A restaurant self-service checkout method and system based on intelligent disk binding

Abstract

The present invention relates to the field of self-service checkout technology, specifically a restaurant self-service checkout method and system based on smart tray binding, comprising the following steps: capturing contact trajectory by installing a sensor on the edge of the tray, determining the trajectory ownership and marking the tray and seat matching, obtaining a time period classification meal mapping table through a time series group, extracting payment requests and identifying delays to obtain a list of abnormal payment records, updating the payment interface display structure and outputting an updated list of interface payment methods. In the present invention, seat matching is achieved through tray sensing and identification, consumption sources are clearly identified and data confusion is avoided, trajectories are merged to construct consumption sequences, data continuity is improved, time period mapping is associated with meal information, data structure linkage is enhanced, delayed payment behavior is identified to improve processing efficiency, the payment interface is dynamically sorted by abnormal frequency and call volume, operation fluency and system stability are optimized, and peak period settlement efficiency and payment process stability are comprehensively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of self-service checkout, and in particular to a restaurant self-service checkout method and system based on a smart disk. Background Art

[0002] The field of self-checkout technology includes related technologies that allow users to independently complete the payment process for goods or services in service industries such as retail and catering. The core content of this technology field is to optimize the efficiency of the payment link after consumers complete consumption, reduce dependence on manual services, and improve overall operational efficiency. Self-checkout technology covers processes such as identity recognition, product information entry, fee calculation, and payment execution, involving specific means such as barcode recognition equipment, payment integration, interface interaction design, information transmission and verification mechanisms. In the catering industry, self-checkout technology is gradually shifting from relying on waiter operations to systems that are completed by users independently, covering mobile payment, code scanning and ordering, electronic menus, etc., forming a complete self-service consumption process system.

[0003] Among them, the restaurant self-service checkout method refers to the operation process in which users view consumption details and complete payment by scanning the desktop QR code or using the restaurant mobile application during the restaurant dining process. The patent subject is aimed at the operation method of the checkout link during the dining process, covering specific technical matters such as table QR code encoding and seat binding, real-time synchronization of order information, user-side order information display, automatic generation of payment links, third-party payment platform interface call, payment status feedback, etc. Its completion method includes binding each table with a unique identifier to generate an exclusive QR code, and then automatically calling the server-side order information after the user scans it, and integrating the payment channel to complete the fee settlement process.

[0004] Existing technology often uses QR codes to bind seats and complete the payment process by scanning the code. However, QR code binding lacks the ability to recognize dynamic behavior. As a result, it is difficult to accurately distinguish consumption attribution when multiple customers dine at the same time or change seats, which in turn causes bill confusion and settlement errors. Consumption behavior records overly rely on static order synchronization on the server side. Once network delays or system update lags occur, it is easy to cause inconsistencies between the clamping behavior and the order item, affecting the accuracy of settlement. The payment process is uniformly displayed using a standard interface, and the interface ranking is not optimized according to the actual responsiveness of different payment methods. As a result, some payment methods frequently time out but are still prioritized, reducing overall payment efficiency. In terms of handling abnormal payment records, only the status returned by the payment interface is used for judgment. There is a lack of in-depth identification methods based on behavior trajectory and time nodes, making it difficult to timely discover and optimize structural bottlenecks in the system. Especially during peak dining times, slow system response and frequent payment delays have a significant impact on operational efficiency. Summary of the Invention

[0005] To address the existing problems of using QR codes to bind seats and completing the payment process by scanning the code, the QR code binding lacks the ability to identify dynamic behavior, making it difficult to accurately distinguish consumption attribution when multiple customers dine at the same time or change seats, resulting in bill confusion and settlement errors. Consumption behavior records are overly dependent on static order synchronization on the server side. Once network delays or system updates lag in the middle, it is easy to cause inconsistencies between the clamping behavior and the order items, affecting the accuracy of settlement. The payment process is uniformly displayed in a standard interface, and the interface ranking is not optimized according to the responsiveness of different payment methods in actual operation. As a result, some payment methods frequently time out and are still prioritized, reducing overall payment efficiency. In terms of handling abnormal payment records, only the return status of the payment interface is used for judgment, lacking in-depth identification methods based on behavior trajectory and time nodes, making it difficult to timely discover and optimize structural bottlenecks in the system. Especially during peak dining hours, the slow system response and frequent payment delays have a significant impact on operational efficiency. The present invention provides a restaurant self-service checkout method and system based on smart disk binding. The technical solution is as follows:

[0006] In one aspect, a restaurant self-service checkout method based on a smart disk binding is provided, the method comprising:

[0007] S1: Install a sensor on the edge of the pallet and capture the sensor contact trajectory. By determining the contact time difference and offset direction between the trajectory starting point and the pallet edge trigger area, the continuously changing coordinates of the gripping trajectory path are extracted, the trajectory ownership is determined, and the unique matching result between the pallet and the seat is marked to obtain the pallet-bound seat identification value.

[0008] S2: Based on the tray-bound seat identification value, the time node of each tray triggering and the corresponding gripping event are collected, and continuous records with intervals less than the standard dining cycle are filtered in chronological order and merged into a group of consumption behaviors to obtain a consumption behavior time series group;

[0009] S3: Based on the consumption behavior time series group and the preset business period table, each picking time is classified into its corresponding time period, and the time node of the time period is aligned with the meal delivery record, and the meal name and time period type are marked to obtain a time period classification meal mapping table;

[0010] S4: According to the checkout items in the meal mapping table classified by the time period, the time points of payment request sending and return are extracted, the time difference is identified and compared with the payment delay threshold, and the payment record numbers that exceed the delay limit are screened to obtain a list of abnormal payment records.

[0011] As a further solution of the present invention, the tray-bound seat identification value includes a unique path identifier, a trajectory stability factor, and a trigger position parameter; the consumption behavior time series group includes a gripping frequency distribution, a time interval sequence, and a behavior duration; the time period classification meal mapping table includes a time period label, a meal type set, and a meal delivery record number; and the abnormal payment record list includes a payment delay duration, a corresponding payment method code, and an abnormal identification label.

