A one-stop unmanned industrial supermarket intelligent management system and method

Abstract

The present invention discloses a one-stop unmanned industrial supermarket intelligent management system and method, which relates to intelligent management technology and is used to improve the problem of goods identification errors caused by users putting goods back in disorder after selecting them. The method comprises scanning the status of goods in different containers, comparing the current status with the status when the goods were last closed, setting and displaying the corresponding serial number indicator light value at the head of each container according to the comparison result, monitoring the behavior of people in the container in real time, dynamically selecting to light up or extinguish the indicator light at the head of the container according to the display value of the indicator light with the same serial number, detecting the height and center offset position of goods without displaying the light to set the cargo size threshold of each container, recording the change behavior of the indicator light display value and counting the number of indicator light change behaviors, collecting the opening frequency of all containers and calculating the opening frequency of each container, comprehensively judging whether it is necessary to mark the container, and updating the cargo change time period of the marked container according to the marking result.

Description

Technical Field

[0001] The present invention relates to the field of intelligent management technology, and more specifically, to a one-stop unmanned industrial supermarket intelligent management system and method. Background Art

[0002] Intelligent management technology refers to the use of artificial intelligence to improve the management efficiency and decision-making ability of an organization, help optimize resource allocation, improve operational efficiency, and achieve intelligent decision-making. The application of intelligent management technology in industrial supermarkets can improve the management efficiency of supermarkets;

[0003] The existing technology has the following deficiencies:

[0004] In previous unmanned supermarket intelligent management systems, the goods placed in the cabinets were of the same type. However, most unmanned supermarkets did not have a self-service return processing mechanism after the goods were placed. When users took the goods and put them back in disorder, the goods in the cabinets would be placed in a disorderly manner, which would easily lead to recognition errors and goods obstruction problems, resulting in reduced management efficiency. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a one-stop unmanned industrial supermarket intelligent management system and method, which sets the display value of the serial indicator light according to different types of goods, and determines whether to light up or turn off the indicator light according to the behavior of the personnel, and dynamically analyzes the change of goods to update the indicator light to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A one-stop unmanned industrial supermarket intelligent management method includes the following steps:

[0008] Step S1: Before the cargo door is opened, scan the cargo in different containers and compare the cargo status in each container with the cargo status when the cargo door was last closed. According to the comparison results, set different serial number indicator light display values ​​and display them at the head of each container;

[0009] Step S2: Real-time monitoring of the behavior of personnel in the container with the same serial number indicator light display value, turning on or off the serial number indicator light display value at the head of the corresponding container according to the personnel behavior, and detecting the cargo height and center offset position of each cargo in the container where the serial number indicator light display value is not displayed;

[0010] Step S3: Set the cargo size threshold for each container based on the cargo height and center offset position, set a cargo change time period, update the cargo size threshold within the cargo change time period, and use the container head serial number indicator light display value to light up or off to record the change behavior of the corresponding container head serial number indicator light display value;

[0011] Step S4: Count the number of times the serial number indicator light display value of each container head changes, collect the opening frequency of all containers within a period of time, calculate the opening frequency of each container, calculate the key marking result based on the number of times the serial number indicator light display value of the container head changes and the opening frequency, and determine whether to mark the container as a key mark. Update the cargo change time period of the marked container according to the key marking result.

[0012] In a preferred embodiment, in step S1, the cargo status is the cargo type of the first cargo in the container. When a person enters the monitoring range, the cargo label of the first cargo in different containers is identified and the identification result is obtained. The identification result is the cargo type of the corresponding cargo, and the cargo label identification result of the first cargo in each container after the cargo door is closed last time is called in the historical database.

[0013] In a preferred embodiment, in step S1, the label recognition result of the first cargo in each container is compared with the recognition result of the first cargo in the current container after the cargo door was last closed. If the two comparison results are inconsistent, the serial number of the current container is recorded, and the recognition result of the first cargo in the current container is traversed with the recognition results of the first cargo in all containers recorded after the cargo door was last closed. Containers with the same label are identified and recorded as cross-containers and the container serial numbers are recorded.

