An intelligent scale interference identification method, device, system and storage medium

Abstract

This invention discloses a method, device, system, and storage medium for identifying interference on smart scales. The method includes: if weighing behavior is detected, acquiring an image of a target area within a target time period and a liveness detection result; wherein the target time period starts from the moment the weighing data changes and ends when the weighing data stabilizes; based on the liveness detection result, determining the recognition intent of the target area image, and performing recognition according to the recognition intent to obtain a recognition result; based on the recognition result, determining whether visual interference exists in the weighing behavior. This technical solution can solve the problem of low accuracy in identifying interference on smart scales, improving the accuracy of interference identification while providing customers with a better shopping experience and saving labor costs for merchants.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to a method, device, system, and storage medium for identifying interference in a smart scale. Background Technology

[0002] With the rapid development of artificial intelligence, smart scales are now widely used in supermarkets and shopping malls. Customers place the items to be weighed on the smart scale, the camera on the scale identifies the items, and the corresponding barcode is sent back to the weighing software. Finally, the weighted item is displayed on the screen, and the customer simply clicks on the image of the item to print the price tag and complete the weighing process. This not only brings convenience to customers but also saves labor costs for supermarkets and shopping malls.

[0003] In real-world scenarios, due to the lack of dedicated weighing personnel, customers may intentionally or unintentionally touch the weighing platform during self-service weighing, leading to inaccurate weighing results and losses for the supermarket or the customer. For example, customers may maliciously reduce the weight by lifting or pulling the goods during the weighing process. Additionally, in some cases, hands, packaging bags, etc., may completely or partially obscure the goods being weighed, causing misidentification or failure to identify the goods, resulting in inaccurate pricing, losses for customers or merchants, and unnecessary disputes.

[0004] Current technologies typically use infrared detection to check for living objects near the weighing platform of smart scales. However, they cannot determine whether detected living objects, such as hands, are interfering with the smart scale. Therefore, the accuracy of interference identification using these methods is low, and false alarms are prone to occur. Summary of the Invention

[0005] This invention provides a method, device, system, and storage medium for identifying interference on smart scales, which solves the problem of low accuracy in identifying interference on smart scales. It can improve the accuracy of interference identification, bring a good shopping experience to customers, and save labor costs for merchants.

[0006] According to one aspect of the present invention, a method for identifying interference in a smart scale is provided, the method comprising:

[0007] If weighing behavior is detected, the target area image and liveness detection results within the target time period are acquired; wherein, the target time period starts from the moment when the weighing data changes and ends when the weighing data stabilizes.

[0008] Based on the liveness detection results, the recognition intent of the target region image is determined, and recognition is performed according to the recognition intent to obtain the recognition result;

[0009] Based on the recognition results, it is determined whether visual interference exists in the weighing process.

[0010] According to another aspect of the present invention, an intelligent scale interference identification device is provided. The device includes: an image and detection result acquisition module, configured to acquire an image of a target area and a liveness detection result within a target time period if a weighing behavior is detected; wherein the target time period starts from the moment when the weighing data changes and ends when the weighing data stabilizes.

[0011] The recognition result generation module is used to determine the recognition intent of the target region image based on the liveness detection result, and to perform recognition according to the recognition intent to obtain the recognition result;

[0012] A visual interference determination module is used to determine whether visual interference exists in the weighing behavior based on the recognition results.

[0013] According to another aspect of the present invention, an intelligent scale interference identification system is provided, the system comprising: a liveness detection device, an image acquisition device, a weighing data acquisition device, at least one processor, and a memory;

[0014] The liveness detection device, image acquisition device, and weighing data acquisition device are all communicatively connected to the processor, and the processor is communicatively connected to the memory.

[0015] The liveness detection device is used to detect whether there is a live person obstructing the target area;

[0016] The image acquisition device is used to acquire images of the target area;

[0017] The weighing data acquisition device is used to collect weighing data from the smart scale;

[0018] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to implement the intelligent scale interference identification method according to any embodiment of the present invention when the at least one processor is able to execute it.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the intelligent scale interference identification method according to any embodiment of the present invention.

