Cashier data monitoring management system based on data analysis

Abstract

The invention relates to the technical field of cashier data monitoring, and particularly discloses a cashier data monitoring management system based on data analysis, and the system specifically comprises a cashier data module which obtains a cashier transaction time value, carries out the judgment, and obtains an abnormal transaction. The method comprises the following steps: acquiring a cashier transaction record time value, judging whether the transaction record time value is in a normal business time period or not based on the normal business time period of a merchant, and if not, marking the transaction as an abnormal transaction, so that the abnormal transaction in the cashier record can be acquired in time; calculating an abnormal time characterization value and an abnormal amount characterization value of the abnormal transaction, substituting the abnormal time characterization value and the abnormal amount characterization value into a formula to calculate a risk judgment value, judging the risk degree of the abnormal transaction in each analysis period in the non-business time, generating a low-risk signal or a high-risk signal, and sending the low-risk signal or the high-risk signal to the server. Therefore, timely response can be carried out based on the abnormal transaction risk degree, and potential risks caused by abnormal transactions are reduced.

Description

Technical Field

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

[0002] In the modern business environment, cash register data is the core record of the transaction process, and its accuracy and security are directly related to the business benefits of merchants and the protection of consumers' rights and interests; However, with the continuous increase in transaction volume, many potential risks are hidden in the cash register data, such as abnormal transactions and fraudulent behaviors, which pose a serious threat to the financial security and business stability of merchants. Most of the existing cash register data monitoring systems can only identify simple abnormal transactions, such as excessive transaction amounts, abnormal transaction times, etc., but lack analysis of more complex abnormal transaction patterns, such as frequent small transactions, abnormal transaction time intervals, etc., and some monitoring and management systems lack the ability to deeply analyze and process abnormal accounts, and cannot effectively identify potential fraud. Summary of the invention

[0003] The purpose of the present invention is to provide a cash register data monitoring and management system based on data analysis to solve the technical problems in the above background.

[0004] The purpose of the present invention can be achieved through the following technical solutions: The present invention provides a cash register data monitoring and management system based on data analysis, which specifically includes: Cashier data module: obtain the cashier transaction time value, make a judgment, obtain the abnormal transaction, and process it to obtain the abnormal data of the abnormal transaction; wherein the abnormal data includes the abnormal time representation value and the abnormal amount representation value of the abnormal transaction; risk judgment value calculation module: calculate the risk judgment value based on the abnormal data of the abnormal transaction in each analysis period; abnormal risk degree judgment module: compare the risk judgment value with the risk judgment threshold, if the risk judgment value is less than or equal to the risk judgment threshold, then generate a low risk signal; abnormal judgment data acquisition module: based on the generated low risk signal, obtain the target analysis account and the abnormal judgment data of the target analysis account; wherein the abnormal judgment data includes the percentage of the number of abnormal transactions and the total value of the abnormal transaction amount deviation ratio; target analysis account abnormal judgment module: calculate the abnormal assessment value based on the abnormal judgment data of each target analysis account, compare the abnormal assessment value with the abnormal assessment threshold, if the abnormal assessment value is greater than the abnormal assessment threshold, generate an account abnormal signal; abnormal account risk judgment module: based on the generated account abnormal signal, obtain the abnormal account, obtain the historical transaction record data of the abnormal account, and judge the risk level of the abnormal account.

[0005] As a further solution of the present invention: the acquisition process of the abnormal transaction is: Get the normal business hours of the merchant, where the merchant's daily normal business hours are from the daily business start time to the daily business end time; Get the daily cashier transaction record time value, and compare the cashier transaction record time value with the normal business hours; If the time value of the cash register transaction record is not within the normal business hours, it means that the cash register transaction record is not within the normal business hours, and a transaction time abnormality signal is generated; The transaction record time value corresponding to the generated transaction time abnormality signal is obtained, marked as the transaction abnormality time value, and the transaction is marked as an abnormal transaction.

[0006] As a further solution of the present invention: the process of obtaining the risk judgment value is: Obtain the abnormal time representation value and abnormal amount representation value for each analysis period; Substitute into the formula , the risk judgment value FX is calculated, where JE represents the abnormal amount representation value, SJ represents the abnormal time representation value, and a1 and a2 are preset proportional coefficients.