[0014] According to the container serial number, set the same serial number indicator light display value for the current container and the cross container, and display it at the container head.

[0015] In a preferred embodiment, in step S2, the personnel behaviors are respectively taking behaviors and putting back behaviors, and the personnel behaviors are judged by recording the weight of the container. When the weight of the container after the cargo door is opened is higher than the weight of the container before the cargo door is opened, the personnel behaviors are judged to be putting back behaviors; when the weight of the container is lower than the weight of the container before the cargo door is opened, the personnel behaviors are judged to be taking behaviors.

[0016] In a preferred embodiment, in step S2, when the behavior of the person in the container is determined to be taking, the system will scan the container and screen out the cargo labels lost due to the behavior, and then extinguish the serial number indicator display value of the corresponding cargo label; on the contrary, when it is determined to be a return behavior, the system identifies the label of the returned cargo and randomly selects a value that does not appear in other container heads as the new serial number indicator display value, and lights it up on the current container head;

[0017] The center offset position is the distance between the cargo and the container boundary. By comparing the distance between the cargo and the left boundary of the container and the distance between the cargo and the right boundary of the container, the maximum boundary distance is selected as the distance between the cargo and the container boundary.

[0018] In a preferred embodiment, in step S3, the detected heights of multiple cargo items in the container that do not display the sequence indicator light are combined into a cargo height set, and the center offset positions are combined into a center offset position set. By traversing the cargo height set and the center offset position set, the mode of the cargo heights and the mode of the center offsets are respectively calculated as the median value of the cargo size threshold;

[0019] Based on the median value of the cargo size threshold, the cargo size threshold is formed by setting the threshold fluctuation percentage;

[0020] Compare multiple goods in the container with the cargo size threshold. If the goods are greater than or equal to the cargo size threshold, identify the corresponding goods and mark them. Then identify the cargo label of the marked goods to obtain the cargo type of the corresponding goods.

[0021] In a preferred embodiment, in step S3, the cargo label identification results of the marked cargo are compared with the cargo label identification results of the first cargo of all containers after the cargo door was closed last time. If the identification results are the same, the container serial numbers of the two containers are recorded, and the display value of the indicator light with the same serial number is set and displayed at the head of the corresponding container;

[0022] Set a cargo change period based on the cargo shelf scheduling cycle. During the cargo change period, enable the threshold update mode and re-calculate the cargo height set and center offset position set every cargo change period.

[0023] If the difference between the newly calculated median value of the corresponding cargo size threshold and the median value of the corresponding cargo size threshold in the previous cargo change period is greater than or equal to the preset adjustment threshold, the cargo size threshold of the current container is updated;

[0024] By recording the on or off behavior of the serial number indicator light at the container head, the change behavior of the serial number indicator light at the container head is obtained.

[0025] In a preferred embodiment, in step S4, the number of changes in the serial number indicator lights at the container heads is counted to obtain the number of changes in the serial number indicator lights at each container head;

[0026] Set the collection time period, obtain the number of times all containers are opened during the collection time period, and obtain the opening frequency of all containers;

[0027] The average container opening frequency is calculated by calculating the ratio of the opening frequency of all containers to the number of containers. The opening frequency of each container is calculated by calculating the ratio of the opening frequency of each container to the average container opening frequency.

[0028] The number of times the serial indicator light on each container head changes and the opening frequency of each container are standardized and substituted into the weighted fusion model to obtain the key marking coefficient.

[0029] In a preferred embodiment, in step S4, the key marking coefficient is compared with a preset key marking threshold value, and if the key marking coefficient is greater than or equal to the key marking threshold value, the corresponding container is marked as a key mark;

[0030] Counting the containers that have been marked as key containers, taking them as key marking results, and sorting and grading the key marking coefficients corresponding to the key marked containers;

[0031] Set different reduction levels to correspond to the reduction levels of the container change time period after sorting and grading, and perform reduction operations on the cargo change time period.