[0020] The technical solution of this invention determines the recognition intent of the target area image through liveness detection results, obtains the recognition result, and then determines whether there is visual interference in the weighing process based on the recognition result. This solution can solve the problem of low accuracy in interference recognition for smart scales, improve the accuracy of interference recognition, provide customers with a better shopping experience, and save labor costs for merchants.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, 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 the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of an interference identification method for a smart scale according to Embodiment 1 of the present invention;

[0024] Figure 2A This is a flowchart of an interference identification method for a smart scale according to Embodiment 2 of the present invention;

[0025] Figure 2B This is a schematic diagram comparing normal and abnormal weighing curves according to Embodiment 2 of the present invention;

[0026] Figure 3 This is a schematic diagram of the structure of an intelligent scale interference identification device according to Embodiment 3 of the present invention;

[0027] Figure 4 This is a schematic diagram of the structure of an intelligent scale interference identification system that implements the intelligent scale interference identification method of this invention. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] Example 1

[0031] Figure 1 This is a flowchart illustrating a smart scale interference identification method according to Embodiment 1 of the present invention. This embodiment is applicable to smart scale interference identification. The method can be executed by a smart scale interference identification device, which can be implemented in hardware and / or software and can be configured within a smart scale interference identification system. Figure 1 As shown, the method includes:

[0032] S110. If weighing behavior is detected, the target area image and liveness detection result within the target time period are obtained; wherein, the target time period starts from the moment when the weighing data changes and ends when the weighing data stabilizes.

[0033] This solution can be executed by an intelligent scale interference recognition system, which may include a liveness detection device, an image acquisition device, a weighing data acquisition device, and at least one processor and memory. The intelligent scale interference recognition system can collect weighing data from the intelligent scale through the weighing data acquisition device and determine whether a weighing action has occurred based on the weighing data. For example, the intelligent scale interference recognition system can detect whether there is a change in the weighing weight; if so, it is considered that a weighing action has occurred. Furthermore, the intelligent scale interference recognition system can also detect information such as the magnitude and timing of the weight change to avoid misjudgment of weighing action and improve the accuracy of weighing action judgment.

[0034] The intelligent weighing interference identification system can use the time interval from the moment the weighing data changes to the moment the weighing data stabilizes as the target time period for the weighing behavior. The moment the weighing data stabilizes can be defined as the last moment when the weighed weight reaches a certain value and remains unchanged for a preset time period. For example, if the weighing data starts changing from 0 kg at 7:00:00, reaches 3 kg at 7:00:01, and remains unchanged at 3 kg for the next second, the intelligent weighing interference identification system can determine that the moment the weighing data changes is 7:00:00, and the moment the weighing data stabilizes is 7:00:02.

[0035] The intelligent scale interference recognition system can acquire images of the target area captured by an image acquisition device within a target time period, as well as liveness detection results obtained by a liveness detection device detecting the target area. The target area can include areas that affect the recognition of weighed items, such as the intelligent scale platform area, and can also include areas where weighing fraud may occur, such as the area surrounding the intelligent scale.

[0036] Understandably, the liveness detection device can be an infrared liveness detector, used to detect whether there is a human hand or other living object obstructing the target area. The liveness detection device can be configured in one location or in multiple locations. Specifically, the liveness detection device can be configured above the smart scale platform or around the smart scale. If the liveness detection device detects a live object in the target area, it considers that there is a live object obstructing the target area. The image acquisition device is used to acquire images of the target area and can be an optical imaging device, such as a visible light camera, or a thermal imaging device, such as an infrared thermal imager.

[0037] S120. Based on the liveness detection result, determine the recognition intent of the target region image, and perform recognition according to the recognition intent to obtain the recognition result.

[0038] It is easy to understand that the liveness detection result can include whether liveness occlusion exists. The intelligent scale interference recognition system can determine whether liveness occlusion exists based on the duration of liveness within the target time period. For example, if the duration of liveness exceeds 50% of the target time period, then liveness occlusion is determined to exist. Assuming the target time period is 2 seconds and the liveness duration is 1.5 seconds, then the liveness detection result can be determined to be liveness occlusion. The intelligent scale interference recognition system can also determine whether liveness occlusion exists based on the number of times liveness occurs within the target time period. For example, if the number of times liveness occurs within the target time period exceeds a preset threshold, then liveness occlusion is determined to exist. Assuming the preset threshold is 3 times and the number of times liveness occurs within the target time period is 5 times, then the liveness detection result can be determined to be liveness occlusion.

