Commodity settlement processing method and apparatus

Abstract

Embodiments of the present specification provide a commodity settlement processing method and device, wherein the commodity settlement processing method comprises: in the process of commodity settlement of a store device of a merchant store, collecting a commodity image of a commodity to be settled and extracting a commodity feature, performing feature matching on the commodity feature, a device feature library of the store device and a network feature library, determining a candidate commodity according to a feature matching result, in the case that a target commodity corresponding to a commodity settlement instruction is not a candidate commodity, determining a feature synchronization type of the target commodity, and synchronizing the commodity feature of the current commodity image by submitting a commodity synchronization request to a server, so as to keep the commodity feature of the store device of the merchant store and the server synchronized.

Description

Technical Field

[0001] This document relates to the field of image processing technology, and in particular to a method and apparatus for processing commodity settlement. Background Technology

[0002] With the continuous development of internet technology, the commodity sales sector is transforming and upgrading towards digitalization and intelligence. The sales pace is also accelerating with the rapid changes in consumer demand. In the commodity settlement process, automated settlement has become a key direction for merchants to improve settlement efficiency. Among them, intelligent settlement devices that can achieve rapid settlement by automatically identifying goods are widely used in various merchant stores. However, as the scenarios for commodity sales increase, how to quickly settle commodity transactions in various scenarios has become a focus of attention in the industry. Summary of the Invention

[0003] This specification provides one or more embodiments of a product settlement processing method applied to store equipment in a merchant's store. The method includes: acquiring product images of products to be settled, and extracting product features from the product images to obtain product features; matching the product features with a device feature library and a network feature library of the store equipment, and determining candidate products based on the feature matching results; if the candidate products do not contain the target product corresponding to the product settlement instruction, determining the feature synchronization type of the target product; and submitting a product synchronization request corresponding to the feature synchronization type to the server to perform feature synchronization processing of the target product according to the feature synchronization type.

[0004] This specification provides one or more embodiments of another product settlement processing method applied to a server. The method includes: receiving a product synchronization request submitted by a store's equipment, carrying a product image of a target product; the product synchronization request is generated when the candidate products determined by feature matching between the product features of the product to be settled and the equipment feature library and network feature library of the store equipment do not include the target product corresponding to the product settlement instruction; performing feature synchronization detection on the product features of the target product according to the feature synchronization type corresponding to the product synchronization request; if the detection passes, performing feature synchronization processing on the product features according to the feature synchronization type deployed to the product feature library on the server.

[0005] This specification provides one or more embodiments of a merchandise checkout processing device, which operates in a merchant's store. The device includes: a feature extraction module configured to acquire merchandise images of goods to be settled and extract features from the merchandise images to obtain merchandise features; a feature matching module configured to match the merchandise features with a device feature library and a network feature library of the store equipment, and determine candidate goods based on the feature matching results; a synchronization type determination module configured to determine the feature synchronization type of the target goods if the candidate goods do not contain the target goods corresponding to the merchandise checkout instruction; and a feature synchronization processing module configured to submit a merchandise synchronization request corresponding to the feature synchronization type to a server to perform feature synchronization processing on the target goods according to the feature synchronization type.

[0006] This specification provides one or more embodiments of another commodity settlement processing apparatus, running on a server. The apparatus includes: a synchronization request receiving module configured to receive a commodity synchronization request submitted by a merchant's store equipment, carrying a commodity image of a target commodity; the commodity synchronization request is generated when the candidate commodities determined by feature matching of the commodity features of the commodity to be settled with the store equipment's device feature library and network feature library do not include the target commodity corresponding to the commodity settlement instruction; a feature synchronization detection module configured to perform feature synchronization detection on the commodity features of the target commodity according to the feature synchronization type corresponding to the commodity synchronization request; and a feature synchronization processing module configured to, if the detection passes, perform feature synchronization processing on the commodity features in a commodity feature library deployed on the server according to the feature synchronization type.

[0007] This specification provides one or more embodiments of a merchandise checkout processing device, including: a processor; and a memory configured to store computer-executable instructions, which, when executed, cause the processor to: acquire a merchandise image of a merchandise to be checked out, and extract features from the merchandise image to obtain merchandise features; perform feature matching between the merchandise features and a device feature library and a network feature library of a merchant's store equipment, and determine candidate merchandise based on the feature matching results; if the candidate merchandise does not contain a target merchandise corresponding to the merchandise checkout instruction, determine the feature synchronization type of the target merchandise; and submit a merchandise synchronization request corresponding to the feature synchronization type to a server to perform feature synchronization processing of the target merchandise according to the feature synchronization type.

[0008] This specification provides one or more embodiments of another merchandise settlement processing device, including: a processor; and a memory configured to store computer-executable instructions, which, when executed, cause the processor to: receive a merchandise synchronization request submitted by a store device of a merchant's store, carrying a merchandise image of a target merchandise; the merchandise synchronization request is generated when the candidate merchandise determined by feature matching of the merchandise features of the merchandise to be settled with the device feature library and network feature library of the store device does not include the target merchandise corresponding to the merchandise settlement instruction; and, according to the feature synchronization type corresponding to the merchandise synchronization request, perform feature synchronization detection on the merchandise features of the target merchandise. If the detection passes, perform feature synchronization processing on the merchandise features in a merchandise feature library deployed on a server according to the feature synchronization type.

[0009] This specification provides one or more embodiments of a computer-readable storage medium for storing computer-executable instructions. When executed, these instructions implement the following process: acquiring an image of a product to be settled, and extracting features from the image to obtain product features; matching the product features with a device feature library and a network feature library of a merchant's store equipment, and determining candidate products based on the matching results; if the candidate products do not include the target product corresponding to the settlement instruction, determining the feature synchronization type of the target product; and submitting a product synchronization request corresponding to the feature synchronization type to the server to perform feature synchronization processing on the target product according to the specified feature synchronization type.

[0010] This specification provides one or more embodiments of another computer-readable storage medium for storing computer-executable instructions, which, when executed, implement the following process: receiving a product synchronization request submitted by a store device of a merchant store, carrying a product image of a target product; the product synchronization request is generated when the candidate products determined by feature matching of the product features of the product to be settled with the device feature library and network feature library of the store device do not include the target product corresponding to the product settlement instruction; performing feature synchronization detection on the product features of the target product according to the feature synchronization type corresponding to the product synchronization request; if the detection passes, performing feature synchronization processing on the product features in the product feature library deployed on the server according to the feature synchronization type. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in one or more embodiments of this specification or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 A schematic diagram illustrating the implementation environment of a commodity settlement processing method provided in one or more embodiments of this specification;

[0013] Figure 2 A flowchart illustrating a commodity settlement processing method provided in one or more embodiments of this specification;

[0014] Figure 3 A flowchart illustrating a product settlement processing method applied in a cashier settlement scenario, provided for one or more embodiments of this specification;

[0015] Figure 4 A flowchart illustrating another product settlement processing method provided in one or more embodiments of this specification;

[0016] Figure 5 A schematic diagram of an embodiment of a commodity settlement processing device provided for one or more embodiments of this specification;

[0017] Figure 6 A schematic diagram of another embodiment of a commodity settlement processing device provided in one or more embodiments of this specification;

[0018] Figure 7 A schematic diagram of the structure of a commodity checkout processing device provided for one or more embodiments of this specification;

[0019] Figure 8 This is a schematic diagram of another commodity settlement processing device provided in one or more embodiments of this specification. Detailed Implementation

[0020] To enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of this document.

[0021] The merchandise settlement processing method provided in one or more embodiments of this specification can be applied to the merchandise settlement implementation environment of a merchant's store equipment. (Refer to...) Figure 1 The implementation environment includes at least: the store equipment 101 of the merchant's store and the server 102;

[0022] Among them, the store equipment 101 of the merchant store is equipped with a network feature library 101-1 and a device feature library 101-2. The network feature library 101-1 is used to store the synchronized product features synchronized from the server 102 and to synchronize the newly added product features to the device feature library 101-2; the device feature library 101-2 is used to store the features of products settled locally in the store.

[0023] The server 102 is equipped with a product feature library 102-1. Specifically, the product feature library 102-1 is used to store all product features within the merchant's scope. It can receive and process product synchronization requests submitted by the store equipment 101 and synchronize product features to the network feature library 101-1.

[0024] In this implementation environment, during the merchandise checkout process, store equipment 101 collects merchandise images of the merchandise to be settled and extracts merchandise features. The obtained merchandise features are then matched with the equipment feature library 101-2 and the network feature library 101-1. Based on the matching results, the feature synchronization type of the target merchandise is determined, and a merchandise synchronization request corresponding to the feature synchronization type is submitted to the server. Correspondingly, server 102 receives the merchandise synchronization request submitted by store equipment 101, performs feature synchronization detection on the merchandise features of the target merchandise according to the feature synchronization type corresponding to the merchandise synchronization request, and if the detection passes, performs feature synchronization with the network feature library 101-1 according to the feature synchronization type and updates the merchandise feature library 102-1, thereby keeping the merchandise features of the merchant's store equipment synchronized with those of the server.

[0025] Furthermore, a single merchant store may deploy multiple store devices, or other merchant stores under the same merchant may deploy corresponding store devices. The product settlement process for these store devices is the same as that of store device 101. They all extract features by collecting images of the products to be settled, and match them with their own device feature library and network feature library to determine candidate products. If the target product is not among the candidate products, the feature synchronization type is determined and a request is submitted to the server. Correspondingly, after receiving the product synchronization request submitted by the store device, the server 102 performs feature synchronization detection according to the same logic. If the detection passes, the server synchronizes the features with the network feature library according to the feature synchronization type and updates the product feature library 102-1, thereby keeping the product features of the merchant store's store devices synchronized with those of the server.

[0026] One or more embodiments of a commodity settlement processing method provided in this specification are as follows:

[0027] Reference Figure 2 The product settlement processing method provided in this embodiment can be used in the store equipment of a merchant's store. The method specifically includes steps S202 to S208.

[0028] Step S202: Collect product images of the goods to be settled, and extract product features from the product images to obtain product features.