[0032] A one-stop unmanned industrial supermarket intelligent management system is used to implement the above-mentioned one-stop unmanned industrial supermarket intelligent management method, including a goods scanning module, an indication setting module, an indication control module and an indication optimization module, and the modules are connected by electrical signals;

[0033] Cargo scanning module: Before the cargo door is opened, the system scans the cargo status in different containers and compares it with the status when it was last closed. Based on the comparison results, the serial number indicator light value of the corresponding container is set and displayed;

[0034] Indicator Setting Module: Real-time monitoring of personnel behavior in the container, dynamically lighting or extinguishing the indicator lights on the cabinet head based on the display values ​​of the indicator lights with the same serial number, and at the same time, detecting the height and center offset of the cargo that is not displayed;

[0035] Indicator control module: Sets cargo size thresholds based on cargo height and center offset, updates the thresholds during cargo change periods, and uses indicator lights to record container status changes, ensuring the system's real-time response to cargo dynamics.

[0036] Indication optimization module: Counts the number of changes in the indicator light display value, collects the frequency of container opening to calculate the opening frequency, determines whether to mark the container, and updates the corresponding cargo change time period.

[0037] The technical effects and advantages of the one-stop unmanned industrial supermarket intelligent management system and method of the present invention are as follows:

[0038] The present invention scans the status of goods in different containers and compares the current status with the status when it was last closed. According to the comparison results, the system sets and displays the corresponding serial number indicator light value at the head of each container, providing convenient guidance for classification management, improving management efficiency, and monitoring the behavior of people in the container in real time. According to the display value of the indicator light with the same serial number, the system dynamically chooses to light up or extinguish the indicator light at the head of the container, detects the height and center offset position of the goods without displaying the light, sets the cargo size threshold of each container according to the height and center offset of the goods, sets the threshold update within the cargo change time period, maintains data synchronization, reduces the error caused by delayed data, records the change behavior of the indicator light display value, counts the number of times the indicator light at the head of each container changes, collects the opening frequency of all containers within a period of time to calculate the opening frequency of each container, comprehensively judges whether the container needs to be marked, and updates the cargo change time period of the marked container according to the marking result, thereby improving the efficiency of cargo return in different containers. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a schematic diagram of a one-stop unmanned industrial supermarket intelligent management method according to the present invention.

[0040] Figure 2 This is a mind map of the one-stop unmanned industrial supermarket intelligent management method of the present invention.

[0041] Figure 3 This is a flow chart of a one-stop unmanned industrial supermarket intelligent management system of the present invention. DETAILED DESCRIPTION

[0042] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0043] The present invention scans the cargo status in different containers and compares the current status with the status when it was last closed. According to the comparison results, the system sets and displays the corresponding serial number indicator light value at the head of each container, monitors the behavior of people in the container in real time, and dynamically chooses to light up or extinguish the indicator light at the head of the container based on the display value of the indicator light with the same serial number, detects the height and center offset position of the cargo that does not display the light, sets the cargo size threshold of each container based on the height and center offset of the cargo, sets the threshold update within the cargo change time period, records the change behavior of the indicator light display value, counts the number of times the indicator light at the head of each container changes, collects the opening frequency of all containers within a period of time, calculates the opening frequency of each container, comprehensively judges whether the container needs to be marked, and updates the cargo change time period of the marked container based on the marking result, thereby improving the efficiency of cargo return in different containers.

[0044] Example 1, a one-stop unmanned industrial supermarket intelligent management method, such as Figure 1 and Figure 2 As shown, the following steps are included:

[0045] Step S1: Before the cargo door is opened, scan the cargo in different containers and compare the cargo status in each container with the cargo status when the cargo door was last closed. According to the comparison results, set different serial number indicator light display values ​​and display them at the head of each container;

[0046] Step S2: Real-time monitoring of the behavior of personnel in the container with the same serial number indicator light display value, turning on or off the serial number indicator light display value at the head of the corresponding container according to the personnel behavior, and detecting the cargo height and center offset position of each cargo in the container where the serial number indicator light display value is not displayed;