[0039] The intelligent scale interference recognition system can determine whether a live object is obstructing the weighing process and affecting normal item recognition based on the liveness detection results. If the liveness detection result indicates the presence of live object obstruction, the system can determine whether the obstruction affects item recognition based on the target area image. If the liveness detection result indicates the absence of live object obstruction, the system can determine whether non-live object obstruction exists based on the target area image.

[0040] After determining the recognition intent of the target area image, the intelligent scale interference recognition system can call different recognition models according to the recognition intent to obtain recognition results. Assuming recognition intent A is to determine whether live object occlusion affects object recognition, and recognition intent B is to determine whether non-live object occlusion exists, for recognition intent A, the intelligent scale interference recognition system can call an image detection model or an image segmentation model to obtain information such as the area and location of the live object occlusion region. For recognition intent B, the intelligent scale interference recognition system can call an image classification model to determine whether non-live object interference exists or to determine the type of non-live object occlusion. Simultaneously, the intelligent scale interference recognition system can also call an image detection model or an image segmentation model to further determine information such as the area and location of the non-live object occlusion region.

[0041] S130. Based on the recognition result, determine whether there is visual interference in the weighing behavior.

[0042] Based on information such as the type, area, and location of the obstruction, the intelligent weighing interference recognition system can determine whether visual interference exists during weighing, affecting the normal identification of the weighed item. Since multiple images of the target area may exist within a target time period, the system can also determine the presence of visual interference based on the proportion of recognition results for each target area image within that time period. For example, if the number of target area images with the same recognition result exceeds 50% of the total number of images within the target time period, then visual interference is determined to exist. If 10 target area images are generated within the target time period, and one of these images shows a living obstruction affecting item identification, then visual interference cannot be considered to exist during the weighing process.

[0043] This technical solution uses liveness detection results to determine the recognition intent of the target area image, obtains the recognition result, and then determines whether there is visual interference in the weighing process based on the recognition result. This solution can solve the problem of low accuracy in interference recognition for smart scales, improving the accuracy of interference recognition while providing customers with a better shopping experience and saving labor costs for merchants.

[0044] Example 2

[0045] Figure 2AThis is a flowchart of an interference identification method for a smart scale provided in Embodiment 2 of the present invention. This embodiment is a refinement based on the above embodiment. Figure 2A As shown, the method includes:

[0046] S210. If weighing behavior is detected, the target area image and liveness detection result within the target time period are obtained; wherein, the target time period starts from the moment when the weighing data changes and ends when the weighing data stabilizes.

[0047] S220. Determine whether the liveness detection result indicates that there is liveness occlusion.

[0048] In this scheme, the liveness detection result is divided into two cases: liveness occlusion and no liveness occlusion. If the liveness detection result indicates that liveness occlusion exists, then S230 is executed; if the liveness detection result indicates that liveness occlusion does not exist, then S250 is executed.

[0049] S230. Based on the target area image, determine whether the live occlusion area affects object recognition.

[0050] The intelligent scale interference recognition system can utilize an image detection model to detect the location and area of ​​live occluders in a target area image. Then, based on the location and area of ​​the live occluder, it determines whether the occluded area affects object recognition. For example, if the live occluder is located in the center of the target area image and its area exceeds 50% of the target area image area, it can be considered that the live occluder affects object recognition. To more accurately determine the location and area of ​​the live occluder, the intelligent scale interference recognition system can also employ an image segmentation model to more precisely mark the boundaries of the live occluder. Then, based on the area covered within the boundaries of the live occluder, it determines whether the live occluder affects object recognition. The image detection model and the image segmentation model can be implemented based on traditional graphics algorithms, deep learning algorithms, or a combination of both.

[0051] It should be noted that after confirming that a live object is obstructing the weighing process, the intelligent weighing interference recognition system can further determine whether there is non-live object obstructing the weighing process, in order to overcome the problem of multiple types of obstruction during the weighing process.

