Electronic price tag position identification method and system

Abstract

The invention relates to the field of electronic price tag management, in particular to an electronic price tag position identification method and system. The method comprises the following steps: acquiring real-time image data from a retail environment, and enhancing the image data through a multi-modal sensor to obtain a standardized image sequence; carrying out denoising, enhancement and quality optimization on the image sequence, extracting image features through a deep convolutional neural network, and generating an electronic price tag position candidate region; the real position coordinates of the electronic price tag are calculated in combination with the image space information, and the commodity price is synchronously updated; the updated electronic price tag position and price information are sent to a cloud computing platform for storage, analysis and management; based on real-time feedback and historical data, an image processing and position identification strategy is optimized through reinforcement learning, and adaptive adjustment parameters are generated. According to the invention, the position of the electronic price tag can be efficiently and accurately identified in a complex retail environment, real-time price synchronous updating is realized, and automation and accuracy are high.

Description

Technical Field

[0001] The present invention relates to the field of new generation information technology and retail, and in particular to a method and system for identifying the position of an electronic price tag. Background Art

[0002] With the development of intelligence and automation in the retail industry, electronic price tags have become an important identification tool in modern retail environments. Electronic price tags can not only display product prices, promotional information, etc., but also interact with product management systems in real time to achieve automatic update and synchronization of price information. Especially in large-scale retail environments, efficient management and accurate identification of electronic price tags have become the key to improving operational efficiency and reducing labor costs. However, existing electronic price tag systems face technical challenges of accurate identification and real-time synchronization in complex and dynamic retail environments, especially under conditions such as lighting changes, product occlusion, and different viewing angles.

[0003] Current electronic price tag recognition methods mainly rely on image processing and computer vision technology, but due to the layout of goods in the retail environment, the wide variety of goods, and the interference of environmental factors, it is difficult for existing technologies to achieve efficient and accurate electronic price tag location recognition in a changing environment. In addition, although existing technologies can achieve electronic price tag location recognition in some specific environments, their accuracy and real-time performance in complex environments are still low, especially in the application of multimodal data fusion and deep learning algorithms.

[0004] Therefore, how to accurately identify the location of electronic price tags and achieve real-time price synchronization updates through multimodal sensor data and deep learning algorithms in a complex and dynamic retail environment is a core problem that needs to be solved in current technology. Solving this problem can not only improve the automation level of electronic price tag management, but also significantly improve the accuracy and stability of the system in a changing environment. Summary of the invention

[0005] The present invention provides an electronic price tag location recognition method and system to solve the problem of how to achieve accurate location recognition and real-time price synchronization update of electronic price tags in a complex and dynamic retail environment through multimodal sensor data and deep learning algorithms, so as to improve the automation and accuracy of electronic price tag management.

[0006] In order to solve the above technical problems, the present invention provides a method for identifying the position of an electronic price tag, comprising: Acquire real-time image data from a retail environment and enhance the image data through a multimodal sensor to obtain a standardized image sequence; De-noising and enhancing the standardized image sequence to optimize the image quality, and extracting image features through a deep convolutional neural network to generate a sequence of candidate regions for electronic price tag positions; Based on the candidate region sequence of the electronic price tag position, combined with the spatial information of the image, the real position coordinates of the electronic price tag are calculated; and the price of the commodity is synchronously updated according to the position and price information of the electronic price tag; Send the updated electronic price tag location and price information to the cloud computing platform for storage, analysis and management; Based on real-time data feedback and historical environmental data, image processing and location recognition strategies are optimized through reinforcement learning, adaptive adjustment parameters are generated, and subsequent recognition and update processes are tracked.

[0007] Furthermore, before the step of acquiring real-time image data from the retail environment, the method further includes: Multiple sensors are configured to acquire image data under different lighting, viewing angles and environmental changes, and the sensors include RGB image sensors, depth sensors and infrared sensors.

[0008] Furthermore, the step of performing denoising and enhancement processing on the image sequence specifically includes: Image denoising algorithm is used to eliminate noise in the image, and further image enhancement processing such as brightness and contrast is performed.

[0009] Furthermore, the step of extracting image features through a deep convolutional neural network specifically includes: The image sequence is input into a deep convolutional neural network, the local features in the image are extracted through the convolution layer, and the data dimension is reduced through the pooling layer to generate a feature map containing key information of the image.

[0010] Furthermore, the deep convolutional neural network includes multiple convolutional layers and pooling layers, and the spatial features in the image are extracted layer by layer through the multi-layer network, and image features for position recognition are generated. Furthermore, the step of performing accurate position calculation based on the sequence of candidate regions for electronic price tags specifically includes: Combined with the spatial information of the image, the real position coordinates of the electronic price tag are calculated through perspective transformation and depth image information, and subsequent price synchronization is updated based on the coordinate information.

[0011] Furthermore, the step of calculating the position coordinates of the electronic price tag through perspective transformation and depth information further includes: The electronic price tag candidate area is corrected using the camera internal and external parameters of the image, so as to accurately calculate its three-dimensional spatial position.

[0012] Furthermore, the step of sending the updated electronic price tag location and price information to the cloud computing platform for storage, analysis and management specifically includes: The electronic price tag location and price information are transmitted to a cloud computing platform via a network. The cloud computing platform is used to store and manage data in real time and provide a data analysis and query interface.

[0013] Furthermore, the step of optimizing the image processing and location recognition strategy by reinforcement learning specifically includes: Based on real-time feedback data and historical environmental data, the image processing and location recognition models are optimized through reinforcement learning algorithms, and adaptive adjustment parameters are generated to improve recognition accuracy and system adaptability.

