Self-service cashier loss prevention behavior monitoring method, monitoring system, medium and product

Abstract

The invention relates to the technical field of behavior monitoring, in particular to a self-service cashier loss prevention behavior monitoring method and system, a medium and a product, and the method comprises the steps: obtaining a cashier desk image, carrying out the feature recognition of the cashier desk image, and judging whether the cashier desk image contains a preset abnormal identifier or not; when the cashier desk image contains a preset abnormal identifier, abnormal feature recognition is carried out on the cashier desk image to determine the abnormal type of the abnormal commodity, and the abnormal type comprises wrong scanning, scale missing and scanning missing; prompt information and lighting alarm information are determined based on the abnormal type, the prompt information is displayed on the operation interface, and the prompt information comprises correction scanning video or scanning guiding voice; and generating an inspection request instruction based on the prompt information and the lighting alarm information, and feeding back the inspection request instruction to the terminal equipment of the loss prevention personnel. According to the invention, abnormal behaviors existing in the self-service cashier process can be found in time, and timely and effective response can be realized.

Description

Technical Field

[0001] The present application relates to the field of behavior monitoring technology, and in particular to a self-service checkout loss prevention behavior monitoring method, monitoring system, medium and product. Background Art

[0002] With the rapid development of electronic technology and consumers' increasing requirements for shopping experience, electronic cash registers have emerged and gradually replaced traditional cash registers. Self-service cash registers can provide faster and more flexible checkout methods, so as to reduce consumers' waiting time at the checkout stage and improve consumers' shopping experience. Although the use of self-service cash register systems is convenient for improving checkout efficiency, its inherent loss prevention problems are also becoming increasingly prominent, especially abnormal behaviors such as missed scanning, missed weighing, and wrong scanning, which will not only cause commodity losses, but may also affect consumers' shopping satisfaction and merchants' operating efficiency. Therefore, it is particularly important to monitor loss prevention behaviors during the self-service cash register process.

[0003] In the related art, manual patrol is generally used to monitor or intervene in abnormal behaviors that occur during self-service checkout. However, due to the subjectivity and fatigue of manual monitoring, it is difficult to maintain high concentration and vigilance for a long time. Therefore, it is difficult to detect and respond to abnormal behaviors in a timely manner during the monitoring process. Summary of the invention

[0004] In order to facilitate timely detection of abnormal behaviors in the self-service checkout process and timely and effective response, the embodiments of the present application provide a self-service checkout loss prevention behavior monitoring method, monitoring system, medium and product.

[0005] In the first aspect, the present application provides a self-service checkout loss prevention behavior monitoring method, which adopts the following technical solution: A self-service cashier loss prevention behavior monitoring method, comprising: Acquire a cashier counter image, perform feature recognition on the cashier counter image, and determine whether the cashier counter image contains a preset abnormal mark; When the cashier image contains the preset abnormal identification, the cashier image is subjected to abnormal feature recognition to determine the abnormal type of the abnormal commodity, wherein the abnormal type includes wrong scanning, missed weighing and missed scanning; Determine prompt information and light-on warning information based on the abnormality type, and display the prompt information on the operation interface, the prompt information including a correction scanning video or a scanning guidance voice; An inspection request instruction is generated based on the prompt information and the light-on alarm information, and the inspection request instruction is fed back to the terminal device of the loss prevention personnel.

[0006] By adopting the above technical solution, when a preset abnormal mark is detected in the cash register image, the cash register image is analyzed and viewed in time, and processing measures are fed back based on the analysis results, so as to improve the abnormal response rate in the process of monitoring loss prevention behavior. In addition, when determining the feedback processing measures, personalized feedback is provided based on the abnormal type corresponding to the abnormal situation, so as to improve the accuracy of responding to the abnormality, thereby facilitating the improvement of the rate of eliminating the abnormality.

[0007] In a possible implementation, when the abnormality type is a wrong scan, determining prompt information based on the abnormality type includes: Determining an abnormally entered commodity code based on the entered commodity order information, wherein the entered commodity order information is commodity information that has been entered at the cashier counter, and the abnormally entered commodity code is a commodity code corresponding to the abnormal commodity; Acquire a real-time image of the storage platform, and when the real-time image of the storage platform contains the abnormal commodity, identify edge information of the abnormal commodity from the real-time image of the storage platform, and mark the abnormal commodity based on the edge information of the abnormal commodity to obtain an abnormal marking image; Acquire a loading platform image corresponding to the abnormal time, and when the loading platform image corresponding to the abnormal time includes a newly added commodity, identify edge information of the newly added commodity from the loading platform image corresponding to the abnormal time, and mark the newly added commodity based on the edge information of the newly added commodity to obtain a newly added mark image, wherein the abnormal time is the time when the abnormal input commodity code is determined from the input commodity order information; The prompt information is determined based on the preset guidance mark, the abnormal mark image and the newly added mark image.

[0008] By adopting the above technical solution, when the abnormal type is wrong scanning, by analyzing the real-time image of the storage table and the image of the loading table, it is convenient to determine the abnormal goods in the storage table and the new goods in the loading table. When a wrong scanning occurs, it is not just a simple voice prompt to the consumer, but the exchange prompt is given after the goods that need to be exchanged are identified, which is convenient for improving the accuracy of the consumer's exchange operation and the consumer's shopping experience. In addition, by marking the goods that need to be exchanged and feeding back the prompt information generated after marking to the consumer, it is convenient for the consumer to determine the goods that need to be exchanged from multiple goods, which is convenient for improving the accuracy of the exchange process.

[0009] In one possible implementation, the method further includes: Obtaining the product pick-up time, where the product pick-up time is the time when the consumer picks up the newly added product from the loading platform; If the product is picked up at a first preset time period, and the newly added product is located on the storage table within a second preset time period, then the anomaly is eliminated; If the product picking-up time is not within the first preset time period, the abnormal product code is removed from the input product order information.

