Method and system for determining repetitive abnormality of measuring instrument, and computer readable medium

Abstract

The invention provides a repetitive anomaly judgment method and system of a measuring instrument and a computer readable medium. The repetitive anomaly judgment method comprises the following steps: acquiring a real-time image and / or real-time metering data of the metering instrument in a metering process; according to the real-time image and / or the real-time metering data, judging whether the metering instrument performs repeated actions in the metering process or not; and if the repeated actions occur, acquiring a plurality of effective metering data corresponding to the repeated actions, calculating a repeatability error of the effective metering data, and if the repeatability error exceeds a verification standard, judging that the metering instrument has repeatability abnormity. According to the invention, on the premise that the actual application of the measuring instrument is not interfered, the repetitive abnormity of the measuring instrument can be found in time, whether the measuring instrument needs to be calibrated is judged, and the measuring instrument is submitted for inspection in time, so that the calibration efficiency of the measuring instrument is improved.

Description

Technical Field

[0001] The present application mainly relates to the field of calibration of measuring instruments, and in particular to a method, system and computer-readable medium for determining repeatability anomalies of measuring instruments. Background Art

[0002] During use, measuring instruments are easily affected by factors such as temperature, humidity, vibration interference, electromagnetic interference, and intensity of use, which in turn affect the measurement performance and results. Metrology regulations stipulate that measuring equipment in trade settlement needs to be calibrated regularly. The specific practice is: through regular manual calibration, the calibration data is recorded and analyzed, and when the calibration is qualified, a calibration certificate is issued for a period of one year. When the calibration certificate expires, it is calibrated again. However, the practice of regular calibration has the following problems: (1) The operating environment and frequency of use of measuring instruments vary. The use of a fixed calibration cycle cannot adapt to the personalized use of measuring instruments; (2) It is impossible to monitor the status and performance of measuring instruments in daily use, timely discover existing measurement risks and correct and stop losses, so that the measurement performance will only be detected when it causes major problems or losses.

[0003] One solution is to log abnormal events that affect metering performance based on the intelligent diagnostic function of digital weighing sensors. However, since these abnormal events do not necessarily lead to metering performance problems, if these logs are only checked when metering problems occur, it is impossible to timely discover performance problems of the metering instrument during its use. Another solution is to prompt customers as soon as an abnormal event occurs, which will lead to excessive prompts and repeated erroneous prompts. Summary of the invention

[0004] The technical problem to be solved by the present application is to provide a method, system and computer-readable medium for real-time determination of repeatability anomalies of a measuring instrument.

[0005] In order to solve the above technical problems, the present application provides a method for determining repeatability anomalies of a measuring instrument, comprising: obtaining real-time images and / or real-time measurement data of the measuring instrument during the measurement process; judging whether the measuring instrument undergoes repeated actions during the measurement process based on the real-time images and / or real-time measurement data; if repeated actions occur, obtaining multiple valid measurement data corresponding to multiple repeated actions, calculating the repeatability errors of the multiple valid measurement data, and if the repeatability error exceeds the calibration standard, determining that the measuring instrument has a repeatability anomaly.

[0006] In one embodiment of the present application, the step of determining whether repeated action occurs in the measuring instrument during the measuring process based on the real-time image and the real-time measurement data includes: extracting image features and effective measurement moments of the real-time image corresponding to each effective measurement data; calculating the similarity of multiple image features, determining whether multiple real-time images correspond to the measurement process for the same item, and if the result is yes, determining whether multiple effective measurement moments meet preset requirements, and if so, determining that repeated action occurs.

[0007] In one embodiment of the present application, the step of determining whether the plurality of valid metering moments meet preset requirements includes calculating the interval duration between adjacent valid metering moments, and if the interval duration is less than the preset duration, determining that the plurality of valid metering moments meet the preset requirements.

[0008] In one embodiment of the present application, after the step of determining whether the measuring instrument has a repeatable abnormality, it also includes: obtaining a diagnostic record of the measuring instrument, the diagnostic record including abnormal events of the measuring instrument; determining a confidence level for the repeatable abnormality based on the abnormal event, and when the confidence level exceeds a preset confidence threshold, determining that the measuring instrument needs to be calibrated, wherein the confidence level is used to characterize the credibility of the repeatable abnormality.

[0009] In one embodiment of the present application, the greater the number of abnormal events, the greater the confidence level.

[0010] In one embodiment of the present application, the diagnostic record includes any item of the abnormality type, the time when the abnormality occurred, and the number of times the abnormality recurred of the measuring instrument, and the step of determining the confidence level for the repetitive abnormality based on the abnormal event includes: determining the confidence level based on any item of the abnormality type, the time when the abnormality occurred, and the number of times the abnormality recurred.

[0011] In one embodiment of the present application, the abnormality type includes any item of overload, impact, peak abnormality, temperature gradient abnormality, temperature abnormality, and tilt abnormality.

[0012] In one embodiment of the present application, when the abnormality type is overload, the multiple of the overload to the sensor capacity of the measuring instrument is proportional to the confidence level; when the abnormality type is impact, the peak value of the impact is proportional to the confidence level.