[0052] S240. If the live occlusion area affects object recognition, then it is determined that the weighing behavior is subject to visual interference.

[0053] S250. Based on the target area image, determine whether there is any non-living object obstructing the weighing process.

[0054] The intelligent weighing interference recognition system, assuming no live occlusion, can further determine whether non-live occlusion exists in the target area image using an image classification model. Similar to image detection and segmentation models, the image classification model can be implemented based on traditional graphics algorithms, deep learning algorithms, or a combination of both. The image classification model can be pre-trained to learn the normal items to be identified, such as all goods within the supermarket's operating area. When the image classification model cannot classify the target area image, the unidentified object is a non-live occluder. The intelligent weighing interference recognition system can also identify all objects using the image classification model. When a non-live occluder is detected, it can be classified normally, and then the classification result is compared with the list of items to be weighed. If the classification result does not correspond to any item in the list, it indicates that the object is a non-live occluder.

[0055] S260. If there is non-living object occlusion during the weighing process, determine whether the non-living object occlusion area affects object recognition.

[0056] Furthermore, the intelligent interference recognition system can also use image detection models or image segmentation models to determine whether non-living occlusion areas affect object recognition. It should be noted that the recognition of non-living and living occlusions can be achieved using the same image detection model or image segmentation model, or different image detection models or image segmentation models.

[0057] S270. If the non-living occlusion area affects object recognition, then it is determined that the weighing behavior is subject to visual interference.

[0058] Optionally, in this scheme, after detecting the weighing action, the method further includes:

[0059] Acquire the weighing data of the smart scale within the target time period, and determine the anomaly judgment result of the weighing data;

[0060] Based on the anomaly judgment result, combined with the liveness detection result or the identification result, it is determined whether the weighing behavior is subject to weighing interference.

[0061] The weighing data can be a weighing curve. The intelligent weighing interference identification system can determine whether the weighing curve is abnormal based on the comparison result between the weighing curve and the preset standard weight change rules. The standard weight change rules can include two items: (1) the number of times the shaking phenomenon occurs is lower than the preset number threshold; (2) the duration of the stabilization process is within the preset stabilization duration range. Figure 2B This is a schematic diagram comparing normal and abnormal weighing curves according to Embodiment 2 of the present invention, as shown in the figure. Figure 2BA normal weighing curve has a stabilization time of 600ms, characterized by a smooth surface and rapid weight stabilization. A curve with a stabilization time of 1200ms is considered abnormal, exhibiting multiple fluctuations on its surface, potentially caused by malicious lifting during weighing. Furthermore, abnormal weighing curves show a slower weight stabilization rate. Therefore, if the number of fluctuations in the weighing curve exceeds a preset threshold, or if the stabilization time of the weight change curve is outside the preset stabilization time range, the weighing curve is determined to be abnormal.

[0062] The weighing data can also be a weighing vector. The intelligent weighing interference identification system can use a classification model to classify the weighing vectors and determine whether they are abnormal weighing vectors. Alternatively, the intelligent weighing interference identification system can use a similarity calculation model to calculate the similarity between the weighing vector and a preset standard weighing vector, and then compare the calculated similarity with a similarity threshold to obtain the final anomaly judgment result.

[0063] Intelligent weighing interference identification systems can determine whether cheating or other weighing interference is occurring based on anomaly detection results. However, relying on single weighing data can easily lead to misjudgments of weighing interference. To increase the reliability of weighing interference detection, intelligent weighing interference identification systems can combine liveness detection results or recognition results. On the one hand, this multi-dimensional information enables more accurate weighing interference detection; on the other hand, it can also correct the causes of weighing interference, thus preventing its occurrence.

[0064] This solution can reliably identify weighing interference, which helps create a fair and just weighing environment, avoiding losses for merchants while providing customers with a good shopping experience.

[0065] In one feasible solution, determining whether there is weighing interference in the weighing behavior based on the anomaly judgment result, combined with the liveness detection result or the identification result, includes:

[0066] If the weighing data is abnormal, and the liveness detection result indicates the presence of a live occlusion, then it is determined that the weighing behavior is subject to weighing interference; wherein, the weighing interference is liveness interference.

