Abnormal weighing detection method, device, and related device
By acquiring weighing information and internal code value readings, and using linear relationships and abnormal quantile intervals to determine weighing anomalies, the problem of low weighing accuracy and high cost in logistics sorting is solved, achieving efficient anomaly detection and verification, and reducing transportation costs.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SF TECH CO LTD
- Filing Date
- 2022-09-01
- Publication Date
- 2026-06-09
AI Technical Summary
Existing technologies suffer from low accuracy and high cost in the weighing process during logistics sorting, especially when the number of goods increases and the distance between adjacent goods decreases, making it difficult to effectively detect weighing anomalies.
By acquiring the weighing information and internal code value readings of the target object after it is placed on the scale, the fitted internal code value is determined using a linear relationship, and the difference between the internal code values is calculated. Combined with the abnormal quantile interval, it is determined whether the weighing reading is abnormal, and alarm information is generated for verification.
It improves the accuracy and efficiency of weighing anomaly detection, reduces transportation costs, and lowers the risk of increased expenses for enterprises.
Smart Images
Figure CN117629372B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of logistics sorting technology, specifically to a weighing anomaly detection method, device, and related devices. Background Technology
[0002] Weighing is a common step in express delivery transit centers and other assembly lines. The inventors of this application have discovered that as the number of goods increases and the distance between adjacent goods decreases, the accuracy of weighing often decreases at certain times. However, existing methods generally use repeated weighing for detection, which requires adding corresponding hardware to the assembly line every day, resulting in high costs and limited improvement in detection accuracy.
[0003] Therefore, how to detect weighing anomalies in a low-cost and accurate manner is a technical problem that urgently needs to be solved in the field of current logistics sorting technology. Summary of the Invention
[0004] This application provides a method, apparatus, and related devices for detecting weighing anomalies, aiming to solve the technical problem of how to detect weighing anomalies accurately and at low cost.
[0005] On the one hand, this application provides a method for detecting weighing anomalies, the method comprising:
[0006] The weighing information of the target object after it is placed on the scale is obtained. The weighing information includes the weighing reading and the internal code value reading. The scale is a dynamic scale.
[0007] Based on the weighing reading and a preset linear relationship, the fitted internal code value of the target object is determined, wherein the linear relationship is the linear relationship between the weighing reading and the fitted internal code value;
[0008] Based on the internal code value display and the fitted internal code value, the difference in internal code value of the target object is determined;
[0009] Based on the difference in the internal code value and the preset abnormal quantile interval for weighing detection, it is determined whether the weighing reading of the target object is abnormal.
[0010] In one possible implementation of this application, the abnormal quantile interval includes an inner interval and an outer interval of the abnormal quantile. Determining whether the weighing reading of the target object is abnormal based on the difference in the internal code value and a preset abnormal quantile interval for weighing detection includes:
[0011] Determine whether the difference in the internal code value is within the range of the abnormal quantile interval;
[0012] If the difference in the internal code value is within the range of the abnormal quantile interval, then the weighing reading of the target object is determined to be normal.
[0013] If the difference in the internal code value is in the outer range of the abnormal quantile interval, then the weighing reading of the target object is determined to be abnormal.
[0014] In one possible implementation of this application, before determining whether the weighing reading of the target object is abnormal based on the difference in the internal code value and a preset abnormal quantile interval for weighing detection, the method further includes:
[0015] Based on the linear relationship, a preset number of test code value differences are determined;
[0016] The preset number of test code value differences are sorted to obtain a sequence set of test code value differences;
[0017] Based on the quantile method and the sequence set, the abnormal quantile intervals are determined.
[0018] In one possible implementation of this application, before determining the fitted internal code value of the target object based on the weighing reading and a preset linear relationship, the method further includes:
[0019] Obtain a set of first weighing data pairs of a preset number of experimental goods on the dynamic scale. The first weighing data pair includes the first experimental weighing reading of the experimental goods and the first experimental internal code value reading corresponding to the first experimental weighing reading.
[0020] Based on the set of the first weighing data pairs, the linear relationship is constructed.
[0021] In one possible implementation of this application, the dynamic scale includes a start-up status determination display, an infeed status determination display, and an outfeed status determination display; the method further includes:
[0022] When the start-up state determination reading is the start-up state reading, the weighing state determination reading is the weighing state reading with no goods entering the weighing surface, and the weighing state determination reading is the weighing state reading with no goods passing through the weighing surface, a set of second weighing data pairs of a preset number of experimental goods on the dynamic scale is obtained. The second weighing data pair includes the second experimental weighing reading of the experimental goods and the first experimental internal code value reading corresponding to the second experimental weighing reading.
[0023] Based on the set of the second set of weighing data pairs, the fitting coefficient of the linear relationship is adjusted to optimize the linear relationship.
[0024] In one possible implementation of this application, determining the fitted internal code value of the target object based on the weighing reading and a preset linear relationship includes:
[0025] The weighing reading is input into a preset linear relationship to generate the fitted internal code value of the target object.