[0013] In one embodiment of the present application, it also includes: determining a prompt level based on the diagnostic record, the prompt level including a temporary prompt, an optional calibration prompt and a compulsory calibration protection prompt, wherein the temporary prompt is used to automatically disappear after being displayed on the user interface for a period of time without interrupting the operation of the measuring instrument; the optional calibration prompt is used to provide an optional calibration page on the user interface without interrupting the operation of the measuring instrument; the compulsory calibration protection prompt is used to provide a compulsory calibration page on the user interface while interrupting the operation of the measuring instrument.

[0014] In order to solve the above-mentioned technical problems, the present application also proposes a repeatability anomaly determination system for a measuring instrument, comprising: an image acquisition module, used to obtain real-time images of the measuring instrument during the measurement process; a measurement data acquisition module, used to obtain real-time measurement data of the measuring instrument during the measurement process; an anomaly determination module, used to determine whether the measuring instrument has repeated actions during the measurement process based on the real-time image or the real-time measurement data; if repeated actions occur, multiple valid measurement data corresponding to multiple repeated actions are obtained, and the repeatability errors of the multiple valid measurement data are calculated; if the repeatability error exceeds the calibration standard, it is determined that the measuring instrument has a repeatability anomaly.

[0015] In one embodiment of the present application, it also includes a main controller and an intelligent digital sensor subsystem, the abnormality judgment module is arranged in the main controller, the metering data acquisition module is arranged in the intelligent digital sensor subsystem, the intelligent digital sensor subsystem is also used to obtain diagnostic records, and the intelligent digital sensor subsystem sends the real-time metering data and diagnostic records to the main controller through the communication module.

[0016] In one embodiment of the present application, the measuring instrument includes a weighing instrument, and the real-time measuring data includes weighing data.

[0017] In one embodiment of the present application, the abnormality judgment module is also used to determine the prompt level based on the diagnostic record, and the prompt level includes a temporary prompt, an optional calibration prompt and a compulsory calibration protection prompt, wherein the temporary prompt is used to automatically disappear after being displayed on the user interface for a period of time without interrupting the operation of the measuring instrument; the optional calibration prompt is used to provide an optional calibration page on the user interface without interrupting the operation of the measuring instrument; the compulsory calibration protection prompt is used to provide a compulsory calibration page on the user interface while interrupting the operation of the measuring instrument. The repetitive abnormality judgment system also includes a prompt and alarm module, which is used to display the prompt level and give an alarm.

[0018] In order to solve the above-mentioned technical problems, the present application also proposes a repeatability anomaly determination system for a measuring instrument, comprising: a memory for storing instructions executable by a processor; and multiple processors, including one or more of a GPU, an NPU and a CPU, for executing the instructions to implement the repeatability anomaly determination method as described above.

[0019] In order to solve the above technical problems, the present application also proposes a computer-readable medium storing a computer program code, and the computer program code implements the above-mentioned repetitive anomaly determination method when executed by a processor.

[0020] The repeatability abnormality determination method of the present application combines machine vision technology and the sensing function of the measuring instrument itself, monitors the weighing process of the measuring instrument in real time, discovers the user's repeated measurement behavior pattern, and captures the image features, measurement data, and measurement time under the behavior pattern, and analyzes these data to determine whether the measuring instrument has a repeatability abnormality, and further determines whether it needs to be calibrated. In this way, the repeatability abnormality of the measuring instrument can be discovered in time without interfering with the actual application of the measuring instrument, and it can be determined whether it needs to be calibrated and sent for inspection in time. It can not only solve the problems existing in regular calibration, but also can timely discover calibration needs in a personalized manner, thereby improving the calibration efficiency of the measuring instrument. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are included to provide a further understanding of the present application. They are included and constitute a part of the present application. The accompanying drawings illustrate embodiments of the present application and together with the present specification serve to explain the principles of the present application. In the accompanying drawings:

[0022] Figure 1 is an exemplary flow chart of a method for determining repeatability anomaly of a measuring instrument according to an embodiment of the present application;

[0023] Figure 2 is a block diagram of a repetitive anomaly determination system according to an embodiment of the present application;

[0024] Figure 3 is an exemplary flow chart of a method for determining repeatability anomaly of a measuring instrument according to another embodiment of the present application;

[0025] Figure 4 It is a block diagram of a repeatability abnormality determination system for a measuring instrument according to another embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0027] As shown in this application, unless the context clearly indicates an exception, the words "a", "an", "a kind" and / or "the" do not refer to the singular, but also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list, and the method or device may also include other steps or elements.

[0028] Unless otherwise specifically stated, the relative arrangement, numerical expressions and numerical values ​​of the parts and steps set forth in these embodiments do not limit the scope of the present application. At the same time, it should be understood that, for ease of description, the sizes of the various parts shown in the accompanying drawings are not drawn according to the actual proportional relationship. The technology, method and equipment known to those of ordinary skill in the relevant field may not be discussed in detail, but in appropriate cases, the technology, method and equipment should be considered as a part of the authorization specification. In all examples shown and discussed here, any specific value should be interpreted as being merely exemplary, rather than as a limitation. Therefore, other examples of exemplary embodiments may have different values. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so that once a certain item is defined in an accompanying drawing, it does not need to be further discussed in subsequent drawings.

[0029] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously. At the same time, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0030] The repeatability abnormality determination method, system and computer-readable medium of the measuring instrument of the present application can be applied to any measuring instrument, including but not limited to weight detection instruments, volume detection instruments, etc. Preferably, the present application is applicable to weighing instruments.