[0047] Step S3: Set the cargo size threshold for each container based on the cargo height and center offset position, set a cargo change time period, update the cargo size threshold within the cargo change time period, and use the container head serial number indicator light display value to light up or off to record the change behavior of the corresponding container head serial number indicator light display value;

[0048] Step S4: Count the number of times the serial number indicator light display value of each container head changes, collect the opening frequency of all containers within a period of time, calculate the opening frequency of each container, calculate the key marking result based on the number of times the serial number indicator light display value of the container head changes and the opening frequency, and determine whether to mark the container as a key mark. Update the cargo change time period of the marked container according to the key marking result.

[0049] The specific implementation is as follows:

[0050] In step S1, the cargo status is the cargo type of the first cargo in the container. When a person enters the monitoring range, the system starts to operate, identifies the cargo label of the first cargo in different containers and obtains the identification result, obtains the cargo type of the first cargo in the corresponding container, and calls the cargo label identification result of the first cargo in each container after the cargo door is closed last time in the historical database;

[0051] Compare the results of cargo label recognition with those of the first cargo in each current container respectively. If the two comparison results are different, record the current container serial number, and traverse the cargo label recognition results of the first cargo in the current container among the cargo label recognition results of the first cargo in all containers after the last cargo door was closed. Record the containers with the same cargo label recognition results as cross-containers, obtain the cross-container serial number, and set the same serial number indicator light display value for the current container and the cross-container according to the container serial number and display it at the container head.

[0052] For example, there are three containers, namely 1, 2 and 3. The display values ​​of the serial indicator lights are set to 1 and 2 respectively. Identification starts from container 1. When the cargo label identification result of the first cargo in container 1 is the same as the cargo label identification result of the first cargo in container 3 after the cargo door is closed last time, container 3 is regarded as a cross container of container 1, and the serial indicator light display value 1 is selected. 1 is displayed at the cabinet heads of containers 1 and 3 respectively; identification starts from container 2. When the cargo label identification result of the first cargo in container 2 is the same as the cargo label identification result of the first cargo in container 1 after the cargo door is closed last time, container 1 is regarded as a cross container of container 2, and the serial indicator light display value 2 is selected. 2 is displayed at the cabinet heads of containers 1 and 2 respectively.

[0053] It should be noted that the cargo tag stores cargo information of the corresponding cargo, including the cargo type of the corresponding cargo. In addition, the display values ​​of the serial number indicator lights in the same container are not unique.

[0054] In step S2, the behaviors of people in the container with the same serial number indicator light display value are monitored in real time. The behaviors of people are divided into taking behaviors and putting back behaviors. The behaviors of people are judged by recording the weight of the container. When the weight of the container increases, the behavior of people is judged as putting back behaviors; when the weight of the container decreases, the behavior of people is judged as taking behaviors.

[0055] When the behavior of the person in the container is judged as taking, the container is scanned and the cargo tags that will be lost due to the taking behavior are screened out, and the serial number indicator display value set for the corresponding cargo tag is turned off; when the behavior of the person in the container is judged as putting back, the cargo tag of the returned cargo is identified, and a value that does not appear in the display of other container heads is randomly selected as the serial number indicator display value, and the quantity is counted and displayed at the current container head;

[0056] When the cargo door is closed, select the container without the serial indicator light display value, and detect the cargo height and center offset position of each cargo in the corresponding container. The center offset position is the distance between the cargo and the container boundary. Since the cargo boundary is divided into the left boundary and the right boundary, the distance between the cargo and the container boundary at the farthest point is selected as the center offset position of the cargo.

[0057] It should be noted that the distance between the cargo and the container boundary is determined by comparing the distance between the cargo and the left boundary of the container and the distance between the cargo and the right boundary of the container, and selecting the maximum boundary distance as the distance between the cargo and the container boundary.