[0014] Furthermore, an electronic price tag position recognition system includes: A data acquisition module is used to obtain image data related to the retail environment from a variety of sensors, including RGB image sensors, depth sensors, infrared sensors, etc., and to collect commodity images and environmental parameters in the retail environment in real time through these sensors; A data processing module, used for performing denoising, enhancement and standardization processing on the image data acquired from the data acquisition module, and transmitting the processed image data to subsequent modules; A feature extraction and selection module, used to extract key features that can effectively identify the position of the electronic price tag from the processed image data, and screen out the most discriminative features; A location calculation and synchronization update module, which is used to calculate the real location coordinates of the electronic price tag based on the extracted electronic price tag location candidate area features and combined with the spatial information of the image, and to synchronously update the price information of the commodity; a cloud computing platform and data storage module, which is used to store and manage all generated electronic price tag data, and provide data analysis, query and multi-terminal access functions; Real-time feedback and optimization module, which is used to receive feedback data from each module and dynamically adjust the image processing algorithm and recognition strategy according to the real-time data to optimize system performance; User interaction and visualization module, which is used to provide an intuitive user interface, display the location and price information of the electronic price tag, and support real-time data interaction and operation configuration; The system monitoring and adaptation module is used to monitor the operating status of the entire system in real time, adjust system parameters according to environmental changes through an adaptive learning mechanism, and ensure the stability and adaptability of the system in different retail environments.

[0015] The key innovative features of the present invention include: (1) Multimodal sensor data enhancement: By using multimodal sensors such as RGB images, depth sensors, and infrared sensors, the system is able to obtain more comprehensive and reliable environmental data, ensuring high-quality image data in complex retail environments.

[0016] (2) Deep convolutional neural network (CNN) feature extraction: Use deep convolutional neural networks to automatically extract key information from images, effectively identify the shape, size, color and other features of electronic price tags, and optimize the accuracy of location recognition.

[0017] (3) Spatial information fusion and precise position calculation: Combine the spatial information of the image (such as perspective transformation, depth image, etc.) to calculate the real position coordinates of the electronic price tag and improve the accuracy of position recognition.

[0018] The following are its main beneficial effects: The electronic price tag location recognition method and system provided by the present invention can accurately identify the location of the electronic price tag and realize real-time synchronous update of price information through multimodal sensor data and deep learning algorithms in a complex and dynamically changing retail environment. Compared with the traditional image processing method, the multimodal data enhancement and deep convolutional neural network (CNN) of the present invention combined with the precise position calculation of spatial information effectively improve the accuracy of electronic price tag recognition, especially in complex environments such as lighting changes, product occlusion, and different viewing angles, which can ensure the efficiency and stability of location recognition. At the same time, through real-time feedback and optimization of historical data, the system can adaptively adjust the image processing and location recognition strategies, improve the long-term adaptability and stability of the system, and avoid the problems of recognition failure and system performance degradation caused by environmental changes in traditional methods. In addition, the updated electronic price tag data is synchronized to the cloud computing platform for storage and management, which realizes efficient storage, analysis and query of data and improves the overall operation and maintenance efficiency of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A schematic diagram of a flow chart of an electronic price tag location identification method provided in an embodiment of the present application; Figure 2 This is a structural block diagram of an electronic price tag location identification system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0021] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0022] Example 1: Reference Figure 1 , is a flow chart of an electronic price tag location identification method and system provided by an embodiment of the present invention, the flow chart may at least include steps S100-S500: S100, acquires real-time image data from a retail environment and performs data enhancement through a multimodal sensor to obtain a standardized image sequence.

[0023] S200, performing denoising and enhancement processing on the image sequence to optimize image quality, and extracting image features through a deep neural network to generate a sequence of candidate areas for electronic price tag positions.

[0024] S300: Based on the candidate electronic price tag location region sequence, accurate electronic price tag location calculation is performed to determine the final location coordinates, and price information of related commodities is synchronously updated.

[0025] S400: Send the updated electronic price tag location and price information to the cloud computing platform for storage, analysis and management.

[0026] S500, based on real-time data feedback and historical environmental data, optimizes image processing and location recognition strategies through reinforcement learning, generates adaptive adjustment parameters, and tracks subsequent recognition and update processes.

[0027] Step S100 at least includes steps S110-S130: S110: Acquires real-time image data from multiple sensors in a retail environment, covering different viewpoints, lighting, and occlusion conditions.

[0028] In a retail environment, multiple sensors are used to collect real-time image data. Specifically, the sensors include but are not limited to RGB image sensors, depth sensors, infrared sensors, temperature sensors, etc. Each sensor is responsible for obtaining different information dimensions: RGB image sensor: collects visual information in the retail environment, including the color, shape, size, etc. of the goods; Depth sensor: provides depth information of objects, which can help determine the distance, stereoscopic effect and three-dimensional position of objects; Infrared sensor: used to obtain heat distribution in retail environments, helping to identify dark objects due to insufficient light or reflections; Temperature sensor: In certain cases, it can provide additional information related to ambient temperature, which helps to understand image data in complex environments.

[0029] The sensors collect data in real time in a synchronous manner, and the acquired image data covers different viewing angles, lighting and occlusion conditions. These multi-dimensional data ensure that all information in the retail environment can be obtained for subsequent image fusion and analysis. The output of this step is an image data set, denoted as in Contains multimodal data collected from different sensors.

[0030] S120: Enhance the acquired image data using the multimodal data.

[0031] After obtaining multimodal image data After that, it is processed by the multimodal data enhancement technology. Specifically, the image enhancement includes the following aspects: For images captured by RGB image sensors, color balancing and enhancement algorithms are used, such as by adjusting brightness, contrast, saturation, etc., to ensure that the visual effect of the image is more prominent.