[0031] The inventor of this application found in the research process that the repeatability problem of measuring instruments in daily use is often easily overlooked. On the one hand, the repeatability problem requires users to actively observe regularly and cannot be completed automatically without the participation of users. On the other hand, even if users observe the repeatability problem, they cannot determine whether it is a reversible repeatability change caused by environmental factors such as temperature gradient, or an irreversible repeatability change caused by impact or aging. Based on this discovery, the inventor proposed the repeatability abnormality determination method, system and computer-readable medium of the measuring instrument of this application.

[0032] Figure 1 is an exemplary flow chart of a method for determining repeatability anomalies of a measuring instrument according to an embodiment of the present application. Figure 1 As shown, the repeatability abnormality determination method of this embodiment includes the following steps:

[0033] Step S110: acquiring real-time images and / or real-time measurement data of the measuring instrument during the measurement process;

[0034] Step S120: judging whether the measuring instrument has repeated actions during the measuring process according to the real-time image and / or the real-time measuring data;

[0035] Step S130: If a repeated action occurs, multiple valid measurement data corresponding to the multiple repeated actions are obtained, and the repeatability errors of the multiple valid measurement data are calculated. If the repeatability error exceeds the verification standard, it is determined that the measuring instrument has a repeatability abnormality.

[0036] Figure 2 2 is a block diagram of a repeatability anomaly determination system according to an embodiment of the present application. The repeatability anomaly determination system 200 includes an image acquisition module 210, a measurement data acquisition module 220, and an anomaly determination module 230. The repeatability anomaly determination system 200 can be used to execute steps S110 to S130 in the repeatability anomaly determination method described above, but the repeatability anomaly determination method described above is not limited to being executed using the repeatability anomaly determination system 200.

[0037] The following combination Figure 1 and Figure 2 The above steps S110 to S130 are described in detail.

[0038] Can be Figure 2The image acquisition module 210 in step S110 performs the step of obtaining the real-time image of the measuring instrument during the measurement process. The present application does not limit the specific implementation method of the image acquisition module 210 and the format of the real-time image. Various types of image acquisition modules commonly used in the field, such as CMOS, CCD and other modules, and commonly used image formats, such as static image formats bmp, jpg, etc., dynamic video formats avi, mp4, etc., all belong to the scope to be protected by the present application. Preferably, the present application adopts a machine vision system to acquire images and analyze images. It should be noted that the image acquisition module 210 should be set to be able to capture effective images of the measuring instrument during the measurement process, and the effective image should include the items used for measurement. Taking the weighing instrument as an example, the image acquisition module 210 should be able to capture the items on the scale, or capture the scene including the scale and the items. The purpose of this setting is to determine whether repeated actions have occurred during the measurement process of the measuring instrument based on the real-time image. The present application sets the number of repeated actions to at least 2 times. In some embodiments, the number is at least 3 times.

[0039] Can be Figure 2 The metering data acquisition module 220 in the step S110 executes the step of obtaining the real-time metering data of the metering instrument during the metering process. Taking a weighing instrument as an example, the real-time metering data may be weighing data. The metering data acquisition module 220 may be arranged on the metering instrument, or may be arranged in a control module outside the metering instrument, for example, in the abnormality judgment module 230, and may obtain the real-time metering data collected by the metering instrument from the metering instrument through the communication module. This application does not limit the communication method of the communication module.

[0040] Can be used Figure 2 The abnormality judgment module 230 shown in executes step S120. Step S120 includes three judgment methods, first, judging based on real-time images; second, judging based on real-time measurement data; third, judging based on real-time images and real-time measurement data together. According to the judgment of real-time images, image features related to repetitive actions can be obtained by extracting image features, and whether repetitive actions have occurred can be judged based on the image features. According to the judgment of real-time measurement data, the real-time measurement data obtained can be used, for example, to repeatedly obtain several almost identical data, indicating that repetitive actions have occurred.

[0041] The following is an example of making judgments based on real-time images and real-time measurement data simultaneously.

[0042] In some embodiments, in step S120, the step of determining whether the measuring instrument has repeated actions during the measuring process according to the real-time image and the real-time measuring data includes:

[0043] Step S121: extracting the image features and effective measurement time of the real-time image corresponding to each effective measurement data;

[0044] Step S122: Calculate the similarity of multiple image features to determine whether the multiple real-time images correspond to the measurement process for the same item. If the result is yes, determine whether the multiple valid measurement moments meet the preset requirements. If so, determine that repeated actions occur.

[0045] Taking a weighing instrument as an example, the weighing instrument itself has the function of obtaining a valid weighing result. Weighing can include static weighing and dynamic weighing. In static weighing, the valid weighing result is the weighing value after the weighing platform is stable. In dynamic weighing, the valid weighing result is the weighing value obtained by the weighing platform. For example, a vehicle scale, a forklift scale and other instruments are weighed during movement, and a valid weighing result is obtained according to the characteristics of the instrument itself. The valid weighing result can represent the true weight of the item. Accordingly, the effective measurement moment corresponds to the moment when the measuring instrument generates effective measurement data. Therefore, in step S121, the abnormality judgment module 230 can directly obtain the effective measurement data and the effective measurement moment from the measurement data acquisition module 220. In order to obtain a real-time image of the effective measurement moment, the image acquisition module 210 and the measurement data acquisition module 220 should have a synchronization function to determine the correspondence between the effective measurement data, the effective measurement moment and the real-time image.