[0007] As a further solution of the present invention: the process of obtaining the abnormal time characterization value is: During the analysis period, the difference between two adjacent abnormal transaction time values ​​is calculated to obtain the time interval value, the time interval value is compared with the analysis period to obtain the time interval value ratio, and all time interval value ratios are summed and averaged to obtain the time interval value ratio mean; During the analysis period, the number of abnormal transactions is obtained, and the reciprocal of the number of abnormal transactions is taken to obtain the abnormal transaction frequency value; The abnormal time representation value is obtained by multiplying the mean of the time interval value ratio with the abnormal transaction frequency value.

[0008] As a further solution of the present invention: the process of obtaining the abnormal amount characterization value is as follows: During the analysis period, the value of each abnormal transaction amount is obtained, and the ratio of the abnormal transaction amount value to the abnormal transaction amount threshold is calculated to obtain the abnormal transaction amount ratio. All abnormal transaction amount ratios are summed up to obtain the total value of the abnormal transaction amount ratios, which is marked as the abnormal amount representation value.

[0009] As a further solution of the present invention: the process of obtaining the target analysis account is as follows: Based on the generated low-risk signal, an analysis period corresponding to the generated low-risk signal is obtained and marked as an abnormal period; Obtain all abnormal transactions within the abnormal period, mark them as transactions to be analyzed, and obtain the number of transactions to be analyzed; Obtain the source account of funds corresponding to the transaction to be analyzed, mark it as an abnormal account, extract different abnormal accounts, and mark them as target analysis accounts.

[0010] As a further solution of the present invention: the process of obtaining the abnormal evaluation value is: Obtain the percentage of abnormal transactions and the total value of the abnormal transaction amount deviation ratio for each target analysis account; Substitute into the formula , the abnormal assessment value PG is calculated, where GS represents the percentage of abnormal transactions, PC represents the total value of the abnormal transaction amount deviation ratio, and s1 and s2 are preset proportional coefficients.

[0011] As a further solution of the present invention: the process of obtaining the value of the abnormal transaction number ratio is as follows: Obtain abnormal transactions corresponding to the target analysis account, mark them as target analysis transactions, obtain the number of target analysis transactions, perform ratio processing on the number of target analysis transactions and the number of transactions to be analyzed, and obtain the abnormal transaction ratio.

[0012] As a further solution of the present invention: the process of obtaining the total value of the abnormal transaction amount deviation ratio is: Obtain several transaction amount values ​​in the historical data, sum and average all the transaction amount values, and obtain the average of the historical transaction amount; Obtain the abnormal transaction amount value of each target analysis transaction, calculate the difference between the abnormal transaction amount value and the average of historical transaction amounts, take the absolute value of the difference to obtain the abnormal transaction amount deviation value, perform ratio processing on the abnormal transaction amount deviation value and the average of historical transaction amounts to obtain the abnormal transaction amount deviation ratio, sum up all the abnormal transaction amount deviation ratios to obtain the total value of the abnormal transaction amount deviation ratios.

[0013] As a further solution of the present invention: the risk level of the abnormal account is determined as follows: Obtaining the abnormal account corresponding to the generation of the account abnormality signal, and obtaining the historical transaction record data of the abnormal account, wherein the historical transaction record data includes the historical transaction amount value; The historical transaction amount values ​​are summed and averaged to obtain the historical transaction amount average, the historical transaction amount value is calculated to be different from the historical transaction amount average, the difference is taken as the absolute value to obtain the historical transaction amount deviation value, and the historical transaction amount deviation value is compared with the historical transaction amount average to obtain the historical transaction amount deviation ratio; Compare all historical transaction amount deviation ratios with the historical transaction amount deviation ratio threshold respectively; If the historical transaction amount deviation ratio is greater than the historical transaction amount deviation ratio threshold, a large deviation signal is generated; Get the number of generated large deviation signals, and perform ratio processing on the number of generated large deviation signals and the total number of historical transactions to obtain the proportion of large deviations; Compare the percentage of large deviations with the threshold of the percentage of large deviations; If the proportion of large deviations is less than or equal to the threshold of the proportion of large deviations, a low-risk signal for the account is generated; If the proportion of large deviations is greater than the threshold of large deviation proportion, a high-risk signal for the account is generated.