[0032] The depth information provided by the depth sensor is used to perform depth enhancement on the RGB image. Combined with the three-dimensional information of the object, it solves the problems caused by occlusion or spatial distribution of the object and improves the depth and details of the image.

[0033] Information from infrared sensors is used to enhance missing images due to insufficient light or reflection, ensuring that images can still effectively represent the features of objects in retail environments in low-light or backlit environments.

[0034] By enhancing these multimodal data, an enhanced image data set is generated, denoted as Compared with the original data The visual clarity, depth information and environmental adaptability are all improved. Specifically, the enhancement effect of image data can be described by the following formula:

[0035] in, is the enhancement function, which represents the comprehensive processing of image enhancement; is the original image data; For depth information; For infrared information.

[0036] S130: Performing standardization processing on the enhanced image data using a multimodal sensor.

[0037] After completing the data enhancement, the enhanced image data is Standardization is performed to ensure the stability and consistency of subsequent processing. Standardization includes the following steps: The images are resized to a uniform size (e.g., 224×224 pixels) to accommodate the input requirements of the deep learning model. This step ensures that all image data have the same spatial dimension to facilitate subsequent image feature extraction.

[0038] Unify the color space of the image and convert the image from the RGB color space to a standard color space (for example, Lab or grayscale) to remove the interference of color on image recognition and ensure consistency during feature extraction.

[0039] Normalize pixel values ​​to a certain range (for example, between 0 and 1) to reduce the impact of brightness differences between different images and reduce the deviation caused by inconsistent values.

[0040] Through these standardization operations, we finally get a standardized image data set, denoted as It can be directly used for subsequent image feature extraction and position recognition processing.

[0041] The standardized formula is as follows:

[0042] in, is the enhanced image data; μ is the mean of the image data; σ is the standard deviation of the image data.

[0043] This standardization operation ensures that the numerical distribution of the image meets the processing requirements and facilitates the processing of subsequent algorithms.

[0044] Connection between previous and next steps: In the S110 stage, the real-time image data obtained Collected by multiple sensors, covering different viewing angles, lighting, and occlusion conditions, this data set provides raw input data for the subsequent enhancement step (S120).

[0045] In the S120 stage, the image data Enhanced by multimodal sensors to generate enhanced image data , thereby improving the image quality and spatial information. These enhanced images provide a basis for subsequent standardization (S130).

[0046] In the S130 stage, the enhanced image data Standardized to Prepare for subsequent image feature extraction (such as feature extraction of deep features in neural networks) to ensure that image data can be processed efficiently in subsequent algorithms.

[0047] Step S200 at least includes steps S210-S230: S210: removing noise interference in the image through an image denoising algorithm to improve the clarity and effectiveness of the image.

[0048] In step S210, the image sequence The image data (normalized in the previous step) needs to be de-noised by a denoising algorithm to remove the noise interference in the image, thereby improving the clarity and effectiveness of the image. Specifically, the denoising process can be completed through the following steps: Assume that the image data The noise in is Gaussian noise That is, the image pixel value It can be expressed as:

[0049] in, is the pixel value of the real image, For noise.

[0050] Use classic denoising algorithms (such as Gaussian filtering, mean filtering, median filtering, bilateral filtering, etc.) to process the image. The specific steps are as follows:

[0051] in, Indicates that a specific filter is used to remove noise, and σ is the standard deviation of the filter, which controls the strength of denoising. The image obtained after denoising is .

[0052] The signal-to-noise ratio (SNR) is used to evaluate the denoising effect. The denoising effect is measured by calculating the signal-to-noise ratio before and after denoising. The formula for the signal-to-noise ratio is:

[0053] in, Represents the variance of the image or noise.

[0054] Finally, the denoising operation outputs the denoised image data , providing clear data input for subsequent enhancement processing.

[0055] S220: Uses image enhancement technology to improve the prominence of image details and important areas.

[0056] In step S220, for the denoised image , image enhancement technology is used to improve the details and prominence of important areas of the image. The enhancement processing steps include: By adjusting the brightness and contrast of the image, the important areas in the image are made more obvious, especially the electronic price tag and its surrounding areas. This process can be done by adjusting the contrast and brightness of the pixel values:

[0057] Among them, α is the contrast adjustment factor, μ is the mean of the image, and β is the brightness adjustment factor. This operation can effectively enhance the contrast of the image and make the details of the image clearer.

[0058] For important detail areas in the image (such as electronic price tags), use a sharpening algorithm (such as the Laplacian operator or the Sobel operator) to enhance edge information, making these areas more prominent. The specific calculation formula is:

[0059] Where k is the sharpening factor, Represents the second-order gradient (or Laplacian) of an image, used to enhance edge details.

[0060] For some areas of interest in the image (such as the area where the electronic price tag is located), local enhancement technology can be applied to enhance local details using methods such as regional weighted average or Gaussian pyramid:

[0061] in, is the weight coefficient, and N is the number of pixels in the local area.

[0062] Finally, the enhanced image data It provides details and key information of the image, especially enhancing the prominence of the electronic price label area.

[0063] S230: Input the enhanced image sequence into a deep convolutional neural network to extract key features in the image.

[0064] In step S230, the enhanced image data The image is input into a deep convolutional neural network (DCNN) to extract key features in the image for subsequent electronic price tag location recognition.

[0065] First, a convolutional neural network structure suitable for image feature extraction is designed. The network consists of multiple convolutional layers, pooling layers, activation functions, and fully connected layers. The convolutional layer is used to extract local features from the image, and the pooling layer is used for downsampling, reducing the image size and retaining important features.