[0010] By adopting the above technical solution, by setting a time limit for consumers to exchange goods according to the prompt information, that is, once it is detected that the consumer has completed the exchange of goods within the specified time, the normal state can be restored immediately, which is convenient for improving the degree of automation in the process of responding to abnormalities and reducing manual intervention. After eliminating the abnormality, consumers can continue the shopping or settlement process without waiting for relevant staff to manually eliminate the abnormality after the abnormality occurs before settling, which is convenient for improving the overall consumer experience.

[0011] In a possible implementation, when the abnormality type is a missed scale, determining the prompt information based on the abnormality type includes: Obtain the abnormal input image and the missed weighing prompt corresponding to the missed weighing behavior; Generate a missed weighing prompt message based on the abnormal input image corresponding to the missed weighing behavior and the missed weighing prompt message; The missed scale prompt information is fed back to the cashier display interface and the terminal device carried by relevant loss prevention personnel.

[0012] By adopting the above technical solution, by obtaining the abnormal input image and the missing scale prompt corresponding to the missed scale behavior, and generating the missed scale prompt information in real time, it is convenient to ensure a quick response when the missed scale behavior occurs, which helps to reduce the economic losses caused by the missed scale. In addition, by feeding back the abnormal input image and the missing scale prompt when the missed scale behavior occurs to consumers and loss prevention personnel, it is convenient to increase consumers' attention to abnormal situations, and it is also convenient for relevant loss prevention personnel to quickly understand the abnormal situation and deal with the missed scale problem in time.

[0013] In a possible implementation, when the abnormality type is scan miss, the prompt information is determined based on the abnormality type, including: Obtain the abnormal input image and missed scan prompt corresponding to the missed scan behavior; Generate missed scanning prompt information based on the abnormal input image corresponding to the missed scanning behavior and the missed scanning prompt; The missed scan prompt information is fed back to the cashier display interface and the terminal device carried by the relevant loss prevention personnel.

[0014] By adopting the above technical solution, by obtaining the abnormal input image and the missed scanning prompt corresponding to the missed scanning behavior, and generating the missed scanning prompt information in real time, it is convenient to ensure a quick response when the missed scanning behavior occurs, which helps to reduce the economic losses caused by the missed scanning. In addition, by feeding back the abnormal input image and the missed scanning prompt when the missed scanning behavior occurs to the consumer, it is convenient to remind the consumer to make corrections. At the same time, the generated missed scanning prompt information can also be fed back to the relevant loss prevention personnel, so that the relevant loss prevention personnel can quickly understand the abnormal situation and deal with the missed scanning problem in time.

[0015] In one possible implementation, the method further includes: Identify the correction behavior identifier contained in the prompt information corresponding to each inspection request instruction, and determine the correction difficulty score corresponding to each correction behavior identifier based on the behavior score mapping relationship, wherein the behavior score mapping relationship is the correspondence between the correction behavior identifier and the correction difficulty score; Obtaining execution information corresponding to each inspection request instruction, and determining an execution score corresponding to each execution information based on a mapping relationship between the execution information and the execution score, wherein the execution information includes a corrective behavior response time and a success rate when the corresponding consumer corrects according to the prompt information corresponding to the inspection request instruction, and the execution score mapping relationship is a corresponding relationship between the corrective behavior response time and the success rate and the execution score; Based on the correction difficulty score and execution score corresponding to each inspection request instruction, the execution position of the corresponding inspection request instruction in the execution queue is adjusted. The execution queue contains multiple inspection request instructions, and each inspection request instruction is sorted according to the corresponding generation time.

[0016] By adopting the above technical solution, by analyzing the correction behavior identifier contained in each inspection request instruction, it is convenient to understand the difficulty of correction of each inspection request instruction. In addition, by analyzing the execution status of consumers and quantifying the execution status of each consumer on the inspection request instruction, it is convenient to understand the execution status of each inspection request instruction. Finally, according to the correction difficulty score and execution score corresponding to each inspection request instruction, the execution queue is adjusted in real time, that is, different inspection request instructions are sorted in real time, so as to ensure that inspection request instructions with higher difficulty or lower execution efficiency are given priority.

[0017] In one possible implementation, the method further includes: When it is detected that the scan list has not been updated within a third preset time period, acquiring a cashier counter image and identifying consumer behavior from the cashier counter image; When the consumer behavior is a preset behavior, identifying the logo of the commodity to be scanned from the cash register image; Demonstration information is determined based on the identification of the commodity to be scanned, and the demonstration information is displayed on the operation interface.

[0018] By adopting the above technical solution, by checking and analyzing the update status of the scanned list, it is convenient to timely discover the help that consumers may need, and by actively identifying and responding to consumers' needs, relevant demonstration information is provided in time to help consumers solve problems, thereby facilitating enhancing consumers' satisfaction during the shopping process.

[0019] In a second aspect, the present application provides a monitoring system, which adopts the following technical solution: A monitoring system, comprising: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the above-mentioned self-service checkout loss prevention behavior monitoring method.

[0020] In a third aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium includes: a computer program that can be loaded by a processor and execute the self-service checkout loss prevention behavior monitoring method.

[0021] In a fourth aspect, the present application provides a computer program product, which adopts the following technical solution: A computer program product includes a computer program, and when the computer program is executed by a processor, the self-service checkout loss prevention behavior monitoring method is implemented.

[0022] In summary, the present application includes at least one of the following beneficial technical effects: By timely analyzing and checking the cash register image when the preset abnormal mark is detected in the cash register image, and providing feedback on the processing measures based on the analysis results, it is convenient to improve the abnormal response rate in the process of monitoring loss prevention behavior. In addition, when determining the feedback processing measures, personalized feedback is provided based on the abnormal type corresponding to the abnormal situation, so as to improve the accuracy of responding to the abnormality, thereby facilitating the improvement of the rate of eliminating the abnormality.