[0012] As a further solution of the present invention, the step of binding the tray to the seat identification value is specifically as follows:

[0013] S101: A sensor is installed on the edge of the tray and the sensor contact trajectory is captured. The time point when the contact number contacts the trigger area is recorded. The contact coordinate change sequence and movement direction over a continuous time are collected. Based on the coordinate change direction and time sequence, the directional offset and contact interval between the contact point and the tray edge are determined, and the offset direction and time delay value are generated.

[0014] S102: Calling the offset direction and time delay value, extracting the spatial displacement sequence of the same contact point in a continuous time period, identifying the change rate between adjacent coordinate points and the path curvature per unit time, judging the path change stability based on the coherence of the change rate and the curvature fluctuation range, and obtaining a trajectory path continuity index group;

[0015] S103: Based on the trajectory path continuity index group, compare the number attribution of each group of trajectory features in the pallet sensor sequence, identify the matching relationship of the seat number according to the feature attribution result, and generate a pallet-bound seat identification value.

[0016] As a further solution of the present invention, the steps of the consumption behavior time series group are specifically as follows:

[0017] S201: Based on the pallet-bound seat identification value, the pallet identification number and time node of each pallet trigger record are collected, arranged in sequence according to the time node field, and the time intervals between adjacent records are sequentially identified to obtain a pallet time interval sequence;

[0018] S202: Based on the tray time interval sequence and a preset standard meal cycle threshold, the time interval is compared with the threshold, and continuous time periods with intervals less than the threshold are selected. The tray identification numbers and start and end times in each time period are counted, and the tray identification numbers and start and end times in each time period are classified, labeled, and sequentially integrated to obtain a continuous record segment interval group;

[0019] S203: calling the tray identification number in the continuous record segment interval group, locating the corresponding gripping event record and extracting the time node, and merging the start and end time node intervals of the segment to perform time sorting and merging to obtain a consumption behavior time series group.

[0020] As a further solution of the present invention, the consumption behavior time series group adopts the formula:

[0021]

[0022] Among them, G represents the consumption behavior time series group, Q i represents the starting time of the i-th time node, E i represents the end time of the i-th time node, and n represents the total number of time nodes.

[0023] As a further solution of the present invention, the steps of the time period classification meal mapping table are specifically as follows:

[0024] S301: Extracting the grabbing time based on the consumption behavior time series group, comparing it with the start and end time of each time period in the preset business period table, classifying it into business period types based on the time range, eliminating data that does not fall within any time period, and generating business period interval types;

[0025] S302: Call the business hour interval type, compare the short-term pick-up time with the meal delivery record time, extract the matching record meal name, and combine it with the time period to obtain the meal and business hour combination value;

[0026] S303: Classify by time period according to the combination value of the food and business hours, sort the corresponding food names, count the frequencies after removing duplicates, and output them in order of time periods to obtain a time period classification food mapping table.

[0027] As a further solution of the present invention, the step of listing abnormal payment records is specifically as follows:

[0028] S401: Extract the payment request sending time and payment return time from each record based on the checkout items in the time period classification meal mapping table, group them by record number, identify the time difference between the sending time and the return time within each group, store them uniformly by record number, and obtain the payment response time difference;

[0029] The payment response time difference is calculated using the formula:

[0030]

[0031] Where ΔT represents the payment response time difference, W j represents the time when the payment request in the jth group of records is sent, R j represents the payment return time in the jth group of records, and m represents the total number of record groups;

[0032] S402: Call the payment response time difference value, select the time difference corresponding to the record number, compare it with the set payment delay threshold item by item, determine the record number that exceeds the threshold, extract and store the number, and obtain the over-limit payment number set;

[0033] S403: Match corresponding records in the original checkout items according to the set of over-limit payment numbers, extract all fields, eliminate non-abnormal items with time differences within the threshold, and sort in ascending order by record number to obtain a list of abnormal payment records.

[0034] As a further embodiment of the present invention, the method further comprises step S5:

[0035] S5: Based on the payment method number in the abnormal payment record list, extract the current payment interface configuration item, move the abnormal number to the back in the interface sorting, and arrange the updated interface display structure in order of the call frequency of non-abnormal items, and output the updated interface payment method list;

[0036] The interface payment method update list includes the interface arrangement structure, payment method call frequency, and payment method priority label.

[0037] As a further solution of the present invention, the steps of updating the payment method list on the interface are specifically as follows:

[0038] S501: Based on the payment method numbers in the abnormal payment record list, extract the payment method number sequence and display structure from the payment interface configuration, filter out items that match the abnormal numbers, and compare them with the original sequence to generate abnormal payment method mark positions;

[0039] S502: Call the abnormal payment method mark position, move the matching number backward in the original configuration order, and keep the corresponding order unchanged, extract the call count value of the non-abnormal number, sort it by the call count and insert it in front of the abnormal number to obtain the payment method reordering structure;

[0040] S503: According to the payment method reordering structure, the display order field in the original configuration item is updated, duplicate numbers are removed and the sorting value interval is corrected, the payment method number and sorting sequence are retained, and the payment method update list is output on the interface.

[0041] On the other hand, the electric vehicle state monitoring system is used to execute the above electric vehicle state monitoring method, and the system includes:

[0042] The trajectory recognition module installs sensors on the edge of the tray to extract the start and end times of the restaurant slide rail contact, determine the offset direction and time difference, and combine coordinate continuity to match the tray number and seat number to obtain the tray and seat pairing information;

[0043] Based on the tray and seat pairing information, the behavior merging module extracts the picking time points under each tray number, arranges them in chronological order, groups consecutive picking actions with a time interval less than the dining cycle, and marks them as the same dining behavior based on the seat number, thereby obtaining a consumption sequence bound to the seat;

[0044] The time period mapping module extracts each pick-up time based on the consumption sequence of the bound seat, determines the business time period to which it belongs, and matches the meal menu items corresponding to the time period. By comparing the overlapping intervals between the pick-up events and the meal delivery times, the module determines the meal corresponding to each pick-up event and obtains a list of meals corresponding to the time period.

[0045] The payment screening module extracts the payment sending time and return time of each record based on the checkout records in the meal list corresponding to the time period, and filters the record numbers that exceed the preset response time to obtain a set of abnormal payment numbers;

[0046] The interface update module counts the payment method numbers in the abnormal payment number set, the ranking position and call frequency of the numbers in the interface configuration, sorts the timed numbers backward, rearranges the remaining numbers according to the frequency, and outputs the interface payment method update list.