[0066] The enhanced image Input into the convolutional neural network and perform a series of convolution and pooling operations. The convolution operation of each layer can be expressed as:

[0067] in, is the feature map of the i-th layer, is the convolution kernel, * indicates the convolution operation, is the bias, and σ(·) is the activation function (such as ReLU).

[0068] After multiple layers of convolution and pooling operations, the high-level features extracted by the network Contains key information in the image, such as the location features of the electronic price tag. The final output of feature extraction It can be used for subsequent generation of candidate areas for electronic price tag locations.

[0069] Finally, the feature map obtained by the deep convolutional neural network A sequence of candidate locations for electronic price tags is provided to prepare for subsequent precise location calculation and synchronous update.

[0070] Connection between the previous and next steps: In step S210, the image data Denoised, output denoised image , providing clearer data for subsequent image enhancement.

[0071] In step S220, the denoised image is further enhanced to generate an enhanced image , increasing the prominence of details and key information.

[0072] In step S230, the enhanced image data It is fed into a deep convolutional neural network to extract key features from the image. , used to generate a sequence of candidate regions for electronic price tag locations.

[0073] Step S300 at least includes steps S310-S330: S310: Use the computing model to further analyze and process the candidate area for the electronic price tag location, and calculate the actual location coordinates of the electronic price tag in combination with the spatial information of the image.

[0074] In step S310, the candidate region sequence of the electronic price tag position The candidate area (obtained from the image features extracted by the deep convolutional neural network) needs to be further analyzed and processed, and the real position coordinates of the electronic price tag are calculated in combination with the spatial information of the image. The specific steps are as follows: First, based on the candidate area of ​​the electronic price tag obtained in the previous step By analyzing the spatial information of the image (e.g., perspective transformation in the image, camera position and angle, etc.), each candidate region can be obtained The two-dimensional coordinates in the image. corresponds to the position on the image plane.

[0075] By combining image data acquired from multiple sensors , as well as the camera intrinsic and extrinsic parameters of the image (such as focal length, optical center, rotation matrix, etc.), the image can be spatially corrected using a spatial geometry model (such as perspective transformation, camera matrix calculation, etc.) to obtain the true three-dimensional position of each candidate region ri. The specific calculation formula is:

[0076] in, is the three-dimensional position coordinate of the electronic price tag, K is the intrinsic parameter matrix of the camera, R and T are the rotation matrix and translation matrix of the camera respectively, Candidate area The pixel coordinates of (assuming normalization).

[0077] Using known camera parameters and image information, the coordinate calculation can be further optimized, and multi-view information (for example, using stereo vision or optical flow) can be combined to obtain a more accurate electronic price tag location. With this spatial information, the real spatial coordinates of each electronic price tag candidate area can be accurately calculated.

[0078] Finally, the calculated real electronic price tag position coordinates Will serve as input for subsequent steps.

[0079] S320: Acquire price information of the corresponding product in combination with the calculated accurate electronic price tag position, and synchronously update the price information and the electronic price tag position.

[0080] In step S320, the precise electronic price tag position calculated in the previous step is combined , obtain the corresponding commodity price information, and synchronize the price information with the electronic price tag position. The specific steps are as follows: The price information It can be obtained in many ways, for example, by barcode scanning, RFID technology, commodity database query, etc., to obtain the commodity price information corresponding to each electronic price tag from the commodity management system. Suppose the price information of a certain commodity is , then for each electronic price tag position You can find the corresponding price information , where i represents the i-th electronic price tag.

[0081] Through the data synchronization mechanism, the calculated electronic price tag position And the corresponding price information Specifically, the electronic price tag location and price information can be sent to the cloud platform or management system via the network:

[0082] The synchronization process can use a standardized data format for transmission and storage, for example, using JSON or XML format for transmission of data packets.

[0083] During the synchronization update process, if there is a mismatch in price information or an incorrect electronic price tag location, an anomaly detection algorithm can be used to handle it to ensure the correctness of the location information and price information of each electronic price tag in the system.

[0084] Finally, the synchronously updated electronic price tag position and price information provides support for subsequent data management and storage.

[0085] S330: Generate new electronic price tag data based on the updated electronic price tag location and price information, and provide data support for subsequent data storage, transmission and management In step S330, new electronic price tag data is generated based on the updated electronic price tag location and price information, and data support is provided for subsequent data storage, transmission and management. The specific steps are as follows: According to the electronic price tag position after synchronization update and price information , generate new electronic price tag data , which contains the coordinate information of the electronic price tag and the corresponding price information. The data format can be a standardized data structure, for example:

[0086] in, Indicates the timestamp of data generation. A unique identifier for the electronic price tag.

[0087] The generated electronic price tag data Stored in a database or cloud platform for subsequent query, management and analysis. During storage, the data will be indexed and classified according to the location and price of the electronic price tag for efficient retrieval and update.

[0088] The generated electronic price tag data also needs to be transmitted to the terminal device (such as an electronic price tag display) through the network. Specifically, the updated electronic price tag data is sent to the corresponding electronic tag terminal through wireless communication (such as Wi-Fi, Bluetooth or RFID).

[0089] The system can continuously optimize the data management process of electronic price tags based on historical data and real-time feedback, for example, using cloud computing platforms for batch updates, anomaly detection, data archiving and other operations.

[0090] Finally, through the above steps, the new electronic price tag data Generates and provides support for subsequent storage, transmission and management.

[0091] Connection between previous and next steps: In step S310, the candidate region The image is further analyzed and combined with the spatial information of the image to calculate the precise location of the electronic price tag. , providing the necessary location information for subsequent synchronization updates and data storage.

[0092] In step S320, the precise location Price information of the combined products Synchronous updates are carried out to provide necessary input for subsequent electronic price tag data generation.