[0046] The present application does not limit the method for extracting the image features in step S121. Conventional image processing methods in the art, including but not limited to machine learning, deep neural network and other image processing methods, can be used to extract image features from each real-time image, and the image features include the objects in the region of interest.

[0047] In step S122, a similarity calculation method commonly used in the art can be used to calculate the similarity of image features in multiple real-time images corresponding to multiple valid measurement moments. For example, a cosine similarity calculation method is used. Based on the similarity, it can be determined whether the multiple real-time images correspond to the measurement process for the same item.

[0048] Specifically, it is assumed that a deep neural network model is used to extract image features v1, v2, ..., vn each time the effective weight is obtained, and the effective weight w1, w2, ..., wn each time, and the effective measurement time t1, t2, ... tn are recorded, where n is the total number of times recorded. In some embodiments, n≥3. In step S122, the similarity of multiple image features v1, v2, ..., vn is first calculated to determine whether the multiple real-time images correspond to the measurement process for the same item. If the result is yes, it is determined whether the multiple effective measurement moments t1, t2, ... tn meet the preset requirements. If they meet, it is determined that repeated actions occur. The preset requirements are, for example: the multiple effective measurement moments t1, t2, ... tn belong to the same narrow continuous time interval, indicating that the measured items have not been replaced within this interval. Specifically, in some embodiments, in step S122, the step of determining whether the multiple effective measurement moments meet the preset requirements includes: calculating the interval duration between adjacent effective measurement moments. If the interval duration is less than the preset duration, it is determined that the multiple effective measurement moments meet the preset requirements. For example, the preset time length is set to 1 second. If the interval between two adjacent valid measurement moments is less than 1 second, it means that the objects measured at the two valid measurement moments are the same object.

[0049] In step S122, by adding the judgment of the effective measurement moment, the error of the similarity judgment of the image features can be removed. For example, taking the cashier weighing scene as an example, for some similar but actually different items, such as two items are a bag of fruit, one bag is more and the other bag is less, but the difference is not big, then the similarity judgment of the image features may not be able to identify the difference between the two items. Then, by judging the effective measurement moment, it can be further judged that the time interval for weighing the two items exceeds the preset time length, and it should belong to the weighing of different items, and it will not be judged that repeated actions occur.

[0050] In practical applications, users may weigh the same item repeatedly for various purposes, and such operations may occur. However, the system does not know when the user will perform such operations. Therefore, the repeatability abnormality determination method of the present application monitors the weighing process of the measuring instrument in real time, discovers the user's repeated weighing behavior pattern through real-time images and / or real-time measurement data, and captures the image features, effective measurement data, and effective measurement moments under the behavior pattern, and analyzes these data to determine whether the measuring instrument has a repeatability abnormality, and further determines whether it needs to be calibrated. In this way, it is possible to promptly discover whether the measuring instrument needs to be calibrated and sent for inspection in time without interfering with the actual application of the measuring instrument, which can not only solve the problems existing in regular calibration, but also can promptly discover the calibration requirements in a personalized manner, thereby improving the calibration efficiency of the measuring instrument.

[0051] After determining that the measuring instrument has indeed undergone repeated actions in step S122, the repeatability error can be calculated in step S130 based on the valid measurement data corresponding to these repeated actions. Specifically, the repeatability error can be obtained using statistical methods. For example, the variance of multiple valid measurement data can be calculated. In some embodiments, the maximum and minimum values ​​of multiple valid measurement data are obtained, and the difference between the maximum and minimum values ​​is compared with a preset standard to determine whether the repeatability error exceeds the verification standard.

[0052] The verification standards described in the embodiments of the present application may be custom standards or may refer to national standards, such as the National Measurement Verification Regulations JJG 539-2016. It should be noted that for weighing instruments, the verification standards vary with the size range of the load of the weighed object. For example, for a common dual-range electronic scale used in supermarkets (medium accuracy Max 6 / 15kg, e=2 / 5g), the following settings should be met:

[0053] If the mass is less than or equal to 500e, that is, the mass is less than or equal to 1kg, then the difference between multiple weighing results is less than or equal to 1g;

[0054] If 500e<mass<=2000e, that is, 1kg<mass<=10kg, then the difference between multiple weighing results is <=1.0e (here if the load mass is <=6kg, then 1.0e=2g, and if the mass is >6kg, then 1.0e=5g);

[0055] If the mass > 2000e, that is, the mass > 10kg, the difference between multiple weighing results is <= 1.5e=7.5g.

[0056] Correspondingly, if the repeatability error, ie, the difference value, calculated in step S122 cannot satisfy the above-mentioned set value, it indicates that the electronic scale needs to be calibrated.

[0057] Furthermore, in some embodiments, after determining whether a repeatability abnormality occurs in the measuring instrument in step S130, the repeatability abnormality determination method of the present application further includes:

[0058] Step S131: Acquire the diagnostic record of the measuring instrument, where the diagnostic record includes abnormal events of the measuring instrument.