[0029] The store equipment described in this embodiment refers to terminal equipment deployed in a merchant's store for performing goods settlement-related processing. The store equipment can collect images and can also be used for weighing. Specifically, the store equipment can be a terminal equipment equipped with an image acquisition component or a terminal equipment with an integrated weighing module. In practical applications, different merchant stores under the same merchant can deploy corresponding store equipment, and one or more store equipment can be deployed simultaneously in a single merchant store. For example, a large supermarket can deploy multiple store equipment in the fresh food area and snack area at the same time. In addition, the store equipment can be a handheld settlement terminal or a self-service settlement device that supports self-service settlement. For example, the user places the goods to be settled into the recognition area, and the store equipment completes the settlement of the goods. It can also be a mobile terminal device, such as a smart shopping cart, or an embedded settlement terminal, such as a smart shelf.

[0030] The goods to be settled refer to the goods selected by the user at the offline merchant store and to be settled through the store's equipment. Specifically, the goods to be settled can be goods settled by identifying the product category, such as fruits and vegetables without fixed packaging, or goods settled by weighing. In practical applications, the goods to be settled can be goods settled by scanning the barcode or entering the code through the store equipment, such as bottled beverages and daily necessities, or goods that need to be settled through self-service checkout equipment.

[0031] The product image can be captured by the store equipment, or it can be captured by a peripheral device connected to the store equipment. In this case, the process of capturing the product image of the product to be settled can be replaced by acquiring the product image of the product to be settled captured by the peripheral device connected to the store equipment.

[0032] In real-world scenarios, based on the aforementioned store equipment or peripherals connected to the store equipment capturing images of the goods to be settled, the product images can specifically be images captured during the weighing process, images captured during the identification of product categories, images captured during the scanning or input of codes, or images captured during the self-checkout process by the user through the self-checkout device.

[0033] It should be noted that product images can be standard images or personalized images of the merchant's store. That is, non-standard images formed due to differences in store environment or user operation. For example, product images can be overexposed images due to lighting, missing images that are obscured, or tilted images with poor angles.

[0034] Specifically, the product image can also be an image of the product to be settled from one or more angles. For example, the product image can be a complete frontal image of the product to be settled, a complete side image of the product to be settled, a complete back image of the product to be settled, or a composite image of the product to be settled from multiple angles.

[0035] Specifically, in the process of collecting product images of goods awaiting settlement, the collection triggering method of the store equipment can be that the user or the store clerk manually triggers the collection command of the store equipment after placing the goods. That is, the store clerk or user interacts with the store equipment to manually control the store equipment to collect images. For example, after the store clerk or user places the goods awaiting settlement in the designated collection area of ​​the store equipment, they interact with the store equipment through the touch screen or physical buttons to control the store equipment to collect product images. The collection triggering method of the store equipment can also be that the store equipment automatically collects product images. That is, after the user places the goods awaiting settlement in the designated collection area of ​​the store equipment, the store equipment detects the goods awaiting settlement and automatically collects the product image of the goods awaiting settlement. This embodiment does not limit this.

[0036] The product features refer to image features extracted from product images. These features can be extracted from multi-angle composite images, standard images, or personalized images. For example, product features can be extracted from overexposed images, missing images, or tilted images.

[0037] In practice, during the checkout process at a merchant's store, the store's equipment collects images of the goods to be settled and extracts features from the images to obtain product features. This provides a basis for subsequent matching calculations between the product features and the equipment feature library and the network feature library.

[0038] Furthermore, after the store equipment has completed the image acquisition of the goods to be settled, it can further extract features from the product images. In self-checkout scenarios, the user's self-checkout operation is random, such as placing the goods at an angle, laying them down, covering part of the goods with their hands, or only placing part of the goods in the self-checkout area. This can lead to problems such as angle deviation, partial occlusion, or incomplete information in the acquired product images, affecting the accuracy of feature extraction and thus the success rate of feature matching. In order to ensure that the store equipment can effectively extract product features in self-checkout scenarios, the store equipment can perform adaptive feature extraction based on the anomaly types of product images, thereby improving the accuracy of product feature extraction.

[0039] In one optional implementation of this embodiment, a feature extraction strategy is determined based on the anomaly type of the product image, and feature extraction is performed on the product image based on the extraction strategy, including:

[0040] If the anomaly type of the product image is angle deviation, the store equipment reads the preset standard angle feature template and extracts features from the product image based on the standard angle feature template;

[0041] If the anomaly type of the product image is partial occlusion, the product category is initially located, and the corresponding complete feature distribution template is called based on the confirmed product category. The product image is then used to extract features based on the complete feature distribution template.

[0042] Specifically, during the self-checkout process, when the store equipment detects that a product is placed at an angle or on its side, it determines that the abnormality of the product image is an angle deviation. The store equipment reads a preset standard angle feature template, which is generated based on the store equipment's historical self-checkout data and stored in the store equipment's feature library. It includes feature benchmarks for different angles such as when the product is placed upright or on its side. The store equipment determines the feature benchmark that is closest to the angle of the product image and performs feature extraction on the product image based on this feature benchmark, thereby reducing the impact of angle deviation on feature extraction.

[0043] When a store's automated system detects partial obstruction of a product, it performs a preliminary category determination based on the unobstructed area. If the product's barcode is detected, the system prioritizes scanning the barcode to obtain basic product information and determine its category. If the barcode is not detected, the system extracts features from the unobstructed area and performs a preliminary match between these features and its feature library to filter the product's category. For example, when a user checks out bananas at the automated system, if only a portion of the bananas is placed on the system or if the user obscures most of the bananas, the system will first scan the exposed portion. The system extracts features from the image, such as the curvature of the product and the color of its skin. These extracted features are then matched with local product features stored in the device's feature library to filter out bananas as a product category. After filtering out the product category, the store device calls the complete feature distribution template corresponding to that product to accurately extract the product's features and match them with the product's standard features. If the match is successful, the product is identified. The complete feature distribution template is generated based on the store's self-checkout data and stored in the device's feature library, containing the weight distribution of features in each area of ​​the product.

[0044] Step S204: Perform feature matching between the product features and the device feature library and network feature library of the store equipment, and determine candidate products based on the feature matching results.

[0045] As mentioned above, product images can be standard images or personalized images of merchant stores, i.e., non-standard images formed due to differences in store environment or user operation. Correspondingly, the local product features stored in the device feature library are product features obtained by feature extraction based on personalized images of merchant stores. For example, product features obtained by feature extraction of overexposed images, product features obtained by feature extraction of missing images, and product features obtained by feature extraction of tilted images, thereby improving the success rate of store equipment in recognizing personalized images.

[0046] Correspondingly, the synchronized product features stored in the network feature library include product features obtained by feature extraction based on standard images, such as product features obtained by feature extraction of correctly placed and appropriately lit product images, thereby improving the success rate of store equipment in recognizing standard product images.

[0047] The device feature library described in this embodiment is a database deployed locally on the store equipment. It is used to store local personalized product features, providing localized product features for the store equipment and reducing dependence on the network. The local product features corresponding to the product identifiers recorded in the device feature library can be obtained by feature extraction from the weighing and settlement image of the product to be settled at the current merchant's store, by scanning the QR code of the product to be settled, by generating product information manually entered by the store equipment, or by feature extraction from product images collected during the self-checkout process.

[0048] The network feature database is a database stored locally on the store equipment and synchronized with the product feature database deployed on the server. It is used to expand the product feature coverage of the store equipment. In practical applications, in order to ensure that the product identifiers recorded in the network feature database and the device feature database are synchronized and improve the accuracy of matching, in an optional implementation of this embodiment, the product identifiers recorded in the device feature database of the store equipment are synchronized with the product identifiers recorded in the network feature database of the store equipment.

[0049] It should be noted that the product identifiers recorded in the device feature library of the store equipment are consistent with those in the network feature library, but the corresponding product features are different. The local product features stored in the device feature library are product features obtained by extracting features from the personalized images of the merchant's store, while the synchronized product features stored in the network feature library are product features obtained by extracting features from standard images. Although the product identifiers are synchronized, the product features can be different, which improves the accuracy and success rate of product recognition.

[0050] A product feature library can be a database deployed on a server to store product features of various stores, providing data support for unified management of merchants. The product features stored in the product feature library are standard product features. Each product identifier in the product feature library corresponds to at least one product feature. Specifically, at least one product feature may include: product settlement features obtained by feature extraction from the weighing and settlement images of the same product in the store equipment of various stores of the same merchant; image features extracted from multi-angle composite images; and image features extracted from standard images.

[0051] In real-world scenarios, to improve the real-time performance and accuracy of product features in the product feature library, a mapping relationship can be established between product identifiers and product features in the product feature library. Product features can be obtained through feature extraction by store equipment. In one optional implementation method provided in this embodiment, any product identifier in the product feature library deployed on the server corresponds to at least one product feature.

[0052] At least one product feature includes: product settlement features obtained by feature extraction from the weighing and settlement images of the same product at various stores of the same merchant.

[0053] In practice, the store equipment can extract features during weighing and settlement to obtain product settlement features. Then, the store equipment can upload the product settlement features marked with product identifiers to the server according to a preset period. The server receives the product settlement features uploaded by the store, classifies them based on product identifiers, and associates product settlement features belonging to the same product identifier with that product identifier, thus constructing a mapping relationship between one product identifier and at least one product feature, thereby improving the real-time performance and accuracy of product features in the product feature library.

[0054] In addition, the store equipment can also extract features during self-checkout to obtain product settlement features. Then, the store equipment can upload the product settlement features marked with product identifiers to the server according to a preset period. The server receives the product settlement features uploaded by the store, classifies them based on product identifiers, and associates the product settlement features belonging to the same product identifier with that product identifier, thus building a mapping relationship between one product identifier and at least one product feature. For example, when a user places a product on the store equipment, the store equipment automatically takes pictures of the front and side of the product and extracts the product settlement features based on the images.

[0055] In practical applications, to ensure the synchronization of feature data between the network feature library of the store equipment and the product feature library of the server, the features of the network feature library of the store equipment can be automatically synchronized and updated during the operation of the store equipment through preset trigger commands. In an optional implementation provided in this embodiment, before the process of collecting product images of the products to be settled, the following steps are also included:

[0056] After detecting the start command of the store equipment, obtain the feature snapshot of the product feature library deployed on the server from the server.