[0058] In step S3, the detected heights of multiple cargoes in the container without the serial number indicator light are combined into a cargo height set, and the center offset positions are combined into a center offset position set. By traversing the cargo height set and the center offset position set, the mode of the cargo heights and the mode of the center offsets are respectively calculated as the median value of the cargo size threshold;

[0059] It should be noted that multiple items in a container exhibit distinct clustering characteristics in terms of size (e.g., height) and spatial position (e.g., center offset within the container). Furthermore, from a statistical perspective, the mode represents the most frequently occurring value in a set. Compared to the mean and median, it is less sensitive to extreme values ​​and better reflects the typical characteristic dimensions of the items in the container. Therefore, by extracting the mode from the set of item heights and the set of center offset positions as the median value for the item size threshold, we can effectively avoid threshold shifts caused by individual misplaced or unusually sized items, ensuring the stability and robustness of the system's judgment of item size anomalies.

[0060] Specifically, based on the median value of the cargo size threshold, the cargo size threshold is formed by setting the threshold fluctuation percentage;

[0061] Furthermore, the cargo size threshold is an interval value;

[0062] Specifically, the threshold fluctuation percentage was set based on the statistical distribution characteristics of cargo size data collected at actual logistics sites and the compatibility requirements of different container capacity tolerances. For example, the threshold fluctuation percentage was set to ±10% to calculate the interval boundary of cargo size. This will not be elaborated here.

[0063] It should be noted that the cargo size threshold is used to measure whether the cargo size exceeds the preset cargo form, which will not be explained here in detail;

[0064] Compare multiple cargoes in the container with the cargo size threshold. If the cargo is greater than or equal to the cargo size threshold, identify the corresponding cargo and mark it. Then identify the cargo label of the marked cargo to obtain the cargo type of the corresponding cargo.

[0065] Compare the cargo label identification results of the marked cargo with those of the first cargo in all containers after the cargo door was closed last time. If the identification results are the same, record the container serial numbers of the two containers and set the display value of the indicator light of the same serial number to be displayed at the head of the corresponding container;

[0066] If the cargo is smaller than the cargo size threshold, an end signal is generated;

[0067] Set a cargo change period based on the cargo shelf scheduling cycle. During the cargo change period, enable the threshold update mode and re-calculate the cargo height set and center offset position set every cargo change period.

[0068] Optionally, the experimenter can also set a cargo change time period based on the historical cargo turnover frequency and container utilization rate change trend, which will not be detailed here;

[0069] If the difference between the newly calculated median value of the corresponding cargo size threshold and the median value of the corresponding cargo size threshold in the previous cargo change period is greater than or equal to the preset adjustment threshold, the cargo size threshold of the current container is updated;

[0070] It should be noted that the adjustment threshold was obtained by our experimenters based on the tolerance range of the recognition accuracy for the fluctuation range of the size of different batches of goods and the stacking error of the goods, and will not be elaborated here;

[0071] By recording the on or off behavior of the serial number indicator light at the container head, the change behavior of the serial number indicator light at the container head is obtained;

[0072] Furthermore, the experimenters can use the video image recognition algorithm and the photoelectric sensor detection mechanism to record the behavior of the serial indicator light on or off at the head of the container. For the behavior of lighting up, the cumulative count is increased by 1, and for the behavior of going out, the cumulative count is increased by 1;

[0073] In step S4, the number of changes in the serial number indicator lights at the container heads is counted to obtain the number of changes in the serial number indicator lights at each container head;

[0074] Set the collection time period and count the opening frequency of all containers;

[0075] Among them, the logic for obtaining the opening frequency of all containers is to obtain the number of times all containers are opened during the collection time period;

[0076] Specifically, the number of times all containers are opened is recorded jointly through the record of the indicator light status change and the container door control sensor trigger signal record, which will not be detailed here;

[0077] It should be noted that the collection time period was set by our experimenters based on the operating cycle of typical industrial site operations and the statistical laws of cargo turnover density, and will not be elaborated here;

[0078] The logic for obtaining the opening frequency of each container is to calculate the ratio of the opening frequency of all containers to the number of containers to obtain the average container opening frequency, and then calculate the opening frequency of each container by comparing the number of times each container is opened to the average container opening frequency.