[0023] By analyzing the corrective behavior identifier contained in each inspection request instruction, it is convenient to understand the difficulty of correction of each inspection request instruction. In addition, by analyzing the execution status of consumers and quantitatively evaluating the execution status of each consumer on the inspection request instruction, it is convenient to understand the execution status of each inspection request instruction. Finally, according to the correction difficulty score and execution score corresponding to each inspection request instruction, the execution queue is adjusted in real time, that is, different inspection request instructions are sorted in real time, so as to ensure that inspection request instructions with higher difficulty or lower execution efficiency are given priority. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a flow chart of a self-service checkout loss prevention behavior monitoring method in an embodiment of the present application; Figure 2 It is a schematic diagram of a flow chart of adjusting the execution position in an embodiment of the present application; Figure 3 It is a structural schematic diagram of a monitoring system in an embodiment of the present application. DETAILED DESCRIPTION

[0025] The following is combined with Figure 1-3 This application is described in further detail.

[0026] After reading this specification, those skilled in the art may make non-creative modifications to this embodiment as needed, but such modifications are protected by patent law as long as they are within the scope of the claims of this application.

[0027] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0028] It should be noted that in the optional embodiments of the present application, the object information and other related data involved, when the embodiments in the present application are applied to specific products or technologies, need to obtain the permission or consent of the object, and the collection, use and processing of the relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions. In other words, if the embodiments of the present application involve data related to the object, it needs to be obtained with the authorization and consent of the object, the authorization and consent of the relevant departments, and in compliance with the relevant laws, regulations and standards of the country and region. If personal information is involved in the embodiments, the acquisition of all personal information needs to obtain the consent of the individual. If sensitive information is involved, the separate consent of the information subject needs to be obtained. The embodiments also need to be implemented with the authorization and consent of the object.

[0029] Specifically, the embodiment of the present application provides a self-service cashier loss prevention behavior monitoring method, which is executed by a monitoring system, and the monitoring system can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited to this. The terminal device and the server can be directly or indirectly connected through wired or wireless communication, and the embodiment of the present application does not limit this.

[0030] refer to Figure 1 , Figure 1 : is a flow chart of a self-service checkout loss prevention behavior monitoring method in an embodiment of the present application, the method comprises steps S110 to S140, wherein: Step S110: Acquire a cashier counter image, perform feature recognition on the cashier counter image, and determine whether the cashier counter image contains a preset abnormal mark.

[0031] Specifically, the cashier counter image can be collected by an image acquisition device installed near the cashier counter and then uploaded to the monitoring system. The preset abnormal flag can be a flashing warning light or a pop-up window on the display interface, etc. The specific preset abnormal flag is not specifically limited in the embodiment of the present application. When it is detected that the cashier counter image contains a preset abnormal flag, it indicates that there may be an abnormality in the self-service checkout process. The monitoring system can perform a pre-analysis of the cashier counter image based on the preset abnormal behavior. When the cashier counter image contains the preset abnormal behavior, abnormal feedback can be provided through the flashing warning light or the pop-up window on the display interface, etc. At this time, the cashier counter image needs to be further checked and analyzed to determine the cause of the abnormal situation. Among them, the preset abnormal behavior can be determined by the relevant staff based on the historical abnormal data and uploaded to the monitoring system. The specific abnormal behavior is not specifically limited in the embodiment of the present application.

[0032] In addition, abnormal feedback can also be made through weighing log data, wherein the weighing log data contains all the commodity information placed on the loading platform by all consumers during the self-service settlement process at the cash register, including the weighing date, commodity weight, etc. The cash register generally includes a storage platform and a loading platform, wherein the storage platform is provided with a commodity scanning device for quickly identifying and entering commodity information, and the commodity scanning device can generally be a barcode scanner or an RFID reader, etc. The specific commodity scanning device is not specifically limited in the embodiment of the present application, as long as it can enter commodity information. The scanned goods can be placed on the loading platform, and the loading platform is provided with an induction scale to sense the weight of the goods placed on the loading platform. After the consumer has scanned all the goods, all the goods can be packaged from the loading platform. During the process of the consumer scanning the goods, the weighing log data will determine whether there is an abnormality in the goods placed on the loading platform according to the scanning results. Once it is found that the scanning result is inconsistent with the weight of the goods placed on the loading platform, it can be determined that there is abnormal weighing data. At this time, abnormal feedback can be made, and the cash register image needs to be further viewed and analyzed to determine the cause of the abnormal weighing data.

[0033] Step S120: When the cash register image contains a preset abnormal mark, abnormal feature recognition is performed on the cash register image to determine the abnormal type of the abnormal commodity, and the abnormal type includes wrong scanning, missed weighing and missed scanning.

[0034] Specifically, the abnormal types include wrong scanning, missed weighing and missed scanning. Among them, wrong scanning means that when the consumer scans the product code of other products by mistake, resulting in the recording of incorrect product information. For example, the consumer successfully scans the product code corresponding to product a, but places product b on the loading table; missed weighing means that the consumer does not weigh the products that need to be weighed during the self-service checkout process, so the products are not added to the entered product order information. For example, product a is a weighing product, but the consumer places product a on the loading table without weighing and entering product a; missed scanning means that the consumer fails to successfully scan the product code of the product during the self-service checkout process, resulting in the product not being added to the entered product order information. For example, the consumer does not scan the product code corresponding to product a, or fails to successfully scan the product code corresponding to product a, and places product a on the loading table.

[0035] There are many reasons for abnormal weighing data. For example, it may be improper operation by consumers or equipment failure, or it may be intentional behavior. Once wrong scanning, missed scales, and missed scanning occur during the self-service checkout process, it may not only cause loss of goods, but also affect consumers' shopping experience and merchants' operating efficiency. Therefore, it is necessary to analyze and handle abnormal situations in a timely manner.