[0047] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0048] By setting sensors on the edge of the tray, the continuous coordinate points of the gripping path are extracted with the help of the starting contact time and direction offset of the contact trajectory, and the corresponding relationship is determined based on the continuity of the trajectory and the curve characteristics, so as to achieve a unique match between the tray and the seat, effectively distinguish and identify the source of consumption, and reduce the possibility of confusion in consumption data of different seats. Based on this identification value, the corresponding time node of each gripping is recorded, and the continuous operations are merged into a consumption behavior sequence according to the time interval rules, avoiding the problem of scattered consumption records being difficult to merge in manual settlement. According to the consumption behavior time series, the business period table and the meal delivery record are connected, and the gripping time and meal data are matched to form the meal mapping results under the time period classification, which improves the linkage between consumption data and meal content and provides structured data support for subsequent analysis. Extract and compare the response time of payment records, screen out delayed payment behaviors and form a numbered list, effectively capture potential payment anomalies, and achieve improvements in both accuracy and efficiency. Rearrange the display order according to the payment method number, move the frequently occurring abnormal methods to the back, and optimize the display structure based on the historical call frequency to enhance the stability of the payment interface and the smoothness of user operations. Through precise identification, data merging, behavior mapping and interaction sorting optimization, strengthen the integrity of the consumption data structure and the traceability of the behavior link, and enhance the adaptability of the checkout interface at the operational level, effectively improving the stability of the payment process during peak periods and the overall settlement efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0050] Figure 2 This is a detailed flow chart of S1 of the present invention;

[0051] Figure 3 This is a detailed flow chart of S2 of the present invention;

[0052] Figure 4 This is a detailed flow chart of S3 of the present invention;

[0053] Figure 5 This is a detailed flow chart of S4 of the present invention;

[0054] Figure 6 This is a detailed flow chart of S5 of the present invention;

[0055] Figure 7 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0056] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0057] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "exemplary" in the present invention should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner. Furthermore, in the embodiments of the present invention, "and / or" can mean both or either of the two.

[0058] In the embodiments of the present invention, the terms "image" and "picture" may be used interchangeably. It should be noted that, when the distinction between them is not emphasized, their intended meanings are the same. The terms "of," "corresponding," and "corresponding" may be used interchangeably. It should be noted that, when the distinction between them is not emphasized, their intended meanings are the same.

[0059] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0060] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0061] See also Figure 1The embodiment of the present invention provides a restaurant self-service checkout method based on a smart disk. The processing flow of the method may include the following steps:

[0062] S1: A sensor is installed on the edge of the pallet and captures the sensor contact trajectory. The contact time difference and offset direction between the trajectory starting point and the pallet edge trigger zone are determined to extract the continuously changing coordinates of the gripping trajectory path. The trajectory is determined by combining path continuity and curve stability. The unique matching result between the pallet and the seat is marked to obtain the pallet-bound seat identification value.

[0063] S2: Based on the tray-bound seat identification value, the time node of each tray trigger and the corresponding gripping event are collected. Continuous records with intervals less than the standard dining cycle are filtered in chronological order and merged into a group of consumption behaviors to obtain a consumption behavior time series group.

[0064] S3: Based on the consumer behavior time series group and the preset business hours table, each picking time is classified into its corresponding time period, and the time node of the time period is aligned with the meal delivery record, and the meal name and time period type are marked to obtain a time period classification meal mapping table;

[0065] S4: Classify the checkout items in the meal mapping table based on the time period, extract the time points of payment request sending and return, identify the time difference, and compare it with the payment delay threshold. Filter the payment record numbers that exceed the delay limit to obtain a list of abnormal payment records;

[0066] S5: Based on the payment method number in the abnormal payment record list, extract the current payment interface configuration item, move the abnormal number to the back in the interface sorting, and arrange the updated interface display structure in order of the call frequency of non-abnormal items, and output the interface payment method update list.

[0067] The tray-bound seat identification value includes the path unique identifier, trajectory stability factor, and trigger position parameters; the consumption behavior time series group includes the gripping frequency distribution, time interval sequence, and behavior duration; the time period classification meal mapping table includes the time period label, meal type set, and meal delivery record number; the abnormal payment record list includes the payment delay duration, the corresponding payment method code, and the abnormal identification label; the interface payment method update list includes the interface arrangement structure, payment method call frequency, and payment method priority label.

[0068] Specifically, if Figure 2 As shown, the steps for binding the tray to the seat identification value are as follows:

[0069] S101: A sensor is installed on the edge of the tray and the sensor contact trajectory is captured. The time point when the contact number contacts the trigger area is recorded. The contact coordinate change sequence and movement direction over a continuous time are collected. Based on the coordinate change direction and time sequence, the directional offset and contact interval between the contact point and the tray edge are determined, and the offset direction and time delay value are generated.

[0070] In a high-traffic restaurant environment, waiters use trays equipped with sensors to carry meals. When the edge of the tray contacts a table, chair, or object, the sensor is activated and the coordinate sequence and movement direction of each touch point are recorded. The process involves first initializing the sensor array to ensure the activity and response speed of each sensor, and then continuously monitoring the coordinate changes of the touch points. Whenever the touch point moves, the new coordinate position is captured and the direction and speed of movement are immediately calculated. If the touch point moves in the same direction and at a similar speed for several consecutive times, it is determined that the touch point is moving along the edge rather than simply jittering or accidentally touching. This data is then used to analyze the pattern and path stability of the touch point movement. For example, if a touch point moves 10 cm to the right along the edge of the tray for 5 consecutive seconds and the movement rate remains at 2 cm per second, the system records the behavior pattern and predicts future movement trends, generating offset direction and time delay values. The generated information can be used to evaluate the waiter's handling skills and can also be used for further data analysis, such as optimizing the design of the tray to reduce false triggering.

