Cashier safety management system and method based on AI
By comparing the data of the current cash register cycle and multiple historical cash register cycles, identifying the characteristics of peak transaction periods, and adjusting the number of windows open in the future cash register cycle, the existing technology cannot effectively prevent the excessive load of future cash register business in the future. Problem, achieving more accurate business load forecasting and management adjustments.
Patent Information
- Application Number
- CN202411449350.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-17
- Publication Date
- 2025-02-14
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing AI cashier security management system can only be analyzed based on the data of the current cashier cycle, and cannot effectively prevent the problem of excessive load on cashier business in the future.
By comparing and analyzing the data of the current cash register cycle with the data of multiple historical cash register cycles, the continuity, transaction volume and location of peak transaction periods are identified, and the number of windows open in the future cash register cycle is adjusted based on these analysis results.
It effectively prevents the problem of excessive bank cashier business load due to insufficient opening of the preset cashier system window in the future. Through data analysis of multiple historical cashier cycles, the accuracy of prediction of future business load is improved.
Smart Images
Figure CN119443592A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of intelligent cashier management, and specifically relates to an AI-based cashier safety management system and method. Background Art
[0002] The popularity of IoT AI technology enables various devices to be interconnected, providing a rich data source for the cash register system. At the same time, AI big data technology is used to obtain historical cash register data from multiple historical cash register cycles and current cash register data from the current cash register cycle, and the two are compared and analyzed to determine the situation during the peak cash register period in the current cash register cycle. Based on the situation during the peak cash register period in the current cash register cycle, the management of the number of open windows in future cash register cycles is adjusted to prevent the problem of heavy cash register business load in the future due to insufficient number of open windows in the preset cash register system.
[0003] In the prior art, the AI cashier security management system can only analyze the current cashier data in the current cashier cycle and complete the prediction of the cashier data in the future revenue cycle. However, the present application document compares and analyzes the current cashier data in the current cashier cycle with the historical cashier data in multiple historical cashier cycles, and further analyzes the peak transaction period in the current cashier cycle to obtain whether there is continuity in the peak transaction period, the transaction volume level in the peak transaction period, and the position of the peak transaction period in the current cashier cycle. The peak cashier period in the future cashier cycle is predicted based on whether there is continuity in the peak transaction period, the transaction volume level in the peak transaction period, and the position of the peak transaction period in the current cashier cycle, thereby making preventive adjustments to the management of the number of window openings in the future cashier cycle, thereby preventing the problem of high cashier business load in the future due to insufficient number of window openings in the future preset cashier system.
[0004] To this end, the present invention provides an AI-based cashier security management system and method. Summary of the invention
[0005] In order to make up for the shortcomings of the existing technology, the preventive adjustment of the management of the number of window openings in the future cashier cycle proposed in the background technology is solved to prevent the problem of heavy cashier business load in the future due to insufficient number of window openings in the future preset cashier system.
[0006] The technical solution adopted by the present invention to solve the technical problem is: an AI-based cashier safety management system and method, comprising: Step 1: within multiple historical cashier cycles, historical cashier data within the historical cashier cycles are obtained, wherein the historical cashier data includes historical transaction volumes, and based on the historical cashier data within the multiple historical cashier cycles, historical transaction target volumes are obtained by processing and analyzing; Step 2: In the current cashier cycle, obtain the current cashier data, where the current cashier data includes the current transaction volume, and use AI technology to process and analyze the current cashier data, mark the current cashier time period in the current cashier cycle, and mark the current cashier time period in the current cashier cycle as a peak cashier time period and a non-peak cashier time period. Based on AI technology, process and analyze the peak cashier time period to obtain a cashier business load value, and compare it with a threshold. If the cashier business load value is greater than or equal to the cashier business load threshold, a cashier load high signal is generated; Step 3: Based on the cashier load high signal, the peak cashier period in the current cashier cycle is processed and analyzed to obtain the cashier safety warning value, which is compared with the threshold to generate a signal whether the cashier management should be adjusted; The cashier management whether to adjust the signal includes a cashier management adjustment signal or a cashier management non-adjustment signal; Step 4: Based on the cashier management adjustment signal, obtain the adjustment coefficient and adjust the number of cashier windows open in future transaction cycles.