[0026] In one possible implementation of this application, after determining whether the weighing reading of the target object is abnormal based on the difference in the internal code value and a preset abnormal quantile interval for weighing detection, the method further includes:
[0027] If the weighing reading of the target object is abnormal, an alarm message will be generated;
[0028] The alarm information is sent to a preset user terminal.
[0029] On the other hand, this application provides a weighing anomaly detection device, the device comprising:
[0030] The first acquisition unit is used to acquire the weighing information of the target object after it is put on the scale. The weighing information includes the weighing reading and the internal code value reading. The scale is a dynamic scale.
[0031] The first determining unit is used to determine the fitted internal code value of the target object based on the weighing reading and a preset linear relationship, wherein the linear relationship is the linear relationship between the weighing reading and the fitted internal code value.
[0032] The second determining unit is used to determine the difference in the internal code value of the target object based on the internal code value display and the fitted internal code value.
[0033] The third determining unit is used to determine whether the weighing reading of the target object is abnormal based on the difference in the internal code value and the preset abnormal quantile interval for weighing detection.
[0034] In one possible implementation of this application, the abnormal quantile interval includes an inner interval of the abnormal quantile and an outer interval of the abnormal quantile.
[0035] The third determining unit is specifically used for:
[0036] Determine whether the difference in the internal code value is within the range of the abnormal quantile interval;
[0037] If the difference in the internal code value is within the range of the abnormal quantile interval, then the weighing reading of the target object is determined to be normal.
[0038] If the difference in the internal code value is in the outer range of the abnormal quantile interval, then the weighing reading of the target object is determined to be abnormal.
[0039] In one possible implementation of this application, before determining whether the weighing reading of the target object is abnormal based on the difference in the internal code value and a preset abnormal quantile interval for weighing detection, the device is further configured to:
[0040] Based on the linear relationship, a preset number of test code value differences are determined;
[0041] The preset number of test code value differences are sorted to obtain a sequence set of test code value differences;
[0042] Based on the quantile method and the sequence set, the abnormal quantile intervals are determined.
[0043] In one possible implementation of this application, before determining the fitted internal code value of the target object based on the weighing reading and a preset linear relationship, the device is further configured to:
[0044] Obtain a set of first weighing data pairs of a preset number of experimental goods on the dynamic scale. The first weighing data pair includes the first experimental weighing reading of the experimental goods and the first experimental internal code value reading corresponding to the first experimental weighing reading.
[0045] Based on the set of the first weighing data pairs, the linear relationship is constructed.
[0046] In one possible implementation of this application, the dynamic scale includes a start-up status determination indicator, an infeed status determination indicator, and an outfeed status determination indicator; the device is further used for:
[0047] When the start-up state determination reading is the start-up state reading, the weighing state determination reading is the weighing state reading with no goods entering the weighing surface, and the weighing state determination reading is the weighing state reading with no goods passing through the weighing surface, a set of second weighing data pairs of a preset number of experimental goods on the dynamic scale is obtained. The second weighing data pair includes the second experimental weighing reading of the experimental goods and the first experimental internal code value reading corresponding to the second experimental weighing reading.
[0048] Based on the set of the second set of weighing data pairs, the fitting coefficient of the linear relationship is adjusted to optimize the linear relationship.
[0049] In one possible implementation of this application, the first determining unit includes:
[0050] The weighing reading is input into a preset linear relationship to generate the fitted internal code value of the target object.
[0051] In one possible implementation of this application, after determining whether the weighing reading of the target object is abnormal based on the difference in the internal code value and a preset abnormal quantile interval for weighing detection, the device is further configured to:
[0052] If the weighing reading of the target object is abnormal, an alarm message will be generated;
[0053] The alarm information is sent to a preset user terminal.
[0054] On the other hand, this application also provides a computer device, the computer device comprising:
[0055] One or more processors;
[0056] Memory; and
[0057] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the weighing anomaly detection method.
[0058] On the other hand, this application also provides a computer-readable storage medium having a computer program stored thereon, the computer program being loaded by a processor to perform the steps in the weighing anomaly detection method.
[0059] This application embodiment obtains the weighing information of the target object after it is placed on a scale. The weighing information includes the weighing reading and the internal code value reading, and the scale is a dynamic scale. Based on the weighing reading and a preset linear relationship, the fitted internal code value of the target object is determined. The linear relationship is the linear relationship between the weighing reading and the fitted internal code value. Based on the internal code value reading and the fitted internal code value, the difference in the internal code value of the target object is determined. Based on the difference in the internal code value and a preset abnormal quantile interval for weighing detection, it is determined whether the weighing reading of the target object is abnormal. Compared with traditional methods, by determining the difference in the internal code value based on the internal code value reading and the fitted internal code value of the target object after it is placed on the scale, and then determining whether the weighing reading of the target object is abnormal based on the difference in the internal code value and the preset abnormal quantile interval, abnormal data can be efficiently detected and re-checked. This can reduce the increased transportation costs and other expenses caused by inaccurate weighing for enterprises, thus reducing costs and increasing efficiency. Attached Figure Description
[0060] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0061] Figure 1 This is a schematic diagram of a weighing anomaly detection system provided in an embodiment of this application;
[0062] Figure 2 This is a schematic flowchart of an embodiment of the weighing anomaly detection method provided in this application.