[0036] Step S130: Determine prompt information and light-on alarm information based on the abnormality type, and display the prompt information on the operation interface, the prompt information including a corrected scanning video or a scanning guidance voice.

[0037] Specifically, different abnormality types correspond to different prompt information. Based on the abnormality type, the corresponding prompt information can be called from the monitoring system to provide feedback to consumers. The prompt information corresponding to different abnormality types can be determined by relevant staff according to historical processing data and then uploaded to the monitoring system. The specific content is set in the embodiment of the present application. The prompt information can be a light warning and a voice prompt, that is, different alarm lights and different voice prompt contents are set for different abnormality types. For example, when the abnormality type is wrong scanning, the alarm light can be set to green, and the prompt is "The product you scanned does not match the product placed on the loading platform. Please check whether the product code of other products has been scanned by mistake, and ensure that the scanned product is consistent with the product placed on the loading platform"; when the abnormality type is missed scale, the alarm light can be set to yellow, and the prompt is "The product you scanned has not been weighed, please weigh the product"; when the abnormality type is missed scanning, the alarm light can be set to red, and the prompt voice is "Please note that some of your products have not been scanned. Please make sure that the product code of each product is correctly aligned with the scanning window to avoid missed scanning."

[0038] When the checkout counter is equipped with a display interface, the prompt information may include a correction scanning video in addition to the scanning guidance voice. The correction scanning video includes specific scenarios of wrong scanning, missed weighing and missed scanning, and is accompanied by the correct operating procedures for handling these abnormal situations, so as to guide consumers to correct the abnormal situations in a timely manner.

[0039] Step S140: Generate an inspection request instruction based on the prompt information and the light alarm information, and feed back the inspection request instruction to the terminal device of the loss prevention personnel.

[0040] Specifically, while providing prompt information to the consumer, an inspection request instruction can also be generated and sent to the terminal device carried by the relevant loss prevention personnel to remind the relevant loss prevention personnel to resolve the anomaly for the consumer. The terminal device carried by the loss prevention personnel can be a smart bracelet or a handheld terminal. In order to facilitate the relevant loss prevention personnel to promptly discover the inspection request instruction sent to the terminal device, the relevant loss prevention personnel can also be reminded by vibration or prompt sound while sending the inspection request instruction.

[0041] For the embodiment of the present application, when a preset abnormal mark is detected in the cash register image, the cash register image is analyzed and viewed in a timely manner, and processing measures are fed back based on the analysis results, so as to improve the abnormal response rate in the process of monitoring loss prevention behavior. In addition, when determining the feedback processing measures, personalized feedback is provided based on the abnormal type corresponding to the abnormal situation, so as to improve the accuracy of responding to the abnormality, thereby facilitating the improvement of the rate of eliminating the abnormality.

[0042] Furthermore, when the abnormality type is wrong scanning, the prompt information is determined based on the abnormality type, which may specifically include: Determine the abnormally entered product code based on the entered product order information, where the entered product order information is the product information that has been entered at the checkout counter, and the abnormally entered product code is the product code corresponding to the abnormal product; obtain the real-time image of the storage table, and when the real-time image of the storage table contains abnormal products, identify the edge information of the abnormal products from the real-time image of the storage table, and mark the abnormal products based on the edge information of the abnormal products to obtain an abnormal identification image; obtain the loading platform image corresponding to the abnormal moment, and when the loading platform image corresponding to the abnormal moment contains newly added products, identify the edge information of the newly added products from the loading platform image corresponding to the abnormal moment, and mark the newly added products based on the edge information of the newly added products to obtain a newly added identification image, where the abnormal moment is the moment when the abnormally entered product code is determined from the entered product order information; determine the prompt information based on the preset guidance mark, the abnormal identification image and the newly added identification image.

[0043] Specifically, the input commodity order information is the commodity information that has been completed, including scanning input and weighing input, wherein the abnormal input commodity code is the commodity code corresponding to the abnormal commodity. Once it is found that the newly input content in the input commodity order information is inconsistent with the commodity placed on the loading platform, it can be determined that there is an abnormal situation. When the real-time image of the loading platform contains abnormal commodities, and there are new commodities in the loading platform corresponding to the abnormal moment, it can be determined that the reason for the wrong scan is that the consumer mistakenly entered the commodity information of other commodities when entering the commodity information. For example, the consumer scanned the commodity code corresponding to commodity a, but placed commodity b on the loading platform. At this time, the abnormal commodity can be identified from the real-time image of the loading platform, and the new commodity can be identified from the loading platform, and then a prompt information is generated in the form of adding a guide mark to guide the consumer to correct the abnormal behavior by himself, that is, a correction scanning video is generated in the form of adding a guide mark.

[0044] The real-time image of the storage table corresponding to the current moment is also the image of the storage table corresponding to the moment when the abnormal input product code is determined from the input product order information. The real-time image of the storage table and the loading table image can be intercepted and determined from the cash register image, or can be collected by an image acquisition device set at the storage table or the loading table and uploaded to the monitoring system. The specific acquisition method is not specifically limited in the embodiment of this application. Newly added products are products placed in the loading table by consumers at abnormal times. If consumers put abnormal products into the loading table, abnormal input product codes will not be generated. Therefore, in order to guide consumers to eliminate the abnormality by themselves, it is necessary to identify the edge information of abnormal products from the real-time image of the storage table, and identify the edge information of newly added products from the loading table image, and generate a corrected scan video based on the edge information of both. Among them, when identifying the edge information of abnormal goods from the real-time image of the storage platform, the abnormal position corresponding to the abnormal goods can be determined from the real-time image of the storage platform according to the abnormal input product code, and then the edge information of the abnormal goods can be determined from the real-time image of the storage platform through the preset edge detection algorithm and the abnormal position. Among them, the preset edge detection algorithm can be a Sobel operator algorithm, a Canny operator algorithm, or a Prewitt operator algorithm. The specific preset edge detection algorithm is not specifically limited in the embodiment of the present application. As long as the edge information of the abnormal goods can be determined from the real-time image of the storage platform, when the Sobel operator algorithm is used, the edge information of the abnormal goods can be detected by calculating the gradient of the abnormal position in the horizontal and vertical directions in the real-time image of the storage platform. The method for determining the edge information of the newly added goods can refer to the above-mentioned method for determining the edge information of the abnormal goods, which will not be repeated here.