[0007] As a further solution of the present invention: the method for obtaining the historical transaction target volume is: In each historical cashier cycle, the historical cashier cycle is divided into several historical cashier time periods, and the historical transaction volume in each historical cashier time period is obtained through AI technology; The historical cashier time period with the largest historical transaction volume among all historical cashier time periods is selected as the target historical cashier time period.
[0008] As a further solution of the present invention: the cashier business load value is obtained in the following manner: The cashier load coefficient is multiplied by the ratio of the number of peak cashier hours to calculate the cashier business load value.
[0009] As a further solution of the present invention: within a current cashier cycle, the current cashier cycle is divided into a number of current cashier time periods; Compare the current transaction volume of each current cashier period in the current cashier cycle with the historical transaction target volume. The comparison process is as follows: If the current transaction volume of the current cashier period is greater than or equal to the historical transaction target volume, it means that the transaction volume in the current cashier period is large, and the current cashier period is marked as a peak cashier period; If the current transaction volume of the current cashier period is less than the historical transaction target volume, it means that the transaction volume in the current cashier period is small, and the current cashier period is marked as a non-peak cashier period; Count the number of peak cashier time periods and calculate the ratio with the total number of all current cashier time periods in the current cashier cycle to obtain the peak cashier time period ratio; The method for obtaining the cash register load coefficient is as follows: Get the current transaction volume during the peak cashier period and mark it as the peak cashier transaction volume; Difference between the peak cashier transaction volume and the historical transaction target volume to obtain the peak cashier transaction deviation value; Add up all the peak cashier transaction deviation values in the current cashier cycle to obtain the cashier load value; The cashier load level value is calculated by ratio with the cashier load level threshold to obtain the cashier load level coefficient.
[0010] As a further solution of the present invention: the peak cashier continuation coefficient is obtained as follows: In the current cashier cycle, obtain the number of intervals between all peak cashier periods and the number of off-peak cashier periods between all peak cashier periods; The ratio of the number of non-peak checkout periods between all peak checkout periods to the number of intervals between peak checkout periods is calculated to obtain the average value of the interval between non-peak checkout periods; The peak cashier duration coefficient is obtained by comparing the average value of the interval between non-peak cashier periods with the total number of current cashier periods in the current cashier cycle.
[0011] As a further solution of the present invention: the ranking coefficient is obtained as follows: In the current cashier cycle, all current cashier time periods in the current cashier cycle are ranked; Get the ranking of the peak cashier period in the current cashier cycle, perform difference processing with the total ranking, and take the absolute value of the difference to get the ranking difference of the peak cashier period. Sum the ranking differences of all peak cashier periods to get the total ranking difference. Get the total difference of the target ranking, and compare the total difference of the ranking with the total difference of the target ranking to get the ranking coefficient.
[0012] As a further solution of the present invention: the cashier safety warning value is obtained in the following manner: Substitute the peak cashier duration coefficient, peak cashier period ratio and ranking coefficient into the formula , get the cashier safety warning value , where LX represents the peak cashier duration coefficient, GS represents the ratio of the number of peak cashier periods, and WZ represents the ranking coefficient. , , Expressed as a preset weight coefficient.
[0013] As a further solution of the present invention: the cashier safety warning value is compared with the cashier safety warning threshold, and the comparison process is as follows: If the cashier safety warning value is greater than or equal to the cashier safety warning threshold, a cashier management adjustment signal is generated; If the cashier safety warning value is less than the cashier safety warning threshold, a cashier management non-adjustment signal is generated.