[0071] S102: Call the offset direction and time delay value to extract the spatial displacement sequence of the same contact point in a continuous time period, identify the change rate between adjacent coordinate points and the path curvature per unit time, and judge the path change stability based on the consistency of the change rate and the curvature fluctuation range to obtain a trajectory path continuity index group;

[0072] Food is transported using trays equipped with sensors. By analyzing the contact displacement sequence over continuous time, stable and unstable transport trajectories are identified. The process involves first extracting the spatial displacement sequence of each contact point from the stored data, and then calculating the displacement rate and path curvature between adjacent coordinate points. For example, if the contact point moves from coordinates (10, 10) to (15, 10) within 2 seconds, the movement rate is 2.5 cm per second. The continuity of the rate is then evaluated. If the subsequent contact rate drops significantly to 1 cm per second, the system marks the trajectory as unstable. Based on the data, the path continuity indicators of each contact point are further calculated, such as the average rate, rate variation coefficient, maximum and minimum curvatures. The indicator set is used to judge the stability of the entire movement process, and ultimately a trajectory path continuity indicator group is obtained. This data helps management optimize the workflow of the packaging line and ensure the accuracy and safety of food transportation.

[0073] S103: Based on the trajectory path continuity index group, compare the number attribution of each set of trajectory features in the pallet sensor sequence, identify the matching relationship of the seat number based on the feature attribution result, and generate the pallet-bound seat identification value;

[0074] By analyzing the trajectory path continuity indicators captured by each sensor on the pallet, the trajectory data is matched with the preset seat numbers on the pallet. This process involves using an algorithm to compare each trajectory indicator with the known pallet seat standard template. For example, if the average speed and curvature of a trajectory match the preset trajectory characteristics of a specific seat, the trajectory is marked as that seat. In this way, the pallet seat corresponding to each product can be accurately identified. This identification is not based on a single trajectory feature, but is based on a comprehensive judgment of a series of continuity indicators. Ultimately, a pallet-bound seat identification value is generated. This value is crucial to ensuring the correct sorting and efficient processing of products in logistics automation configurations.

[0075] Specifically, if Figure 3 As shown in Figure 2, the steps of the consumption behavior time series group are as follows:

[0076] S201: Based on the pallet-bound seat identification value, the pallet identification number and time node of each pallet trigger record are collected, arranged in sequence according to the time node field, and the time intervals between adjacent records are identified in sequence to obtain a pallet time interval sequence;

[0077] In a restaurant environment, every time a waiter or customer uses a sensor-equipped tray to pick up food from the cashier, the tray's identification number and pickup time are recorded. Each subsequent time the tray triggers the sensor (e.g., when it is set down or picked up again) generates a new time node. This recording method can help restaurants track the mobility and frequency of tray usage. Data is arranged in chronological order based on the time nodes. This arrangement process involves data extraction, time formatting, and sequence generation. For example, if tray number 001 is picked up at 12:00 and triggers the sensor at 12:15 and 12:45 on different tables, these three time nodes are recorded and arranged in sequence. Subsequently, the intervals between adjacent time nodes are identified and recorded. Calculating the intervals helps analyze the tray usage cycle and the length of customer dining time. Generating the time interval involves a simple subtraction operation between two time points. For example, the interval from 12:00 to 12:15 is 15 minutes, and the interval from 12:15 to 12:45 is 30 minutes. This results in a tray time interval sequence, which provides important data on restaurant operational efficiency and can be used to further optimize customer service and resource allocation.

[0078] S202: Based on the tray time interval sequence and a preset standard meal cycle threshold, the time interval is compared with the threshold, and continuous time periods with intervals less than the threshold are selected. The tray identification numbers and start and end times in each time period are counted, and the tray identification numbers and start and end times in each time period are classified, labeled, and sequentially integrated to obtain a continuous record segment interval group;

[0079] Restaurant management sets a standard dining cycle of 30 minutes. This threshold is derived from statistical analysis of average dining time data. The threshold setting process includes collecting historical data, calculating the mean and standard deviation, and determining the optimal threshold to accommodate the dining habits of most customers. Once a sequence of tray time intervals is generated, each interval is compared to the 30-minute threshold. This comparison is a basic conditional judgment process. For example, if an interval is 20 minutes, which is less than the 30-minute threshold, the interval is recorded as a fast meal. All intervals less than the threshold are filtered out, indicating fast meal transitions or very busy periods. The filtering operation involves traversing the time interval sequence and applying conditional statements. The tray identification number and start and end time within each time period are counted, and then classified, labeled, and sequentially integrated. This counting and integration process involves categorizing the data and determining the time period. For example, all fast meal time periods and corresponding tray numbers are determined. The information is then integrated in chronological order to obtain a group of continuous record segment intervals. This group of intervals provides the restaurant with insights into peak dining times and customer dining behavior patterns, helping to further adjust the restaurant layout and service strategy to meet customer needs.

[0080] S203: calling the tray identification number in the continuous record segment interval group, locating the corresponding gripping event record and extracting the time node, and integrating it into the start and end time node interval of the segment to perform time sorting and merging to obtain the consumption behavior time series group;

[0081] The consumption behavior time series group uses the formula:

[0082]

[0083] Among them, G represents the consumption behavior time series group, Q i represents the starting time of the i-th time node, E i represents the end time of the i-th time node, and n represents the total number of time nodes;

[0084] The "consumption behavior time series group" is formed by arranging the multiple gripping records generated during the use of the tray in the restaurant in chronological order, and screening the continuous records with a time interval less than the "standard dining cycle" and merging them. The specific process includes: first, identifying the tray number and time node to form a tray time interval sequence; then, combining the continuous segments with a time interval less than the threshold (i.e., the standard dining cycle) into a group of consumption behaviors; finally, extracting the gripping events in these segments and integrating them into the final "consumption behavior time series group". It can be seen from these steps that the scope of the "accumulation process" is limited based on whether the time interval is less than the standard dining cycle. Any continuous gripping behavior that meets this condition will be regarded as a continuous dining behavior and included in the calculation scope. Therefore, this process does not accumulate all gripping records indiscriminately, but has a behavior merging threshold limit, that is, the boundary condition of the "dining cycle". This method ensures the temporal coherence and behavioral integrity of the consumption sequence, and is a conditional "limited accumulation";

[0085] This formula is used to sort a set of time nodes to obtain the final consumption behavior time series. The acquisition and processing of each parameter in the formula are as follows:

[0086] G: The final sorted time series group, which represents the sorted set of time nodes of all consumption behaviors. This result represents the time nodes arranged in chronological order, reflecting the temporal relationship of each consumption behavior;

[0087] Q i : The starting time of the i-th time node. This refers to the starting time of a consumption behavior in the entire time interval. The acquisition of this parameter needs to be automatically recorded by the system, which is collected by sensing devices or IoT sensors, such as the timestamp of barcode scanning or time tagging method. When actually collecting data, Q i The unit is seconds. The timestamp of the acquisition can be obtained through the system's time interface and is measured in seconds.