[0067] If the weighing data is abnormal, and the identification result indicates that there is non-living body obstruction during the weighing process, then it is determined that the weighing behavior is subject to weighing interference; wherein, the weighing interference is non-living body interference.

[0068] It should be noted that if the weighing data is abnormal, the liveness detection result indicates the presence of a live object occlusion, and the identification result indicates the presence of a non-live object occlusion during the weighing process, then it indicates that there are multiple interferences in the weighing behavior.

[0069] This solution can reliably identify and correct weighing interference, minimizing economic losses for businesses.

[0070] In another feasible approach, after determining that visual interference exists in the weighing process, the method further includes:

[0071] If the weighing process is visually disruptive, and the occlusion area affects object recognition, the user is prompted to remove the occlusion.

[0072] After determining that visual interference exists during the weighing process, the intelligent scale interference recognition system can determine whether the visual interference is caused by a living object or a non-living object based on the recognition results of the target area image. If it is caused by a living object, such as a human hand, the intelligent scale interference recognition system can prompt the user to remove the living object to achieve item recognition.

[0073] This solution can alert users based on the cause of visual interference, which helps to eliminate obstructions in a timely manner, achieve reliable and accurate item recognition, and thus avoid economic losses caused by misidentifying items as belonging to merchants.

[0074] In a preferred embodiment, after determining that visual interference exists in the weighing process, the method further includes:

[0075] If the weighing process is subject to visual interference, and the non-living occlusion area affects object recognition, then the category and location information of the non-living occlusion are determined by a pre-trained non-living occlusion detection model.

[0076] Based on the category information and the location information, the user is prompted to remove the non-living obstruction.

[0077] If visual interference is caused by a non-living object, such as a plastic bag, the intelligent scale interference recognition system can use a non-living object detection model to determine the category and location of the object. This non-living object detection model can be a pre-trained image detection model specifically designed for non-living objects. Based on the category and location information, the intelligent scale interference recognition system can generate a prompt voice to guide the user in eliminating visual interference caused by the non-living object, such as, "Dear customer, weighing failed. Please open the plastic bag in the center of the scale for accurate product identification. Thank you!"

[0078] This solution utilizes a non-living occlusion detection model to determine the category and location information of non-living occlusions, which helps to accurately describe non-living occlusions to users, thereby eliminating visual interference from non-living occlusions in a timely manner and achieving accurate object identification.

[0079] This technical solution uses liveness detection results to determine the recognition intent of the target area image, obtains the recognition result, and then determines whether there is visual interference in the weighing process based on the recognition result. This solution can solve the problem of low accuracy in interference recognition for smart scales, improving the accuracy of interference recognition while providing customers with a better shopping experience and saving labor costs for merchants.

[0080] Example 3

[0081] Figure 3 This is a schematic diagram of the structure of an intelligent scale interference identification device provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes:

[0082] The image and detection result acquisition module 310 is used to acquire the target area image and the liveness detection result within the target time period if a weighing behavior is detected; wherein, the target time period starts from the moment when the weighing data changes and ends when the weighing data stabilizes.

[0083] The recognition result generation module 320 is used to determine the recognition intent of the target region image based on the liveness detection result, and to perform recognition according to the recognition intent to obtain the recognition result;

[0084] The visual interference determination module 330 is used to determine whether visual interference exists in the weighing behavior based on the recognition result.

[0085] In one feasible solution, optionally, the recognition result generation module 320 includes:

[0086] An object recognition determination unit is used to determine whether the occlusion area affects object recognition based on the target area image if the liveness detection result indicates that there is liveness occlusion.

[0087] Accordingly, the visual interference determination module 330 includes:

[0088] A live visual interference determination unit is used to determine that visual interference exists in the weighing behavior if the live occlusion area affects object recognition.

[0089] In another feasible solution, optionally, the recognition result generation module 320 includes:

[0090] The non-living occlusion determination unit is used to determine whether there is non-living occlusion during the weighing process based on the target area image if the liveness detection result is that there is no liveness occlusion.