[0063] Figure 3This is a schematic flowchart of an embodiment of determining abnormal quantile intervals provided in this application;
[0064] Figure 4 This is a schematic diagram of an embodiment of the process of constructing a linear relationship between the weighing reading and the fitted internal code value provided in this application;
[0065] Figure 5 This is a flowchart illustrating an embodiment of the abnormal alarm provided in this application.
[0066] Figure 6 This is a schematic diagram of an embodiment of the weighing anomaly detection device provided in this application.
[0067] Figure 7 This is a schematic diagram of an embodiment of the computer device provided in this application. Detailed Implementation
[0068] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0069] In the description of this application, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.
[0070] In this application, the term "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be made without using these specific details. In other instances, well-known structures and processes are not described in detail to avoid obscuring the description of this application with unnecessary detail. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.
[0071] This application provides a weighing anomaly detection method, apparatus, and related devices, which will be described in detail below.
[0072] like Figure 1 As shown, Figure 1 This is a schematic diagram of a weighing anomaly detection system provided in an embodiment of this application. The weighing anomaly detection system may include a computer device 100, which integrates a weighing anomaly detection device, such as... Figure 1 Computer equipment 100.
[0073] In this embodiment, the computer device 100 is mainly used to acquire the weighing information of the target object after it is placed on the scale. The weighing information includes the weighing reading and the internal code value reading, and the scale is a dynamic scale. Based on the weighing reading and a preset linear relationship, the fitted internal code value of the target object is determined, and the linear relationship is the linear relationship between the weighing reading and the fitted internal code value. Based on the internal code value reading and the fitted internal code value, the difference in the internal code value of the target object is determined. Based on the difference in the internal code value and a preset abnormal quantile interval for weighing detection, it is determined whether the weighing reading of the target object is abnormal.
[0074] In this embodiment, the computer device 100 can be a terminal or a server. When the computer device 100 is a server, it can be a standalone server or a server network or server cluster. For example, the computer device 100 described in this embodiment includes, but is not limited to, computers, network hosts, single network servers, multiple sets of network servers, or cloud servers constructed from multiple servers. The cloud server is constructed from a large number of computers or network servers based on cloud computing.
[0075] It is understood that when the computer device 100 in this embodiment is a terminal, the terminal used can be a device that includes both receiving and transmitting hardware, that is, a device with receiving and transmitting hardware capable of performing bidirectional communication on a bidirectional communication link. Such a device may include: cellular or other communication devices, which have a single-line display, a multi-line display, or a cellular or other communication device without a multi-line display. Specifically, the computer device 100 may be a desktop terminal or a mobile terminal, and the computer device 100 may also be one of a mobile phone, tablet computer, laptop computer, medical auxiliary instrument, etc.
[0076] Those skilled in the art will understand that Figure 1 The application environment shown is merely one application scenario for the solution in this application and is not intended to limit the application scenario of the solution in this application. Other application environments may include more than one. Figure 1 The number of computer devices shown is more or less, for example Figure 1 Only one computer device is shown in the diagram. It is understood that the weighing anomaly detection system may also include one or more other computer devices, which are not specified here.
[0077] Those skilled in the art will understand that Figure 1 The application environment shown is merely one application scenario for the solution in this application and is not intended to limit the application scenario of the solution in this application. Other application environments may include more than one. Figure 1 The number of computer devices shown is more or less, for example Figure 1 Only one computer device is shown in the diagram. It is understood that the weighing anomaly detection system may also include one or more other computer devices, which are not specified here.
[0078] In addition, such as Figure 1 As shown, the weighing anomaly detection system may also include a memory 200 for storing data, such as weighing information of the target object after it is placed on the scale and weighing anomaly detection data, such as weighing anomaly detection data during the operation of the weighing anomaly detection system.
[0079] It should be noted that, Figure 1 The schematic diagram of the weighing anomaly detection system shown is merely an example. The weighing anomaly detection system and scenario described in this application are for the purpose of more clearly illustrating the technical solutions of this application, and do not constitute a limitation on the technical solutions provided in this application. As those skilled in the art will know, with the evolution of weighing anomaly detection systems and the emergence of new business scenarios, the technical solutions provided in this application are also applicable to similar technical problems.
[0080] Next, we will introduce the weighing anomaly detection method provided in the embodiments of this application.