[0079] The number of times the serial indicator lights on each container head changed and the opening frequency of each container were standardized and substituted into the weighted fusion model to obtain the key marking coefficient;

[0080] It should be noted that the standardization methods include but are not limited to standard linear transformation based on interval scaling, Z-Score standardization method based on statistics, or normalization method based on nonlinear mapping function. The application methods of standardization are not described in detail here.

[0081] Specifically, the weighted fusion model implementation formula is as follows:

[0082] ;

[0083] Where, is the key marking coefficient, The number of times the serial indicator light on each container head changes behavior, is the opening frequency of each container, and are the weighted coefficients of the number of changes in the serial indicator lights at the heads of each container and the opening frequency of each container, respectively, and i is the i-th container;

[0084] It should be noted that meeting ,The specific weight coefficient is set by the experimenter based on the ,usage characteristics of containers in actual industrial sites, and will not ,be described here;

[0085] Compare the key marking coefficient with the preset key marking threshold. If the key marking coefficient is greater than or equal to the key marking threshold, the corresponding container will be marked as a key mark. If the key marking coefficient is less than the key marking threshold, the end signal will be executed.

[0086] The key mark threshold was obtained by our experimenters based on the system resource scheduling capacity limitations and the historical container usage behavior distribution characteristics, and will not be elaborated here;

[0087] Counting the containers that have been marked as key containers, taking them as key marking results, and sorting and grading the key marking coefficients corresponding to the key marked containers;

[0088] Specifically, the higher the key mark coefficient, the shorter the corresponding cargo change time period. Different reduction levels are set to correspond to the reduction level of the container change time period after sorting and grading, and the cargo change time period is shortened.

[0089] It should be noted that the specific reduction level was obtained by the experimenters based on the sorting and grading results and the joint statistical characteristics of the cargo size fluctuation rate and abnormal trigger frequency of different containers in the historical period. It will not be elaborated here.

[0090] Example 2, a one-stop unmanned industrial supermarket intelligent management system, such as Figure 3 As shown, it includes a cargo scanning module, an indication setting module, an indication control module and an indication optimization module, and the modules are connected by electrical signals;

[0091] Cargo scanning module: Before the cargo door is opened, the system scans the cargo status in different containers and compares it with the status when it was last closed. Based on the comparison results, the serial number indicator light value of the corresponding container is set and displayed;

[0092] Indicator Setting Module: Real-time monitoring of personnel behavior in the container, dynamically lighting or extinguishing the indicator lights on the cabinet head based on the display values ​​of the indicator lights with the same serial number, and at the same time, detecting the height and center offset of the cargo that is not displayed;

[0093] Indicator control module: Sets cargo size thresholds based on cargo height and center offset, updates the thresholds during cargo change periods, and uses indicator lights to record container status changes, ensuring the system's real-time response to cargo dynamics.

[0094] Indication optimization module: Counts the number of changes in the indicator light display value, collects the frequency of container opening to calculate the opening frequency, determines whether to mark the container, and updates the corresponding cargo change time period.