[0093] In step S330, the updated electronic price tag location and price information and Used to generate new electronic price tag data and provides support for subsequent data storage, transmission and management.

[0094] Step S400 at least includes steps S410-S430: S410: Sending the accurately calculated and updated electronic price tag location and price information to the cloud computing platform via the network.

[0095] In step S410, the electronic price tag location and price information is accurately calculated and updated. It needs to be transmitted to the cloud computing platform through the network. The specific process is as follows: The electronic price tag position and price information The data will be packaged into data packets and transmitted in a standardized format. For example, the data can be packaged in JSON or XML format, and each data packet contains the electronic price tag location, price information, and other metadata (such as timestamp, device ID, etc.). Assume that the data packet The format is:

[0096] in, Indicates the timestamp of data generation. A unique identifier for the electronic price tag.

[0097] Send formatted data packets via wireless networks (such as Wi-Fi, Bluetooth, or proprietary communication protocols) Send to the cloud computing platform. During the transmission process, encryption protocols (such as HTTPS) can be used to ensure the security of the data.

[0098] Use reliable data transmission protocols (for example, TCP / IP) to ensure the integrity and order of data packets. If a network failure or packet loss occurs during transmission, the system will automatically retry to ensure that the data reaches the cloud platform accurately.

[0099] At the receiving end of the cloud computing platform, the data packet The data received by the cloud will be cached for storage and analysis.

[0100] Through these steps, the updated electronic price tag location and price information are successfully transmitted to the cloud computing platform.

[0101] S420: Storing the electronic price tag location and price information in the cloud computing platform In step S420, the electronic price tag data is sent to the cloud computing platform via the network. It needs to be stored in the cloud for subsequent query, analysis and management. The specific steps are as follows: In the cloud computing platform, electronic price tag data It will be stored in a distributed database or cloud storage system. In order to facilitate efficient management, the data will be stored according to the unique identifier of the electronic price tag. and location For example, electronic price tag data It can be stored in a database table named TagData, and the table structure is:

[0102] In the cloud computing platform, the electronic price tag data can be classified and stored in layers according to different commodity categories, commodity locations or timestamps. For example, different electronic price tag data can be stored according to regions (such as "region A", "region B") or commodity types (such as "food", "home appliances") to improve retrieval efficiency in subsequent data queries.

[0103] In order to ensure data security, the electronic price tag data stored on the cloud platform will be redundantly backed up. This can be achieved through multi-copy storage technology, which can be backed up between different cloud servers or data centers to cope with hardware failures or network problems.

[0104] In addition to the location information and price information of the electronic price tag, the data packet also includes other metadata (such as timestamp, device ID, etc.) These metadata will be used for subsequent data synchronization, query and update.

[0105] Through these steps, the electronic price tag data D_{tagi} is stored in the cloud computing platform, ensuring the security and accessibility of the data in the cloud.

[0106] S430: Analyze and manage the stored electronic price tag data on the cloud computing platform, classify the data, update synchronously, and process abnormal data In step S430, the stored electronic price tag data Analysis and management will be carried out in the cloud computing platform. The specific steps are as follows: By classifying and indexing the stored data, the electronic price tag data can be classified and managed according to the product type, location or timestamp. For example, the data can be indexed by product type or region to facilitate quick retrieval of electronic price tag data of a specific category or region. The structure of the index table can be: The electronic price tag data It will be synchronized and updated to the master database of the cloud computing platform. If the data of an electronic price tag changes (for example, price update or location change), the relevant data synchronization mechanism will synchronize the updated data to all copies and terminal devices in a timely manner to ensure the consistency of cloud and terminal data. During the synchronization and update process, use scheduled tasks or real-time update mechanisms to ensure the timeliness of data.

[0107] During the analysis process, the cloud platform will perform anomaly detection on the electronic price tag data. If data anomalies are detected (for example, missing price information or incorrect location data), the system will automatically trigger the exception handling mechanism. Abnormal data can be handled in the following ways: Automatic correction: By connecting with the interface of the product management system, it can automatically obtain the latest price information or location data and update abnormal data.

[0108] Manual review: For data that cannot be automatically corrected, the system will mark it as "abnormal" and notify the administrator for manual review and processing.

[0109] Data recording: The processing process of abnormal data will be recorded and a log file will be generated for subsequent analysis and optimization.

[0110] The electronic price tag data stored in the cloud platform can also be used for big data analysis to provide business decision support. For example, by analyzing historical price data, you can find the price fluctuation pattern and optimize the pricing strategy. At the same time, based on the location information of the electronic price tag and product category data to analyze sales areas, customer behavior, etc.

[0111] Through the above steps, the stored electronic price tag data Be effectively managed and analyzed to ensure efficient operation of the system and accuracy of data.

[0112] Connection between the previous and next steps: In step S410, the electronic price tag position is accurately calculated and updated. and price information It is transmitted to the cloud computing platform via the network to provide input for subsequent data storage and management.

[0113] In step S420, the electronic price tag data It is stored on the cloud computing platform and efficiently managed through an index structure, providing a basis for subsequent analysis and synchronous updates.

[0114] In step S430, the stored electronic price tag data will be classified and updated synchronously, and the accuracy and consistency of the data will be ensured through an abnormal data processing mechanism to provide support for subsequent query and analysis.

[0115] Step S500 at least includes steps S510-S530: S510: Evaluate the current image processing and location recognition strategies based on the real-time feedback data, provide a basis for optimization, identify potential problems and make adjustments.

[0116] In step S510, the system first evaluates the effectiveness of the current image processing and location recognition strategy based on real-time feedback data. The specific process is as follows: The real-time feedback data includes the latest image data acquired by the multimodal sensor Real-time electronic price tag location candidate area , as well as the system's operating status and recognition accuracy data (such as recognition accuracy error and processing time). These data may include real-time image sequences, real-time location coordinates, differences between recognition results and true annotations, etc.