[0081] In this embodiment of the weighing anomaly detection method, a weighing anomaly detection device is used as the execution subject. For simplicity and ease of description, this execution subject will be omitted in subsequent method embodiments. The weighing anomaly detection device is applied to a computer device. The method includes: acquiring weighing information of a target object after it is placed on a scale, the weighing information including a weighing reading and an internal code value reading, the scale being a dynamic scale; determining a fitted internal code value of the target object based on the weighing reading and a preset linear relationship, the linear relationship being the linear relationship between the weighing reading and the fitted internal code value; determining the difference in internal code values of the target object based on the internal code value reading and the fitted internal code value; and determining whether the weighing reading of the target object is abnormal based on the difference in internal code values and a preset abnormal quantile interval for weighing detection.
[0082] Please see Figures 2 to 7 , Figure 2 This is a schematic flowchart of an embodiment of the weighing anomaly detection method provided in this application. The weighing anomaly detection method includes:
[0083] 201. Obtain the weighing information of the target object after it is placed on the scale. The weighing information includes the weighing reading and the internal code value reading.
[0084] The target object is the goods to be weighed. Specifically, the goods can be loaded onto the scale via a conveyor belt. The scale is a dynamic scale, specifically a belt-driven dynamic scale. The weighing reading and internal code value are digital weighing signals generated by the dynamic scale as the goods pass over it, used to display the weighing feedback information of the goods. Specifically, the dynamic scale can be connected to a weighing anomaly detection system, allowing direct reading of the weighing information generated by the dynamic scale.
[0085] 202. Based on the weighing reading and the preset linear relationship, determine the fitted internal code value of the target object;
[0086] Wherein, the linear relationship is the linear relationship between the weighing reading and the fitted internal code value.
[0087] In some embodiments of this application, determining the fitted internal code value of the target object based on the weighing reading and a preset linear relationship includes: inputting the weighing reading into a preset linear relationship to generate the fitted internal code value of the target object.
[0088] 203. Determine the difference in internal code values of the target object based on the internal code value reading and the fitted internal code value;
[0089] The internal code value difference is the difference between the displayed internal code value of the target object and the fitted internal code value. Specifically, the difference between the displayed internal code value and the fitted internal code value is the internal code value difference of the target object.
[0090] 204. Based on the difference in internal code values and the preset abnormal quantile intervals for weighing detection, determine whether the weighing reading of the target object is abnormal.
[0091] The preset abnormal quantile intervals for weighing detection are determined by confirming the confidence level using quantiles. Then, based on this confidence level, left and right quantiles are determined. Finally, the inner and outer intervals of the abnormal quantiles are determined based on the differences between these two quantiles and a preset number of test internal code values. For example, when confirming the confidence level using quantiles, this confidence level generally needs to be greater than 0.9. When the confidence level is 0.9, the left quantile should be 0.05, and the right quantile should be 1-0.05=0.95. This means that 90% of the data in the preset number of test internal code value differences Δy after sorting are reliable, and values outside the quantile range are unreliable. The intervals of Δy corresponding to the left and right quantiles can then be obtained. Furthermore, the inner and outer intervals of the abnormal quantiles can be determined using these left and right quantiles. In a preferred embodiment, 8000 sets of experimental internal code value differences can be selected.
[0092] In some embodiments of this application, the abnormal quantile interval includes an inner interval and an outer interval of the abnormal quantile. Determining whether the weighing reading of the target object is abnormal based on the difference in internal code values and a preset abnormal quantile interval for weighing detection includes: determining whether the difference in internal code values is within the inner interval of the abnormal quantile interval. For example, if the inner interval of the abnormal quantile interval is [3, 5], and the difference in internal code values is 1, then the difference in internal code values is determined to be within the outer interval of the abnormal quantile interval; if the difference in internal code values is 3, then the difference in internal code values is determined to be within the inner interval of the abnormal quantile interval. If the difference in internal code values is within the inner interval of the abnormal quantile interval, then the weighing reading of the target object is normal; if the difference in internal code values is within the outer interval of the abnormal quantile interval, then the weighing reading of the target object is abnormal.
[0093] In this embodiment, compared to traditional methods, the difference between the internal code value and the fitted internal code value is determined by the internal code value reading of the target object after it is placed on the scale. Then, based on the difference between the internal code values and the preset abnormal quantile interval, it is determined whether the weighing reading of the target object is abnormal. Thus, abnormal data can be detected efficiently and re-checked. This can reduce the increase in transportation costs and other expenses caused by inaccurate weighing for enterprises, thereby reducing costs and increasing efficiency.
[0094] In some other embodiments of this application, such as Figure 3As shown, before determining whether the weighing reading of the target object is abnormal based on the difference in the internal code value and a preset abnormal quantile interval for weighing detection, the method further includes:
[0095] 301. Based on the linear relationship, determine a preset number of test code value differences;
[0096] Specifically, determining a preset number of test code value differences based on a linear relationship can include: obtaining a preset number of actual weighing information, inputting the weighing readings from the actual weighing information into a linear relationship to obtain the corresponding preset number of fitted code values, and then determining the preset number of test code value differences based on the code value readings from the actual weighing information and the preset number of fitted code values.