[0057] The network feature library of store equipment is updated synchronously based on the product features contained in the feature snapshot.

[0058] Specifically, after detecting the start command of the store device, the store device actively pulls a feature snapshot from the product feature library on the server and updates the network feature library of the store device based on the product features contained in the feature snapshot. If there are old features in the network feature library, they are overwritten and updated. If the product feature library adds a product identifier and corresponding product features, the network feature library is supplemented and stored. This ensures that the feature data of the network feature library of the store device is synchronized with the product feature library of the server, thereby improving the accuracy and reliability of product settlement processing.

[0059] It should be noted that during the automatic synchronization and update of features in the network feature library, the product identifiers and features in the product feature library are consistent with those in the network feature library: the product feature library and the network feature library store the standard features of the product, while the personalized features of other stores are not within the synchronization scope. This allows the network feature library to better match with the device feature library, thereby improving the success rate and accuracy of product recognition.

[0060] In practice, after collecting product images of the goods to be settled and extracting features from the product images to obtain product features, the product features are matched with the equipment feature library and network feature library of the store equipment, and candidate products are determined based on the feature matching results.

[0061] Specifically, in the process of matching product features with the device feature library and network feature library of store equipment, product features can be matched with local product features in the device feature library and synchronous product features in the network feature library. Specifically, when product features come from personalized images of the store, such as overexposed or missing images, the device feature library can achieve more accurate matching. When product features come from standard images, such as correctly placed and appropriately lit images, the standard features in the network feature library can achieve better matching results. Candidate products are determined based on the feature matching results of the two libraries. By matching the device feature library and the network feature library in parallel, the recognition needs of personalized scenarios in the store are met, while the recognition of standardized scenarios is also covered, thereby improving the success rate and accuracy of feature matching.

[0062] In one optional implementation of this embodiment, the product features are matched with the device feature library and the network feature library of the store equipment, and candidate products are determined based on the feature matching results, including:

[0063] The product features are matched with the local product features in the device feature library to obtain the first matching product set, and the product features are matched with the synchronous product features in the network feature library to obtain the second matching product set.

[0064] The first and second matching product sets are merged and calculated to obtain at least one matching product as a candidate product.

[0065] In the specific implementation process, the product features are matched with the local product features in the device feature library to obtain the first matching product set. Specifically, the matching calculation can be performed by calculating feature similarity, filtering products with similarity reaching a threshold, and using the filtered products as the matching product set, or by comparing them through a matching model.

[0066] Similarly, the product features are matched with the synchronous product features in the network feature library to obtain a second matching product set. Specifically, the matching calculation can be performed by calculating feature similarity, filtering products with similarity reaching a threshold, and using the filtered products as the matching product set, or it can be compared using a matching model.

[0067] The first and second matching product sets are fused together to obtain at least one matching product as a candidate product. Specifically, the fusion calculation can be performed by setting different weights for the first and second matching product sets respectively, and then selecting the highest-ranked products as candidate products based on their respective weighted calculations. Alternatively, the intersection method can be used, that is, only products that exist in both the first and second matching product sets are retained, and the products obtained through the intersection operation are used as candidate products.

[0068] In addition, during the process of matching product features with the equipment feature library and network feature library of store equipment, the product features can first be matched with the equipment feature library of store equipment to obtain the matching results. The network feature library makes a judgment based on the matching results and determines the candidate products according to the judgment results.

[0069] In the specific implementation process, the product characteristics of the goods to be settled are matched with the local product characteristics in the equipment feature library to obtain an initial candidate product set. Specifically, the matching calculation can be carried out by calculating feature similarity and filtering out products with similarity reaching a threshold, and using the filtered products as the initial candidate product set, or it can be compared by a matching model.

[0070] If the initial candidate product set is not empty, that is, if there are local product features in the device feature library that match the product to be settled, the network feature library will no longer perform matching and the product in the initial candidate product set will be determined as the candidate product.

[0071] If the initial candidate product set is empty, meaning there are no matching local product features in the device feature library (e.g., the product is a new product or a product transferred from another store), then the product features of the product to be settled will be matched with the synchronous product features in the network feature library to filter out products with similarity reaching the threshold, and the filtered products will be determined as candidate products.

[0072] Furthermore, if there are no matching results in the network feature database, the store equipment will trigger an error message that the product cannot be identified, and at the same time provide an entry point for manual input, such as manually entering product information to generate temporary features for emergency product settlement.

[0073] In the above scenario, the step of matching product features with the equipment feature library and network feature library of store equipment and determining candidate products based on the feature matching results can be replaced by matching product features with the equipment feature library of store equipment and obtaining matching results, making a judgment based on the matching results of the network feature library, and determining candidate products based on the judgment results.

[0074] Step S206: If the candidate products do not include the target product corresponding to the product settlement instruction, determine the feature synchronization type of the target product.

[0075] In practice, after completing the feature matching of the product characteristics and determining the candidate products, the store equipment first determines whether the candidate products contain the target product corresponding to the product settlement instruction. If the candidate products do not contain the target product, the feature synchronization type of the target product can be determined to improve the success rate of the settlement process. In addition, if the candidate products contain the target product, settlement processing can be carried out based on the target product, such as executing the settlement process according to the preset price of the target product.

[0076] Among them, the product settlement instruction refers to the settlement instruction initiated through the store equipment, which is used to lock the settlement object and provide a basis for determining whether the candidate products include the target product. The product settlement instruction can be initiated by the user or by the store staff. Specifically, the product settlement instruction includes: when the candidate products include the target product, the user or staff selects the corresponding candidate product to generate the product settlement instruction; when the candidate products do not include the target product, the staff enters the target product barcode to generate the product settlement instruction.

[0077] Among them, feature synchronization type refers to the type of feature synchronization request that a store device initiates to the server when the candidate products do not include the target product. Feature synchronization type includes outlier feature synchronization and new product feature synchronization.

[0078] In one optional implementation of this embodiment, determining the feature synchronization type of the target product includes:

[0079] If the network feature database stores the product identifier of the target product, then determine the feature synchronization type as outlier feature synchronization.

[0080] If not, confirm the feature synchronization type as new product feature synchronization.

[0081] In practice, the feature synchronization type can be determined based on whether the target product's identifier is stored in the network feature library of the store equipment. Specifically, if the target product's identifier is stored in the network feature library of the store equipment, it means that the target product has already completed product feature entry on the server or in other stores. The reason for not including the target product could be that the feature corresponding to the product identifier in the store equipment's network feature library is abnormal, or that the feature corresponding to the product identifier in the store equipment's network feature library is missing. In this case, the feature synchronization type of the target product is determined to be outlier feature synchronization. If the target product's identifier is not stored in the network feature library of the store equipment, it can be considered that the target product is being settled with the current merchant for the first time. The product identifier and corresponding product features of the target product are not recorded in the network feature library, the device feature library, and the server's product feature library. In this case, the feature synchronization type of the target product is determined to be new product feature synchronization.

[0082] Step S208: Submit a product synchronization request corresponding to the feature synchronization type to the server to perform feature synchronization processing of the target product according to the feature synchronization type.

[0083] The product synchronization request described in this embodiment refers to a request submitted by the store equipment to the server after determining the feature synchronization type, for synchronizing the features of the target product. Specifically, the information carried in the product synchronization request includes: the product image of the target product, the product features of the target product, the feature synchronization type of the target product, and / or the basic information of the target product. The basic information of the target product can be the product barcode and / or product name manually entered by the store staff.

[0084] In practice, after determining the feature synchronization type of the target product, the store equipment constructs a product synchronization request based on the feature synchronization type and submits it to the server. After receiving the product synchronization request, the server can perform feature synchronization processing of the target product according to the feature synchronization type.

[0085] As mentioned above, feature synchronization types include new product feature synchronization and outlier feature synchronization. Specifically, for new product feature synchronization, in one optional implementation of this embodiment, the feature synchronization processing of the target product is performed according to the feature synchronization type, and is implemented in the following way:

[0086] If the feature synchronization type is new product feature synchronization, feature deduplication detection is performed on the product image carried in the product synchronization request based on the product feature library deployed on the server.

[0087] After the detection is passed, the product characteristics are synchronized to the store equipment of each merchant's store so as to update the product characteristics to the network characteristic database of each merchant's store equipment.

[0088] In the specific implementation process, if the feature synchronization type is new product feature synchronization, the product image carried in the product synchronization request is subjected to feature deduplication detection based on the product feature library deployed on the server. Specifically, feature deduplication detection can be performed by the server extracting features from the product image based on the product feature library deployed on the server, and comparing the extracted product features with the product features in the product feature library. If the similarity is lower than the threshold, the detection is deemed to have passed. If the similarity is higher than the threshold, a "product already exists" prompt is returned to the store device, and the feature synchronization process is terminated.

[0089] Furthermore, if the similarity is below a threshold, i.e., the feature deduplication detection passes, the server synchronizes the product features of the target product with the store equipment of each merchant's store, thereby ensuring feature synchronization between the store and the server. In one optional implementation of this embodiment, synchronizing product features with the store equipment of each merchant's store includes:

[0090] Create synchronous tasks for product features and add them to the asynchronous task queue for task execution;

[0091] The task execution includes: submitting product features to the IoT center connected to the store equipment of each merchant's store, and pushing product features to the store equipment of each merchant's store through the IoT center.

[0092] In the specific implementation process, after the feature deduplication detection passes, the server creates a synchronization task for the product features and uploads it to the asynchronous task queue for task execution. Specifically, the task execution includes: submitting product features to the IoT center connected to the store devices of each merchant store, and pushing the product features to the store devices of each merchant store through the IoT center, so as to ensure that the product features of the stores and the server are synchronized. For example, if a store submits a new product synchronization request for fruit A, after the feature deduplication detection passes, the server pushes the features of fruit A to the other stores of the chain supermarket to which the store belongs through the IoT center. The network feature database of the stores involved adds the feature and the corresponding product identifier, so that it can be directly matched when settling for fruit A.

[0093] After the new product features are synchronized to the network feature library, the network feature library will trigger an identifier synchronization mechanism with the device feature library, that is, to synchronize the newly added product identifier to the device feature library of the store equipment, ensuring that the device feature library contains a product identifier corresponding to the new product.