[0095] The above embodiments may be implemented in whole or in part through software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0096] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application of the technical solution and the invention constraints. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0097] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0098] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0099] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A one-stop unmanned industrial supermarket intelligent management method, characterized in that: The following steps are involved: Step S1: Before the cargo door is opened, scan the cargo in different containers and compare the cargo status in each container with the cargo status when the cargo door was last closed. According to the comparison results, set different serial number indicator light display values ​​and display them at the head of each container; In step S1, the cargo status is the cargo type of the first cargo in the container. When a person enters the monitoring range, the cargo tag of the first cargo in different containers is identified and the identification result is obtained. The identification result is the cargo type of the corresponding cargo. The cargo tag identification result of the first cargo in each container after the cargo door is closed last time is called in the historical database; Compare the tag recognition result of the first cargo in each container with the recognition result of the first cargo in the current container after the door was closed last time. If the two comparison results are inconsistent, record the serial number of the current container, and traverse the recognition result of the first cargo in the current container with the recognition results of the first cargo in all containers recorded after the door was closed last time. Identify the containers with the same tag and record them as cross containers and record the container serial number. According to the container serial number, set the same serial number indicator light display value for the current container and the cross container, and display it at the container head; Step S2: Real-time monitoring of the behavior of personnel in the container with the same serial number indicator light display value, turning on or off the serial number indicator light display value at the head of the corresponding container according to the personnel behavior, and detecting the cargo height and center offset position of each cargo in the container where the serial number indicator light display value is not displayed; Step S3: Set the cargo size threshold for each container based on the cargo height and center offset position, set a cargo change time period, update the cargo size threshold within the cargo change time period, and use the container head serial number indicator light display value to light up or off to record the change behavior of the corresponding container head serial number indicator light display value; In step S3, the detected heights of multiple cargoes in the container without the serial number indicator light are combined into a cargo height set, and the center offset positions are combined into a center offset position set. By traversing the cargo height set and the center offset position set, the mode of the cargo heights and the mode of the center offsets are respectively calculated as the median value of the cargo size threshold; Based on the median value of the cargo size threshold, the cargo size threshold is formed by setting the threshold fluctuation percentage; Compare multiple cargoes in the container with the cargo size threshold. If the cargo is greater than or equal to the cargo size threshold, identify the corresponding cargo and mark it. Then identify the cargo label of the marked cargo to obtain the cargo type of the corresponding cargo. Compare the cargo label identification results of the marked cargo with those of the first cargo in all containers after the cargo door was closed last time. If the identification results are the same, record the container serial numbers of the two containers and set the display value of the indicator light of the same serial number to be displayed at the head of the corresponding container; Set a cargo change period based on the cargo shelf scheduling cycle. During the cargo change period, enable the threshold update mode and re-calculate the cargo height set and center offset position set every cargo change period. If the difference between the newly calculated median value of the corresponding cargo size threshold and the median value of the corresponding cargo size threshold in the previous cargo change period is greater than or equal to the preset adjustment threshold, the cargo size threshold of the current container is updated; By recording the on or off behavior of the serial number indicator light at the container head, the change behavior of the serial number indicator light at the container head is obtained; Step S4: Count the number of times the serial indicator light on each container head changes, collect the opening frequency of all containers, calculate the opening frequency of each container, determine whether to mark the container, and update the cargo change time period of the marked container according to the marking result.

2. The one-stop unmanned industrial supermarket intelligent management method according to claim 1 is characterized by: In step S2, the personnel behaviors are respectively taking behaviors and putting back behaviors. The personnel behaviors are judged by recording the weight of the container. When the weight of the container after the cargo door is opened is higher than the weight of the container before the cargo door is opened, the personnel behaviors are judged to be putting back behaviors; when the weight of the container is lower than the weight of the container before the cargo door is opened, the personnel behaviors are judged to be taking behaviors.

3. The one-stop unmanned industrial supermarket intelligent management method according to claim 2 is characterized by: In step S2, when the behavior of the person in the container is judged as taking, the system will scan the container and filter out the cargo labels lost due to the behavior, and then turn off the serial number indicator display value of the corresponding cargo label; on the contrary, when it is judged as putting back, the system will identify the label of the returned goods and randomly select a value that does not appear in other container heads as the new serial number indicator display value, and light it up on the current container head; The center offset position is the distance between the cargo and the container boundary. By comparing the distance between the cargo and the left boundary of the container and the distance between the cargo and the right boundary of the container, the maximum boundary distance is selected as the distance between the cargo and the container boundary.

4. The one-stop unmanned industrial supermarket intelligent management method according to claim 1 is characterized by: In step S4, the number of changes in the serial number indicator lights at the container heads is counted to obtain the number of changes in the serial number indicator lights at each container head; Set the collection time period, obtain the number of times all containers are opened during the collection time period, and obtain the opening frequency of all containers; The average container opening frequency is calculated by calculating the ratio of the opening frequency of all containers to the number of containers. The opening frequency of each container is calculated by calculating the ratio of the opening frequency of each container to the average container opening frequency. The number of times the serial indicator light on each container head changes and the opening frequency of each container are standardized and substituted into the weighted fusion model to obtain the key marking coefficient.