[0097] In a preferred embodiment of this application, the preset quantity is 8000 sets, that is, 8000 sets of actual weighing information are obtained. These 8000 sets of actual weighing information include 8000 sets of weighing readings, internal code value readings, and fitted internal code values obtained based on linear relationships and weighing readings. Then, based on these 8000 sets of internal code value readings and fitted internal code values, the differences between these 8000 test internal code values are calculated.
[0098] 302. Sort the preset number of test code value differences to obtain a sequence set of test code value differences;
[0099] Specifically, a preset number of test code value differences can be sorted according to their numerical values to obtain a sequence set of test code value differences.
[0100] 303. Based on the quantile method and sequence set, determine the interval of abnormal quantiles.
[0101] Specifically, determining the interval of an abnormal quantile based on the quantile method and sequence set can include: determining the confidence level according to the quantile method, then determining the left and right quantiles based on the confidence level, and finally determining the inner interval and outer interval of the abnormal quantile based on these two quantiles and the sequence set.
[0102] The technical solution disclosed in this application, through the quantile method and sequence set, can efficiently and accurately determine the abnormal quantile interval, thereby improving the accuracy and efficiency of subsequent determination of whether the weighing reading of the target object is abnormal.
[0103] In some other embodiments of this application, such as Figure 4 As shown, before determining the fitted internal code value of the target object based on the weighing reading and a preset linear relationship, the method further includes:
[0104] 401. Obtain a set of first weighing data pairs of a preset number of experimental goods on the dynamic scale. The first weighing data pair includes the first experimental weighing reading of the experimental goods and the first experimental internal code value reading corresponding to the first experimental weighing reading.
[0105] 402. Based on the set of the first weighing data pairs, construct a linear relationship.
[0106] Based on the set of first weighing data pairs, obtain a relationship graph between the first experimental weighing reading and the corresponding first experimental internal code value reading. Based on the relationship graph, construct a linear relationship. Specifically, the linear relationship is a linear relationship between the weighing reading and the internal code value, which is y = k*x + b.
[0107] The technical solution disclosed in this application can accurately construct a linear relationship by using a large set of first weighing data pairs of experimental goods, thereby improving the accuracy and efficiency of subsequently determining whether the weighing reading of the target object is abnormal.
[0108] In some other embodiments of this application, the dynamic scale includes a start-up state determination display, an entry-in-weighing state determination display, and an exit-in-weighing state determination display. The method further includes: acquiring a set of second weighing data pairs of a preset number of experimental goods on the dynamic scale when the start-up state determination display is the start-up state display, the entry-in-weighing state determination display is the state display indicating no goods have entered the weighing surface, and the exit-in-weighing state determination display is the state display indicating no goods have passed through the weighing surface. The second weighing data pair includes a second experimental weighing display of the experimental goods and a first experimental internal code value display corresponding to the second experimental weighing display. Based on the set of the second weighing data pairs, the fitting coefficient of the linear relationship is adjusted to optimize the linear relationship.
[0109] The system can be configured with the following indicators: s1 for the start-up status, s2 for the weighing entry status, and s4 for the weighing exit status. s1 displays 0 to indicate the machine is off, and 1 to indicate it is on. s2 displays 0 to indicate no goods have entered the weighing surface, and 1 to indicate goods have begun to cross the weighing surface (i.e., a weighing entry determination). s4 is the weighing exit determination; 0 indicates no goods have crossed the weighing surface, and 1 indicates goods have crossed the weighing surface. After screening the data, it was found that s1 = 1, and the values of s2 and s4 affect the fitting relationship between the weighing reading and the internal code value. Specifically, this results in a large fluctuation in Δy (i.e., the values of s2 and s4 affect the fitting coefficient k and the fitting constant b).
[0110] Analysis shows that the smaller the fluctuation of Δy, the better. Therefore, the self-learning data can be adjusted. Data with s1 = 1, s2 = 0, and s4 = 0 can be included in the self-learning process (the reason for the large fluctuation of Δy when s2 = 1 or s4 = 1 is that there is a high probability that an acceleration will accompany the entry and exit of the scale, causing the scale reading to be abnormal).
[0111] The technical solution disclosed in this application optimizes the linear relationship by selecting a set of second weighing data pairs generated under specific conditions and adjusting the fitting coefficient of the linear relationship, thereby further improving the accuracy and efficiency of subsequently determining whether the weighing reading of the target object is abnormal.
[0112] In some other embodiments of this application, after optimization of the above embodiments, the self-learning length of 8000 is kept unchanged, and 200,000 timestamps after obtaining the 8000-timestamp learning length are still selected for verification. The verification results are shown in the table below:
[0113] Table 1:
[0114]
[0115]
[0116] After optimization, with a self-learning length of 8000 and a confidence level of 0.9, the anomaly rate decreased to 18.96%. This demonstrates the significant effect of the optimization, but careful screening of the data selected within the self-learning length is necessary.