[0094] For outlier feature synchronization, this embodiment provides an optional implementation method in which the feature synchronization processing of the target product is performed according to the feature synchronization type, and is implemented in the following way:

[0095] If the feature synchronization type is outlier feature synchronization, the product features are used as outlier features for outlier feature detection; outlier feature detection includes inputting the outlier features into the outlier detection model to obtain the detection results;

[0096] After outlier detection passes, the outlier features are stored in the product feature library deployed on the server and mapped to the product identifier of the target product.

[0097] In the specific implementation process, if the feature synchronization type is outlier feature synchronization, after the server receives the product synchronization request, it uses the product features carried in the product synchronization request as outlier features for outlier feature detection. Specifically, the product features can be added to the outlier feature pool for outlier feature detection. Outlier feature detection includes: inputting the outlier features into the outlier detection model for outlier feature detection; the outlier detection model analyzes the Euclidean distance between the outlier feature and the product features corresponding to the same product identifier in the network feature library; if the distance is less than or equal to the threshold, the detection is deemed successful, and the outlier feature is stored in the product feature library deployed on the server and mapped to the product identifier of the target product; if the distance is greater than the threshold, the detection is deemed unsuccessful, and a "re-collect image" prompt is returned to the store equipment.

[0098] After outlier detection is passed, the outlier features are stored in the server's product feature library and mapped to the product identifier of the target product. Specifically, after completing outlier detection, the server establishes a mapping relationship between the outlier features and the product identifier based on the product identifier of the target product, thereby completing the storage of the outlier features.

[0099] In addition, to improve merchants' unified management and control capabilities across stores, in one optional implementation of this embodiment, the product features in the product feature library deployed on the server include: product features obtained by extracting features from new product images uploaded by the merchant's authorized devices.

[0100] Specifically, merchants can directly upload standard images and preset product identifiers for new products through their authorized devices. The authorized device automatically constructs a synchronization request for the product and submits it to the server. The server verifies the device's permissions, and after confirming that the permissions are granted, it receives the synchronization request, extracts features from the new product image uploaded by the merchant's authorized device, and stores the obtained product features in the server's product feature library. Then, the product features are pushed to each store. For example, if a chain supermarket headquarters introduces a new product A, the staff at the merchant headquarters submit the image and identifier of new product A to the server through an authorized device. After verifying the device's permissions, the server extracts features from the image of new product A, stores the image features in the product feature library, and then pushes it to each store.

[0101] In summary, the product settlement processing method for store equipment in merchant stores provided in this embodiment first acquires product images of the products to be settled during the product settlement process, and extracts product features from the product images to provide basic data support for subsequent feature matching. Secondly, in order to improve the success rate and accuracy of product recognition, the obtained product features are matched with the device feature library and network feature library of the store equipment, and candidate products are determined based on the matching results. Then, in order to ensure the accuracy of feature synchronization, if the candidate products do not include the target product, the feature synchronization type of the target product is determined. Finally, a product synchronization request corresponding to the feature synchronization type is submitted to the server, and the server performs feature synchronization processing of the target product according to the feature synchronization type, thereby keeping the product features of the store equipment in the merchant store synchronized with those of the server.

[0102] Furthermore, the product settlement processing method for store equipment provided in this embodiment improves the success rate of feature matching and the accuracy of candidate products by matching and calculating product features with equipment feature libraries and network feature libraries, and then performing fusion calculation based on the matching calculation results in the feature matching stage. In the new product feature synchronization stage, the server performs feature deduplication detection based on the network feature library, which improves the reliability of features. In the outlier feature synchronization stage, outlier feature detection improves the fault tolerance of feature matching, thereby improving the success rate and accuracy of product recognition.

[0103] Steps S202 to S208 provided in this embodiment can be executed by the store equipment of the merchant's store. It should be noted that the steps S202 to S208 executed by the store equipment and steps S402 to S406 executed by the server in the following embodiment can cooperate with each other during the execution process. Therefore, when reading this embodiment, please refer to the corresponding content of steps S402 to S406 provided in the following method embodiment, and when reading the following method embodiment, please refer to the corresponding content of steps S202 to S208 provided in this embodiment.

[0104] The following example uses a product settlement processing method provided in this embodiment applied to a merchant's store equipment in a checkout scenario, combined with... Figure 3 The commodity settlement processing method provided in this embodiment will be further explained below. See [link to documentation]. Figure 3 The product settlement processing method applied to the cashier settlement scenario includes the following steps.

[0105] Step S302: Collect product images of the goods to be settled.

[0106] Step S304: Extract features from the product image to obtain product features.

[0107] Step S306: Match the product features with the equipment feature library and network feature library of the store equipment to obtain the first matching product set and the second matching product set.

[0108] Step S308: Perform a fusion calculation based on the first matching product set and the second matching product set to obtain candidate products.

[0109] Step S310: If the candidate products do not include the target product corresponding to the product settlement instruction, determine the feature synchronization type of the target product.

[0110] Step S312: Submit a product synchronization request corresponding to the feature synchronization type to the server.

[0111] Step S314: Receive the product synchronization request submitted by the store equipment.

[0112] Step S316: If the feature synchronization type is new product feature synchronization, perform feature deduplication detection on the product image based on the product feature library.

[0113] Step S318: After the detection is passed, synchronize the product features to the store equipment of each merchant's store.

[0114] Step S320: If the feature synchronization type is outlier feature synchronization, add the product features as outliers to the outlier feature pool for outlier feature detection.

[0115] Step S322: After outlier detection passes, the outlier features are stored in the product feature library and mapped to the product identifier of the target product.

[0116] Step S324: Synchronize product features with the store equipment of each merchant's store.

[0117] In this embodiment, steps S302 to S312 are executed by the store equipment of the merchant's store. It should be noted that steps S302 to S312 executed by the store equipment of the merchant's store can cooperate with steps S314 to S324 executed by the server in the following embodiment. Therefore, when reading this embodiment, please refer to the corresponding content of steps S314 to S324 provided in the following method embodiment, and when reading the following method embodiment, please refer to the corresponding content of steps S302 to S312 provided in this embodiment.

[0118] It should be noted that any one or more steps in steps S302 to S312 can be combined with any one or more steps in steps S202 to S208 to form a new implementation method according to the needs of implementation and deployment. In addition, any one or more technical features in steps S302 to S312 can be selected and combined with any one or more technical features provided in steps S202 to S208 to form a new implementation method according to the actual deployment needs. Alternatively, any one or more technical features in steps S302 to S312 can be replaced with any one or more technical features provided in steps S202 to S208 to form a new implementation method according to the actual deployment needs. These will not be elaborated on here.

[0119] One or more embodiments of another commodity settlement processing method provided in this specification are as follows:

[0120] Reference Figure 4 The product settlement processing method provided in this embodiment is applied to the server side, and the method specifically includes steps S402 to S406.

[0121] Step S402: Receive a product synchronization request from the store's equipment, which carries a product image of the target product.

[0122] The store equipment described in this embodiment refers to terminal equipment deployed in a merchant's store for performing goods settlement-related processing. The store equipment can collect images and can also be used for weighing. Specifically, the store equipment can be a terminal equipment equipped with an image acquisition component or a terminal equipment with an integrated weighing module. In practical applications, different merchant stores under the same merchant can deploy corresponding store equipment, and one or more store equipment can be deployed simultaneously in a single merchant store. For example, a large supermarket can deploy multiple store equipment in the fresh food area and snack area at the same time. In addition, the store equipment can be a handheld settlement terminal or a self-service settlement device that supports self-service settlement. For example, the user places the goods to be settled into the recognition area, and the store equipment completes the settlement of the goods. It can also be a mobile terminal device, such as a smart shopping cart, or an embedded settlement terminal, such as a smart shelf.

[0123] The product image can be captured by the store equipment, or it can be captured by a peripheral device connected to the store equipment. In this case, the process of capturing the product image of the product to be settled can be replaced by acquiring the product image of the product to be settled captured by the peripheral device connected to the store equipment.

[0124] In real-world scenarios, based on the aforementioned store equipment or peripherals connected to the store equipment capturing images of the goods to be settled, the product images can specifically be images captured during the weighing process, images captured during the identification of product categories, images captured during the scanning or input of codes, or images captured during the self-checkout process by the user through the self-checkout device.

[0125] It should be noted that product images can be standard images or personalized images of the merchant's store. That is, non-standard images formed due to differences in store environment or user operation. For example, product images can be overexposed images due to lighting, missing images that are obscured, or tilted images with poor angles.

[0126] Specifically, the product image can also be an image of the product to be settled from one or more angles. For example, the product image can be a complete frontal image of the product to be settled, a complete side image of the product to be settled, a complete back image of the product to be settled, or a composite image of the product to be settled from multiple angles.

[0127] Specifically, in the process of collecting product images of goods awaiting settlement, the collection triggering method of the store equipment can be that the user or the store clerk manually triggers the collection command of the store equipment after placing the goods. That is, the store clerk or user interacts with the store equipment to manually control the store equipment to collect images. For example, after the store clerk or user places the goods awaiting settlement in the designated collection area of ​​the store equipment, they interact with the store equipment through the touch screen or physical buttons to control the store equipment to collect product images. The collection triggering method of the store equipment can also be that the store equipment automatically collects product images. That is, after the user places the goods awaiting settlement in the designated collection area of ​​the store equipment, the store equipment detects the goods awaiting settlement and automatically collects the product image of the goods awaiting settlement. This embodiment does not limit this.

[0128] The server can be deployed at the merchant's headquarters or in the cloud to manage the product feature data of each merchant's store, receive and process product synchronization requests from store equipment. The server has a product feature library, which stores standard product features. Each product identifier in the product feature library corresponds to at least one product feature. Specifically, at least one product feature may include: product settlement features obtained by feature extraction from the weighing and settlement images of the same product in the store equipment of each merchant's stores of the same merchant; image features extracted from multi-angle composite images; and image features extracted from standard images.