[0059] After determining whether the measuring instrument has a repetitive abnormality in step S130, the following steps may also be performed:

[0060] Step S140: Determine whether the measuring instrument needs to be calibrated based on the repeatability anomaly. The specific steps include:

[0061] Step S141: Determine a confidence level for the repeatable anomaly based on the abnormal event. When the confidence level exceeds a preset confidence threshold, determine that the measuring instrument needs to be calibrated. The confidence level is used to characterize the credibility of the repeatable anomaly.

[0062] According to the above embodiment, when a repetitive abnormality is found, the calibration is not immediately determined, but the diagnosis record of the measuring instrument is further combined to make a judgment, which can further avoid false alarms and improve the accuracy of the calibration prompt in combination with the confidence level.

[0063] It should be noted that in this embodiment, the measuring instrument itself has an intelligent diagnosis function and stores a diagnosis record. Abnormal events may include abnormal operation, abnormal environment, etc. Abnormal operation includes, for example, impact and overload, and abnormal environment includes, for example, high temperature and high humidity.

[0064] It can be understood that the more abnormal events are recorded, the greater the possibility that the measuring instrument is indeed abnormal. Therefore, the confidence level can be determined according to the number of abnormal events recorded. The more abnormal events there are, the greater the confidence level, which means that the repeatability abnormality results obtained according to steps S110 to S130 are more credible.

[0065] In some embodiments, the diagnostic record includes any item of the abnormality type, the time when the abnormality occurred, and the number of times the abnormality recurs of the measuring instrument. The step of determining the confidence level for repetitive abnormalities based on the abnormal event in step S141 includes: determining the confidence level based on any item of the abnormality type, the time when the abnormality occurred, and the number of times the abnormality recurs.

[0066] In some embodiments, the abnormality type includes any of overload, shock, peak abnormality, temperature gradient abnormality, temperature abnormality, and tilt abnormality.

[0067] In these embodiments, a relatively complex judgment logic can be set according to the characteristics of the measuring instrument. For example, different weights are assigned to different types of abnormalities, such as a weight of 1 for temperature abnormalities and a weight of 2 for tilt abnormalities. For example, different weights are set for different abnormal occurrence times. For example, if the abnormal occurrence time is 10 days ago, the weight is 1, and if the abnormal occurrence time is 1 day ago, the weight is 10. For example, different weights are assigned to different abnormal repetition times. For example, if the abnormal repetition times are 0 to 5 times, the weight is 1, and if they are 6 to 10 times, the weight is 2. Machine learning can also be used to obtain a more accurate prediction model through training to predict whether the measuring instrument needs to be calibrated based on the diagnostic record.

[0068] In some embodiments, when the abnormality type is overload, the multiple of the overload to the sensor capacity of the measuring instrument is proportional to the confidence level; when the abnormality type is impact, the peak value of the impact is proportional to the confidence level. For example, if the overload reaches 1.5 times the capacity of the weighing sensor, the confidence level is 2, and if it exceeds 3 times, the confidence level is 3; if the peak value of the impact reaches more than 2 times the sensor capacity, the confidence level is 2, and if it exceeds 3 times, the confidence level is 3.

[0069] In some embodiments, Figure 2 The abnormality determination module 230 shown in is also used to determine the prompt level according to the diagnostic record. In these embodiments, Figure 2 The illustrated repeatability anomaly determination system 200 may also include a prompt and alarm module 240, which may have functions such as display, sound, and light, so as to provide prompts and alarms to the user in a visual and auditory manner. The prompt and alarm module 240 may be, for example, a graphical user interface. The prompt levels include temporary prompts, optional verification prompts, and mandatory verification protection prompts, wherein the temporary prompt is used to automatically disappear after being displayed on the user interface for a period of time without interrupting the operation of the measuring instrument; the optional verification prompt is used to provide an optional verification page on the user interface without interrupting the operation of the measuring instrument; the mandatory verification protection prompt is used to provide a mandatory verification page on the user interface while interrupting the operation of the measuring instrument.

[0070] More specifically, the abnormality determination module 230 determines the prompt level according to the abnormality type, abnormality occurrence time, and abnormality recurrence times in the diagnosis record. The step of determining the prompt level is performed after it is determined in step S122 that the measuring instrument has indeed undergone repeated actions.

[0071] The present application does not restrict the prompt forms of each level. The temporary prompt has the lowest level and the lowest calibration requirement, followed by the optional calibration prompt, and the mandatory calibration protection prompt has the highest level, so it will forcibly interrupt the operation of the measuring instrument, indicating that the repeatability error of the measuring instrument has exceeded the preset standard at this time, and it is impossible to accurately reflect the measurement result, and calibration must be forced. According to this embodiment, it can be clearly understood that the abnormality judgment module 230 is also used to communicate with the main controller to send the judgment result to the main controller, and the main controller controls the measuring instrument, such as forcibly shutting down. According to these embodiments, the repeatability abnormality judgment method of the present application not only gives the result of whether to calibrate, but also controls the measuring instrument according to the result, so as to avoid settlement problems caused by performance problems of the measuring instrument.

[0072] Figure 3 2 is an exemplary flow chart of a method for determining repeatability anomaly of a measuring instrument according to another embodiment of the present application. This embodiment takes a weighing instrument as an example. Figure 3 As shown, the repeatability abnormality determination method of this embodiment includes the following steps:

[0073] Step S310: When the weight is stable, the image features of the scale are extracted through the machine vision system.