[0117] Through real-time feedback data and The effectiveness of the current image processing and location recognition strategies can be evaluated through analysis. For example, the effect evaluation indicators of the image processing module (such as image denoising accuracy, enhancement effect, etc.) and the accuracy error of location recognition can be calculated. , the formula is as follows:

[0118] in, For the real electronic price tag location, is the electronic price tag position predicted by the system, and n is the number of feedback data points.

[0119] Based on the evaluation results, potential problems that may exist in the current strategy can be identified. For example, if the recognition accuracy error in the real-time feedback data If the threshold is exceeded, it may be that there are deficiencies in the image processing algorithm or the location recognition algorithm. At this time, the system will identify key links that need to be adjusted, such as image denoising algorithms, enhancement algorithms, or the network structure of deep learning models.

[0120] Based on the problem identification results, corresponding adjustment suggestions are generated. These suggestions may include optimizing image denoising parameters, modifying image enhancement algorithms, adjusting convolutional neural network hyperparameters, etc., further providing a basis for subsequent model optimization.

[0121] Through the above steps, the system conducts a preliminary evaluation of the image processing and location recognition strategies based on real-time feedback data, and provides a basis for subsequent optimization.

[0122] S520: Optimize based on historical environmental data, evaluate past experience, adjust model parameters and identification strategies, and improve the long-term adaptability of the system.

[0123] In step S520, the system combines historical environmental data and optimizes the model by evaluating past experience to improve long-term adaptability. The specific steps are as follows: The historical environment data includes historical image data , Historical electronic price tag location data , as well as factors such as noise levels and lighting changes in historical environments. By integrating historical data, we can obtain information about system performance under different environmental conditions and help evaluate the adaptability of the current strategy under different situations.

[0124] Retrospective evaluation of the system's performance in different environments using historical data. For example, historical image data and historical location data Used to evaluate past recognition accuracy and image processing effects. Similar to step S510, calculate the recognition accuracy error under historical environment :

[0125] in, and are the real position and predicted position in the historical environment, is the number of historical data points.

[0126] Based on the recognition accuracy error in historical data The system will adjust the model's parameters and strategies based on other environmental factors (such as lighting changes, scene complexity, etc.). For example, if historical data shows that recognition accuracy is low in low-light environments, it may be necessary to adjust the image enhancement algorithm and add processing methods such as brightness enhancement.

[0127] Based on the feedback from historical environmental data, the system will propose specific optimization measures, such as adjusting the parameters of the image enhancement algorithm, modifying certain layers in the convolutional neural network, or increasing adaptability to specific environments (such as optimizing the recognition of low-light environments by training the model). These adjustments will affect subsequent real-time strategies to improve the long-term stability and adaptability of the system.

[0128] Through the above steps, combined with historical environmental data, the system can optimize image processing and location recognition strategies under different environmental conditions and provide feedback for subsequent reinforcement learning.

[0129] S530: Utilizes reinforcement learning algorithms to optimize image processing and location recognition strategies through continuous training and feedback, generating adjustment parameters that adapt to different retail environments In step S530, the system uses a reinforcement learning algorithm to continuously optimize the image processing and location recognition strategies and generate adaptive adjustment parameters. The specific process is as follows: In the reinforcement learning framework, the system is based on real-time feedback data. and historical data Interact with the environment and use the reward function to provide feedback on the effect of the current strategy. Specifically, the reward function R is defined as a comprehensive indicator of image recognition accuracy and processing efficiency, for example:

[0130] in, are the recognition accuracy errors in real-time and historical environments respectively, T is the processing time, is the weight coefficient.

[0131] In the framework of reinforcement learning, the system continuously interacts with the environment (i.e., continuous execution of image processing and location recognition) and optimizes the policy based on the reward function R. For example, Q-learning or deep Q network (DQN) is used to update the policy function Q(S,a), where S is the state (such as the current image and location data) and a is the action (such as adjusting the image enhancement parameters or the number of layers of the convolutional neural network). The update formula is as follows:

[0132] in, is the learning rate, is the discount factor, S' is the new state, and a' is the next possible action.

[0133] Through continuous training, the adjustment parameters generated by the system will be applied in image processing algorithms (such as denoising, enhancement) and location recognition strategies to optimize the performance of the overall system. For example, if the image enhancement algorithm fails to effectively improve the recognition accuracy in certain scenarios, reinforcement learning will guide the system to adjust parameters and try new strategies until the best performance is achieved.

[0134] Through the above optimization process, the system continuously generates adjustment parameters that adapt to different retail environments. ,These parameters will dynamically adjust the system's image processing and location recognition strategies to adapt to different environmental conditions.

[0135] Through continuous training and feedback of the reinforcement learning algorithm, the system can gradually improve its adaptability and recognition accuracy in various environments.

[0136] Connection between previous and subsequent steps: In step S510, the system evaluates the effectiveness of the current strategy based on real-time feedback data, identifies potential problems, and provides a basis for optimization.

[0137] In step S520, historical environmental data is combined, past experience is evaluated, and strategies and model parameters are adjusted to improve the long-term adaptability of the system.

[0138] In step S530, the image processing and location recognition strategies are optimized by combining real-time and historical data through a reinforcement learning algorithm to generate adjustment parameters that are suitable for different retail environments.

[0139] The key innovative features of the present invention include: (1) Multimodal sensor data enhancement: By using multimodal sensors such as RGB images, depth sensors, and infrared sensors, the system is able to obtain more comprehensive and reliable environmental data, ensuring high-quality image data in complex retail environments.