[0045] When marking abnormal commodities based on their edge information, colored lines can be used to mark the edge lines of abnormal commodities in the real-time image of the storage table, or a logo can be superimposed on the abnormal commodities. The method of marking abnormal commodities is not specifically limited in the embodiments of this application. As long as it is convenient for consumers to quickly and accurately locate and identify abnormal commodities from the real-time image of the storage table, the real-time image of the storage table after superimposing the logo line or the logo is determined as an abnormal identification image. The method of determining the newly added identification image can refer to the method of determining the abnormal identification image in the above embodiment, which will not be repeated here.

[0046] The preset guidance mark can be an interchange arrow or a symbol representing the meaning of the exchange. It can be set by relevant staff and uploaded to the monitoring system. The specific content is not limited in the embodiments of the present application, as long as it can provide exchange prompts to relevant consumers.

[0047] In addition, when the real-time image of the storage table does not contain abnormal goods, the abnormal input image corresponding to the wrong scanning behavior is obtained; the wrong scanning prompt is obtained from the monitoring system, and the wrong scanning prompt information is generated based on the abnormal input image corresponding to the wrong scanning behavior and the wrong scanning prompt; the wrong scanning prompt information is fed back to the cash register display interface and the terminal device carried by relevant loss prevention personnel.

[0048] Specifically, when the real-time image of the storage table does not contain abnormal goods, it can be characterized that the reason for the wrong scanning behavior may be that the goods do not match the product code. For example, the consumer enters the product code of product a, but the product code of product b is displayed in the entered product order information. At this time, the consumer may not be able to correct the abnormal behavior by himself. When the reason for the wrong scanning behavior is that the goods do not match the product code, the corresponding wrong scanning prompt can be obtained from the monitoring system, and the corresponding abnormal input image during the wrong scanning behavior can be obtained. Among them, the monitoring system contains a preset wrong scanning prompt that can be directly obtained. The wrong scanning prompt can be "There is a wrong scanning behavior, please wait for the relevant staff to handle it." The specific wrong scanning prompt is not specifically limited in the embodiment of this application, and can be determined by the relevant staff and uploaded to the monitoring system. The corresponding abnormal input image during the wrong scanning behavior can be captured from the cash register image. After determining the error scanning prompt information, the abnormal input image and the error scanning prompt word can be played on the cash register display interface to remind consumers. In order to increase consumers' attention to abnormal situations, a preset abnormal prompt logo can be displayed on the cash register display interface during the playing of the error scanning prompt information. The abnormal prompt logo can be an exclamation mark or a cross. The specific content is not limited in the embodiment of the present application and can be set by relevant technical personnel.

[0049] Furthermore, in order to reduce the waiting time, the method provided in the embodiment of the present application also includes: The product pick-up time is obtained, which is the time when the consumer picks up the newly added product from the loading platform; if the product pick-up time is within the first preset time period, and the newly added product is on the loading platform within the second preset time period, the abnormality is eliminated; if the product pick-up time is not within the first preset time period, the abnormal product code is removed from the entered product order information.

[0050] Specifically, when a consumer uses the self-service checkout system to settle accounts and an abnormal situation of incorrect scanning occurs, it may be because the consumer picked up multiple items at the same time, causing the product scanning device installed at the storage table to mistakenly enter the product code of other items. It is also possible that the product codes of different items are located similarly, and the consumer fails to accurately align the product code of the target item when performing the entry operation. At this time, if the consumer can immediately replace the product in a short time after receiving the feedback prompt information, that is, the abnormal product in the storage table is immediately replaced with the new product in the loading table, the abnormal situation can be eliminated without the need for manual intervention by relevant loss prevention personnel to eliminate the abnormal situation, thereby reducing the waiting time caused by consumer erroneous operations.

[0051] The first preset time period and the second preset time period are both a period of time after the prompt information is generated. The duration corresponding to the first preset time period can be 3 seconds or 5 seconds, and the duration corresponding to the second preset time period can be 6 seconds or 10 seconds. The duration corresponding to the second preset time period is longer than the duration corresponding to the first preset time period. The specific duration is not specifically limited in the embodiment of the present application and can be set by relevant technical personnel. When the moment of picking up the product is in the first preset time period, and the picked up product has fallen into the storage table within the second preset time period, it can be characterized that the consumer has exchanged the product in a short time. At this time, the abnormal situation can be eliminated, that is, the consumer can continue to settle the bill.

[0052] When obtaining the time when the product is picked up, the picking behavior can be determined by checking and analyzing the cash register image. When the picking behavior is detected in the cash register image, and the picked-up item corresponding to the picking behavior is a newly added product, the time when the picking behavior is determined is determined as the product picking-up time. If the product picking-up time is not in the first preset time period, it means that the consumer has not exchanged the product in time. Since the consumer has picked up the newly added product from the loading platform at this time, the abnormally entered product code in the product order information can be directly removed. After the abnormally entered product code is removed, there is no abnormal situation. When the consumer re-scans the newly picked up new product, the newly added product code corresponding to the newly added product will be entered instead of re-entering the abnormally entered product code with an abnormal situation.