[0117] In some other embodiments of this application, such as Figure 5 As shown, after determining whether the weighing reading of the target object is abnormal based on the difference in the internal code value and the preset abnormal quantile interval for weighing detection, the method further includes:
[0118] 501. If the weighing reading of the target object is abnormal, an alarm message will be generated;
[0119] 502. Send the alarm information to the preset user terminal.
[0120] Specifically, alarm information can be sent to preset user terminals via SMS, WeChat, email, and telephone.
[0121] The technical solution disclosed in this application can effectively solve abnormal situations by alarming when the weighing reading of the target object is abnormal. This can reduce the increase in transportation costs and other expenses caused by inaccurate weighing for enterprises, thereby reducing costs and increasing efficiency.
[0122] To better implement the weighing anomaly detection method in the embodiments of this application, a weighing anomaly detection device is also provided in the embodiments of this application, such as... Figure 6 As shown, the weighing anomaly detection device 600 includes:
[0123] The first acquisition unit 601 is used to acquire the weighing information of the target object after it is put on the scale. The weighing information includes the weighing reading and the internal code value reading. The scale is a dynamic scale.
[0124] The first determining unit 602 is used to determine the fitted internal code value of the target object based on the weighing reading and a preset linear relationship, wherein the linear relationship is the linear relationship between the weighing reading and the fitted internal code value;
[0125] The second determining unit 603 is used to determine the difference in the internal code value of the target object based on the internal code value display and the fitted internal code value.
[0126] The third determining unit 604 is used to determine whether the weighing reading of the target object is abnormal based on the difference in the internal code value and the preset abnormal quantile interval for weighing detection.
[0127] In one possible implementation of this application, the abnormal quantile interval includes an inner interval of the abnormal quantile and an outer interval of the abnormal quantile.
[0128] The third determining unit 604 is specifically used for:
[0129] Determine whether the difference in the internal code value is within the range of the abnormal quantile interval;
[0130] If the difference in the internal code value is within the range of the abnormal quantile interval, then the weighing reading of the target object is determined to be normal.
[0131] If the difference in the internal code value is in the outer range of the abnormal quantile interval, then the weighing reading of the target object is determined to be abnormal.
[0132] In one possible implementation of this application, before determining whether the weighing reading of the target object is abnormal based on the difference in the internal code value and a preset abnormal quantile interval for weighing detection, the device is further configured to:
[0133] Based on the linear relationship, a preset number of test code value differences are determined;
[0134] The preset number of test code value differences are sorted to obtain a sequence set of test code value differences;
[0135] Based on the quantile method and the sequence set, the abnormal quantile intervals are determined.
[0136] In one possible implementation of this application, before determining the fitted internal code value of the target object based on the weighing reading and a preset linear relationship, the device is further configured to:
[0137] Obtain a set of first weighing data pairs of a preset number of experimental goods on the dynamic scale. The first weighing data pair includes the first experimental weighing reading of the experimental goods and the first experimental internal code value reading corresponding to the first experimental weighing reading.
[0138] Based on the set of the first weighing data pairs, the linear relationship is constructed.
[0139] In one possible implementation of this application, the dynamic scale includes a start-up status determination indicator, an infeed status determination indicator, and an outfeed status determination indicator; the device is further used for:
[0140] When the start-up state determination reading is the start-up state reading, the weighing state determination reading is the weighing state reading with no goods entering the weighing surface, and the weighing state determination reading is the weighing state reading with no goods passing through the weighing surface, a set of second weighing data pairs of a preset number of experimental goods on the dynamic scale is obtained. The second weighing data pair includes the second experimental weighing reading of the experimental goods and the first experimental internal code value reading corresponding to the second experimental weighing reading.
[0141] Based on the set of the second set of weighing data pairs, the fitting coefficient of the linear relationship is adjusted to optimize the linear relationship.
[0142] In one possible implementation of this application, the first determining unit 602 includes:
[0143] The weighing reading is input into a preset linear relationship to generate the fitted internal code value of the target object.
[0144] In one possible implementation of this application, after determining whether the weighing reading of the target object is abnormal based on the difference in the internal code value and a preset abnormal quantile interval for weighing detection, the device is further configured to:
[0145] If the weighing reading of the target object is abnormal, an alarm message will be generated;
[0146] The alarm information is sent to a preset user terminal.
[0147] This application embodiment uses a first acquisition unit 601 to acquire the weighing information of a target object after it is placed on a scale. The weighing information includes the weighing reading and the internal code value reading. The scale is a dynamic scale. A first determination unit 602 is used to determine the fitted internal code value of the target object based on the weighing reading and a preset linear relationship. The linear relationship is the linear relationship between the weighing reading and the fitted internal code value. A second determination unit 603 is used to determine the difference in the internal code value of the target object based on the internal code value reading and the fitted internal code value. A third determination unit 604 is used to determine whether the weighing reading of the target object is abnormal based on the difference in the internal code value and a preset abnormal quantile interval for weighing detection. Compared to traditional methods, this method determines the difference between the internal code value and the fitted internal code value after the target object is placed on the scale. Then, based on the difference in the internal code value and the preset abnormal quantile interval, it determines whether the weighing reading of the target object is abnormal. This allows for efficient detection of abnormal data and subsequent re-verification, which can reduce the increased transportation costs and other expenses caused by inaccurate weighing for enterprises, thus reducing costs and increasing efficiency.