[0140] (2) Deep convolutional neural network (CNN) feature extraction: Use deep convolutional neural networks to automatically extract key information from images, effectively identify the shape, size, color and other features of electronic price tags, and optimize the accuracy of location recognition.

[0141] (3) Spatial information fusion and precise position calculation: Combine the spatial information of the image (such as perspective transformation, depth image, etc.) to calculate the real position coordinates of the electronic price tag and improve the accuracy of position recognition.

[0142] The following are its main beneficial effects: The electronic price tag location recognition method and system provided by the present invention can accurately identify the location of the electronic price tag and realize real-time synchronous update of price information through multimodal sensor data and deep learning algorithms in a complex and dynamically changing retail environment. Compared with the traditional image processing method, the multimodal data enhancement and deep convolutional neural network (CNN) of the present invention combined with the precise position calculation of spatial information effectively improve the accuracy of electronic price tag recognition, especially in complex environments such as lighting changes, product occlusion, and different viewing angles, which can ensure the efficiency and stability of location recognition. At the same time, through real-time feedback and optimization of historical data, the system can adaptively adjust the image processing and location recognition strategies, improve the long-term adaptability and stability of the system, and avoid the problems of recognition failure and system performance degradation caused by environmental changes in traditional methods. In addition, the updated electronic price tag data is synchronized to the cloud computing platform for storage and management, which realizes efficient storage, analysis and query of data and improves the overall operation and maintenance efficiency of the system.

[0143] Embodiment 2: Figure 2 FIG. 2 shows a structural block diagram of an electronic price tag location recognition system according to an embodiment of the present invention. Figure 2 As shown, the system may include: The data acquisition module 10 is used to obtain image data related to the retail environment from a variety of sensors. The sensors include RGB image sensors, depth sensors, infrared sensors, etc., through which commodity images and environmental parameters (such as light, temperature and humidity, etc.) in the retail environment are collected in real time. Specifically, the sensor can provide data under different viewing angles, lighting and occlusion conditions to ensure the extensiveness and effectiveness of the collected data. In addition, the data acquisition module is also responsible for transmitting the collected data to the data processing module 20 in real time for subsequent processing.

[0144] The data processing module 20 is used to perform preliminary processing on the image data obtained from the data acquisition module 10. The specific processing steps include image denoising, enhancement, standardization, etc. to ensure the consistency and accuracy of the data. First, the denoising algorithm is used to eliminate the noise and interference in the image, and then the clarity of the key information in the image is improved through enhancement processing. Finally, the image data is standardized to ensure that the image data input to the subsequent modules meets the predetermined format requirements. In addition, the data processing module is also responsible for transmitting the processed image data to the subsequent feature extraction and selection module 30.

[0145] The feature extraction and selection module 30 is responsible for extracting key features that can effectively identify the location of the electronic price tag from the processed image data. Through deep learning algorithms such as deep convolutional neural networks (CNN), local and global features in the image, such as the shape, size, color, etc. of the electronic price tag, are automatically extracted. Furthermore, the feature selection algorithm is used to screen out the most discriminative features to reduce redundant features and improve the accuracy and efficiency of subsequent location recognition. The extracted and selected features will be sent as input to the position calculation and synchronization update module 40.

[0146] The position calculation and synchronization update module 40 accurately calculates the position of the electronic price tag based on the feature data provided by the feature extraction and selection module 30. By combining the spatial information of the image (such as perspective transformation, depth information, etc.) and the candidate area of ​​the electronic price tag position obtained by the previous processing, the real position coordinates of the electronic price tag in the three-dimensional space are calculated, and the price information is updated synchronously through the interface with the commodity management system. This module ensures the accuracy of the electronic price tag position and the consistency of the commodity price and its corresponding electronic price tag data.

[0147] The cloud computing platform and data storage module 50 are responsible for storing and managing all the electronic price tag data generated by the system. Through an efficient cloud storage solution, all electronic price tag location and price information (including real-time updated data) will be securely stored in the cloud to ensure data persistence and reliability. At the same time, the cloud computing platform can also analyze the stored data, provide query interfaces, and support multi-terminal data access and management. Through data classification, synchronous update and abnormal data processing mechanisms, the high availability and consistency of the electronic price tag data on the cloud platform are ensured.

[0148] The real-time feedback and optimization module 60 is responsible for receiving feedback data from various modules of the system and optimizing the position recognition strategy. By real-time monitoring of the system's operating status and processing effect, the module can dynamically adjust the image processing algorithm and recognition strategy according to the actual operating data (such as recognition accuracy, processing speed, etc.), thereby optimizing system performance. The module can make fine adjustments based on real-time feedback data to improve the stability and accuracy of the system in different environments and ensure efficient recognition of electronic price tags.

[0149] The user interaction and visualization module 70 provides an intuitive user interface for the system, supporting real-time data display and interactive operation. Users can view the recognition results, price information and product status of the electronic price tag through this module, and can adjust or configure the system as needed. Specifically, this module displays the location and price information of the electronic price tag through a graphical interface to help users quickly understand and use the system. Through this module, users can effectively interact with the system to improve decision-making efficiency and user experience.

[0150] The system monitoring and adaptive module 80 is responsible for real-time monitoring of the operating status of the entire system, including hardware devices, data transmission, algorithm execution, etc. Through the adaptive learning mechanism, the module can automatically adjust various system parameters (such as image processing algorithms, model parameters, etc.) according to environmental changes and feedback data to ensure the adaptability and stability of the system in different retail environments. The module can also trigger alarms and perform fault diagnosis when abnormal situations occur to ensure the continuous and efficient operation of the system.