[0053] Once it is detected that the consumer has completed the commodity exchange within the specified time, the normal state can be restored immediately, which is convenient for improving the degree of automation in the process of responding to exceptions and reducing manual intervention. After the exception is eliminated, the consumer can continue the shopping or settlement process without having to wait for the relevant staff to manually eliminate the exception before settling, which is convenient for improving the overall consumer experience.

[0054] Furthermore, when the abnormality type is a missed scale, the prompt information determined based on the abnormality type includes: Acquire the abnormal input image and the missed weighing prompt corresponding to the missed weighing behavior; generate the missed weighing prompt information based on the abnormal input image and the missed weighing prompt corresponding to the missed weighing behavior; and feed back the missed weighing prompt information to the cash register display interface and the terminal device carried by the relevant loss prevention personnel.

[0055] Specifically, when the abnormal type is missing scale, it indicates that the consumer has missed scale in the self-service checkout process. The missing scale behavior indicates that the consumer has not weighed and entered the weighed goods, and put the weighed goods into the loading platform. For example, commodity a is a weighed commodity. During the commodity settlement process, the consumer needs to place commodity a on the input weighing platform. The input weighing platform can convert the weighing result into the input commodity information and add it to the input commodity order information. However, when the consumer directly puts commodity a into the loading platform without weighing and entering the commodity a, an abnormal situation will occur. At this time, the consumer can correct the abnormal behavior by himself. Therefore, when the missing scale behavior occurs, the corresponding missing scale prompt can be obtained from the monitoring system, and the corresponding abnormal input image during the missing scale behavior is obtained. Among them, the monitoring system contains a preset missing scale prompt, which can be directly obtained. The missing scale prompt can be "there is a missing scale behavior, please weigh and enter the missing weighed goods". The specific missing scale prompt is not specifically limited in the embodiment of the present application, and can be determined by the relevant staff and uploaded to the monitoring system. The corresponding abnormal input image during the process of missed weighing behavior can be captured from the cashier image. After the missed weighing prompt information is determined, the abnormal input image and missed weighing prompt message can be played on the cashier display interface to remind consumers. At the same time, by feeding back the generated missed weighing prompt information to the relevant loss prevention personnel, it is convenient for the relevant loss prevention personnel to quickly understand the abnormal situation and deal with the missed weighing problem in a timely manner.

[0056] Furthermore, when the abnormality type is scan miss, the prompt information is determined based on the abnormality type, including: Acquire the abnormal input image and the missed scanning prompt corresponding to the missed scanning behavior; generate missed scanning prompt information based on the abnormal input image and the missed scanning prompt corresponding to the missed scanning behavior; and feed back the missed scanning prompt information to the cash register display interface and the terminal device carried by relevant loss prevention personnel.

[0057] Specifically, when the abnormal type is missed scanning, it indicates that the consumer has missed scanning during the self-service checkout process. The missed scanning behavior indicates that the consumer has not scanned and entered the scanned goods, and then put the scanned goods into the loading platform. For example, product b is a scanned product. During the commodity settlement process, the consumer needs to align the scanned product b with the product code scanning device. The product code scanning device can convert the scanning result into the input product information and add it to the input product order information. However, when the consumer does not scan and enter the product b and directly puts the product b into the loading platform, an abnormal situation will occur. At this time, the consumer can correct the abnormal behavior by himself. Therefore, when missed scanning occurs, the corresponding missed scanning prompt can be obtained from the monitoring system, and the corresponding abnormal input image in the process of missed scanning can be obtained. Among them, the monitoring system contains a preset missed scanning prompt, which can be directly obtained. The missed scanning prompt can be "there is a missed scanning behavior, please scan and enter the missed scanning goods". The specific missed scanning prompt is not specifically limited in the embodiment of this application, and can be determined by the relevant staff and uploaded to the monitoring system. The corresponding abnormal input image in the process of missed scanning can be intercepted from the cashier image. After the missed scan prompt information is determined, the abnormal input image and missed scan prompt message can be played on the cash register display interface to remind consumers. At the same time, the generated missed scan prompt information is fed back to the relevant loss prevention personnel, so that the relevant loss prevention personnel can quickly understand the abnormal situation and deal with the missed scan problem in time.

[0058] During the process of playing the missed scale reminder information or the missed scan reminder information, a preset abnormal prompt mark can be displayed in the cash register display interface, where the abnormal prompt mark can be an exclamation mark or a cross, and the specific content is not specifically limited in the embodiments of the present application.

[0059] Further, in order to ensure that inspection request instructions with higher difficulty or lower execution efficiency are processed first, the method provided in the embodiment of the present application further includes steps S1 to S3, such as Figure 2 As shown, where: Step S1: Identify the corrective action identifier contained in the prompt information corresponding to each inspection request instruction, and determine the corrective difficulty score corresponding to each corrective action identifier based on the action score mapping relationship, where the action score mapping relationship is the correspondence between the corrective action identifier and the corrective difficulty score.

[0060] Specifically, after guiding consumers to make corrections themselves by generating prompt information, multiple inspection request instructions may still exist. However, due to the limited number of relevant loss prevention personnel, when multiple inspection request instructions exist in a short period of time, the generated multiple inspection request instructions may need to be sorted to wait for relevant loss prevention personnel to intervene manually.

[0061] When sorting multiple inspection request instructions, the correction behavior identifier in the prompt information corresponding to each inspection request instruction containing the correction scanning video can be identified first to analyze the difficulty of the correction scanning video corresponding to each inspection request instruction. Different correction behavior identifiers correspond to different correction difficulty scores. For example, the correction behavior identifier may be to enter the product code in a flat format or adjust the scanning angle, or it may be to dismantle the original combination packaging and scan the individual packages in turn. It can be identified from the correction scanning video by feature recognition. The specific feature recognition method is not specifically limited in the embodiment of the present application. The correction difficulty score corresponding to each correction behavior identifier can be determined through the behavior score mapping relationship. The behavior score mapping relationship includes the correction difficulty score corresponding to any correction behavior identifier. The mapping relationship can be determined by relevant staff based on historical experimental data and uploaded to the monitoring system. The specific content is not specifically limited in the embodiment of the present application. The more complex the correction behavior, the higher the corresponding correction difficulty score.