[0148] In addition to the weighing anomaly detection methods and devices described above, embodiments of this application also provide a computer device that integrates any of the weighing anomaly detection devices provided in the embodiments of this application. The computer device includes:
[0149] One or more processors;
[0150] Memory; and
[0151] One or more applications, wherein the one or more applications are stored in the memory and configured by the processor to perform the operation of any of the methods described in any of the embodiments of the above-described weighing anomaly detection method.
[0152] This application also provides a computer device that integrates any of the weighing anomaly detection devices provided in this application. For example... Figure 7 As shown, it illustrates a structural schematic diagram of the computer device involved in the embodiments of this application, specifically:
[0153] The computer device may include components such as a processor 701 with one or more processing cores, a storage unit 702 with one or more computer-readable storage media, a power supply 703, and an input unit 704. Those skilled in the art will understand that... Figure 7 The computer device structure shown does not constitute a limitation on the computer device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:
[0154] The processor 701 is the control center of the computer device. It connects various parts of the computer device via various interfaces and lines, and performs various functions and processes data by running or executing software programs and / or modules stored in the storage unit 702, and by calling data stored in the storage unit 702, thereby providing overall monitoring of the computer device. Optionally, the processor 701 may include one or more processing cores; preferably, the processor 701 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may also not be integrated into the processor 701.
[0155] Storage unit 702 can be used to store software programs and modules. Processor 701 executes various functional applications and data processing by running the software programs and modules stored in storage unit 702. Storage unit 702 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device, etc. In addition, storage unit 702 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, storage unit 702 may also include a memory controller to provide processor 701 with access to storage unit 702.
[0156] The computer device also includes a power supply 703 that supplies power to the various components. Preferably, the power supply 703 can be logically connected to the processor 701 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 703 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.
[0157] The computer device may also include an input unit 704, which can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.
[0158] Although not shown, the computer device may also include a display unit, etc., which will not be described in detail here. Specifically, in the embodiments of this application, the processor 701 in the computer device loads the executable files corresponding to the processes of one or more application programs into the storage unit 702 according to the following instructions, and the processor 701 runs the application programs stored in the storage unit 702 to realize various functions, as follows:
[0159] The weighing information of the target object after it is placed on the scale is obtained. The weighing information includes the weighing reading and the internal code value reading. The scale is a dynamic scale. Based on the weighing reading and a preset linear relationship, the fitted internal code value of the target object is determined. The linear relationship is the linear relationship between the weighing reading and the fitted internal code value. Based on the internal code value reading and the fitted internal code value, the difference in the internal code value of the target object is determined. Based on the difference in the internal code value and a preset abnormal quantile interval for weighing detection, it is determined whether the weighing reading of the target object is abnormal.
[0160] This application embodiment obtains the weighing information of a target object after it is placed on a scale. The weighing information includes the weighing reading and the internal code value reading, and the scale is a dynamic scale. Based on the weighing reading and a preset linear relationship, a fitted internal code value of the target object is determined. The linear relationship is the linear relationship between the weighing reading and the fitted internal code value. Based on the internal code value reading and the fitted internal code value, the difference in the internal code value of the target object is determined. Based on the difference in the internal code value and a preset abnormal quantile interval for weighing detection, it is determined whether the weighing reading of the target object is abnormal. Compared with traditional methods, by determining the difference in the internal code value based on the internal code value reading and the fitted internal code value of the target object after it is placed on the scale, and then determining whether the weighing reading of the target object is abnormal based on the difference in the internal code value and the preset abnormal quantile interval, abnormal data can be efficiently detected and re-checked. This can reduce the increased transportation costs and other expenses caused by inaccurate weighing for enterprises, thus reducing costs and increasing efficiency.
[0161] Therefore, embodiments of this application provide a computer-readable storage medium, which may include: read-only memory (ROM), random access memory (RAM), a disk, or an optical disk, etc. The computer-readable storage medium stores multiple instructions, which can be loaded by a processor to execute the steps in any of the weighing anomaly detection methods provided in embodiments of this application. For example, the instructions can execute the following steps:
[0162] The weighing information of the target object after it is placed on the scale is obtained. The weighing information includes the weighing reading and the internal code value reading. The scale is a dynamic scale. Based on the weighing reading and a preset linear relationship, the fitted internal code value of the target object is determined. The linear relationship is the linear relationship between the weighing reading and the fitted internal code value. Based on the internal code value reading and the fitted internal code value, the difference in the internal code value of the target object is determined. Based on the difference in the internal code value and a preset abnormal quantile interval for weighing detection, it is determined whether the weighing reading of the target object is abnormal.
