CN114445980B

CN114445980B - Commodity checkout method and device, electronic equipment and storage medium

Info

Publication number: CN114445980B
Application number: CN202210104938.2A
Authority: CN
Inventors: 程前; 李成蹊; 杨浩; 张帅; 伊帅
Original assignee: Chengdu Sensetime Technology Co Ltd
Current assignee: Chengdu Sensetime Technology Co Ltd
Priority date: 2022-01-28
Filing date: 2022-01-28
Publication date: 2023-11-28
Anticipated expiration: 2042-01-28
Also published as: CN114445980A

Abstract

The disclosure relates to a commodity checkout method and device, electronic equipment and storage medium, wherein the method comprises the following steps: acquiring at least one image of a commodity to be checked out; determining a target commodity image matched with the at least one image from a first image library; acquiring a checkout mode and commodity attribute information corresponding to the target commodity image according to a preset association relation; and determining the commodity total price of the commodity to be checked out according to the checking out mode and the commodity attribute information. The embodiment of the disclosure can realize that whether the commodity has the identification code or not, the checkout can be efficiently and accurately completed.

Description

Commodity checkout method and device, electronic equipment and storage medium

Technical Field

The disclosure relates to the field of computer technology, and in particular, to a commodity checkout method and device, electronic equipment and storage medium.

Background

In some supermarkets, convenience stores and other merchants mainly providing commodity shopping services for customers, a relatively wide-application checkout mode is a checkout mode for acquiring commodity information by scanning identification codes (including bar codes). The checkout method requires that the commodity be pre-packaged and that the package be printed or otherwise affixed with an identification code corresponding to the commodity. Some merchants do not offer packaging for some goods, such as vegetables, fruits, pastries, etc., due to human labor costs, packaging material costs, and the like. For the goods which cannot be scanned to acquire the identification code because of no package, a customer or staff is required to manually inquire and input the goods code during checkout, so that the checkout flow is very complicated and easy to miss. In addition, in the aspect of checkout of commodities with identification codes, the situation that the code scanning device is out of order or the identification codes are fuzzy may occur, so that the checkout efficiency is reduced.

Therefore, there is a need for a commodity checkout scheme that allows for efficient and accurate checkout regardless of the presence or absence of an identification code for the commodity.

Disclosure of Invention

The present disclosure provides a checkout technique for goods.

According to an aspect of the present disclosure, there is provided a checkout method of an article, including: acquiring at least one image of a commodity to be checked out; determining a target commodity image matched with the at least one image from a first image library; acquiring a checkout mode and commodity attribute information corresponding to the target commodity image according to a preset association relation; and determining the commodity total price of the commodity to be checked out according to the checking out mode and the commodity attribute information.

Determining that the commodity to be checked out is the recorded commodity in the first image library by acquiring at least one image of the commodity to be checked out and determining a target commodity image matched with the at least one image from the first image library; and acquiring the checkout mode and commodity attribute information corresponding to the target commodity image, so that the commodity total price of the commodity to be checked out can be obtained according to the checkout mode and commodity attribute information. According to the embodiment of the disclosure, the commodity can be checked out through the information acquired from the image of the commodity to be checked out, and the commodity can be checked out efficiently and accurately no matter whether the identification code exists or not.

In one or more alternative embodiments, prior to the acquiring the at least one image of the item to be checked out, the method further comprises: acquiring commodity images of at least one commodity type, wherein each commodity type corresponds to at least one commodity image; screening at least one commodity image corresponding to each commodity type to obtain a preset commodity image with image quality meeting a first preset condition; acquiring a checkout mode and commodity attribute information of each preset commodity image, and establishing an association relationship among the preset commodity images, the checkout mode and the commodity attribute information; and storing each preset commodity image and the association relation in the first image library.

In this way, the storage of the preset commodity image and the association relationship in the first image bank can be realized. The preset commodity images in the first image library are subjected to image quality screening to meet the condition, so that the target commodity image which is determined from the first image library and matched with at least one image is high in accuracy, and the accuracy of the final determined commodity total price is further improved.

In one or more alternative embodiments, the determining, from the first image library, the target commodity image that matches the at least one image includes: determining a first similarity degree of each image and a preset commodity image in the first image library aiming at the at least one image; acquiring a first distinguishing feature of the preset commodity image with the first similarity degree larger than a first threshold value; extracting a second distinguishing feature of each image for the at least one image; determining a second degree of similarity of the first distinguishing feature to the second distinguishing feature; determining the preset commodity image with the highest second similarity degree as the target commodity image matched with the at least one image; the first distinguishing feature and the second distinguishing feature are used for distinguishing preset commodity images of different commodity types.