[0129] In real-world scenarios, to improve the real-time performance and accuracy of product features in the product feature library, a mapping relationship can be established between product identifiers and product features in the product feature library. Product features can be obtained through feature extraction by store equipment. In one optional implementation method provided in this embodiment, any product identifier in the product feature library deployed on the server corresponds to at least one product feature.

[0130] At least one product feature includes: product settlement features obtained by feature extraction from the weighing and settlement images of the same product at various stores of the same merchant.

[0131] In practice, the store equipment can extract features during weighing and settlement to obtain product settlement features. Then, the store equipment can upload the product settlement features marked with product identifiers to the server according to a preset period. The server receives the product settlement features uploaded by the store, classifies them based on product identifiers, and associates product settlement features belonging to the same product identifier with that product identifier, thus constructing a mapping relationship between one product identifier and at least one product feature, thereby improving the real-time performance and accuracy of product features in the product feature library.

[0132] In addition, the store equipment can also extract features during self-checkout to obtain product settlement features. Then, the store equipment can upload the product settlement features marked with product identifiers to the server according to a preset period. The server receives the product settlement features uploaded by the store, classifies them based on product identifiers, and associates the product settlement features belonging to the same product identifier with that product identifier, thus building a mapping relationship between one product identifier and at least one product feature. For example, when a user places a product on the store equipment, the store equipment automatically takes pictures of the front and side of the product and extracts the product settlement features based on the images.

[0133] In practical applications, to ensure the synchronization of feature data between the network feature library of the store equipment and the product feature library of the server, the features of the network feature library of the store equipment can be automatically synchronized and updated during the operation of the store equipment through preset trigger commands. In an optional implementation provided in this embodiment, before the process of collecting product images of the products to be settled, the following steps are also included:

[0134] After detecting the start command of the store equipment, obtain the feature snapshot of the product feature library deployed on the server from the server.

[0135] The network feature library of store equipment is updated synchronously based on the product features contained in the feature snapshot.

[0136] Specifically, after detecting the start command of the store device, the store device actively pulls a feature snapshot from the product feature library on the server and updates the network feature library of the store device based on the product features contained in the feature snapshot. If there are old features in the network feature library, they are overwritten and updated. If the product feature library adds a product identifier and corresponding product features, the network feature library is supplemented and stored. This ensures that the feature data of the network feature library of the store device is synchronized with the product feature library of the server, thereby improving the accuracy and reliability of product settlement processing.

[0137] It should be noted that during the automatic synchronization and update of features in the network feature library, the product identifiers and features in the product feature library are consistent with those in the network feature library: the product feature library and the network feature library store the standard features of the product, while the personalized features of other stores are not within the synchronization scope. This allows the network feature library to better match with the device feature library, thereby improving the success rate and accuracy of product recognition.

[0138] Optionally, a product synchronization request is generated if the candidate products identified by matching the product characteristics of the product to be settled with the device feature library and network feature library of the store equipment do not include the target product corresponding to the product settlement instruction.

[0139] In the specific execution process, the product characteristics of the goods to be settled are matched with the equipment feature library and network feature library of the store equipment to determine candidate goods, thereby improving the success rate and accuracy of feature matching. In an optional implementation method provided in this embodiment, the product characteristics are matched with the equipment feature library and network feature library of the store equipment, and candidate goods are determined based on the feature matching results, including:

[0140] The product features are matched with the local product features in the device feature library to obtain the first matching product set, and the product features are matched with the synchronous product features in the network feature library to obtain the second matching product set.

[0141] The first and second matching product sets are merged and calculated to obtain at least one matching product as a candidate product.

[0142] In the specific implementation process, the product features are matched with the local product features in the device feature library to obtain the first matching product set. Specifically, the matching calculation can be done by calculating feature similarity, filtering products with similarity reaching the threshold, and using the filtered products as the matching product set, or by comparing them through a matching model.

[0143] Similarly, the product features are matched with the synchronous product features in the network feature library to obtain a second matching product set. Specifically, the matching calculation can be performed by calculating feature similarity, filtering products with similarity reaching a threshold, and using the filtered products as the matching product set, or it can be compared using a matching model.

[0144] The first and second matching product sets are fused together to obtain at least one matching product as a candidate product. Specifically, the fusion calculation can be performed by setting different weights for the first and second matching product sets respectively, and then selecting the highest-ranked products as candidate products based on their respective weighted calculations. Alternatively, the intersection method can be used, that is, only products that exist in both the first and second matching product sets are retained, and the products obtained through the intersection operation are used as candidate products.

[0145] In addition, during the process of matching product features with the equipment feature library and network feature library of store equipment, the product features can first be matched with the equipment feature library of store equipment to obtain the matching results. The network feature library makes a judgment based on the matching results and determines the candidate products according to the judgment results.

[0146] In the specific implementation process, the product characteristics of the goods to be settled are matched with the local product characteristics in the equipment feature library to obtain an initial candidate product set. Specifically, the matching calculation can be carried out by calculating feature similarity and filtering out products with similarity reaching a threshold, and using the filtered products as the initial candidate product set, or it can be compared by a matching model.

[0147] If the initial candidate product set is not empty, that is, if there are local product features in the device feature library that match the product to be settled, the network feature library will no longer perform matching and the product in the initial candidate product set will be determined as the candidate product.

[0148] If the initial candidate product set is empty, meaning there are no matching local product features in the device feature library (e.g., the product is a new product or a product transferred from another store), then the product features of the product to be settled will be matched with the synchronous product features in the network feature library to filter out products with similarity reaching the threshold, and the filtered products will be determined as candidate products.

[0149] Furthermore, if there are no matching results in the network feature database, the store equipment will trigger an error message that the product cannot be identified, and at the same time provide an entry point for manual input, such as manually entering product information to generate temporary features for emergency product settlement.

[0150] Step S404: Based on the feature synchronization type corresponding to the product synchronization request, perform feature synchronization detection on the product features of the target product.

[0151] The feature synchronization type described in this embodiment refers to the type of feature synchronization request that a store device initiates to the server when the candidate products do not include the target product. Feature synchronization types include outlier feature synchronization and new product feature synchronization.

[0152] In one optional implementation of this embodiment, determining the feature synchronization type of the target product includes:

[0153] If the network feature database stores the product identifier of the target product, then determine the feature synchronization type as outlier feature synchronization.

[0154] If not, confirm the feature synchronization type as new product feature synchronization.

[0155] In practice, the feature synchronization type can be determined based on whether the target product's identifier is stored in the network feature library of the store equipment. Specifically, if the target product's identifier is stored in the network feature library of the store equipment, it means that the target product has already completed product feature entry on the server or in other stores. The reason for not including the target product could be that the feature corresponding to the product identifier in the store equipment's network feature library is abnormal, or that the feature corresponding to the product identifier in the store equipment's network feature library is missing. In this case, the feature synchronization type of the target product is determined to be outlier feature synchronization. If the target product's identifier is not stored in the network feature library of the store equipment, it can be considered that the target product is being settled with the current merchant for the first time. The product identifier and corresponding product features of the target product are not recorded in the network feature library, the device feature library, and the server's product feature library. In this case, the feature synchronization type of the target product is determined to be new product feature synchronization.

[0156] In specific implementation, the server can perform feature synchronization detection of the target product according to the feature synchronization type. In one optional implementation provided in this embodiment, feature synchronization detection of the target product's features is performed according to the feature synchronization type corresponding to the product synchronization request, including:

[0157] Based on the product feature library deployed on the server, feature deduplication detection is performed on the product images carried in the product synchronization request, or product features are added as outlier features to the outlier feature pool for outlier feature detection; outlier feature detection includes inputting outlier features into the outlier detection model to obtain detection results.

[0158] In the specific implementation process, if the feature synchronization type is new product feature synchronization, the product image carried in the product synchronization request is subjected to feature deduplication detection based on the product feature library deployed on the server. Specifically, feature deduplication detection can be performed by the server extracting features from the product image based on the product feature library deployed on the server, and comparing the extracted product features with the product features in the product feature library. If the similarity is lower than the threshold, the detection is deemed to have passed. If the similarity is higher than the threshold, a "product already exists" prompt is returned to the store device, and the feature synchronization process is terminated.

[0159] If the feature synchronization type is outlier feature synchronization, after receiving the product synchronization request, the server adds the product features carried in the product synchronization request as outlier features to the outlier feature pool for outlier feature detection. Specifically, outlier feature detection includes: inputting the outlier feature into the outlier detection model for outlier feature detection; the outlier detection model analyzes the Euclidean distance between the outlier feature and the product features corresponding to the same product identifier in the network feature library; if the distance is less than or equal to the threshold, the detection is deemed successful, and the outlier feature is stored in the product feature library deployed on the server and mapped to the product identifier of the target product; if the distance is greater than the threshold, the detection is deemed unsuccessful, and a "re-capture image" prompt is returned to the store equipment.

[0160] Step S406: If the detection passes, perform feature synchronization processing of the product features to the product feature library deployed on the server according to the feature synchronization type.

[0161] In the specific implementation process, after the feature synchronization detection on the server side passes, feature synchronization processing is performed on the product feature library according to the feature type. In one optional implementation method provided in this embodiment, feature synchronization processing of product features is performed on the product feature library deployed on the server side according to the feature synchronization type, including:

[0162] If the feature synchronization type is new product feature synchronization, synchronize the product features to the store equipment of each merchant's store to update the product features to the network feature database of each merchant's store equipment;

[0163] If the feature synchronization type is outlier feature synchronization, the outlier features will be stored in the product feature library deployed on the server and mapped to the product identifier of the target product.

[0164] Specifically, if the feature synchronization type is new product feature synchronization, the server needs to synchronize product features with the store equipment of each merchant's store. In one optional implementation method provided in this embodiment, synchronizing product features with the store equipment of each merchant's store includes:

[0165] Create synchronous tasks for product features and add them to the asynchronous task queue for task execution;

[0166] The task execution includes: submitting product features to the IoT center connected to the store equipment of each merchant's store, and pushing product features to the store equipment of each merchant's store through the IoT center.