[0014] As a further solution of the present invention: the process of adjusting the number of cashier windows open in the future transaction cycle is as follows: By formula: , calculate the adjustment coefficient, where It is indicated as the cashier safety warning value. It is indicated as the cashier safety warning threshold; Get the number of future preset cash register system windows open, and substitute the number of future preset cash register system windows open into the formula: , calculate the adjusted number of cash register system windows open ,in, It represents the number of cash register system windows that are preset to be opened in the future, and K represents the adjustment coefficient.
[0015] An AI-based cashier safety management system, comprising: AI collection and processing module: in multiple historical cashier cycles, obtain historical cashier data in the historical cashier cycles, where the historical cashier data includes historical transaction volume, and process and analyze the historical cashier data in multiple historical cashier cycles to obtain the historical transaction target volume; AI processing and analysis module: in the current cashier cycle, obtain the current cashier data, where the current cashier data includes the current transaction volume, and use AI technology to process and analyze the current cashier data, mark the current cashier time period in the current cashier cycle, mark the current cashier time period in the current cashier cycle as a peak cashier time period and a non-peak cashier time period, process and analyze the peak cashier time period based on AI technology, obtain the cashier business load value, and compare it with the threshold. If the cashier business load value is greater than or equal to the cashier business load threshold, a cashier load high signal is generated; AI analysis and prediction module: Based on the high cashier load signal, the peak cashier period in the current cashier cycle is processed and analyzed to obtain the cashier safety warning value, which is compared with the threshold to generate a signal whether the cashier management should be adjusted; The cashier management whether to adjust the signal includes a cashier management adjustment signal or a cashier management non-adjustment signal; AI management adjustment module: Based on the cashier management adjustment signal, obtain the adjustment coefficient and adjust the number of cashier windows open in the future transaction cycle.
[0016] The beneficial effects of the present invention are as follows: (1) The present invention obtains historical transaction target amounts in multiple historical cash register cycles, obtains current transaction values in the current cash register cycle, compares the current transaction amount of each current cash register time period in the current cash register cycle with the historical transaction target amount, obtains the peak cash register time period, obtains the peak cash register time period number ratio and the cash register load degree coefficient, obtains the cash register business load value, and compares it with the threshold value. If the cash register business load value is greater than or equal to the cash register business load threshold value, a cash register load high signal is generated. If the cash register business load value is less than the cash register business load threshold value, a cash register load low signal is generated. Thus, by comparing the average of the historical transaction amounts in multiple historical cash register cycles with the transaction amount in each current cash register time period in the current cash register cycle, the peak cash register time period in the current cycle is determined, the proportion of the peak cash register time period in the current cycle and the cash register load degree are analyzed, and then the business load degree in the current cash register cycle is evaluated. (2) Based on the cashier load high signal, the present invention further analyzes the peak cashier time period in the current cashier cycle to obtain a cashier safety warning value, and compares it with the threshold. If the cashier safety warning value is greater than or equal to the cashier safety warning threshold, it means that the peak cashier time in the future transaction cycle will last longer, the number of peak cashier time periods will account for a larger proportion, and the peak cashier time periods will be located later. Therefore, by analyzing the peak cashier time period in the current cashier cycle, a preliminary assessment of the business load level of the future cashier cycle is completed; (3) Based on the cashier management adjustment signal, the present invention substitutes the cashier safety warning value and the cashier safety warning threshold into the formula, calculates the adjustment coefficient, and obtains the future preset number of cashier system window openings. The future preset number of cashier system window openings and the adjustment coefficient are substituted into the formula to calculate the adjusted number of cashier system window openings, thereby preventing the problem of high cashier business load in the future due to insufficient number of cashier system window openings in the future. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] The present invention will be further described below in conjunction with the accompanying drawings.
[0018] Figure 1 is a flowchart of the steps of Embodiment 1 of the present invention; Figure 2 is a flowchart of the steps of Embodiment 2 of the present invention; Figure 3 is a flowchart of the steps of Embodiment 3 of the present invention; Figure 4 It is a system module diagram of embodiment 4 of the present invention. DETAILED DESCRIPTION
[0019] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.