[0014] Beneficial effects of the present invention: (1) The present invention obtains the time value of the cash register transaction record and determines whether the transaction record time value is within the normal business time period based on the normal business time period of the merchant. If not, the transaction is marked as an abnormal transaction, so that the abnormal transaction in the cash register record can be obtained in time. Based on the obtained abnormal transaction, the abnormal time characterization value and the abnormal amount characterization value of the abnormal transaction are calculated. The abnormal time characterization value and the abnormal amount characterization value are substituted into the formula to calculate the risk judgment value, and the abnormal transaction risk level of each analysis period during non-business hours is judged, and a low risk signal or a high risk signal is generated, so that timely response can be carried out based on the risk level of the abnormal transaction to reduce the potential danger caused by the abnormal transaction; (2) The present invention obtains the target analysis account and the abnormal judgment data of the target analysis account, i.e., the percentage of the number of abnormal transactions and the total value of the deviation ratio of the abnormal transaction amount, when generating a low-risk signal, and calculates the abnormal assessment value based on the percentage of the number of abnormal transactions and the total value of the deviation ratio of the abnormal transaction amount. By comparing the abnormal assessment value with the abnormal assessment threshold, it is evaluated whether the target analysis account is an abnormal account, so that when the risk is low, the source account of abnormal transaction funds can be further analyzed, and then the abnormal account can be discovered and handled in time, thereby reducing the losses caused by fraud and illegal activities, improving the security and accuracy of transactions, and increasing the ability to identify potentially unsafe transactions of accounts. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The present invention will be further described below in conjunction with the accompanying drawings.

[0016] Figure 1 It is a flow chart of a cash register data monitoring and management system based on data analysis of the present invention; Figure 2 It is a flow chart of obtaining risk judgment value in a cash register data monitoring and management system based on data analysis of the present invention. DETAILED DESCRIPTION

[0017] 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 embodiments of 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.