[0088] E i : The end time of the i-th time node, indicating the end time of the corresponding consumption behavior, similar to Q i , the data is collected by the sensor of the automation system, the unit is second, the data quantification process is the same as Q i The same, and the end time of each consumption behavior is also collected through the recording device;

[0089] n: The total number of time nodes, which represents the number of all collected time nodes. This parameter is obtained by counting consumption behavior records within a period of time. In the calculation, this parameter represents the total number of all consumption event records;

[0090] Qi and E i Time parameters can be automatically recorded through IoT sensors, barcode scanners, and mobile device timestamps. Whenever a consumption behavior occurs, its start and end time will be recorded in seconds, indicating the time since a fixed time point (such as epoch time);

[0091] Calculation of n: n is obtained by counting the start and end time of each consumption event. In a certain period of time, the total number of start and end time points of consumption behavior is counted, and the value of n is determined based on the number of time points;

[0092] Unification of time units: All time parameters (Q i and E i ) are all in seconds to ensure consistency. If the data source uses different time units (such as milliseconds or minutes), appropriate conversions must be performed to ensure consistency.

[0093] Assume that 5 consumption behavior events are collected in a time period, and their corresponding start and end times are:

[0094] Q1=10 seconds, E1=15 seconds, Q2=25 seconds, E2=35 seconds, Q3=50 seconds, E3=55 seconds, Q4=70 seconds, E4=75 seconds, Q5=90 seconds, E5=100 seconds;

[0095] Step 1: Calculate the absolute time difference for each time period:

[0096] |Q1-E1|=|10-15|=5 seconds;

[0097] |Q2-E2|=|25-35|=10 seconds;

[0098] |Q3-E3|=|50-55|=5 seconds;

[0099] |Q4-E4|=|70-75|=5 seconds;

[0100] |Q5-E5|=|90-100|=10 seconds;

[0101] Compute the square root term:

[0102]

[0103] Calculate the time node sorting results:

[0104]

[0105] The final G value is 4.24, which represents the weighted sum of the total time series combination after time sorting. The value 4.24 indicates the sum of the weighted time differences within the specified time interval. This value can be further used in subsequent analysis to reflect the temporal characteristics of each consumer behavior event in the entire sequence.

[0106] Specifically, if Figure 4 As shown, the steps of the time period classification meal mapping table are as follows:

[0107] S301: Extract the picking time based on the consumption behavior time series group, compare it with the start and end time of each period in the preset business period table, classify it into business period types according to the time range, eliminate data that does not fall within any period, and generate business period interval types;

[0108] Extract the picking time and compare it with the start and end time of each time period in the preset business hours table. In the actual operation of the restaurant, the picking time is extracted from each customer's buffet picking record. For example, a customer picks up food at 12:05 and compares this time with the restaurant's preset business hours. The business hours table sets the lunch period from 11:00 to 14:00 and the dinner period from 17:00 to 20:00. First, compare the time point of 12:05 with the start and end time of each business period one by one to determine whether it is within the preset time period. If it is picked up at 12:05, the time point is compared with the start and end time of each business period. The time 12:05 is between 11:00 and 14:00, so this time point is classified as "lunch period". Then all the picking times are processed in the same way, classified by time period, and those data that are not in any time period are eliminated. For example, if a picking time is 10:30, the system will eliminate it because it does not conform to any preset business hours. Finally, data of the business hour interval type is generated, in which each picking time is accurately classified into the corresponding time period interval, for example, 12:05 is classified as "lunch period" and 10:30 is eliminated.

[0109] S302: Call the business hour interval type, compare the short-term pickup time with the meal delivery record time, extract the matching record meal name, and combine it with the time period to obtain the meal and business hour combination value;

[0110] In the restaurant's automated ordering, customers select and pick up dishes through self-service equipment, record the time of each pick-up, and then compare it with the kitchen's serving records. For example, a customer picks up dish A at 12:05, and checks whether there is a serving time that matches this pick-up time. Assuming that the kitchen completes the preparation of dish A and prepares to serve it at 12:07, it is found that the time difference between the two is small, that is, it is a pick-up and serving record in a short period of time. At this time, the system will extract the name of the dish in the record, such as dish A, and then combine the dish with the "lunch period" in which it is located to generate a combination value of the dish and the business period. For example, dish A and "lunch period" are combined into one value. This process is performed similarly for each pick-up time and serving record, and finally a combination of the dish and the time period to which it belongs is obtained. The combination value will help the restaurant analyze the most popular dishes in each time period and optimize the food supply strategy.

[0111] S303: Classify the items by time period based on the combination of the items and the business hours, sort the corresponding item names, remove duplicates, count the frequencies, and output them in order of time periods to obtain a time period classification item mapping table;

[0112] When processing the combination values ​​of dishes and business hours, classify and organize them according to the combination of dishes in each time period, and classify all dishes by business hours. For example, put all dishes in the "lunch period" together, and all dishes in the "dinner period" together, and then remove duplicate dish names to ensure that each dish is counted only once in the time period, and count the frequency of each dish in each time period. For example, suppose dish A appears 5 times and dish B appears 3 times in the lunch period. Count the frequency and output the results in time period order. The dishes in all time periods and their frequency data will generate a time period classification meal mapping table in time period order. In this example, dish A is obtained 5 times and dish B is obtained 3 times in the lunch period, and dish C is obtained 8 times and dish D is obtained 4 times in the dinner period, etc. Finally, a time period classification meal mapping table is generated, which can provide specific data support for the restaurant's operational decisions.