[0163] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.
[0164] The above provides a detailed description of a weighing anomaly detection method, apparatus, and related devices provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.
Claims
1. A method for detecting weighing anomalies, characterized in that, The method includes: The weighing information of the target object after it is placed on the scale is obtained. The weighing information includes the weighing reading and the internal code value reading. The scale is a dynamic scale. Based on the weighing reading and a preset linear relationship, the fitted internal code value of the target object is determined, wherein the linear relationship is the linear relationship between the weighing reading and the fitted internal code value; Based on the internal code value display and the fitted internal code value, the difference in internal code value of the target object is determined; Based on the difference in the internal code value and the preset abnormal quantile interval for weighing detection, it is determined whether the weighing reading of the target object is abnormal. The abnormal quantile interval includes the inner interval of the abnormal quantile and the outer interval of the abnormal quantile. The step of determining whether the weighing reading of the target object is abnormal based on the difference in the internal code value and a preset abnormal quantile interval for weighing detection includes: Determine whether the difference in the internal code value is within the range of the abnormal quantile interval; If the difference in the internal code value is within the range of the abnormal quantile interval, then the weighing reading of the target object is determined to be normal. If the difference in the internal code value is in the outer range of the abnormal quantile interval, then the weighing reading of the target object is determined to be abnormal.
2. The weighing anomaly detection method according to claim 1, characterized in that, Before determining whether the weighing reading of the target object is abnormal based on the difference in the internal code value and a preset abnormal quantile interval for weighing detection, the method further includes: Based on the linear relationship, a preset number of test code value differences are determined; The preset number of test code value differences are sorted to obtain a sequence set of test code value differences; Based on the quantile method and the sequence set, the abnormal quantile intervals are determined.
3. The weighing anomaly detection method according to claim 1, characterized in that, Before determining the fitted internal code value of the target object based on the weighing reading and a preset linear relationship, the method further includes: Obtain a set of first weighing data pairs of a preset number of experimental goods on the dynamic scale. The first weighing data pair includes the first experimental weighing reading of the experimental goods and the first experimental internal code value reading corresponding to the first experimental weighing reading. Based on the set of the first weighing data pairs, the linear relationship is constructed.
4. The weighing anomaly detection method according to claim 1, characterized in that, The dynamic scale includes a start-up status determination display, an infeed status determination display, and an outfeed status determination display. The method further includes: When the start-up state determination reading is the start-up state reading, the weighing state determination reading is the weighing state reading with no goods entering the weighing surface, and the weighing state determination reading is the weighing state reading with no goods passing through the weighing surface, a set of second weighing data pairs of a preset number of experimental goods on the dynamic scale is obtained. The second weighing data pair includes the second experimental weighing reading of the experimental goods and the first experimental internal code value reading corresponding to the second experimental weighing reading. Based on the set of the second set of weighing data pairs, the fitting coefficient of the linear relationship is adjusted to optimize the linear relationship.
5. The weighing anomaly detection method according to claim 1, characterized in that, The step of determining the fitted internal code value of the target object based on the weighing reading and a preset linear relationship includes: The weighing reading is input into a preset linear relationship to generate the fitted internal code value of the target object.
6. The weighing anomaly detection method according to claim 1, characterized in that, After determining whether the weighing reading of the target object is abnormal based on the difference in the internal code value and a preset abnormal quantile interval for weighing detection, the method further includes: If the weighing reading of the target object is abnormal, an alarm message will be generated; The alarm information is sent to a preset user terminal.
7. A weighing anomaly detection device, characterized in that, The device includes: The first acquisition unit is used to acquire the weighing information of the target object after it is put on the scale. The weighing information includes the weighing reading and the internal code value reading. The scale is a dynamic scale. The first determining unit is used to determine the fitted internal code value of the target object based on the weighing reading and a preset linear relationship, wherein the linear relationship is the linear relationship between the weighing reading and the fitted internal code value. The second determining unit is used to determine the difference in the internal code value of the target object based on the internal code value display and the fitted internal code value. The third determining unit is used to determine whether the weighing reading of the target object is abnormal based on the difference in the internal code value and a preset abnormal quantile interval for weighing detection. The abnormal quantile interval includes an inner interval and an outer interval of the abnormal quantile. The determination of whether the weighing reading of the target object is abnormal based on the difference in the internal code value and the preset abnormal quantile interval for weighing detection includes: determining whether the difference in the internal code value is within the inner interval of the abnormal quantile interval; if the difference in the internal code value is within the inner interval of the abnormal quantile interval, then the weighing reading of the target object is determined to be normal; if the difference in the internal code value is within the outer interval of the abnormal quantile interval, then the weighing reading of the target object is determined to be abnormal.
8. A computer device, characterized in that, The computer device includes: One or more processors; Memory; and One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the weighing anomaly detection method according to any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that, It stores a computer program, which is loaded by a processor to execute the steps of the weighing anomaly detection method according to any one of claims 1 to 6.