[0018] Embodiment 1: See also Figure 1 and Figure 2 As shown, cashier transaction records occurring during non-normal business hours often have a certain impact on financial security. Therefore, it is important to perform abnormal monitoring and abnormal analysis on abnormal transactions corresponding to the time value of cashier transaction records. A cashier data monitoring and management system based on data analysis according to an embodiment of the present invention specifically includes: Cashier data module: obtains the cashier transaction time value, makes judgments, obtains abnormal transactions, processes them, and obtains abnormal data of abnormal transactions; In some embodiments, the process of obtaining abnormal transactions is: Get the normal business hours of the merchant, where the merchant's daily normal business hours are from the daily business start time to the daily business end time; Get the daily cashier transaction record time value, and compare the cashier transaction record time value with the normal business hours; If the cash register transaction record time value is within the normal business hours, it means that the cash register transaction record is within the normal business hours, and a normal transaction time signal is generated; If the time value of the cash register transaction record is not within the normal business hours, it means that the cash register transaction record is not within the normal business hours, and a transaction time abnormality signal is generated; Obtain the transaction record time value corresponding to the generated transaction time abnormality signal, mark it as the transaction abnormality time value, and mark the transaction as an abnormal transaction; The process of obtaining abnormal data of abnormal transactions is as follows: During non-business hours, preset analysis periods and obtain abnormal data of abnormal transactions in each analysis period; The abnormal data includes the abnormal time representation value and the abnormal amount representation value of the abnormal transaction; It should be noted that the non-business time period is the time period outside the normal business time period of the day. For example, if the normal business hours of the merchant are 8:00-22:00, the non-business time period is from 22:00 on the same day to 8:00 on the next day; For example, the process of obtaining the abnormal time characterization value is as follows: During the analysis period, the difference between two adjacent abnormal transaction time values ​​is calculated to obtain the time interval value, the time interval value is compared with the analysis period to obtain the time interval value ratio, and all time interval value ratios are summed and averaged to obtain the time interval value ratio mean; During the analysis period, the number of abnormal transactions is obtained, and the reciprocal of the number of abnormal transactions is taken to obtain the abnormal transaction frequency value; The average value of the time interval value ratio is multiplied by the abnormal transaction frequency value to obtain the abnormal time representation value; It should be explained that the meaning of the abnormal time characterization value is as follows: the abnormal time characterization value is composed of the mean value of the time interval value ratio and the abnormal transaction frequency value, that is, the smaller the mean value of the time interval value ratio is, the smaller the interval time of abnormal transactions in the analysis period is, the smaller the abnormal time characterization value is, and the higher the transaction risk is, that is, the smaller the abnormal transaction frequency value is, the more abnormal transactions occur in the analysis period, the smaller the abnormal time characterization value is, and the higher the transaction risk is; Exemplarily, the process of obtaining the abnormal amount characterization value is as follows: During the analysis period, the value of each abnormal transaction amount is obtained, and the abnormal transaction amount value is calculated by ratio calculation with the abnormal transaction amount threshold to obtain the abnormal transaction amount ratio, and all abnormal transaction amount ratios are summed up to obtain the total value of the abnormal transaction amount ratios, which is marked as the abnormal amount representation value; The abnormal transaction amount threshold is used to determine whether the abnormal transaction amount is a large-amount transaction or a small-amount transaction, and is set by technicians in this field based on experience. It should be explained that the meaning of the abnormal amount representation value is: the abnormal amount representation value is the ratio of the abnormal transaction amount to the total value. The larger the abnormal transaction amount is to the total value, the larger the total value of the abnormal transaction amount is, and the higher the transaction risk level is; It should be noted that the above abnormal time representation value and abnormal amount representation value are calculated under the condition that abnormal transactions occur during the analysis period; Risk judgment value calculation module: calculates the risk judgment value based on the abnormal data of abnormal transactions in each analysis period; In some embodiments, abnormal transaction data of each analysis period is obtained, where the abnormal transaction data is an abnormal time representation value and an abnormal amount representation value; Substitute into the formula , the risk judgment value FX is calculated, where JE represents the abnormal amount representation value, SJ represents the abnormal time representation value, and a1 and a2 are preset proportional coefficients; Abnormal risk level judgment module: compares the risk judgment value with the risk judgment threshold to generate a low risk signal or a high risk signal; In some embodiments, a risk judgment value is obtained, and the risk judgment value is compared with a risk judgment threshold, wherein the risk judgment threshold is set by a person skilled in the art based on a summary of multiple historical experimental data; If the risk judgment value is less than or equal to the risk judgment threshold, it means that the risk level of abnormal transactions during the analysis period is low, and a low risk signal is generated; If the risk judgment value is greater than the risk judgment threshold, it means that the risk level of abnormal transactions during the analysis period is high, and a high-risk signal is generated; Based on the high risk signals generated above, the system immediately stops trading; The technical solution of the embodiment of the present invention is mainly as follows: by obtaining the time value of the cashier transaction record, based on the normal business time period of the merchant, it is determined whether the transaction record time value is within the normal business time period. If not, the transaction is marked as an abnormal transaction, so that the abnormal transactions in the cashier record can be obtained in time, and based on the obtained abnormal transactions, the abnormal time characterization value and the abnormal amount characterization value of the abnormal transaction are calculated, and the abnormal time characterization value and the abnormal amount characterization value are substituted into the formula to calculate the risk judgment value, and the risk degree of abnormal transactions in each analysis period during non-business hours is determined, and a low-risk signal or a high-risk signal is generated, so that timely response can be made based on the risk degree of abnormal transactions to reduce the potential dangers caused by abnormal transactions.