[0020] Example 1 like Figure 1 As shown, an AI-based cashier safety management method according to an embodiment of the present invention includes: Step 1: within multiple historical cashier cycles, historical cashier data within the historical cashier cycles are obtained, wherein the historical cashier data includes historical transaction volumes, and based on the historical cashier data within the multiple historical cashier cycles, historical transaction target volumes are obtained by processing and analyzing; In some embodiments, in each historical cashier cycle, the historical cashier cycle is divided into a number of historical cashier time periods, and the historical transaction volume in each historical cashier time period is obtained by using AI technology; Select the historical cashier time period with the largest historical transaction volume among all historical cashier time periods as the target historical cashier time period; Obtain the target historical cashier time period in all historical cashier cycles, sum and average the historical transaction volumes in all target historical cashier time periods, and obtain the historical transaction target volume; It should be noted that the meaning of the historical transaction target volume is: among all historical cashier time periods, the time period with the largest historical transaction volume is selected as the target historical cashier time period. For these selected target historical cashier time periods, the historical transaction volumes of each of them in their respective cashier cycles are calculated, and these transaction volumes are summed up. Finally, the average of this sum is taken to obtain the historical transaction target volume. The historical transaction target volume represents the average transaction volume level that can be achieved in each of the cashier time periods with the most significant (or "busy") transaction volumes in history. Step 2: In the current cashier cycle, obtain the current cashier data, where the current cashier data includes the current transaction volume, and use AI technology to process and analyze the current cashier data, mark the current cashier time period in the current cashier cycle, and mark the current cashier time period in the current cashier cycle as a peak cashier time period and a non-peak cashier time period. Based on AI technology, process and analyze the peak cashier time period to obtain the cashier business load value, compare it with the threshold, and generate a cashier load high and low signal; The cashier load high and low signals include a cashier load high signal or a cashier load low signal; In some embodiments, within a current cash register cycle, the current cash register cycle is divided into a number of current cash register time periods; It should be noted that the current cash register cycle is divided in the same way as the historical cash register cycle; It can be further understood that the current transaction volume means: the transaction volume corresponding to each current cashier time period in the current cashier cycle; Compare the current transaction volume of each current cashier period in the current cashier cycle with the historical transaction target volume. The comparison process is as follows: If the current transaction volume of the current cashier period is greater than or equal to the historical transaction target volume, it means that the transaction volume in the current cashier period is large, and the current cashier period is marked as a peak cashier period; If the current transaction volume of the current cashier period is less than the historical transaction target volume, it means that the transaction volume in the current cashier period is small, and the current cashier period is marked as a non-peak cashier period; Count the number of peak cashier time periods and calculate the ratio with the total number of all current cashier time periods in the current cashier cycle to obtain the peak cashier time period ratio; Get the current transaction volume during the peak cashier period and mark it as the peak cashier transaction volume; Difference between the peak cashier transaction volume and the historical transaction target volume to obtain the peak cashier transaction deviation value; Add up all the peak cashier transaction deviation values in the current cashier cycle to obtain the cashier load value; Calculate the ratio of the cashier load level value to the cashier load level threshold to obtain the cashier load level coefficient; The cashier load coefficient is multiplied by the ratio of the number of peak cashier hours to calculate the cashier business load value; It can be understood that the meaning of the cashier business load value is: it combines the load degree of the cashier business during the peak cashier period and the proportion of the peak cashier period, reflecting the business load degree in the current cashier cycle. Specifically, the larger the value, the greater the proportion of the peak cashier period in the current cashier cycle, the