The preset commodity image of which the first degree of similarity satisfies the condition may be an image that is similar to the image of the commodity to be checked out as a whole, and the preset commodity image of which the second degree of similarity satisfies the condition may be an image that is similar to both the image of the commodity to be checked out as a target commodity image that matches the commodity image of the commodity to be checked out as a whole and the characteristic portion. In this way, the accuracy of the determined target commodity image can be ensured.

In one or more alternative embodiments, in the event that a target merchandise image matching the at least one image is not determined from the first image library, the method further comprises: under the condition that the commodity to be checked out comprises an identification code, acquiring a checking out mode and commodity attribute information of the commodity to be checked out in a mode of scanning the identification code; or under the condition that the commodity to be checked out does not comprise the identification code, receiving first feedback information, wherein the first feedback information is used for indicating a check-out mode and commodity attribute information of the commodity to be checked out; determining the commodity total price of the commodity to be checked out according to the check-out mode and the commodity attribute information in the first feedback information; and outputting first prompt information, wherein the first prompt information is used for indicating that the commodity image of the commodity to be checked out is added into the first image library.

When the target commodity image cannot be determined, the payment terminal can be assisted to complete the checkout by manually scanning the identification code or manually inputting the checkout mode and commodity attribute information required by the checkout, and the flexibility of the checkout mode can be improved.

In one or more alternative embodiments, in the event that a target merchandise image matching the at least one image is not determined from the first image library, the method further comprises: searching whether the checkout videos of the same type of commodities exist in the commodities to be checked out or not through monitoring camera shooting; acquiring related information of a checkout process of the same type of commodity indicated by the checkout video under the condition that the checkout video exists, wherein the related information of the checkout process comprises a checkout mode and commodity attribute information of the same type of commodity; and determining the commodity total price of the commodity to be checked out according to the check-out mode and the commodity attribute information of the commodity of the same type.

By the method, the identification code does not need to be scanned manually or the checkout mode and commodity attribute information which are needed by checkout are input manually, the checkout of the commodity can be completed under the condition that the target commodity image is not determined, and the efficiency and the accuracy of determining the commodity total price by the payment terminal can be improved.

In one or more alternative embodiments, after determining, for the at least one image, a first degree of similarity of each of the images to a preset merchandise image in a first image library, the method further comprises: judging whether the number of the preset commodity images with the first similarity degree larger than a first threshold value is a plurality of; if the number of the preset commodity images with the first similarity degree larger than a first threshold value is a plurality of, determining that the preset commodity images are similar commodity images; the acquiring the first distinguishing feature of the preset commodity image with the first similarity degree larger than a first threshold value comprises the following steps: acquiring a first distinguishing characteristic of each similar commodity image; the determining the target commodity image with the highest second similarity degree as the target commodity image matched with the at least one image comprises the following steps: and determining the similar commodity image with the highest second similarity degree as the target commodity image matched with the at least one image.

When the number of the preset commodity images with the first similarity degree larger than the first threshold value is a plurality of, the plurality of preset commodity images can be considered to be more similar. In this way, the accuracy of the determined target commodity image can be further improved when the plurality of preset commodity images are similar.

In one or more optional embodiments, the commodity attribute information further includes at least one of a date of production, a shelf life, quality qualification information, and a manufacturer, and after acquiring the checkout mode and the commodity attribute information corresponding to the target commodity image according to a preset association relationship, the method further includes: judging whether invalid information exists in the production date, the quality qualified information and the manufacturer; if the production date, the quality qualified information and the invalid information do not exist in the production factory, determining the commodity total price of the commodity to be checked out according to the checking-out mode and the commodity attribute information; or judging whether the commodity to be checked out is an expired product according to the production date and the quality guarantee period; and if the commodity to be checked out is not an expired product, determining the commodity total price of the commodity to be checked out according to the checking out mode and the commodity attribute information.

In this way, the quality and safety of the finished goods can be ensured, and the checkout experience of the customer is improved.

In one or more alternative embodiments, the checkout mode includes checkout by piece, and the commodity attribute information includes commodity type and price of a single commodity; the determining the commodity total price of the commodity to be checked out according to the check out mode and the commodity attribute information comprises the following steps: determining the quantity of each type of commodity included in the commodity to be checked out according to the at least one image; and determining the commodity total price according to the sum of the products of the quantity of each type of commodity in the commodity to be checked out and the price of the single commodity of the type of commodity.