[0167] In the specific implementation process, after the feature deduplication detection passes, the server creates a synchronization task for the product features and uploads it to the asynchronous task queue for task execution. Specifically, the task execution includes: submitting product features to the IoT center connected to the store devices of each merchant store, and pushing the product features to the store devices of each merchant store through the IoT center, so as to ensure that the product features of the stores and the server are synchronized. For example, if a store submits a new product synchronization request for fruit A, after the feature deduplication detection passes, the server pushes the features of fruit A to the other stores of the chain supermarket to which the store belongs through the IoT center. The network feature database of the stores involved adds the feature and the corresponding product identifier, so that it can be directly matched when settling for fruit A.

[0168] After the new product features are synchronized to the network feature library, the network feature library will trigger an identifier synchronization mechanism with the device feature library, that is, to synchronize the newly added product identifier to the device feature library of the store equipment, ensuring that the device feature library contains a product identifier corresponding to the new product.

[0169] The following example uses a product settlement processing method provided in this embodiment applied to the server side, specifically in a cashier settlement scenario, as an example. Figure 3 The commodity settlement processing method provided in this embodiment will be further explained below. See [link to documentation]. Figure 3 The product settlement processing method applied to the cashier settlement scenario specifically includes the following steps:

[0170] Step S314: Receive the product synchronization request submitted by the store equipment.

[0171] Step S316: If the feature synchronization type is new product feature synchronization, perform feature deduplication detection on the product image based on the product feature library.

[0172] Step S318: After the detection is passed, synchronize the product features to the store equipment of each merchant's store.

[0173] Step S320: If the feature synchronization type is outlier feature synchronization, add the product features as outliers to the outlier feature pool for outlier feature detection.

[0174] Step S322: After outlier detection passes, the outlier features are stored in the product feature library and mapped to the product identifier of the target product. The product features are then synchronized to the store equipment of each merchant's store.

[0175] Step S324: Synchronize product features with the store equipment of each merchant's store.

[0176] It should be noted that any one or more steps in steps S314 to S324 can be combined with any one or more steps in steps S402 to S406 to form a new implementation method according to the needs of implementation and deployment. In addition, any one or more technical features in steps S314 to S324 can be selected and combined with any one or more technical features provided in steps S402 to S406 to form a new implementation method according to the actual deployment needs. Alternatively, any one or more technical features in steps S314 to S324 can be replaced with any one or more technical features provided in steps S402 to S406 to form a new implementation method according to the actual deployment needs. These will not be elaborated on here.

[0177] The following is an embodiment of a commodity checkout processing device provided in this specification:

[0178] In the above embodiments, a product settlement processing method is provided, and correspondingly, a product settlement processing device is also provided, which operates in the store equipment of the merchant's store, and will be described below with reference to the accompanying drawings.

[0179] Reference Figure 5 The diagram shows an embodiment of a commodity settlement processing device provided in this embodiment.

[0180] Since the apparatus embodiments correspond to the method embodiments, the descriptions are relatively simple. For relevant parts, please refer to the corresponding descriptions of the method embodiments provided above. The apparatus embodiments described below are merely illustrative.

[0181] This embodiment provides a merchandise checkout processing device, which operates in a merchant's store. The device includes:

[0182] The feature extraction module 502 is configured to acquire product images of the products to be settled and to extract product features from the product images.

[0183] The feature matching module 504 is configured to perform feature matching between the product features and the device feature library and network feature library of the store equipment, and determine candidate products based on the feature matching results.

[0184] Synchronization type determination module 506 is configured to determine the feature synchronization type of the target product if the candidate products do not contain the target product corresponding to the product settlement instruction.

[0185] The feature synchronization processing module 508 is configured to submit a product synchronization request corresponding to the feature synchronization type to the server, so as to perform feature synchronization processing of the target product according to the feature synchronization type.

[0186] For ease of description, the above devices are described by dividing them into various modules or units based on their functions. Of course, when implementing one or more of these specifications, the functions of each module or unit can be implemented in the same or different software and / or hardware, or a module that performs the same function can be implemented by a combination of multiple sub-modules or sub-units, etc. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0187] Another embodiment of the commodity settlement processing device provided in this manual is as follows:

[0188] In the above embodiments, another commodity settlement processing method is provided, and correspondingly, another commodity settlement processing device is also provided, which will be described below with reference to the accompanying drawings.

[0189] Reference Figure 6 This illustration shows a schematic diagram of another embodiment of the commodity settlement processing device provided in this embodiment.

[0190] Since the apparatus embodiments correspond to the method embodiments, the descriptions are relatively simple. For relevant parts, please refer to the corresponding descriptions of the method embodiments provided above. The apparatus embodiments described below are merely illustrative.

[0191] This embodiment provides a commodity settlement processing device, which operates on a server. The device includes:

[0192] The synchronization request receiving module 602 is configured to receive a product synchronization request submitted by the store equipment of a merchant store, which carries a product image of the target product; the product synchronization request is generated when the product features of the product to be settled are matched with the device feature library and network feature library of the store equipment and the candidate products determined do not include the target product corresponding to the product settlement instruction.

[0193] The feature synchronization detection module 604 is configured to perform feature synchronization detection on the product features of the target product according to the feature synchronization type corresponding to the product synchronization request.

[0194] The feature synchronization processing module 606 is configured to perform feature synchronization processing of the product features in the product feature library deployed on the server according to the feature synchronization type if the detection passes.

[0195] For ease of description, the above devices are described by dividing them into various modules or units based on their functions. Of course, when implementing one or more of these specifications, the functions of each module or unit can be implemented in the same or different software and / or hardware, or a module that performs the same function can be implemented by a combination of multiple sub-modules or sub-units, etc. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0196] The following is an example of a commodity checkout processing device provided in this manual:

[0197] Corresponding to the commodity settlement processing method described above, based on the same technical concept, one or more embodiments of this specification also provide a commodity settlement processing device, which is used to execute the commodity settlement processing method provided above. Figure 7 This is a schematic diagram of the structure of a commodity settlement processing device provided for one or more embodiments of this specification.

[0198] This embodiment provides a commodity settlement processing device, including:

[0199] like Figure 7As shown, device 700 mainly consists of a communication interface 702, a user interface 704, a processor 706, and a data storage 708. These components are interconnected and communicate with each other via a system bus, network, or other connection mechanism 710. Communication interface 702 enables device 700 to communicate with other devices, access networks, and transmission networks via analog or digital modulation. For example, communication interface 702 may include a chipset and antenna for wireless communication with a radio access network or access point. Furthermore, communication interface 702 can be a wired interface such as Ethernet, Token Ring, or USB port, or a wireless interface such as Wi-Fi, Bluetooth, Global Positioning System (GPS), or wide area wireless interface (e.g., WiMAX or LTE). Of course, communication interface 702 can also support other forms of physical layer interfaces and standard or proprietary communication protocols. Communication interface 702 may also include multiple physical communication interfaces, such as Wi-Fi, Bluetooth, and wide area wireless interfaces. User interface 704 includes receiving user input and providing output to the user. Therefore, user interface 704 may include input components such as a keypad, keyboard, touch-sensitive or presence-sensitive panel, computer mouse, trackball, joystick, microphone, still camera, and video camera, and output components such as a display screen (which may be combined with a touch-sensitive panel), CRT, LCD, LED, display using DLP technology, printer, and other similar devices known or developed in the future. User interface 704 may also generate auditory output via speakers, speaker jacks, audio output ports, audio output devices, headphones, and other similar devices known or developed in the future. In some embodiments, user interface 704 may include software, circuitry, or other forms of logic capable of transmitting data to and receiving data from external user input / output devices. Additionally or alternatively, device 700 may support remote access from other devices via communication interface 702 or another physical interface (not shown). User interface 704 may be configured to receive user input, the position and movement of which may be indicated by indicators or cursors described herein. User interface 704 may also be configured as a display device for rendering or displaying text fragments.

[0200] Processor 706 may include one or more general-purpose processors and / or dedicated processors. Data storage 708 may include one or more volatile and / or non-volatile storage components, and may be integrated wholly or partially with processor 706. Data storage 708 may include removable and non-removable components.

[0201] Processor 706 is capable of executing program instructions 718 (e.g., compiled or uncompiled program logic and / or machine code) stored in data storage 708 to perform the various functions described herein. Data storage 708 may comprise a non-transitory computer-readable medium on which program instructions are stored, which, when executed by device 700, enable device 700 to perform any methods, processes, or functions disclosed in this specification and / or the accompanying drawings. Execution of program instructions 718 by processor 706 may result in processor 706 using data 712. For example, program instructions 718 may include an operating system 722 (e.g., an operating system kernel, device drivers, and / or other modules) installed on device 700 and one or more application programs 720 (e.g., a browser, social application, or game application). Similarly, data 712 may include operating system data 716 and application data 714. Operating system data 716 is primarily accessible to operating system 722, while application data 714 is primarily accessible to one or more application programs 720. Application data 714 may reside in a file system visible or hidden from the user of device 700. Application 720 can communicate with operating system 722 through one or more application programming interfaces (APIs). These APIs facilitate application 720 in reading and / or writing application data 714, transmitting or receiving information via communication interface 702, and receiving or displaying information on user interface 704. In some terms, application 720 may be simply referred to as "app". Furthermore, application 720 can be downloaded to device 700 through one or more online app stores or app markets. However, applications can also be installed on device 700 in other ways, such as through a web browser or a physical interface on device 700 (e.g., a USB port).

[0202] In one specific embodiment, the goods checkout processing device includes a memory and one or more programs, wherein one or more programs are stored in the memory, and one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the goods checkout processing device, and is configured to be executed by one or more processors. The one or more programs include computer-executable instructions for performing the following:

[0203] Collect product images of the goods to be settled, and extract product features from the product images to obtain product features;

[0204] The product features are matched with the equipment feature library and network feature library of the merchant's store equipment, and candidate products are determined based on the feature matching results;

[0205] If the candidate products do not include the target product corresponding to the product settlement instruction, determine the feature synchronization type of the target product;

[0206] Submit a product synchronization request corresponding to the feature synchronization type to the server so as to perform feature synchronization processing of the target product according to the feature synchronization type.

[0207] Another embodiment of the commodity checkout processing equipment provided in this manual is as follows:

[0208] Corresponding to the other commodity settlement processing method described above, based on the same technical concept, one or more embodiments of this specification also provide another commodity settlement processing device, which is used to execute the other commodity settlement processing method provided above. Figure 8 This is a schematic diagram of another commodity settlement processing device provided in one or more embodiments of this specification.