greater the transaction volume in the peak cashier period, and therefore, the cashier business load is higher. On the contrary, the smaller the value, the smaller the proportion of the peak cashier period in the current cashier cycle, the smaller the transaction volume in the peak cashier period, and therefore, the cashier business load is lower. The cash register business load value is compared with the cash register business load threshold. The comparison process is as follows: If the cashier business load value is greater than or equal to the cashier business load threshold, it means that in the current cashier cycle, the peak cashier period accounts for a large proportion, and the transaction volume in the peak cashier period is large. Therefore, the cashier business load is high, and a cashier load high signal is generated; If the cashier business load value is less than the cashier business load threshold, it means that in the current cashier cycle, the peak cashier period accounts for a small proportion, and the transaction volume in the peak cashier period is small. Therefore, the cashier business load is low, and a cashier load low signal is generated; The specific implementation scheme of the embodiment of the present invention is as follows: in multiple historical cashier cycles, the historical transaction target amount is obtained by using AI technology, and in the current cashier cycle, the current transaction value is obtained, and the current transaction amount of each current cashier time period in the current cashier cycle is compared with the historical transaction target amount to obtain the peak cashier time period, and the peak cashier time period number ratio and the cashier load degree coefficient are obtained to obtain the cashier business load value, and compare it with the threshold value. If the cashier business load value is greater than or equal to the cashier business load threshold value, a cashier load high signal is generated, and if the cashier business load value is less than the cashier business load threshold value, a cashier load low signal is generated, thereby comparing the average value of the historical transaction volume in multiple historical cashier cycles with the transaction volume in each current cashier time period in the current cashier cycle, determining the peak cashier time period in the current cycle, analyzing the proportion of the peak cashier time period and the cashier load degree in the current cycle, and then evaluating the level of the business load degree in the current cashier cycle; Example 2 like Figure 2 As shown, based on Example 1, an AI-based cashier safety management method according to an embodiment of the present invention includes: Step 3: Based on the cashier load high signal, the peak cashier period in the current cashier cycle is processed and analyzed to obtain the cashier safety warning value, which is compared with the threshold to generate a signal whether the cashier management should be adjusted; The cashier management whether to adjust the signal includes a cashier management adjustment signal or a cashier management non-adjustment signal; In some embodiments, when a high cashier load signal is generated, a further analysis is performed on the peak cashier period in the current cashier cycle, and the analysis process is as follows: In the current cashier cycle, obtain the number of intervals between all peak cashier periods and the number of off-peak cashier periods between all peak cashier periods; The ratio of the number of non-peak checkout periods between all peak checkout periods to the number of intervals between peak checkout periods is calculated to obtain the average value of the interval between non-peak checkout periods; The peak cashier duration coefficient is obtained by comparing the average value of the interval between non-peak cashier periods with the total number of current cashier periods in the current cashier cycle. In the current cashier cycle, all current cashier time periods in the current cashier cycle are ranked; Get the ranking of the peak cashier period in the current cashier cycle, perform difference processing with the total ranking, and take the absolute value of the difference to get the ranking difference of the peak cashier period. Sum the ranking differences of all peak cashier periods to get the total ranking difference. Obtain the total difference of the target ranking, and perform ratio processing on the total difference of the ranking and the total difference of the target ranking to obtain the ranking coefficient; It should be noted that the total difference in target ranking is calculated based on the ranking of peak checkout hours under ideal conditions, and the total difference in target ranking is obtained in the same way as the total difference in ranking; It should be noted that the peak cashier time ranking under ideal conditions means that the peak cashier time ranking is continuously at the back in the current cashier cycle; For example, if there are 30 current checkout periods in the current