[0091] Accordingly, the visual interference determination module 330 includes:

[0092] The non-living object affecting object recognition determination unit determines whether the non-living object occlusion area affects object recognition if there is non-living object occlusion during the weighing process.

[0093] The non-living visual interference determination unit determines that the weighing behavior is subject to visual interference if the non-living occlusion area affects object recognition.

[0094] Based on the above solution, optionally, the device further includes:

[0095] The anomaly judgment result determination module is used to acquire the weighing data of the smart scale within the target time period and determine the anomaly judgment result of the weighing data.

[0096] The weighing interference determination module is used to determine whether there is weighing interference in the weighing behavior based on the anomaly judgment result, combined with the liveness detection result or the identification result.

[0097] In this solution, optionally, the weighing interference determination module is specifically used for:

[0098] If the weighing data is abnormal, and the liveness detection result indicates the presence of a live occlusion, then it is determined that the weighing behavior is subject to weighing interference; wherein, the weighing interference is liveness interference.

[0099] If the weighing data is abnormal, and the identification result indicates that there is non-living body obstruction during the weighing process, then it is determined that the weighing behavior is subject to weighing interference; wherein, the weighing interference is non-living body interference.

[0100] Optionally, the device further includes:

[0101] The "Live Obstruction Removal Prompt" module is used to prompt the user to remove the live obstruction if the weighing process is visually disruptive and the live obstruction area affects object recognition.

[0102] In a preferred embodiment, the device further includes:

[0103] The non-living occlusion information determination module is used to determine the category and location information of the non-living occlusion object by using a pre-trained non-living occlusion object detection model if the weighing behavior is subject to visual interference and the non-living occlusion area affects object recognition.

[0104] The non-living obstruction removal prompt module is used to prompt the user to remove the non-living obstruction based on the category information and the location information.

[0105] The smart scale interference identification device provided in this embodiment of the invention can execute the smart scale interference identification method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0106] Example 4

[0107] Figure 4 A schematic diagram of a smart scale interference detection system 410, which can be used to implement embodiments of the present invention, is shown. The smart scale interference detection system is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The smart scale interference detection system can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0108] like Figure 4 As shown, the intelligent scale interference identification system 410 includes at least one processor 411, a liveness detection device 416, an image acquisition device 417, a weighing data acquisition device 418, and a memory, such as a read-only memory (ROM) 412 or a random access memory (RAM) 413, communicatively connected to the at least one processor 411. The memory stores computer programs executable by the at least one processor. The processor 411 can perform various appropriate actions and processes based on the computer program stored in the ROM 412 or loaded from storage unit 421 into the RAM 413. The RAM 413 can also store various programs and data required for the operation of the intelligent scale interference identification system 410. The processor 411, ROM 412, and RAM 413 are interconnected via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.

[0109] Multiple components in the intelligent scale interference identification system 410 are connected to the I / O interface 415, including: a liveness detection device 416 for detecting the presence of a live object obstructing the target area, such as an infrared liveness detector; an image acquisition device 417 for acquiring images of the target area, such as a visible light camera; a weighing data acquisition device 418 for acquiring weighing data from the intelligent scale, such as an intelligent scale weighing sensor; an input unit 419, such as a keyboard or mouse; an output unit 420, such as various types of displays or speakers; a storage unit 421, such as a hard disk or optical disk; and a communication unit 422, such as a network card, modem, or wireless transceiver. The communication unit 422 allows the intelligent scale interference identification system 410 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0110] Processor 411 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 411 performs the various methods and processes described above, such as the interference identification method for smart scales.

[0111] In some embodiments, the smart scale interference identification method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 421. In some embodiments, part or all of the computer program may be loaded and / or installed on the smart scale interference identification system 410 via ROM 412 and / or communication unit 422. When the computer program is loaded into RAM 413 and executed by processor 411, one or more steps of the smart scale interference identification method described above may be performed. Alternatively, in other embodiments, processor 411 may be configured to perform the smart scale interference identification method by any other suitable means (e.g., by means of firmware).

[0112] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0113] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0114] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0115] To provide user interaction, the systems and techniques described herein can be implemented on a smart scale interference detection system, which includes: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the smart scale interference detection system. Other types of devices can also be used to provide user interaction; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0116] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0117] A computing system can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is established by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosting and VPS services, such as high management difficulty and weak business scalability.