[0209] This embodiment provides a commodity settlement processing device, including:

[0210] like Figure 8As shown, device 800 mainly consists of a communication interface 802, a user interface 804, a processor 806, and a data storage 808. These components are interconnected and communicate with each other via a system bus, network, or other connection mechanism 810. The communication interface 802 enables device 800 to communicate with other devices, access networks, and transmission networks via analog or digital modulation. For example, the communication interface 802 may include a chipset and antenna for wireless communication with a radio access network or access point. Furthermore, the communication interface 802 can be a wired interface such as Ethernet, Token Ring, or a USB port, or a wireless interface such as Wi-Fi, Bluetooth, Global Positioning System (GPS), or a wide-area wireless interface (e.g., WiMAX or LTE). Of course, the communication interface 802 can also support other forms of physical layer interfaces and standard or proprietary communication protocols. The communication interface 802 may also include multiple physical communication interfaces, such as Wi-Fi, Bluetooth, and wide-area wireless interfaces. The user interface 804 includes receiving user input and providing output to the user. Therefore, user interface 804 may include input components such as a keypad, keyboard, touch-sensitive or presence-sensitive panel, computer mouse, trackball, joystick, microphone, still camera, and video camera, and output components such as a display screen (which may be combined with a touch-sensitive panel), CRT, LCD, LED, display using DLP technology, printer, and other similar devices known or developed in the future. User interface 804 may also generate auditory output via speakers, speaker jacks, audio output ports, audio output devices, headphones, and other similar devices known or developed in the future. In some embodiments, user interface 804 may include software, circuitry, or other forms of logic capable of transmitting and receiving data to and from external user input / output devices. Additionally or alternatively, device 800 may support remote access from other devices via communication interface 802 or another physical interface (not shown). User interface 804 may be configured to receive user input, the position and movement of which may be indicated by indicators or cursors described herein. User interface 804 may also be configured as a display device for rendering or displaying text fragments.

[0211] Processor 806 may include one or more general-purpose processors and / or special-purpose processors. Data storage 808 may include one or more volatile and / or non-volatile storage components, and may be integrated wholly or partially with processor 806. Data storage 808 may include removable and non-removable components.

[0212] Processor 806 is capable of executing program instructions 818 (e.g., compiled or uncompiled program logic and / or machine code) stored in data storage 808 to perform the various functions described herein. Data storage 808 may comprise a non-transitory computer-readable medium on which program instructions are stored, which, when executed by device 800, enable device 800 to perform any methods, processes, or functions disclosed in this specification and / or the accompanying drawings. Execution of program instructions 818 by processor 806 may result in processor 806 using data 812. For example, program instructions 818 may include an operating system 822 (e.g., an operating system kernel, device drivers, and / or other modules) installed on device 800 and one or more application programs 820 (e.g., a browser, social application, or game application). Similarly, data 812 may include operating system data 816 and application data 814. Operating system data 816 is primarily accessible to operating system 822, while application data 814 is primarily accessible to one or more application programs 820. Application data 814 may reside in a file system visible or hidden from the user of device 800. Application 820 can communicate with operating system 822 through one or more application programming interfaces (APIs). These APIs facilitate application 820 in reading and / or writing application data 814, transmitting or receiving information via communication interface 802, and receiving or displaying information on user interface 804. In some terms, application 820 may be simply referred to as "app". Furthermore, application 820 can be downloaded to device 800 through one or more online application stores or app markets. However, applications can also be installed on device 800 in other ways, such as through a web browser or a physical interface on device 800 (e.g., a USB port).

[0213] In one specific embodiment, the goods checkout processing device includes a memory and one or more programs, wherein one or more programs are stored in the memory, and one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the goods checkout processing device, and is configured to be executed by one or more processors. The one or more programs include computer-executable instructions for performing the following:

[0214] Receive a product synchronization request submitted by the store equipment of the merchant's store, which carries a product image of the target product; the product synchronization request is generated when the product features of the product to be settled are matched with the device feature library and network feature library of the store equipment and the candidate products determined do not include the target product corresponding to the product settlement instruction;

[0215] Based on the feature synchronization type corresponding to the product synchronization request, feature synchronization detection is performed on the product features of the target product;

[0216] If the detection passes, the product features are synchronized with the product feature library deployed on the server according to the specified feature synchronization type.

[0217] This specification provides an embodiment of a computer-readable storage medium as follows:

[0218] Corresponding to the commodity settlement processing method described above, based on the same technical concept, one or more embodiments of this specification also provide a computer-readable storage medium.

[0219] The computer-readable storage medium provided in this embodiment is used to store computer-executable instructions, which, when executed, implement the following process:

[0220] Collect product images of the goods to be settled, and extract product features from the product images to obtain product features;

[0221] The product features are matched with the device feature library and network feature library of the store equipment, and candidate products are determined based on the feature matching results.

[0222] If the candidate products do not include the target product corresponding to the product settlement instruction, determine the feature synchronization type of the target product;

[0223] Submit a product synchronization request corresponding to the feature synchronization type to the server so as to perform feature synchronization processing of the target product according to the feature synchronization type.

[0224] It should be noted that the embodiments of a computer-readable storage medium described in this specification and the embodiments of a commodity settlement processing method described in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can be referred to the implementation of the corresponding method described above, and the repeated parts will not be described again.

[0225] Another embodiment of a computer-readable storage medium provided in this specification is as follows:

[0226] In response to another commodity settlement processing method described above, based on the same technical concept, one or more embodiments of this specification also provide another computer-readable storage medium.

[0227] The computer-readable storage medium provided in this embodiment is used to store computer-executable instructions, which, when executed, implement the following process:

[0228] Receive a product synchronization request submitted by the store equipment of the merchant's store, which carries a product image of the target product; the product synchronization request is generated when the product features of the product to be settled are matched with the device feature library and network feature library of the store equipment and the candidate products determined do not include the target product corresponding to the product settlement instruction;

[0229] Based on the feature synchronization type corresponding to the product synchronization request, feature synchronization detection is performed on the product features of the target product;

[0230] If the detection passes, the product features are synchronized with the product feature library deployed on the server according to the specified feature synchronization type.

[0231] It should be noted that the embodiments of another computer-readable storage medium described in this specification and the embodiments of another commodity settlement processing method described in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can be referred to the implementation of the corresponding method described above, and the repeated parts will not be described again.

[0232] This specification provides an example of a computer program product as follows:

[0233] Corresponding to the commodity settlement processing method described above, based on the same technical concept, one or more embodiments of this specification also provide a computer program product.

[0234] A computer program product includes a computer program / instructions that, when executed by a processor, perform the following steps:

[0235] Collect product images of the goods to be settled, and extract product features from the product images to obtain product features;

[0236] The product features are matched with the device feature library and network feature library of the store equipment, and candidate products are determined based on the feature matching results.

[0237] If the candidate products do not include the target product corresponding to the product settlement instruction, determine the feature synchronization type of the target product;

[0238] Submit a product synchronization request corresponding to the feature synchronization type to the server so as to perform feature synchronization processing of the target product according to the feature synchronization type.

[0239] It should be noted that the embodiments of a computer program product described in this specification and the embodiments of a commodity settlement processing method described in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can be referred to the implementation of the corresponding method described above, and the repeated parts will not be described again.

[0240] Another example of a computer program product provided in this specification is as follows:

[0241] Corresponding to the other commodity settlement processing method described above, based on the same technical concept, one or more embodiments of this specification also provide another computer program product.

[0242] A computer program product includes a computer program / instructions that, when executed by a processor, perform the following steps:

[0243] Receive a product synchronization request submitted by the store equipment of the merchant's store, which carries a product image of the target product; the product synchronization request is generated when the product features of the product to be settled are matched with the device feature library and network feature library of the store equipment and the candidate products determined do not include the target product corresponding to the product settlement instruction;

[0244] Based on the feature synchronization type corresponding to the product synchronization request, feature synchronization detection is performed on the product features of the target product;

[0245] If the detection passes, the product features are synchronized with the product feature library deployed on the server according to the specified feature synchronization type.

[0246] It should be noted that the embodiments of another computer program product described in this specification and the embodiments of another commodity settlement processing method described in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can be referred to the implementation of the corresponding method described above, and the repeated parts will not be described again.

[0247] The various embodiments in this specification are described in a progressive manner. For the same or similar parts between the various embodiments, please refer to each other. Each embodiment focuses on describing the differences from other embodiments. For example, the device embodiments, equipment embodiments, computer-readable storage medium embodiments, and computer program product embodiments are all similar to the method embodiments, so the descriptions are relatively simple. For reading the relevant content of the device embodiments, equipment embodiments, computer-readable storage medium embodiments, and computer program product embodiments, please refer to the description of the method embodiments.

[0248] While one or more embodiments of this specification provide method steps as described in the embodiments or flowcharts, it is understood that the order of steps listed in the embodiments or flowcharts is merely one possible execution order among many steps, and does not represent the only execution order. Therefore, when the claims involve method steps, any changes or adjustments to the order of such steps, or the parallelism between steps, are also within the scope of protection of the claims. This specification uses specific terms to describe embodiments of this specification. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "an embodiment," "one embodiment," or "an alternative embodiment" mentioned twice or more in different locations in this specification do not necessarily refer to the same embodiment. Furthermore, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0249] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0250] In the 1930s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many improvements to the methodology today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that an improvement to the methodology cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program and "integrate" a digital system onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must also be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0251] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0252] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0253] For ease of description, the above apparatus is described by dividing it into various functional units. Of course, when implementing the embodiments of this specification, the functions of each unit can be implemented in one or more software and / or hardware.

[0254] Those skilled in the art will understand that one or more embodiments of this specification can be provided as a method, system, or computer program product. Therefore, one or more embodiments of this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this specification may take the form of a computer program product embodied on one or more computer-readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0255] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0256] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0257] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0258] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0259] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0260] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer-readable storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0261] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising at least one…" does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0262] One or more embodiments of this specification can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a particular task or implement a particular abstract data type. One or more embodiments of this specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0263] The above description is merely an embodiment of this document and is not intended to limit the scope of this document. Various modifications and variations can be made to this document by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this document should be included within the scope of the claims of this document.