[0113] Specifically, if Figure 5 As shown, the steps for listing abnormal payment records are as follows:

[0114] S401: Based on the checkout items in the meal mapping table classified by time period, extract the payment request sending time and payment return time from each record, group them by record number, identify the time difference between the sending time and the return time within each group, store them uniformly by record number, and obtain the payment response time difference;

[0115] Pay the response time difference using the formula:

[0116]

[0117] Where ΔT represents the payment response time difference, Wj represents the time when the payment request in the jth group of records is sent, R j represents the payment return time in the jth group of records, and m represents the total number of record groups;

[0118] The "Payment Response Time Difference" is obtained by extracting the time of payment request submission and payment confirmation for each payment record, and calculating the difference between these two time points, representing the time elapsed between payment request and payment response. This time difference is used to assess the responsiveness of the payment system and can reveal whether certain payment methods are experiencing processing delays, providing data for optimizing the checkout experience.

[0119] The calculation method of "dividing the difference by the total number of records in the group" mentioned in the article does not simply calculate the difference of a single record. Instead, it unifies the response time differences of multiple records. That is, by calculating the sum of the response time differences of all payment records and dividing it by the total number of records, the "average payment response time difference" is obtained. This calculation method does not calculate the difference between two values ​​within a group, but rather reflects the overall response performance of the entire payment system in a certain time period or for a certain payment method.

[0120] This calculation method is used to achieve data standardization and trend identification. By averaging the differences in response times of multiple payments, we can avoid interference caused by individual extreme values ​​and enable the system to judge the overall trend of payment performance at a macro level. If the average response time of a payment method is significantly higher than the system's preset delay threshold, it can be determined that the method is abnormal and will be ranked lower in the interface or marked as low priority. This method not only improves the rationality of payment method display, but also optimizes user experience and system stability.

[0121] This formula is used to calculate the difference in response time between the payment request sending time and the payment return time for each set of records. The specific process for obtaining and quantifying each parameter is as follows:

[0122] W j : represents the payment request sending time in the jth group of records. This data is obtained by real-time monitoring and recording in the payment system. The unit is seconds. The payment request sending time is the moment when the user sends the payment request after the payment operation. It is obtained through the server log or the payment platform API. For example, if in a certain group of records, W j =12:05:01 (i.e. 12:05:01);

[0123] R j: represents the payment return time in the jth group of records. This time is obtained from the confirmation information record returned by the payment platform. The unit is seconds. It represents the response time after the payment request is sent. It is obtained through the confirmation response of the payment platform or the return time record of the payment system. For example, if in a certain group of records, R j =12:05:10 (i.e. 12:05:10);

[0124] |W j -R j |: Calculates the absolute difference between the sending time and the return time, in seconds. This value represents the response time difference of each payment operation, reflecting the time delay of payment processing. For example, the payment request of the first set of records was sent at 12:05:01 and the payment was returned at 12:05:10. The response time difference is:

[0125] |W j -R j |=|12:05:10-12:05:01|=9;

[0126] The sum of the squares of the response time differences in all records, where m is the number of record groups. The response time difference of each group of records is calculated by taking its absolute value and then squared. The squared values ​​of all records are accumulated to get the total. For example, if there are three groups of records, the calculated response time differences are 9 seconds, 7 seconds, and 5 seconds respectively.

[0127]

[0128] m: The total number of record groups, indicating the number of payment request groups currently being counted. For the above example, assuming there are 3 groups of records, m = 3;

[0129] By inserting the data, the average value of the payment response time difference can be calculated;

[0130] The specific calculation is as follows:

[0131] The calculation results show that the average response time difference of the three groups of payment records counted is 51.67 seconds. This result reflects the average delay time between payment request and payment return. This value can be used to evaluate the delay between payment system processing requests and responses, and further optimize system performance.

[0132] S402: Call the payment response time difference value, select the time difference corresponding to the record number, compare it with the set payment delay threshold item by item, determine the record number that exceeds the threshold, extract and store the number, and obtain the excess payment number set;

[0133] In smart restaurant self-service checkout, the payment response time difference is the time difference between the customer completing the payment operation and the payment system confirming the payment status. First, the payment response time difference is calculated based on the time node of each payment event record. For example, if a customer completes the payment at 12:10:05 and the payment confirmation time is 12:10:30, the payment response time difference is 25 seconds. The time difference of each payment record is compared with the preset payment delay threshold. If the payment delay threshold is set to 20 seconds, then 25 seconds exceeds the threshold and the payment operation number is recorded as an exception. Payment events exceeding the threshold indicate slow payment confirmation speed, resulting in a poor customer experience. All record numbers with payment response times greater than the set threshold are filtered, and the numbers of abnormal payment events are extracted and stored, ultimately obtaining a set of over-limit payment numbers. For example, payment events numbered 101, 102, and 105 are recorded as the over-limit payment number set, which provides basic data for subsequent exception processing.

[0134] S403: Match the corresponding records in the original checkout items based on the set of over-limit payment numbers, extract all fields, eliminate non-abnormal items with time differences within the threshold, and sort in ascending order by record number to obtain a list of abnormal payment records;

[0135] By matching the set of over-limit payment numbers with the payment records in the original checkout record table, each payment record includes fields such as payment number, payment time, customer number, and payment amount. According to the extracted over-limit payment number, the corresponding complete payment record is found, and all relevant fields are extracted from it. For example, assuming that the record with payment number 101 involves customer A paying 100 yuan and the payment time is 12:10:05, customer A's payment information is extracted from the original checkout record table, including all fields such as payment time and payment amount. Further, those normal payment records whose payment response time is within the preset threshold are eliminated, that is, those data whose payment response time is less than or equal to the set threshold are eliminated. This can be achieved through filtering operations in the database. All qualified abnormal payment records will be extracted and sorted in ascending order by record number for subsequent review and processing, and a list of abnormal payment records sorted by time is obtained.