checkout cycle, and there are 8 peak checkout periods, assuming that the peak checkout periods in the ideal state are ranked 23, 24, 25, 26, 27, 28, 29, and 30 respectively, and the peak checkout period ranking differences corresponding to the ideal state are 7, 6, 5, 4, 3, 2, 1, and 0 respectively, the ranking differences of all peak checkout periods corresponding to the ideal state are added together to obtain the total difference of the target ranking; Substitute the peak cashier duration coefficient, peak cashier period ratio and ranking coefficient into the formula , get the cashier safety warning value , where LX represents the peak cashier duration coefficient, GS represents the ratio of the number of peak cashier periods, and WZ represents the ranking coefficient. , , Expressed as a preset weight coefficient; It can be understood that the meaning of the cashier safety warning value is: it combines the three factors of the duration of the peak cashier time period, the ratio of the number of peak cashier time periods and the total difference of the target ranking, and is used to evaluate the overall safety performance of the cashier system in the future transaction cycle and to warn of potential cashier risks in the future transaction cycle. Specifically, the larger the value, the longer the peak cashier time in the future transaction cycle, the larger the proportion of the peak cashier time periods, and the more the peak cashier time periods are located at the back. On the contrary, the smaller the value, the shorter the peak cashier time in the future transaction cycle, the smaller the proportion of the peak cashier time periods, and the more the peak cashier time periods are located at the front. The cashier safety warning value is compared with the cashier safety warning threshold. The comparison process is as follows: If the cashier safety warning value is greater than or equal to the cashier safety warning threshold, it means that the peak cashier period lasts longer, the number of peak cashier periods accounts for a larger proportion, and the current transaction peak period is relatively late, generating a cashier management adjustment signal; If the cashier safety warning value is less than the cashier safety warning threshold, it means that the duration of the peak cashier period is shorter, the number of peak cashier periods accounts for a smaller proportion, and the current transaction peak period is relatively early, generating a signal that cashier management does not need to be adjusted; The specific implementation plan of the embodiment of the present invention is: based on the high cashier load signal, the peak cashier time period in the current cashier cycle is further analyzed to obtain the cashier safety warning value, and compared with the threshold. If the cashier safety warning value is greater than or equal to the cashier safety warning threshold, it means that the peak cashier time in the future transaction cycle will last longer, the number of peak cashier time periods will account for a larger proportion, and the peak cashier time periods will be located relatively later. Therefore, by analyzing the peak cashier time period in the current cashier cycle, a preliminary assessment of the business load level of the future cashier cycle can be completed.
[0021] Example 3 like Figure 3 As shown, based on Example 1 and Example 2, an AI-based cashier safety management method described in an embodiment of the present invention includes: Step 4: Based on the cashier management adjustment signal, obtain the adjustment coefficient and adjust the number of cashier windows open in the future transaction cycle; In some embodiments, when a cashier management adjustment signal is generated, the process of adjusting the number of cashier windows open in future transaction cycles is as follows: By formula: , calculate the adjustment coefficient, where It is indicated as the cashier safety warning value. It is indicated as the cashier safety warning threshold; Get the number of future preset cash register system windows open, and substitute the number of future preset cash register system windows open into the formula: , calculate the adjusted number of cash register system windows open ,in, It represents the number of cash register system windows that will be opened in the future, and K represents the adjustment coefficient; The specific implementation method of the embodiment of the present invention is: based on the cashier management adjustment signal, the cashier safety warning value and the cashier safety warning threshold are substituted into the formula to calculate the adjustment coefficient, and the future preset number of open cashier system windows is obtained, and the future preset number of open cashier system windows and the adjustment coefficient are substituted into the formula to calculate the adjusted number of open cashier system windows, thereby preventing the problem of high cashier business load of the bank in the future due to insufficient number of open cashier system windows in the future.