Claims

1. A merchandise settlement processing method, applied to store equipment in a merchant's store, the method comprising: Collect product images of the goods to be settled, and extract product features from the product images to obtain product features; The product features are matched with the local product features in the device feature library of the store equipment and the standard product features in the network feature library. Candidate products are determined based on the feature matching results. The network feature library is synchronized with the product feature library deployed on the server. The product identifiers recorded in the device feature library are synchronized with the product identifiers recorded in the network feature library. The local product features are obtained by feature extraction based on the personalized image of the merchant's store, and the standard product features are obtained by feature extraction based on the standard image. If the candidate products do not include the target product corresponding to the product settlement instruction, determine the feature synchronization type of the target product; Submit a product synchronization request corresponding to the feature synchronization type to the server so as to perform feature synchronization processing of the target product according to the feature synchronization type.

2. The commodity settlement processing method according to claim 1, wherein the step of performing feature matching between the commodity features and the local commodity features in the device feature library of the store equipment and the standard commodity features in the network feature library, and determining candidate commodities based on the feature matching results, includes: The product features are matched with local product features in the device feature library to obtain a first matching product set, and the product features are matched with standard product features in the network feature library to obtain a second matching product set. The first matching product set and the second matching product set are fused together to obtain at least one matching product as the candidate product.

3. The commodity settlement processing method according to claim 1, wherein determining the feature synchronization type of the target commodity includes: Detect whether the product identifier of the target product is stored in the network feature library; if so, determine that the feature synchronization type is outlier feature synchronization. If not, determine that the feature synchronization type is new product feature synchronization.

4. The commodity settlement processing method according to claim 1, wherein the feature synchronization processing of the target commodity according to the feature synchronization type is implemented in the following manner: If the feature synchronization type is new product feature synchronization, feature deduplication detection is performed on the product image carried in the product synchronization request based on the product feature library deployed on the server. After the detection is passed, the product features are synchronized to the store equipment of each merchant's store to update the product features to the network feature database of the store equipment of each merchant's store.

5. The commodity settlement processing method according to claim 4, wherein synchronizing the commodity features with the store equipment of each merchant store includes: Create a synchronous task for the product features and add it to an asynchronous task queue for task execution; The task execution includes: submitting the product features to the IoT center connected to the store equipment of each merchant store, and pushing the product features to the store equipment of each merchant store through the IoT center.

6. The commodity settlement processing method according to claim 1, wherein the feature synchronization processing of the target commodity according to the feature synchronization type is implemented in the following manner: If the feature synchronization type is outlier feature synchronization, the product feature is added as an outlier feature to the outlier feature pool for outlier feature detection; the outlier feature detection includes inputting the outlier feature into an outlier detection model to obtain the detection result; After outlier detection is passed, the outlier features are stored in the product feature library deployed on the server and mapped to the product identifier of the target product.

7. The commodity settlement processing method according to claim 4 or 6, wherein the local commodity features corresponding to the commodity identifier recorded in the equipment feature library of the store equipment are obtained by extracting features from the weighing and settlement image of the commodity to be settled in the current merchant store.

8. The commodity settlement processing method according to claim 1, wherein any commodity identifier in the commodity feature library deployed on the server corresponds to at least one commodity feature; The at least one product feature includes: The product settlement features are obtained by extracting features from the weighing and settlement images of the same product from the store equipment of various stores of the same merchant.

9. The commodity settlement processing method according to claim 8 further includes: After detecting the start command of the store equipment, obtain a feature snapshot of the product feature library deployed on the server from the server. The network feature library of the store equipment is updated synchronously based on the product features contained in the feature snapshot.

10. The commodity settlement processing method according to claim 8, wherein the commodity features in the commodity feature database deployed on the server include: Product features are obtained by extracting features from new product images uploaded by merchants' authorized devices.

11. A commodity settlement processing method, applied on a server side, the method comprising: Receive product synchronization requests from the store's equipment, which include product images of the target product. The product synchronization request is generated when the candidate products identified by matching the product features of the product to be settled with the local product features in the device feature library of the store equipment and the standard product features in the network feature library do not include the target product corresponding to the product settlement instruction; the network feature library is synchronized with the product feature library deployed on the server, the product identifiers recorded in the device feature library are synchronized with the product identifiers recorded in the network feature library, the local product features are obtained by feature extraction based on the personalized image of the merchant store, and the standard product features are obtained by feature extraction based on the standard image; Based on the feature synchronization type corresponding to the product synchronization request, feature synchronization detection is performed on the product features of the target product; If the detection passes, the product features are synchronized with the product feature library deployed on the server according to the specified feature synchronization type.

12. The commodity settlement processing method according to claim 11, wherein the step of performing feature synchronization detection on the commodity features of the target commodity according to the feature synchronization type corresponding to the commodity synchronization request includes: Based on the product feature library deployed on the server, feature deduplication detection is performed on the product image carried in the product synchronization request, or the product features are added as outlier features to the outlier feature pool for outlier feature detection; the outlier feature detection includes inputting the outlier features into the outlier detection model to obtain the detection result.

13. The commodity settlement processing method according to claim 11, wherein the step of performing feature synchronization processing of the commodity features in the commodity feature library deployed to the server according to the feature synchronization type includes: If the feature synchronization type is new product feature synchronization, the product features are synchronized to the store equipment of each merchant store to update the product features to the network feature library of the store equipment of each merchant store; If the feature synchronization type is outlier feature synchronization, the outlier feature is stored in the product feature library deployed on the server and mapped to the product identifier of the target product.

14. The commodity settlement processing method according to claim 13, wherein synchronizing the commodity features with the store equipment of each merchant store includes: Create a synchronous task for the product features and add it to an asynchronous task queue for task execution; The task execution includes: submitting the product features to the IoT center connected to the store equipment of each merchant store, and pushing the product features to the store equipment of each merchant store through the IoT center.

15. The commodity settlement processing method according to claim 11, wherein any commodity identifier in the commodity feature library deployed on the server corresponds to at least one commodity feature; The at least one product feature includes: The product settlement features are obtained by extracting features from the weighing and settlement images of the same product from the store equipment of different stores of the same merchant; The network feature library of the store equipment is synchronized with the product feature library deployed on the server, and the product identifiers recorded in the device feature library of the store equipment are synchronized with the product identifiers recorded in the network feature library of the store equipment.

16. A merchandise settlement processing device, operating in a merchant's store, the device comprising: The feature extraction module is configured to acquire product images of the goods to be settled and extract product features from the product images to obtain product features; The feature matching module is configured to perform feature matching between the product features and the local product features in the device feature library of the store equipment and the standard product features in the network feature library, and determine candidate products based on the feature matching results; the network feature library is synchronized with the product feature library deployed on the server, the product identifiers recorded in the device feature library are synchronized with the product identifiers recorded in the network feature library, the local product features are obtained by feature extraction based on the personalized image of the merchant's store, and the standard product features are obtained by feature extraction based on the standard image; The synchronization type determination module is configured to determine the feature synchronization type of the target product if the candidate products do not contain the target product corresponding to the product settlement instruction. The feature synchronization processing module is configured to submit a product synchronization request corresponding to the feature synchronization type to the server, so as to perform feature synchronization processing of the target product according to the feature synchronization type.

17. A commodity settlement processing device, operating on a server, the device comprising: The synchronization request receiving module is configured to receive product synchronization requests submitted by the store equipment of the merchant's store, which carry product images of the target product. The product synchronization request is generated when the candidate products identified by matching the product features of the product to be settled with the local product features in the device feature library of the store equipment and the standard product features in the network feature library do not include the target product corresponding to the product settlement instruction; the network feature library is synchronized with the product feature library deployed on the server, the product identifiers recorded in the device feature library are synchronized with the product identifiers recorded in the network feature library, the local product features are obtained by feature extraction based on the personalized image of the merchant store, and the standard product features are obtained by feature extraction based on the standard image; The feature synchronization detection module is configured to perform feature synchronization detection on the product features of the target product according to the feature synchronization type corresponding to the product synchronization request; The feature synchronization processing module is configured to perform feature synchronization processing of the product features in the product feature library deployed on the server according to the feature synchronization type if the detection passes.

18. A commodity settlement processing device, comprising: processor; And, a memory configured to store computer-executable instructions, which, when executed, cause the processor to: Collect product images of the goods to be settled, and extract product features from the product images to obtain product features; The product features are matched with the local product features in the device feature library of the merchant's store equipment and the standard product features in the network feature library. Candidate products are determined based on the feature matching results. The network feature library is synchronized with the product feature library deployed on the server. The product identifiers recorded in the device feature library are synchronized with the product identifiers recorded in the network feature library. The local product features are obtained by feature extraction based on the personalized image of the merchant's store, and the standard product features are obtained by feature extraction based on the standard image. If the candidate products do not include the target product corresponding to the product settlement instruction, determine the feature synchronization type of the target product; Submit a product synchronization request corresponding to the feature synchronization type to the server so as to perform feature synchronization processing of the target product according to the feature synchronization type.

19. A commodity settlement processing device, comprising: processor; And, a memory configured to store computer-executable instructions, which, when executed, cause the processor to: The system receives a product synchronization request from a merchant's store device, which includes a product image of the target product. This product synchronization request is generated when the candidate products identified through feature matching between the product features of the product to be settled and the local product features in the device feature library and the standard product features in the network feature library do not include the target product corresponding to the product settlement instruction. The network feature library is synchronized with the product feature library deployed on the server, and the product identifiers recorded in the device feature library are synchronized with the product identifiers recorded in the network feature library. The local product features are obtained by feature extraction based on the personalized image of the merchant's store, and the standard product features are obtained by feature extraction based on a standard image. Based on the feature synchronization type corresponding to the product synchronization request, feature synchronization detection is performed on the product features of the target product; If the detection passes, the product features are synchronized with the product feature library deployed on the server according to the specified feature synchronization type.

20. A computer-readable storage medium for storing computer-executable instructions that, when executed, implement the steps of the method of claim 1 or 11.

Images