[0136] Specifically, if Figure 6 As shown, the steps for updating the payment method list on the interface are as follows:

[0137] S501: Based on the payment method numbers in the abnormal payment record list, extract the payment method number sequence and display structure from the payment interface configuration, select items that match the abnormal numbers, and compare them with the original sequence to generate abnormal payment method mark positions;

[0138] According to the payment method number in the abnormal payment record list, the order and display structure of the payment methods are extracted from the payment interface configuration. Assuming that the configuration order of the payment methods in the payment interface is: credit card, WeChat Pay, Alipay, and cash, it is first necessary to extract the position and display order of WeChat Pay from the configuration table based on the payment method number in the abnormal payment record (for example, the record numbered "2" represents WeChat Pay). Then, by comparing the number sequence of each payment method, the items that match the abnormal payment record number are filtered out. Assuming that the payment method number is "3" (i.e., Alipay payment) appears in the abnormal payment record, it will match Alipay in the third position in the display structure, and according to its order in the configuration table, it will be compared with the original order to further determine which payment methods' display order does not meet the requirements, generate an abnormal payment method mark position, and record the abnormal position of the payment method. For example, if Alipay payment should be displayed in the second position but is actually displayed in the third position, the payment method will be marked as abnormal.

[0139] S502: The abnormal payment method mark position is called, the matching number is moved back in the original configuration order, and the corresponding order is kept unchanged. The call count values ​​of the non-abnormal numbers are extracted, sorted by the call count and inserted before the abnormal number to obtain the payment method reordering structure;

[0140] Move the matched payment method number backward in the original configuration order. Assuming that WeChat payment is marked as abnormal and its position in the payment method display order should be second, adjust the payment method number of WeChat payment to the back of the display order, keeping the relative order of the payment methods unchanged. For example, if the order of Alipay payment and cash payment was originally first and fourth, the relative positions of these two payment methods in the updated configuration will remain unchanged, and only WeChat payment will be moved to the last fifth position to ensure that the order of payment methods is adjusted, but the relative order of payment methods is not affected. Extract the call count value of the non-abnormal number. For example, a payment method may be called 10 times, and another payment method is only called 2 times. The system sorts the payment methods according to the call count, and prioritizes the payment methods with more calls. According to the sorting result, the payment method with more calls will be inserted in front of the abnormal number, thereby obtaining the payment method reordering structure.

[0141] S503: Based on the payment method reordering structure, the display order field in the original configuration item is updated, duplicate numbers are removed, and the sorting value interval is corrected. The payment method number and sorting sequence are retained, and the updated payment method list is output on the interface.

[0142] According to the payment method reordering structure, update the display order field in the original payment configuration item. Assuming that the original payment method configuration table has payment methods numbered "1" to "5", rearrange the display order of the payment methods and remove duplicate number records to ensure that each payment method appears only once. Correct the sorting value range of the payment method. If a payment method is numbered "1", it will be ensured to be displayed at the front. If the payment method numbered "5" is moved to the end, update its sorting position in the configuration table according to the new sorting logic to ensure that the display order is accurate, retain the payment method number and its new sorting sequence, and finally output the updated payment method list on the interface. The content in the list will include the number of each payment method, the updated order and the sorting value range, to ensure that the payment interface can display the payment method according to the updated configuration, so that customers can more conveniently choose the payment method during self-service checkout.

[0143] like Figure 7 As shown, a restaurant self-service checkout system based on smart disk binding includes:

[0144] The trajectory recognition module installs sensors on the edge of the tray to extract the start and end times of the restaurant slide rail contact, determine the offset direction and time difference, and combine coordinate continuity to match the tray number and seat number to obtain the tray and seat pairing information;

[0145] The behavior merging module extracts the picking time points under each tray number based on the tray and seat pairing information, arranges them in chronological order, groups consecutive picking actions with a time interval less than the meal cycle, and marks them as the same dining behavior based on the seat number, thus obtaining the consumption sequence bound to the seat.

[0146] The time period mapping module extracts each pickup time based on the consumption sequence of the bound seats, determines the business hours to which it belongs, and matches the menu items corresponding to the time period. By comparing the overlap interval between the pickup events and the food delivery times, it determines the food item corresponding to each pickup event and obtains a list of food items corresponding to the time period.

[0147] The payment screening module extracts the payment sending and return time of each record based on the checkout records in the meal list corresponding to the time period, and filters the record numbers that exceed the preset response time to obtain a set of abnormal payment numbers;

[0148] The interface update module counts the payment method numbers in the abnormal payment number set, the ranking position and call frequency of the numbers in the interface configuration, sorts the timed numbers backward, rearranges the remaining numbers according to frequency, and outputs the interface payment method update list.

[0149] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A restaurant self-service checkout method based on smart disk binding, characterized in that: The following steps are involved: S1: Install a sensor on the edge of the pallet and capture the sensor contact trajectory. By determining the contact time difference and offset direction between the trajectory starting point and the pallet edge trigger area, the continuously changing coordinates of the gripping trajectory path are extracted, the trajectory ownership is determined, and the unique matching result between the pallet and the seat is marked to obtain the pallet-bound seat identification value. S2: Based on the tray-bound seat identification value, the time node of each tray triggering and the corresponding gripping event are collected, and continuous records with intervals less than the standard dining cycle are filtered in chronological order and merged into a group of consumption behaviors to obtain a consumption behavior time series group; S3: Based on the consumption behavior time series group and the preset business period table, each picking time is classified into its corresponding time period, and the time node of the time period is aligned with the meal delivery record, and the meal name and time period type are marked to obtain a time period classification meal mapping table; S4: According to the checkout items in the meal mapping table classified by the time period, the time points of payment request sending and return are extracted, the time difference is identified and compared with the payment delay threshold, and the payment record numbers that exceed the delay limit are screened to obtain a list of abnormal payment records.

2. The restaurant self-service checkout method based on smart disk according to claim 1 is characterized in that: The tray-bound seat identification value includes a unique path identifier, a trajectory stability factor, and a trigger position parameter; the consumption behavior time series group includes a gripping frequency distribution, a time interval sequence, and a behavior duration; the time period classification meal mapping table includes a time period label, a meal type set, and a meal delivery record number; and the abnormal payment record list includes a payment delay duration, a corresponding payment method code, and an abnormal identification label.