[0022] Example 4 like Figure 4As shown, based on Example 1, Example 2 and Example 3, an AI-based cashier safety management system described in an embodiment of the present invention includes: AI collection and processing module: in multiple historical cashier cycles, obtain historical cashier data in the historical cashier cycles, where the historical cashier data includes historical transaction volume, and process and analyze the historical cashier data in multiple historical cashier cycles to obtain the historical transaction target volume; AI processing and analysis module: in the current cashier cycle, obtain the current cashier data, where the current cashier data includes the current transaction volume, and use AI technology to process and analyze the current cashier data, mark the current cashier time period in the current cashier cycle, mark the current cashier time period in the current cashier cycle as a peak cashier time period and a non-peak cashier time period, process and analyze the peak cashier time period based on AI technology, obtain the cashier business load value, and compare it with the threshold. If the cashier business load value is greater than or equal to the cashier business load threshold, a cashier load high signal is generated; AI analysis and prediction module: Based on the high cashier load signal, the peak cashier period in the current cashier cycle is processed and analyzed to obtain the cashier safety warning value, which is compared with the threshold to generate a signal whether the cashier management should be adjusted; The cashier management whether to adjust the signal includes a cashier management adjustment signal or a cashier management non-adjustment signal; AI management adjustment module: Based on the cashier management adjustment signal, obtain the adjustment coefficient and adjust the number of cashier windows open in the future transaction cycle.
[0023] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.
Claims
1. A cashier safety management method based on AI, characterized by: include: Step 1: within multiple historical cashier cycles, historical cashier data within the historical cashier cycles are obtained, wherein the historical cashier data includes historical transaction volumes, and based on the historical cashier data within the multiple historical cashier cycles, historical transaction target volumes are obtained by processing and analyzing; Step 2: In the current cashier cycle, obtain the current cashier data, where the current cashier data includes the current transaction volume, and use AI technology to process and analyze the current cashier data, mark the current cashier time period in the current cashier cycle, and mark the current cashier time period in the current cashier cycle as a peak cashier time period and a non-peak cashier time period. Based on AI technology, process and analyze the peak cashier time period to obtain a cashier business load value, and compare it with a threshold. If the cashier business load value is greater than or equal to the cashier business load threshold, a cashier load high signal is generated; Step 3: Based on the cashier load high signal, the peak cashier period in the current cashier cycle is processed and analyzed to obtain the cashier safety warning value, which is compared with the threshold to generate a signal whether the cashier management should be adjusted; The cashier management whether to adjust the signal includes a cashier management adjustment signal or a cashier management non-adjustment signal; Step 4: Based on the cashier management adjustment signal, obtain the adjustment coefficient and adjust the number of cashier windows open in future transaction cycles.
2. According to claim 1, a cashier safety management method based on AI is characterized by: The method for obtaining the historical transaction target volume is as follows: In each historical cashier cycle, the historical cashier cycle is divided into several historical cashier time periods, and the historical transaction volume in each historical cashier time period is obtained through AI technology; Select the historical cashier time period with the largest historical transaction volume among all historical cashier time periods as the target historical cashier time period; The target historical cashier time period in all historical cashier cycles is obtained, and the historical transaction volumes in all target historical cashier time periods are summed and averaged to obtain the historical transaction target volume.
3. The AI-based cashier safety management method according to claim 1, characterized in that: The cash register business load value is obtained as follows: The cashier load coefficient is multiplied by the ratio of the number of peak cashier hours to calculate the cashier business load value.
4. The AI-based cashier safety management method according to claim 3 is characterized in that: The peak checkout period ratio is obtained as follows: In the current cash register cycle, the current cash register cycle is divided into several current cash register time periods; Compare the current transaction volume of each current cashier period in the current cashier cycle with the historical transaction target volume. The comparison process is as follows: If the current transaction volume of the current cashier period is greater than or equal to the historical transaction target volume, it means that the transaction volume in the current cashier period is large, and the current cashier period is marked as a peak cashier period; If the current transaction volume of the current cashier period is less than the historical transaction target volume, it means that the transaction volume in the current cashier period is small, and the current cashier period is marked as a non-peak cashier period; Count the number of peak cashier time periods and calculate the ratio with the total number of all current cashier time periods in the current cashier cycle to obtain the peak cashier time period ratio; The method for obtaining the cash register load coefficient is as follows: Get the current transaction volume during the peak cashier period and mark it as the peak cashier transaction volume; Difference between the peak cashier transaction volume and the historical transaction target volume to obtain the peak cashier transaction deviation value; Add up all the peak cashier transaction deviation values in the current cashier cycle to obtain the cashier load value; The cashier load level value is calculated by ratio with the cashier load level threshold to obtain the cashier load level coefficient.