[0074] Step S320: Read the stable weight of the weighing sensor.

[0075] Step S330: Determine whether they are the same object based on the image features. If so, execute step S340; if not, return to step S310.

[0076] Step S340: Determine whether the same item is placed repeatedly based on the weighing time when stable. If so, execute step S350; if not, return to step S310.

[0077] Step S350: Determine whether it is a repetitive anomaly based on the stable weight of the same item. If so, execute step S360; if not, return to step S310.

[0078] Step S360: Read the sensor intelligent diagnosis log.

[0079] Step S370: Determine whether it is a repetitive anomaly in combination with the intelligent diagnosis log. If so, execute step S380; if not, return to step S310.

[0080] Step S380: Verification prompt or alarm. This step may also include grading the repetitive anomalies and giving grading prompts.

[0081] Figure 4 is a block diagram of a repeatability abnormality determination system for a measuring instrument according to another embodiment of the present application. Figure 4 As shown, the repeatability abnormality determination system 400 of this embodiment includes a main controller 401 and an intelligent digital sensor subsystem 402, wherein the main controller 401 includes memories M104, M105 and multiple processors M101, M102, and M103. Among them, the memory M104 is a RAM, and the memory M105 is a ROM. The processor M101 is a CPU, the processor M102 is an NPU, and the processor M103 is a GPU. The memories M104, M105 and the processors M101, M102, and M103 establish a communication connection relationship with the output device M201, the input device M202, the camera device M203, the storage device M204, and the communication device M205 through the communication modules M100 and M200. Among them, M100 can be a bus, and M200 can be an I / O interface. The camera device M203 can be one of the specific implementations of the image acquisition module 210 described above. The smart digital sensor subsystem 402 may be composed of a sensor network, such as Figure 4As shown, it includes a weighing sensor, a temperature sensor L202, a humidity sensor L203, a gravity acceleration sensor L204, etc. The weight A / DL201 is used to convert the analog weight signal obtained by the weighing sensor into a digital signal. Each sensor realizes the interaction between the sensed signal and the ROML101, RAML102, and CPUL103 through the I / O interface L200 and the bus L100. At the same time, the main controller 401 and the intelligent digital sensor subsystem 402 are connected in communication through their respective communication devices M205 and L206. The intelligent digital sensor subsystem 402 can send the obtained real-time measurement data and diagnostic records to the main controller 401 through the communication devices M205 and L206.

[0082] The abnormality determination module 230 mentioned above may be arranged in the main controller 401 , and the metering data acquisition module 220 may be arranged in the intelligent digital sensor subsystem 401 .

[0083] It should be noted that since image acquisition and feature extraction require high computing power, high-performance NPU and GPU are used in the main controller 401 to process the image to improve the working efficiency of the repeatability abnormality determination system. In the intelligent digital sensor subsystem 402, an ordinary CPU can be used to process and calculate the sensing signals of each sensor. Figure 4 Such a distributed computing system can improve the computing efficiency as a whole and highlight the real-time performance of the repetitive anomaly determination system of the present application.

[0084] The repeatability anomaly determination method and system of the present application combine machine vision technology and sensor intelligent diagnosis technology to continuously and automatically detect repeatability problems in an automated manner, which can save a lot of manpower; at the same time, the intelligent diagnosis log of the sensor is used to improve the pertinence and confidence of the calibration prompts.

[0085] The following is a specific example. In a retail store, a clerk uses a commodity with a standard appearance, such as a bag of salt with a weight mark of 250g, to perform a repeatability check on an electronic scale. When the scale is empty, the clerk places the bag of salt on the scale for the first time. When the electronic scale reaches a stable state, the timestamp t1 is obtained, the scale image P1 at t1 is obtained through a camera, and the effective weight W1 at t1 is obtained through a digital sensor subsystem. The timestamp is the effective measurement moment mentioned above.

[0086] The clerk then picked up the bag of salt and placed it on the scale twice, obtaining the second and third timestamps, scale images and effective weights, recorded as t2, P2, W2 (second time) and t3, P3, W3 (third time). The interval between the timestamps t1, t2, t3 when the scale reaches a stable or effective weight can be used to infer whether it is a repeated placement of the same item. For example, if the values ​​of t2-t1 and t3-t2 are both less than 2 seconds, it can be considered that the same item is repeatedly placed.

[0087] Preferably, the images P1, P2, and P3 of the scale platform at t1, t2, and t3 are acquired by using a camera device, and a deep neural network model for image feature extraction is loaded by using an NPU. The images are input into the deep neural network to obtain the image feature vectors V1, V2, and V3. Cosine similarity calculations are performed on V1, V2, and V3 in pairs. If the minimum cosine similarity is greater than a certain threshold, such as 0.8, the system determines that the above W1, W2, and W3 are the weights of the same item weighed three times repeatedly. Compared with the judgment method based solely on stable or effective weight timestamps, the repeatability judgment based on image feature extraction is more reliable and can avoid mistaking the repeated alternating playback of different items for the repeated playback of the same item.

