the franchised gas station. Abnormal loss or surplus risk: Calculate monthly loss by product, the inventory at the beginning of the month is L5, the cumulative shipment of this product from the brand's oil depot to the oil depot is L6, the cumulative sales volume of the gas station during the cycle is L7, the inventory at the end of the month is L8, and the monthly loss S is calculated; S = L5 + L6 - L7 - L8. The threshold is defined according to the management agreement of the brand. When S exceeds the threshold, there is an "abnormal loss or surplus" risk; Failure to install waterproof filter cartridges and quality risks of unloading and shipping: Actively identify sales behaviors during the gas station receiving process, match waterproof filter cartridge information with brand franchise stations that have sales behaviors during the gas station purchase process, and issue risk reminders for not installing waterproof filter cartridges for brand gas stations without valid waterproof filter cartridge information; Quality risk of overdue storage of oil products: According to the management agreement of the brand, the storage time thresholds of different types of oil products are clearly defined. Through analysis of detailed inventory data, the oil filling behavior of the oil tank is identified. The first oil filling time is marked as T1, and the second oil filling time is marked as T2. If the time interval between T1 and T2 exceeds the time threshold agreed by the brand, quality inspection information is matched. If there is no quality inspection information, or the quality inspection results do not meet the quality standards set by the brand, there is a risk of overdue storage.

10. The data quality risk control method for brand franchise gas stations according to claim 8 is characterized in that: The correlation is completed by a neural network model. First, the historical refueling data, historical sales detail data and risk type data are preprocessed to eliminate non-objective data generated by human factors; then, according to the chronological order, the preprocessed historical refueling data, historical sales detail data and risk type data are divided into data groups (X t , Y t ), where X t represents the historical refueling data at time t, Y t Represents the historical sales details at time t, Z t represents the risk type data at time t; finally, the data group (X t , Y t , Z t ) is divided into a training set and a test set, and the neural network model is imported for training to obtain a trained neural network model.

Images