5. The AI-based cashier safety management method according to claim 1, characterized in that: The peak cashier continuation coefficient is obtained as follows: In the current cashier cycle, obtain the number of intervals between all peak cashier periods and the number of off-peak cashier periods between all peak cashier periods; The ratio of the number of non-peak checkout periods between all peak checkout periods to the number of intervals between peak checkout periods is calculated to obtain the average value of the interval between non-peak checkout periods; The peak cashier duration coefficient is obtained by comparing the average value of the interval between non-peak cashier periods with the total number of current cashier periods in the current cashier cycle.
6. The cashier safety management method based on AI according to claim 1, characterized in that: The ranking coefficient is obtained as follows: In the current cashier cycle, all current cashier time periods in the current cashier cycle are ranked; Get the ranking of the peak cashier period in the current cashier cycle, perform difference processing with the total ranking, and take the absolute value of the difference to get the ranking difference of the peak cashier period. Sum the ranking differences of all peak cashier periods to get the total ranking difference. Get the total difference of the target ranking, and compare the total difference of the ranking with the total difference of the target ranking to get the ranking coefficient.
7. The AI-based cashier safety management method according to claim 5, characterized in that: The cashier safety warning value is obtained as follows: Substitute the peak cashier duration coefficient, peak cashier period ratio and ranking coefficient into the formula , get the cashier safety warning value , where LX represents the peak cashier duration coefficient, GS represents the ratio of the number of peak cashier periods, and WZ represents the ranking coefficient. , , Represented as a preset weight coefficient.
8. The AI-based cashier safety management method according to claim 7, characterized in that: The cashier safety warning value is compared with the cashier safety warning threshold. The comparison process is as follows: If the cashier safety warning value is greater than or equal to the cashier safety warning threshold, a cashier management adjustment signal is generated; If the cashier safety warning value is less than the cashier safety warning threshold, a cashier management non-adjustment signal is generated.
9. The AI-based cashier safety management method according to claim 1, characterized in that: The adjustment process for the number of cashier windows open in future transaction cycles is as follows: By formula: , calculate the adjustment coefficient, where It is indicated as the cashier safety warning value. It is indicated as the cashier safety warning threshold; Get the number of future preset cash register system windows open, and substitute the number of future preset cash register system windows open into the formula: , calculate the adjusted number of cash register system windows open ,in, It represents the number of cash register system windows that are preset to be opened in the future, and K represents the adjustment coefficient.
10. An AI-based cashier security management system, the system is used to execute the method described in any one of claims 1 to 9, characterized in that: include: AI collection and processing module: in multiple historical cashier cycles, obtain historical cashier data in the historical cashier cycles, where the historical cashier data includes historical transaction volume, and process and analyze the historical cashier data in multiple historical cashier cycles to obtain the historical transaction target volume; AI processing and analysis module: in the current cashier cycle, obtain the current cashier data, where the current cashier data includes the current transaction volume, and use AI technology to process and analyze the current cashier data, mark the current cashier time period in the current cashier cycle, and mark the current cashier time period in the current cashier cycle as a peak cashier time period and a non-peak cashier time period. Based on AI technology, process and analyze the peak cashier time period to obtain the cashier business load value, and compare it with the threshold. If the cashier business load value is greater than or equal to the cashier business load threshold, a cashier load high signal is generated; AI analysis and prediction module: Based on the high cashier load signal, the peak cashier period in the current cashier cycle is processed and analyzed to obtain the cashier safety warning value, which is compared with the threshold to generate a signal whether the cashier management should be adjusted; The cashier management whether to adjust the signal includes a cashier management adjustment signal or a cashier management non-adjustment signal; AI management adjustment module: Based on the cashier management adjustment signal, obtain the adjustment coefficient and adjust the number of cashier windows open in the future transaction cycle.