[0019] Embodiment 2: On the basis of Example 1, a cashier data monitoring and management system based on data analysis described in an embodiment of the present invention specifically further includes: Abnormal judgment data acquisition module: based on the generated low-risk signals, obtains abnormal judgment data of the target analysis account and the target analysis account; In some embodiments, based on the generated low risk signal, obtaining an analysis period corresponding to the generation of the low risk signal and marking it as an abnormal period; Obtain all abnormal transactions within the abnormal period, mark them as transactions to be analyzed, and obtain the number of transactions to be analyzed; Obtain the source account of funds corresponding to the transaction to be analyzed, mark it as an abnormal account, extract different abnormal accounts, and mark them as target analysis accounts; It should be noted that different abnormal accounts refer to: different fund source accounts that appeared during the abnormal period; Obtain the abnormal judgment data of each target analysis account, wherein the abnormal judgment data includes the percentage of abnormal transaction numbers and the total value of the abnormal transaction amount deviation ratio; Exemplarily, the process of obtaining the value of the percentage of abnormal transactions is as follows: Obtain abnormal transactions corresponding to the target analysis account, mark them as target analysis transactions, obtain the number of target analysis transactions, perform ratio processing on the number of target analysis transactions and the number of transactions to be analyzed, and obtain the abnormal transaction ratio; For example, the process of obtaining the total value of the abnormal transaction amount deviation ratio is as follows: Obtain several transaction amount values ​​in the historical data, sum and average all the transaction amount values, and obtain the average of the historical transaction amount; Obtain the abnormal transaction amount value of each target analysis transaction, calculate the difference between the abnormal transaction amount value and the average of the historical transaction amounts, take the absolute value of the difference to obtain the abnormal transaction amount deviation value, perform ratio processing on the abnormal transaction amount deviation value and the average of the historical transaction amounts to obtain the abnormal transaction amount deviation ratio, sum up all the abnormal transaction amount deviation ratios to obtain the total value of the abnormal transaction amount deviation ratios; Target analysis account abnormality judgment module: calculates the abnormality evaluation value based on the abnormality judgment data of each target analysis account, and evaluates whether the target analysis account is an abnormal account; In some embodiments, abnormal judgment data of each target analysis account is obtained, and the abnormal judgment data includes a value of the percentage of the number of abnormal transactions and a total value of the deviation ratio of the amount of abnormal transactions; Substitute into the formula , calculate the abnormal assessment value PG, where GS represents the percentage of abnormal transactions, PC represents the total value of the abnormal transaction amount deviation ratio, and s1 and s2 are preset proportional coefficients; It should be explained that the meaning of the abnormal evaluation value is: the abnormal evaluation value is calculated by the abnormal transaction number ratio and the abnormal transaction amount deviation ratio. That is, the larger the abnormal transaction number ratio, the larger the abnormal evaluation value, and the more abnormal transactions the target analysis account has made during the analysis period. The more frequent the abnormal transactions, the more abnormal the target analysis account is. That is, the larger the abnormal transaction amount deviation ratio, the larger the abnormal evaluation value, and the greater the deviation between the abnormal transaction amount of the target analysis account during the analysis period and the average of the historical transaction amount. There is an abnormal transaction amount phenomenon, and the target analysis account is more abnormal. Compare the abnormal evaluation value with the abnormal evaluation threshold, wherein the abnormal evaluation threshold is set by a person skilled in the art based on a summary of multiple historical experimental data; If the abnormal evaluation value is less than or equal to the abnormal evaluation threshold, it means that the target analysis account is a normal account, the corresponding transaction is a reasonable transaction, and a normal account signal is generated; If the abnormal evaluation value is greater than the abnormal evaluation threshold, it means that the target analysis account is an abnormal account, the corresponding transaction is an unreasonable transaction, and an account abnormality signal is generated; Abnormal account risk judgment module: based on the generated account abnormality signal, obtain abnormal accounts, obtain historical transaction record data of abnormal accounts, and judge the risk level of abnormal accounts; In some embodiments, the abnormal account corresponding to the generation of the account abnormality signal is obtained, and the historical transaction record data of the abnormal account is obtained, wherein the historical transaction record data includes the historical transaction amount value; The historical transaction amount values ​​are summed and averaged to obtain the historical transaction amount average, the historical transaction amount value is calculated to be different from the historical transaction amount average, the difference is taken as the absolute value to obtain the historical transaction amount deviation value, and the historical transaction amount deviation value is compared with the historical transaction amount average to obtain the historical transaction amount deviation ratio; Compare all historical transaction amount deviation ratios with the historical transaction amount deviation ratio threshold respectively, wherein the historical transaction amount deviation ratio threshold is set by a person skilled in the art based on a summary of multiple historical experimental data; If the historical transaction amount deviation ratio is less than or equal to the historical transaction amount deviation ratio threshold, a small deviation signal is generated; If the historical transaction amount deviation ratio is greater than the historical transaction amount deviation ratio threshold, a large deviation signal is generated; Get the number of generated large deviation signals, and perform ratio processing on the number of generated large deviation signals and the total number of historical transactions to obtain the proportion of large deviations; Compare the percentage of large deviations with the threshold of large deviation percentage, wherein the threshold of large deviation percentage is set by a person skilled in the art based on a summary of multiple historical experimental data; If the percentage of large deviations is less than or equal to the percentage threshold of large deviations, it means that although the abnormal account has some large deviation transactions, it is still within the normal range as a whole, and a low-risk signal for the account is generated; Based on the low-risk account signal generated, the system records and continues to monitor the account; If the percentage of large deviations is greater than the percentage threshold of large deviations, it means that the abnormal account has a large number of transactions with large deviations from the average of historical transaction amounts, generating a high-risk signal for the account; Based on the generated high-risk account signals, take corresponding measures immediately, including but not limited to: freezing the account, notifying the merchant or relevant institutions for further investigation.