[0062] Step S2: Obtain the execution information corresponding to each inspection request instruction, and determine the execution score corresponding to each execution information based on the mapping relationship between the execution information and the execution score. The execution information includes the response time and success rate of the corrective behavior when the corresponding consumer corrects according to the prompt information corresponding to the inspection request instruction. The execution score mapping relationship is the correspondence between the response time and success rate of the corrective behavior and the execution score.

[0063] Specifically, the execution information corresponding to each inspection request instruction can be determined by analyzing the reaction of each consumer after receiving the prompt information. The execution information includes the corrective behavior response time and success rate of the consumer. When determining the corrective behavior response time of the consumer, it can be determined by obtaining the corresponding execution screen after the consumer receives the feedback prompt information. The execution screen corresponding to the consumer can be collected by the image acquisition device set at the cashier and uploaded to the monitoring system. Since different inspection request instructions correspond to different abnormal situations faced by consumers, that is, different prompt information corresponds to different execution screens, for any consumer, first identify the execution action contained in the prompt information, when the execution action is detected to appear in the execution screen, determine the execution time of the consumer, obtain the prompt time of the prompt information fed back to the consumer, and determine the corrective behavior response time of the consumer when correcting according to the prompt information corresponding to the inspection request instruction according to the prompt time and the execution time. The corrective behavior response time of each consumer when facing the prompt information is determined by the above method. The longer the corrective behavior response time, the higher the corresponding execution score.

[0064] The success rate when the consumer corrects the prompt information corresponding to the inspection request instruction can be determined by counting the number of times the consumer repeats the corrective behavior. The more times the execution is performed, the lower the corresponding success rate. There is a corresponding relationship between the number of executions and the success rate. Based on the corresponding relationship, the success rate corresponding to any number of executions can be determined. The specific content of the corresponding relationship is not specifically limited in the embodiments of the present application. The lower the success rate, the higher the corresponding execution score.

[0065] After determining the corrective behavior response time and success rate of each consumer when facing the corresponding prompt information, the execution score corresponding to each consumer can be determined based on the execution score mapping relationship. The execution score mapping relationship includes execution scores corresponding to different combinations of corrective behavior response time and success rate. The specific content of the execution score mapping relationship is not specifically limited in the embodiment of the present application, and can be determined by relevant staff based on historical experimental data and uploaded to the monitoring system.

[0066] Step S3: Based on the correction difficulty score and execution score corresponding to each inspection request instruction, adjust the execution position of the corresponding inspection request instruction in the execution queue. The execution queue contains multiple inspection request instructions, and each inspection request instruction is sorted according to the corresponding generation time.

[0067] Specifically, the generation time corresponding to each inspection request instruction is recorded, multiple inspection request instructions are sorted based on the generation time of each inspection request instruction, and an execution queue is generated. The execution queue is sorted in the order of the generation time corresponding to each inspection request instruction. After determining the correction difficulty score and execution score corresponding to each inspection request instruction, that is, after determining the correction difficulty score and execution score corresponding to the prompt information of each inspection request instruction, the total adjustment value of each inspection request instruction is determined, and the position of the inspection request instruction in the execution queue is adjusted based on the total adjustment value. For example, there are 4 inspection request instructions, and after sorting according to the generation time, the execution queue is inspection request instruction a, inspection request instruction b, inspection request instruction c, and inspection request instruction d. After calculation, it is determined that the total adjustment values ​​corresponding to the 4 inspection request instructions are 20, 10, 25, and 30, respectively. Among them, the higher the total adjustment value indicates that the correction behavior of the corresponding prompt information is more complicated, the consumer's correction behavior response time is longer, and the consumer's success rate is lower, which also indicates that the corresponding abnormal situation is more severe. Therefore, it is necessary to readjust the execution position of each inspection request instruction in the execution queue according to the total adjustment value to ensure that inspection request instructions with higher difficulty or lower execution efficiency are given priority.

[0068] Furthermore, the method provided in the embodiment of the present application also includes: When it is detected that the scan list has not been updated within a third preset time period, a cash register image is obtained and consumer behavior is identified from the cash register image; when the consumer behavior is a preset behavior, the identification of the product to be scanned is identified from the cash register image; demonstration information is determined based on the identification of the product to be scanned, and the demonstration information is displayed on the operation interface.

[0069] Specifically, the third preset time period is a period of time after the last update time of the scan list. The duration corresponding to the third preset time period can be 30 seconds or 60 seconds. The specific duration is not specifically limited in the embodiment of the present application. For example, the last update time of the scan list is 10:00, and the third preset time period is 60 seconds. That is, the consumer scanned a product at 10:00 and did not scan other products between 10:00 and 10:01. At this time, it can be determined that the consumer may need help.

[0070] The consumer behavior is determined by analyzing and identifying features of the cash register image. The method of identifying the consumer behavior from the cash register image is not limited in the embodiment of the present application. The preset behavior can be holding the product, rotating the product, etc. The specific preset behavior can be set by relevant technical personnel. When the consumer behavior is consistent with the preset behavior, it can be determined that help needs to be provided to the consumer. The identification of the product to be scanned is the product identification corresponding to the product held by the consumer. The corresponding demonstration information can be called up from the monitoring system through the product identification, and the demonstration information is fed back to help the consumer scan the product. Since the location of the input product code corresponding to different products may be different, when consumers scan different products, it is very likely that they will not be able to locate the location of the input product code in the product in time, or they will not be able to scan effectively in time. At this time, by actively identifying and responding to the needs of consumers, relevant demonstration information is provided in time to help consumers solve problems, thereby facilitating the enhancement of consumer satisfaction during the shopping process.