3. The restaurant self-service checkout method based on smart disk according to claim 1 is characterized in that: The steps of binding the tray to the seat identification value are as follows: S101: A sensor is installed on the edge of the tray and the sensor contact trajectory is captured. The time point when the contact number contacts the trigger area is recorded. The contact coordinate change sequence and movement direction over a continuous time are collected. Based on the coordinate change direction and time sequence, the directional offset and contact interval between the contact point and the tray edge are determined, and the offset direction and time delay value are generated. S102: Calling the offset direction and time delay value, extracting the spatial displacement sequence of the same contact point in a continuous time period, identifying the change rate between adjacent coordinate points and the path curvature per unit time, judging the path change stability based on the coherence of the change rate and the curvature fluctuation range, and obtaining a trajectory path continuity index group; S103: Based on the trajectory path continuity index group, compare the number attribution of each group of trajectory features in the pallet sensor sequence, identify the matching relationship of the seat number according to the feature attribution result, and generate a pallet-bound seat identification value.

4. The restaurant self-service checkout method based on smart disk according to claim 1 is characterized in that: The steps of the consumption behavior time series group are specifically as follows: S201: Based on the pallet-bound seat identification value, the pallet identification number and time node of each pallet trigger record are collected, arranged in sequence according to the time node field, and the time intervals between adjacent records are sequentially identified to obtain a pallet time interval sequence; S202: Based on the tray time interval sequence and a preset standard meal cycle threshold, the time interval is compared with the threshold, and continuous time periods with intervals less than the threshold are selected. The tray identification numbers and start and end times in each time period are counted, and the tray identification numbers and start and end times in each time period are classified, labeled, and sequentially integrated to obtain a continuous record segment interval group; S203: calling the tray identification number in the continuous record segment interval group, locating the corresponding gripping event record and extracting the time node, and merging the start and end time node intervals of the segment to perform time sorting and merging to obtain a consumption behavior time series group.

5. The restaurant self-service checkout method based on smart disk according to claim 4 is characterized in that: The consumption behavior time series group adopts the formula: Among them, G represents the consumption behavior time series group, Q i represents the starting time of the i-th time node, E i represents the end time of the i-th time node, and n represents the total number of time nodes.

6. The restaurant self-service checkout method based on smart disk according to claim 1 is characterized in that: The steps of the time period classification meal mapping table are specifically as follows: S301: Extracting the grabbing time based on the consumption behavior time series group, comparing it with the start and end time of each time period in the preset business period table, classifying it into business period types based on the time range, eliminating data that does not fall within any time period, and generating business period interval types; S302: Call the business hour interval type, compare the short-term pick-up time with the meal delivery record time, extract the matching record meal name, and combine it with the time period to obtain the meal and business hour combination value; S303: Classify by time period according to the combination value of the food and business hours, sort the corresponding food names, count the frequencies after removing duplicates, and output them in order of time periods to obtain a time period classification food mapping table.

7. The restaurant self-service checkout method based on smart disk according to claim 1 is characterized in that: The steps of listing abnormal payment records are as follows: S401: Extract the payment request sending time and payment return time from each record based on the checkout items in the time period classification meal mapping table, group them by record number, identify the time difference between the sending time and the return time within each group, store them uniformly by record number, and obtain the payment response time difference; The payment response time difference is calculated using the formula: Where ΔT represents the payment response time difference, W j represents the time when the payment request in the jth group of records is sent, R j represents the payment return time in the jth group of records, and m represents the total number of record groups; S402: Call the payment response time difference value, select the time difference corresponding to the record number, compare it with the set payment delay threshold item by item, determine the record number that exceeds the threshold, extract and store the number, and obtain the over-limit payment number set; S403: Match corresponding records in the original checkout items according to the set of over-limit payment numbers, extract all fields, eliminate non-abnormal items with time differences within the threshold, and sort in ascending order by record number to obtain a list of abnormal payment records.

8. The restaurant self-service checkout method based on smart disk according to claim 1 is characterized in that: The method further comprises step S5: S5: Based on the payment method number in the abnormal payment record list, extract the current payment interface configuration item, move the abnormal number to the back in the interface sorting, and arrange the updated interface display structure in order of the call frequency of non-abnormal items, and output the updated interface payment method list; The interface payment method update list includes the interface arrangement structure, payment method call frequency, and payment method priority label.

9. The restaurant self-service checkout method based on smart disk binding according to claim 8 is characterized in that: The steps for updating the payment method list on the interface are as follows: S501: Based on the payment method numbers in the abnormal payment record list, extract the payment method number sequence and display structure from the payment interface configuration, filter out items that match the abnormal numbers, and compare them with the original sequence to generate abnormal payment method mark positions; S502: Call the abnormal payment method mark position, move the matching number backward in the original configuration order, and keep the corresponding order unchanged, extract the call count value of the non-abnormal number, sort it by the call count and insert it in front of the abnormal number to obtain the payment method reordering structure; S503: According to the payment method reordering structure, the display order field in the original configuration item is updated, duplicate numbers are removed and the sorting value interval is corrected, the payment method number and sorting sequence are retained, and the payment method update list is output on the interface.

10. A restaurant self-service checkout system based on smart disk binding, characterized in that: The restaurant self-service checkout method based on a smart disk according to any one of claims 1 to 9, wherein the system comprises: The trajectory recognition module installs sensors on the edge of the tray to extract the start and end times of the restaurant slide rail contact, determine the offset direction and time difference, and combine coordinate continuity to match the tray number and seat number to obtain the tray and seat pairing information; Based on the tray and seat pairing information, the behavior merging module extracts the picking time points under each tray number, arranges them in chronological order, groups consecutive picking actions with a time interval less than the dining cycle, and marks them as the same dining behavior based on the seat number, thereby obtaining a consumption sequence bound to the seat; The time period mapping module extracts each pick-up time based on the consumption sequence of the bound seat, determines the business time period to which it belongs, and matches the meal menu items corresponding to the time period. By comparing the overlapping intervals between the pick-up events and the meal delivery times, the module determines the meal corresponding to each pick-up event and obtains a list of meals corresponding to the time period. The payment screening module extracts the payment sending time and return time of each record based on the checkout records in the meal list corresponding to the time period, and filters the record numbers that exceed the preset response time to obtain a set of abnormal payment numbers; The interface update module counts the payment method numbers in the abnormal payment number set, the ranking position and call frequency of the numbers in the interface configuration, sorts the timed numbers backward, rearranges the remaining numbers according to the frequency, and outputs the interface payment method update list.

Images