[0020] The technical solution of the embodiment of the present invention is mainly as follows: when generating a low-risk signal, by obtaining the target analysis account and the abnormal judgment data of the target analysis account, that is, the proportion of the number of abnormal transactions and the total value of the abnormal transaction amount deviation ratio, and calculating the abnormal assessment value based on the proportion of the number of abnormal transactions and the total value of the abnormal transaction amount deviation ratio, by comparing the abnormal assessment value with the abnormal assessment threshold, it is evaluated whether the target analysis account is an abnormal account, so that when the risk is low, the source account of the abnormal transaction funds can be further analyzed, and then whether the abnormal account is a high-risk account can be discovered and judged in time, thereby reducing the losses caused by fraud and illegal activities, improving transaction security and accuracy, and increasing the ability to identify potentially unsafe transactions in accounts.

[0021] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A cash register data monitoring and management system based on data analysis, characterized in that: Specifically include: Cashier data module: obtains the cashier transaction time value, makes judgments, obtains abnormal transactions, processes them, and obtains abnormal data of abnormal transactions; The abnormal data includes the abnormal time representation value and the abnormal amount representation value of the abnormal transaction; Risk judgment value calculation module: calculates the risk judgment value based on the abnormal data of abnormal transactions in each analysis period; Abnormal risk level judgment module: compares the risk judgment value with the risk judgment threshold. If the risk judgment value is less than or equal to the risk judgment threshold, a low risk signal is generated. Abnormal judgment data acquisition module: based on the generated low-risk signals, obtains abnormal judgment data of the target analysis account and the target analysis account; Among them, the abnormal judgment data includes the percentage of abnormal transaction numbers and the total value of the abnormal transaction amount deviation ratio; Target analysis account abnormality judgment module: calculates the abnormality evaluation value based on the abnormality judgment data of each target analysis account, compares the abnormality evaluation value with the abnormality evaluation threshold, and generates an account abnormality signal if the abnormality evaluation value is greater than the abnormality evaluation threshold; Abnormal account risk judgment module: Based on the generated account abnormality signals, obtain abnormal accounts, obtain historical transaction record data of abnormal accounts, and judge the risk level of abnormal accounts.

2. A cashier data monitoring and management system based on data analysis according to claim 1, characterized in that: The acquisition process of the abnormal transaction is as follows: Get the normal business hours of the merchant, where the merchant's daily normal business hours are from the daily business start time to the daily business end time; Get the daily cashier transaction record time value, and compare the cashier transaction record time value with the normal business hours; If the cash register transaction record time value is not within the normal business hours, it means that the cash register transaction record is not within the normal business hours, and a transaction time abnormality signal is generated; Obtain the transaction record time value corresponding to the generated transaction time abnormality signal, mark it as the transaction abnormality time value, and mark the transaction as an abnormal transaction.

3. A cashier data monitoring and management system based on data analysis according to claim 1, characterized in that: The process of obtaining the risk judgment value is as follows: Obtain the abnormal time representation value and abnormal amount representation value for each analysis period; Substitute into the formula , the risk judgment value FX is calculated, where JE represents the abnormal amount representation value, SJ represents the abnormal time representation value, and a1 and a2 are preset proportional coefficients.

4. A cash register data monitoring and management system based on data analysis according to claim 1, characterized in that: The process of obtaining the abnormal time characterization value is as follows: During the analysis period, the difference between two adjacent abnormal transaction time values ​​is calculated to obtain the time interval value, the time interval value is compared with the analysis period to obtain the time interval value ratio, and all time interval value ratios are summed and averaged to obtain the time interval value ratio mean; During the analysis period, the number of abnormal transactions is obtained, and the reciprocal of the number of abnormal transactions is taken to obtain the abnormal transaction frequency value; The abnormal time representation value is obtained by multiplying the mean of the time interval value ratio with the abnormal transaction frequency value.