[0118] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0119] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for identifying interference in a smart scale, characterized in that, The method includes: If weighing activity is detected, the target area image and liveness detection results within the target time period are acquired; wherein, the target time period starts from the moment the weighing data changes and ends when the weighing data stabilizes; the liveness detection results are determined based on the duration of liveness within the target time period, or based on the number of times liveness occurs within the target time period; If the liveness detection result indicates the presence of a live occlusion, then based on the target area image, it is determined whether the live occlusion area affects object recognition; if the liveness detection result indicates the absence of a live occlusion, then based on the target area image, it is determined whether there is a non-live occlusion during the weighing process. If the live occlusion area affects object recognition, then the weighing behavior is determined to have visual interference; if there is non-live occlusion during the weighing process, then it is determined whether the non-live occlusion area affects object recognition; if the non-live occlusion area affects object recognition, then the weighing behavior is determined to have visual interference. The method further includes, after detecting the weighing action: Acquire the weighing data of the smart scale within the target time period, and determine the anomaly judgment result of the weighing data; If the weighing data is abnormal, and the liveness detection result indicates the presence of a live occlusion, then it is determined that the weighing behavior is subject to weighing interference; wherein, the weighing interference is liveness interference. If the weighing data is abnormal, and the identification result indicates that there is non-living body obstruction during the weighing process, then it is determined that the weighing behavior is subject to weighing interference; wherein, the weighing interference is non-living body interference.

2. The method according to claim 1, characterized in that, After determining that visual interference exists in the weighing process, the method further includes: If the weighing process is visually disruptive, and the occlusion area affects object recognition, the user is prompted to remove the occlusion.

3. The method according to claim 1, characterized in that, After determining that visual interference exists in the weighing process, the method further includes: If the weighing process is visually disturbed, and the non-living occlusion area affects object recognition, then the category and location information of the non-living occlusion are determined by a pre-trained non-living occlusion detection model. Based on the category information and the location information, the user is prompted to remove the non-living obstruction.

4. An interference identification device for intelligent scales, characterized in that, include: The image and detection result acquisition module is used to acquire images of the target area and liveness detection results within a target time period if weighing behavior is detected; wherein, the target time period starts from the moment when the weighing data changes and ends when the weighing data stabilizes; the liveness detection results are determined based on the duration of liveness within the target time period, or based on the number of times liveness occurs within the target time period; The recognition result generation module is used to determine whether the occlusion area affects object recognition based on the target area image if the liveness detection result indicates that there is liveness occlusion; and to determine whether there is non-liveness occlusion during the weighing process based on the target area image if the liveness detection result indicates that there is no liveness occlusion. The visual interference determination module is used to determine that the weighing behavior has visual interference if the live occlusion area affects object recognition; if there is non-live occlusion during the weighing process, it determines whether the non-live occlusion area affects object recognition; if the non-live occlusion area affects object recognition, it determines that the weighing behavior has visual interference. The anomaly judgment result determination module is used to acquire the weighing data of the smart scale within the target time period and determine the anomaly judgment result of the weighing data; The weighing interference determination module is used to determine that the weighing behavior is subject to weighing interference if the weighing data is abnormal and the liveness detection result indicates that there is liveness occlusion; wherein the weighing interference is liveness interference; and if the weighing data is abnormal and the identification result indicates that there is non-liveness occlusion during the weighing process, the module determines that the weighing behavior is subject to weighing interference; wherein the weighing interference is non-liveness interference.

5. An intelligent scale interference identification system, characterized in that, The system includes: a liveness detection device, an image acquisition device, a weighing data acquisition device, at least one processor, and a memory; The liveness detection device, image acquisition device, and weighing data acquisition device are all communicatively connected to the processor, and the processor is communicatively connected to the memory. The liveness detection device is used to detect whether there is a live person obstructing the target area; The image acquisition device is used to acquire images of the target area; The weighing data acquisition device is used to collect weighing data from the smart scale; The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the intelligent scale interference identification method according to any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the intelligent scale interference identification method according to any one of claims 1-3.

Images