[0088] The above judgment on the same item can be automatically completed by the system. Since it is easy to repeatedly place the same item in the daily use of electronic scales, the above method can perform repeatability checks anytime and anywhere, and timely discover problems during the use of electronic scales. The above method makes full use of the ability of deep neural networks to automatically extract features, and can use heavy objects without fixed standard shapes for repeatability tests, such as a bag of apples weighing about 10.2kg, which expands the scope of application of the above repeatability inspection method.

[0089] Furthermore, repeatability abnormality judgment is performed. Assuming that the above three values ​​W1, W2, and W3 are respectively: 0.252kg, 0.252kg, and 0.252kg, then according to the verification standard, repeatability is normal; assuming that the above three values ​​are: 0.252kg, 0.258kg; 0.252kg, then according to the verification standard, repeatability is abnormal. The above judgment method can automatically judge repeatability abnormality by repeating weighing actions in daily use without the aid of standard weights, and has the advantage of being simple and easy.

[0090] Furthermore, when an abnormality occurs in the above repeatability check, the intelligent diagnosis log of the digital sensor is queried, and relevant abnormal events in the log are counted, such as impact, overload, high temperature and high humidity, etc. The system determines the confidence of this repeatability abnormality through mathematical modeling, machine learning and other methods according to the number of abnormal events, the time interval from this repeatability abnormality, the number of repeatability abnormalities observed before this repeatability abnormality occurs, etc. For example, if there are 2 impacts in the log, and the most recent one is 1 hour away from this repeatability abnormality, the confidence is 0.8; for another example, if there are 3 overloads in the log, and the time is 2 days away from this repeatability abnormality, the confidence is 0.5; for another example, if there is no abnormal record in the log, the confidence is 0.05;

[0091] Furthermore, the system performs graded calibration prompts according to the confidence level of the repeatability anomaly: for repeatability anomalies with low confidence (for example, <0.1), only a prompt is given; for repeatability anomalies with medium confidence (for example, >=0.1 and <0.8), a prompt is given and a calibration test entry is provided, such as providing an optional calibration page on the user interface; for repeatability anomalies with high confidence (for example, >0.8), the weighing system is interrupted and the user is forced to perform a calibration test; calibration prompts based on confidence levels avoid unnecessary error prompts, and make full use of the intelligent diagnostic log of the digital sensor to continuously evaluate the necessity of calibration tests, thereby improving calibration efficiency.

[0092] The present application also includes a computer-readable medium storing a computer program code, which, when executed by a processor, implements the above-mentioned repetitive anomaly determination method.

[0093] When the data processing method for a database is implemented as a computer program, it can also be stored in a computer-readable storage medium as an article of manufacture. For example, a computer-readable storage medium may include, but is not limited to, a magnetic storage device (e.g., a hard disk, a floppy disk, a magnetic strip), an optical disk (e.g., a compact disk (CD), a digital versatile disk (DVD)), a smart card, and a flash memory device (e.g., an electrically erasable programmable read-only memory (EPROM), a card, a stick, a key drive). In addition, the various storage media described herein can represent one or more devices and / or other machine-readable media for storing information. The term "machine-readable medium" may include, but is not limited to, wireless channels and various other media (and / or storage media) that can store, contain and / or carry code and / or instructions and / or data.

[0094] It should be understood that the embodiments described above are only illustrative. The embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or any combination thereof. For hardware implementation, the processor may be implemented in one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, and / or other electronic units designed to perform the functions described herein, or a combination thereof.

[0095] Some aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". The processor may be one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DAPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, or combinations thereof. In addition, various aspects of the present application may be expressed as computer products located in one or more computer-readable media, which include computer-readable program codes. For example, computer-readable media may include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, tapes ...), optical disks (e.g., compact disks CDs, digital versatile disks DVDs ...), smart cards, and flash memory devices (e.g., cards, sticks, key drives ...).

[0096] A computer-readable medium may include a propagated data signal containing computer program code, such as in baseband or as part of a carrier wave. The propagated signal may have a variety of manifestations, including electromagnetic, optical, etc., or a suitable combination. A computer-readable medium may be any computer-readable medium other than a computer-readable storage medium, which may be connected to an instruction execution system, device or apparatus to communicate, propagate or transmit a program for use. The program code on the computer-readable medium may be propagated via any suitable medium, including radio, cable, fiber optic cable, radio frequency signal, or similar medium, or any combination of the above mediums.

[0097] The basic concepts have been described above. Obviously, for those skilled in the art, the above invention disclosure is only used as an example and does not constitute a limitation of the present application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements and amendments to the present application. Such modifications, improvements and amendments are suggested in the present application, so such modifications, improvements and amendments still belong to the spirit and scope of the exemplary embodiments of the present application.

[0098] At the same time, the present application uses specific words to describe the embodiments of the present application. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, some features, structures or characteristics in one or more embodiments of the present application can be appropriately combined.

[0099] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of the present application are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

Claims

1. A method for determining repeatability anomaly of a measuring instrument, characterized in that: include: Acquiring real-time images and / or real-time measurement data of the measuring instrument during the measurement process; Determining whether the measuring instrument has repeated actions during the measuring process according to the real-time image and / or the real-time measuring data; If a repeated action occurs, a plurality of valid measurement data corresponding to the repeated actions are obtained, and the repeatability errors of the plurality of valid measurement data are calculated. If the repeatability error exceeds the verification standard, it is determined that a repeatability abnormality occurs in the measuring instrument.