[0071] The present application provides a monitoring system, such as Figure 3 As shown, Figure 3 The monitoring system 300 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the monitoring system 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the monitoring system 300 does not constitute a limitation on the embodiments of the present application.

[0072] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0073] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 The fact that only one line is used in the diagram does not mean that there is only one bus or only one type of bus.

[0074] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0075] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0076] The monitoring system includes, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 3 The monitoring system shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0077] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment.

[0078] An embodiment of the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the method in any of the above embodiments is implemented.

[0079] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0080] The above description is only a partial implementation method of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A self-service checkout loss prevention behavior monitoring method, characterized in that: include: Acquire a cashier counter image, perform feature recognition on the cashier counter image, and determine whether the cashier counter image contains a preset abnormal mark; When the cashier image contains the preset abnormal identification, the cashier image is subjected to abnormal feature recognition to determine the abnormal type of the abnormal commodity, wherein the abnormal type includes wrong scanning, missed weighing and missed scanning; Determine prompt information and light-on warning information based on the abnormality type, and display the prompt information on the operation interface, the prompt information including a correction scanning video or a scanning guidance voice; An inspection request instruction is generated based on the prompt information and the light-on alarm information, and the inspection request instruction is fed back to the terminal device of the loss prevention personnel.

2. A self-service checkout loss prevention behavior monitoring method according to claim 1, characterized in that: When the abnormality type is wrong scanning, the prompt information is determined based on the abnormality type, including: Determining an abnormally entered commodity code based on the entered commodity order information, wherein the entered commodity order information is commodity information that has been entered at the cashier counter, and the abnormally entered commodity code is a commodity code corresponding to the abnormal commodity; Acquire a real-time image of the storage platform, and when the real-time image of the storage platform contains the abnormal commodity, identify edge information of the abnormal commodity from the real-time image of the storage platform, and mark the abnormal commodity based on the edge information of the abnormal commodity to obtain an abnormal marking image; Acquire a loading platform image corresponding to the abnormal time, and when the loading platform image corresponding to the abnormal time includes a newly added commodity, identify edge information of the newly added commodity from the loading platform image corresponding to the abnormal time, and mark the newly added commodity based on the edge information of the newly added commodity to obtain a newly added mark image, wherein the abnormal time is the time when the abnormal input commodity code is determined from the input commodity order information; The prompt information is determined based on the preset guidance mark, the abnormal mark image and the newly added mark image.

3. A self-service checkout loss prevention behavior monitoring method according to claim 2, characterized in that: Also includes: Obtaining the product pick-up time, where the product pick-up time is the time when the consumer picks up the newly added product from the loading platform; If the product is picked up at a first preset time period, and the newly added product is located on the storage table within a second preset time period, then the anomaly is eliminated; If the product picking-up time is not within the first preset time period, the abnormally entered product code is removed from the entered product order information.

4. A self-service checkout loss prevention behavior monitoring method according to claim 1, characterized in that: When the abnormality type is a missed scale, the prompt information determined based on the abnormality type includes: Obtain the abnormal input image and the missed weighing prompt corresponding to the missed weighing behavior; Generate a missed weighing prompt message based on the abnormal input image corresponding to the missed weighing behavior and the missed weighing prompt message; The missed scale prompt information is fed back to the cashier display interface and the terminal device carried by relevant loss prevention personnel.

5. A self-service checkout loss prevention behavior monitoring method according to claim 1, characterized in that: When the abnormality type is scan miss, the prompt information is determined based on the abnormality type, including: Obtain the abnormal input image and missed scan prompt corresponding to the missed scan behavior; Generate missed scanning prompt information based on the abnormal input image corresponding to the missed scanning behavior and the missed scanning prompt; The missed scan prompt information is fed back to the cashier display interface and the terminal device carried by the relevant loss prevention personnel.

6. A self-service checkout loss prevention behavior monitoring method according to claim 1, characterized in that: Also includes: Identify the correction behavior identifier contained in the prompt information corresponding to each inspection request instruction, and determine the correction difficulty score corresponding to each correction behavior identifier based on the behavior score mapping relationship, wherein the behavior score mapping relationship is the correspondence between the correction behavior identifier and the correction difficulty score; Obtaining execution information corresponding to each inspection request instruction, and determining an execution score corresponding to each execution information based on a mapping relationship between the execution information and the execution score, wherein the execution information includes a corrective behavior response time and a success rate when the corresponding consumer corrects according to the prompt information corresponding to the inspection request instruction, and the execution score mapping relationship is a corresponding relationship between the corrective behavior response time and the success rate and the execution score; Based on the correction difficulty score and execution score corresponding to each inspection request instruction, the execution position of the corresponding inspection request instruction in the execution queue is adjusted. The execution queue contains multiple inspection request instructions, and each inspection request instruction is sorted according to the corresponding generation time.

7. A self-service checkout loss prevention behavior monitoring method according to claim 1, characterized in that: Also includes: When it is detected that the scan list has not been updated within a third preset time period, acquiring a cashier counter image and identifying consumer behavior from the cashier counter image; When the consumer behavior is a preset behavior, identifying the logo of the commodity to be scanned from the cash register image; Demonstration information is determined based on the identification of the commodity to be scanned, and the demonstration information is displayed on the operation interface.

8. A monitoring system, characterized in that: The monitoring system includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute a self-service checkout loss prevention behavior monitoring method according to any one of claims 1-7.

9. A computer-readable storage medium, characterized in that: include: A computer program is stored which can be loaded by a processor and execute a self-service checkout loss prevention behavior monitoring method as described in any one of claims 1-7.

10. A computer program product, characterized in that It includes a computer program, which, when executed by a processor, implements the steps of a self-service checkout loss prevention behavior monitoring method according to any one of claims 1 to 7.

Images