[0151] Through the design of the above system structure module, the electronic price tag location recognition method and system provided by the present invention have the following beneficial effects: (1) Efficiency and accuracy: By combining multimodal sensors and deep learning algorithms, the system can efficiently identify the location of electronic price tags in complex retail environments and simultaneously update the price information of the goods. The system can process data under different lighting, occlusion and viewing angles to ensure the accuracy of recognition.

[0152] (2) Real-time and flexibility: The system can collect and process image data in real time, and store and manage data through the cloud computing platform, ensuring real-time updating and high availability of price information. Through real-time feedback and optimization mechanisms, the system can adapt to different environmental changes and dynamically adjust strategies to improve the long-term adaptability of the system.

[0153] (3) Intelligence and adaptability: Through the combination of enhanced learning and historical environmental data, the system can continuously optimize image processing and location recognition strategies and generate adaptive adjustment parameters to ensure that the system always maintains optimal performance in an ever-changing retail environment.

[0154] (4) User-friendliness: Through the intuitive user interface, users can easily view and manage electronic price tag information and perform operation configuration, which improves user experience and operational convenience.

[0155] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A method for identifying the position of an electronic price tag, characterized in that: The steps include: Acquire real-time image data from a retail environment and enhance the image data through a multimodal sensor to obtain a standardized image sequence; De-noising and enhancing the standardized image sequence to optimize the image quality, and extracting image features through a deep convolutional neural network to generate a sequence of candidate regions for electronic price tag positions; Based on the candidate region sequence of the electronic price tag position, combined with the spatial information of the image, the real position coordinates of the electronic price tag are calculated; and the price of the commodity is synchronously updated according to the position and price information of the electronic price tag; Send the updated electronic price tag location and price information to the cloud computing platform for storage, analysis and management; Based on real-time data feedback and historical environmental data, image processing and location recognition strategies are optimized through reinforcement learning, adaptive adjustment parameters are generated, and subsequent recognition and update processes are tracked.

2. The method for identifying the position of an electronic price tag according to claim 1, characterized in that: Prior to the step of acquiring real-time image data from the retail environment, the method further includes: Multiple sensors are configured to acquire image data under different lighting, viewing angles and environmental changes, and the sensors include RGB image sensors, depth sensors and infrared sensors.

3. The method for identifying the position of an electronic price tag according to claim 1, characterized in that: The step of performing denoising and enhancement processing on the image sequence specifically comprises: Image denoising algorithm is used to eliminate noise in the image, and further image enhancement processing such as brightness and contrast is performed.

4. The method for identifying the position of an electronic price tag according to claim 1, characterized in that: The step of extracting image features through a deep convolutional neural network specifically includes: The image sequence is input into a deep convolutional neural network, the local features in the image are extracted through the convolution layer, and the data dimension is reduced through the pooling layer to generate a feature map containing key information of the image.

5. The method for identifying the position of an electronic price tag according to claim 4, characterized in that: The deep convolutional neural network includes multiple convolutional layers and pooling layers. The spatial features in the image are extracted layer by layer through the multi-layer network, and image features for location recognition are generated.

6. The method for identifying the position of an electronic price tag according to claim 1, characterized in that: The step of performing accurate position calculation based on the electronic price tag position candidate area sequence specifically includes: Combined with the spatial information of the image, the real position coordinates of the electronic price tag are calculated through perspective transformation and depth image information, and subsequent price synchronization is updated based on the coordinate information.

7. The method for identifying the position of an electronic price tag according to claim 6, characterized in that: The step of calculating the position coordinates of the electronic price tag through perspective transformation and depth information also includes: The electronic price tag candidate area is corrected using the camera internal and external parameters of the image, so as to accurately calculate its three-dimensional spatial position.

8. The method for identifying the position of an electronic price tag according to claim 1, characterized in that: The step of sending the updated electronic price tag location and price information to the cloud computing platform for storage, analysis and management specifically includes: The electronic price tag location and price information are transmitted to a cloud computing platform via a network. The cloud computing platform is used to store and manage data in real time and provide a data analysis and query interface.

9. The method for identifying the position of an electronic price tag according to claim 1, characterized in that: The step of optimizing the image processing and location recognition strategy by reinforcement learning specifically includes: Based on real-time feedback data and historical environmental data, the image processing and location recognition models are optimized through reinforcement learning algorithms, and adaptive adjustment parameters are generated to improve recognition accuracy and system adaptability.

10. An electronic price tag location recognition system, characterized in that: include: A data acquisition module is used to obtain image data related to the retail environment from a variety of sensors, including RGB image sensors, depth sensors, infrared sensors, etc., and to collect commodity images and environmental parameters in the retail environment in real time through these sensors; A data processing module, used for performing denoising, enhancement and standardization processing on the image data acquired from the data acquisition module, and transmitting the processed image data to subsequent modules; A feature extraction and selection module, used to extract key features that can effectively identify the position of the electronic price tag from the processed image data, and screen out the most discriminative features; A position calculation and synchronization update module, which is used to calculate the real position coordinates of the electronic price tag based on the extracted electronic price tag position candidate area features and combined with the spatial information of the image, and to synchronously update the price information of the product; Cloud computing platform and data storage module, used to store and manage all generated electronic price tag data, and provide data analysis, query and multi-terminal access functions; Real-time feedback and optimization module, which is used to receive feedback data from each module and dynamically adjust the image processing algorithm and recognition strategy according to the real-time data to optimize system performance; User interaction and visualization module, which is used to provide an intuitive user interface, display the location and price information of the electronic price tag, and support real-time data interaction and operation configuration; The system monitoring and adaptation module is used to monitor the operating status of the entire system in real time, adjust system parameters according to environmental changes through an adaptive learning mechanism, and ensure the stability and adaptability of the system in different retail environments.

Images