5. The cashier data monitoring and management system based on data analysis according to claim 1 is characterized in that: The process of obtaining the abnormal amount characterization value is as follows: During the analysis period, the value of each abnormal transaction amount is obtained, and the ratio of the abnormal transaction amount value to the abnormal transaction amount threshold is calculated to obtain the abnormal transaction amount ratio. All abnormal transaction amount ratios are summed up to obtain the total value of the abnormal transaction amount ratios, which is marked as the abnormal amount representation value.

6. A cash register data monitoring and management system based on data analysis according to claim 1, characterized in that: The process of obtaining the target analysis account is as follows: Based on the generated low-risk signal, an analysis period corresponding to the generated low-risk signal is obtained and marked as an abnormal period; Obtain all abnormal transactions within the abnormal period, mark them as transactions to be analyzed, and obtain the number of transactions to be analyzed; Obtain the source account of funds corresponding to the transaction to be analyzed, mark it as an abnormal account, extract different abnormal accounts, and mark them as target analysis accounts.

7. The cash register data monitoring and management system based on data analysis according to claim 1 is characterized in that: The process of obtaining the abnormal evaluation value is as follows: Obtain the percentage of abnormal transactions and the total value of the abnormal transaction amount deviation ratio for each target analysis account; Substitute into the formula , the abnormal assessment value PG is calculated, where GS represents the percentage of abnormal transactions, PC represents the total value of the abnormal transaction amount deviation ratio, and s1 and s2 are preset proportional coefficients.

8. The cashier data monitoring and management system based on data analysis according to claim 1 is characterized in that: The process of obtaining the abnormal transaction number ratio is as follows: Obtain abnormal transactions corresponding to the target analysis account, mark them as target analysis transactions, obtain the number of target analysis transactions, perform ratio processing on the number of target analysis transactions and the number of transactions to be analyzed, and obtain the abnormal transaction ratio.

9. The cashier data monitoring and management system based on data analysis according to claim 1 is characterized in that: The process of obtaining the total value of the abnormal transaction amount deviation ratio is as follows: Obtain several transaction amount values ​​in the historical data, sum and average all the transaction amount values, and obtain the average of the historical transaction amount; Obtain the abnormal transaction amount value of each target analysis transaction, calculate the difference between the abnormal transaction amount value and the average of historical transaction amounts, take the absolute value of the difference to obtain the abnormal transaction amount deviation value, perform ratio processing on the abnormal transaction amount deviation value and the average of historical transaction amounts to obtain the abnormal transaction amount deviation ratio, sum up all the abnormal transaction amount deviation ratios to obtain the total value of the abnormal transaction amount deviation ratios.

10. The cash register data monitoring and management system based on data analysis according to claim 1, characterized in that: Determine the risk level of abnormal accounts: Obtaining the abnormal account corresponding to the generation of the account abnormality signal, and obtaining the historical transaction record data of the abnormal account, wherein the historical transaction record data includes the historical transaction amount value; The historical transaction amount values ​​are summed and averaged to obtain the historical transaction amount average, the historical transaction amount value is calculated to be different from the historical transaction amount average, the difference is taken as the absolute value to obtain the historical transaction amount deviation value, and the historical transaction amount deviation value is compared with the historical transaction amount average to obtain the historical transaction amount deviation ratio; Compare all historical transaction amount deviation ratios with the historical transaction amount deviation ratio threshold respectively; If the historical transaction amount deviation ratio is greater than the historical transaction amount deviation ratio threshold, a large deviation signal is generated; Get the number of generated large deviation signals, and perform ratio processing on the number of generated large deviation signals and the total number of historical transactions to obtain the proportion of large deviations; Compare the percentage of large deviations with the threshold of the percentage of large deviations; If the proportion of large deviations is less than or equal to the threshold of the proportion of large deviations, a low-risk signal for the account is generated; If the proportion of large deviations is greater than the threshold of large deviation proportion, a high-risk signal for the account is generated.

Images