2. The method for determining repetitive abnormality according to claim 1, wherein: The step of judging whether the measuring instrument has repeated actions during the measuring process according to the real-time image and the real-time measuring data comprises: Extract image features and effective measurement time of the real-time image corresponding to each effective measurement data; The similarity of the plurality of image features is calculated to determine whether the plurality of real-time images correspond to the measurement process for the same item. If the result is yes, it is determined whether the plurality of effective measurement moments meet the preset requirements. If so, it is determined that repeated actions occur.

3. The method for determining repetitive abnormality according to claim 2, wherein: The step of judging whether the plurality of valid metering moments meet preset requirements comprises: calculating the interval duration between adjacent valid metering moments, and if the interval duration is less than the preset duration, judging that the plurality of valid metering moments meet the preset requirements.

4. The method for determining repetitive abnormality according to claim 1, wherein: After the step of determining whether the measuring instrument has a repeatable abnormality, the method further includes: obtaining a diagnostic record of the measuring instrument, wherein the diagnostic record includes abnormal events of the measuring instrument; determining a confidence level for the repeatable abnormality based on the abnormal events, and when the confidence level exceeds a preset confidence threshold, determining that the measuring instrument needs to be calibrated, wherein the confidence level is used to characterize the credibility of the repeatable abnormality.

5. The method for determining repetitive abnormality according to claim 4, wherein: The greater the number of abnormal events, the greater the confidence level.

6. The method for determining repetitive abnormality according to claim 4, wherein: The diagnostic record includes any item of the abnormality type, abnormality occurrence time, and abnormality recurrence number of the measuring instrument. The step of determining the confidence level for the repetitive abnormality based on the abnormal event includes: determining the confidence level based on any item of the abnormality type, abnormality occurrence time, and abnormality recurrence number.

7. The method for determining repetitive abnormality according to claim 6, wherein: The abnormality type includes any item of overload, impact, peak abnormality, temperature gradient abnormality, temperature abnormality, and tilt abnormality.

8. The method for determining repetitive abnormality according to claim 6, wherein: When the abnormality type is overload, the multiple of the overload to the sensor capacity of the measuring instrument is proportional to the confidence level; when the abnormality type is impact, the peak value of the impact is proportional to the confidence level.

9. The method for determining repetitive abnormality according to claim 4, wherein: Also includes: Determine a prompt level according to the diagnostic record, the prompt level including a temporary prompt, an optional verification prompt, and a mandatory verification protection prompt, wherein the temporary prompt is used to automatically disappear after being displayed on the user interface for a period of time without interrupting the operation of the measuring instrument; The optional calibration prompt is used to provide an optional calibration page on the user interface without interrupting the operation of the measuring instrument; the compulsory calibration protection prompt is used to provide a compulsory calibration page on the user interface while interrupting the operation of the measuring instrument.

10. A repeatability abnormality determination system for a measuring instrument, characterized in that: include: An image acquisition module, used to obtain real-time images of the measuring instrument during the measuring process; A measurement data acquisition module, used to obtain real-time measurement data of the measuring instrument during the measurement process; The abnormality judgment module is used to judge whether the measuring instrument has repeated actions during the measurement process according to the real-time image or the real-time measurement data. If repeated actions occur, multiple valid measurement data corresponding to multiple repeated actions are obtained, and the repeatability errors of the multiple valid measurement data are calculated. If the repeatability error exceeds the verification standard, it is determined that the measuring instrument has a repeatability abnormality.

11. The repetitive abnormality determination system according to claim 10, characterized in that: It also includes a main controller and an intelligent digital sensor subsystem, the abnormality judgment module is arranged in the main controller, the metering data acquisition module is arranged in the intelligent digital sensor subsystem, the intelligent digital sensor subsystem is also used to obtain diagnostic records, and the intelligent digital sensor subsystem sends the real-time metering data and diagnostic records to the main controller through the communication module.

12. The repetitive abnormality determination system according to claim 10, characterized in that: The measuring instrument includes a weighing instrument, and the real-time measuring data includes weighing data.

13. The repetitive abnormality determination system according to claim 11, characterized in that: The abnormality judgment module is also used to determine the prompt level according to the diagnostic record, and the prompt level includes temporary prompts, optional calibration prompts and compulsory calibration protection prompts, wherein the temporary prompt is used to be displayed on the user interface for a period of time without interrupting the operation of the measuring instrument and then disappears automatically; the optional calibration prompt is used to provide an optional calibration page on the user interface without interrupting the operation of the measuring instrument; the compulsory calibration protection prompt is used to provide a compulsory calibration page on the user interface while interrupting the operation of the measuring instrument. The repeatability abnormality judgment system also includes a prompt and alarm module, which is used to display the prompt level and give an alarm.

14. A repeatability abnormality determination system for a measuring instrument, characterized in that: include: a memory for storing instructions executable by a processor; Multiple processors, including one or more of a GPU, an NPU and a CPU, are used to execute the instructions to implement the repetitive anomaly determination method as described in any one of claims 1-9.

15. A computer-readable medium storing computer program codes, wherein the computer program codes, when executed by a processor, implement the repetitive anomaly determination method according to any one of claims 1 to 9.

Images