5. The one-stop unmanned industrial supermarket intelligent management method according to claim 4 is characterized by: In step S4, the key marking coefficient is compared with a preset key marking threshold. If the key marking coefficient is greater than or equal to the key marking threshold, the corresponding container is marked as a key container. Counting the containers that have been marked as key containers, taking them as key marking results, and sorting and grading the key marking coefficients corresponding to the key marked containers; Set different reduction levels to correspond to the reduction levels of the container change time period after sorting and grading, and perform reduction operations on the cargo change time period.

6. A one-stop unmanned industrial supermarket intelligent management system, based on a one-stop unmanned industrial supermarket intelligent management method according to any one of claims 1 to 5, characterized in that: It includes a cargo scanning module, an indication setting module, an indication control module and an indication optimization module, and the modules are connected by electrical signals; Cargo scanning module: Before the cargo door is opened, the system scans the cargo status in different containers and compares it with the status when it was last closed. Based on the comparison results, the serial number indicator light value of the corresponding container is set and displayed; In the cargo scanning module, the cargo status is the cargo type of the first cargo in the container. When a person enters the monitoring range, the cargo label of the first cargo in different containers is identified and the identification result is obtained. The identification result is the cargo type of the corresponding cargo. The cargo label identification result of the first cargo in each container after the last cargo door is closed is called from the historical database; Compare the tag recognition result of the first cargo in each container with the recognition result of the first cargo in the current container after the door was closed last time. If the two comparison results are inconsistent, record the serial number of the current container, and traverse the recognition result of the first cargo in the current container with the recognition results of the first cargo in all containers recorded after the door was closed last time. Identify the containers with the same tag and record them as cross containers and record the container serial number. According to the container serial number, set the same serial number indicator light display value for the current container and the cross container, and display it at the container head; Indicator Setting Module: Real-time monitoring of personnel behavior in the container, dynamically lighting or extinguishing the indicator lights on the cabinet head based on the display values ​​of the indicator lights with the same serial number, and at the same time, detecting the height and center offset of the cargo that is not displayed; Indicator control module: Sets cargo size thresholds based on cargo height and center offset, updates the thresholds during cargo change periods, and uses indicator lights to record container status changes, ensuring the system's real-time response to cargo dynamics. In the indication control module, the detected heights of multiple cargoes in the container without the serial indicator light are combined into a cargo height set, and the center offset positions are combined into a center offset position set. By traversing the cargo height set and the center offset position set, the mode of the cargo heights and the mode of the center offsets are calculated as the median value of the cargo size threshold. Based on the median value of the cargo size threshold, the cargo size threshold is formed by setting the threshold fluctuation percentage; Compare multiple cargoes in the container with the cargo size threshold. If the cargo is greater than or equal to the cargo size threshold, identify the corresponding cargo and mark it. Then identify the cargo label of the marked cargo to obtain the cargo type of the corresponding cargo. Compare the cargo label identification results of the marked cargo with those of the first cargo in all containers after the cargo door was closed last time. If the identification results are the same, record the container serial numbers of the two containers and set the display value of the indicator light of the same serial number to be displayed at the head of the corresponding container; Set a cargo change period based on the cargo shelf scheduling cycle. During the cargo change period, enable the threshold update mode and re-calculate the cargo height set and center offset position set every cargo change period. If the difference between the newly calculated median value of the corresponding cargo size threshold and the median value of the corresponding cargo size threshold in the previous cargo change period is greater than or equal to the preset adjustment threshold, the cargo size threshold of the current container is updated; By recording the on or off behavior of the serial number indicator light at the container head, the change behavior of the serial number indicator light at the container head is obtained; Indication optimization module: Counts the number of changes in the indicator light display value, collects the frequency of container opening to calculate the opening frequency, determines whether to mark the container, and updates the corresponding cargo change time period.

Images