In this way, the acquisition of the total commodity price of the commodity to be checked out on a piece-by-piece basis can be achieved only by at least one image of the commodity to be checked out. Since it is allowed to simultaneously check out a plurality of types of commodities checked out by pieces, it is possible to perform one-step improvement in the efficiency of check out.

In one or more alternative embodiments, the item attribute information further includes a single item weight, the method further comprising: detecting the total weight of the commodity to be checked out when the commodity to be checked out comprises a commodity type; determining a first commodity quantity of the commodity to be checked out according to the commodity total weight of the commodity to be checked out and the weight of the single commodity; determining a second commodity quantity of the commodity to be checked out according to the at least one image; the determining the commodity total price according to the sum of the products of the quantity of each type of commodity in the commodity to be checked out and the price of the single commodity of the type of commodity comprises: and under the condition that the first commodity quantity is consistent with the second commodity quantity, determining the commodity total price according to the product of the first commodity quantity and the price of the single commodity of the type commodity or the product of the second commodity quantity and the price of the single commodity of the type commodity.

By the method, the commodity quantity of the commodity to be checked out can be checked out, and the accuracy of the quantity of the commodity to be checked out is ensured. Determining the total price of the commodity when the number of the commodity to be checked out is accurate enables the accuracy of the total price of the commodity to be improved.

In one or more alternative embodiments, the item attribute information further includes a single item weight, the method further comprising: determining the quantity of each type of commodity included in the commodity to be checked out according to the at least one image; determining the total weight of a first commodity of the commodity to be checked out according to the quantity of each type of commodity included in the commodity to be checked out and the weight of a single commodity; detecting the total weight of a second commodity of the commodity to be checked out; the determining the commodity total price according to the sum of the products of the quantity of each type of commodity in the commodity to be checked out and the price of the single commodity of the type of commodity comprises: and under the condition that the absolute value of the difference between the total weight of the first commodity and the total weight of the second commodity is smaller than a second threshold value, determining the commodity total price according to the sum of the products of the quantity of each type of commodity in the commodities to be checked out and the price of the single commodity of the type of commodity.

By the method, the total weight of the commodities to be checked out can be checked out, and the accuracy of the quantity of the commodities to be checked out is guaranteed. When the total weight of the commodity to be checked out is checked out, the commodity to be checked out can comprise various commodity types, so that the checking mode can be suitable for more application scenes.

In one or more alternative embodiments, the checkout mode includes checkout by weight, and the merchandise attribute information includes merchandise type and merchandise price per unit weight; the determining the commodity total price of the commodity to be checked out according to the check out mode and the commodity attribute information comprises the following steps: detecting the total weight of the commodity to be checked out when the commodity to be checked out comprises a commodity type; and determining the commodity total price according to the product of the commodity total weight of the commodity to be checked out and the commodity price per unit weight.

In this way, the checkout of the weight-checkout commodity can be achieved. The terminal equipment or the server for executing the commodity checkout method disclosed by the embodiment of the invention not only can realize the commodity checkout according to the piece checkout, but also can realize the commodity checkout according to the weight checkout, and can improve the checkout capacity of the terminal equipment or the server.

According to an aspect of the present disclosure, there is provided a checkout device of an article, comprising: the first acquisition module is used for acquiring at least one image of the commodity to be checked out; the first determining module is used for determining a target commodity image matched with the at least one image from the first image library; the second acquisition module is used for acquiring a checkout mode and commodity attribute information corresponding to the target commodity image according to a preset association relation; and the second determining module is used for determining the commodity total price of the commodity to be checked out according to the checking-out mode and the commodity attribute information.

In one or more alternative embodiments, the apparatus further comprises: the third acquisition module is used for acquiring commodity images of at least one commodity type, wherein each commodity type corresponds to at least one commodity image; the first screening module is used for screening at least one commodity image corresponding to each commodity type to obtain preset commodity images with image quality meeting a first preset condition; a fourth obtaining module, configured to obtain a checkout mode and commodity attribute information of each preset commodity image, and establish an association relationship among the preset commodity image, the checkout mode and the commodity attribute information; and the first storage module is used for storing each preset commodity image and the association relation in the first image library.

In one or more optional embodiments, the first determining module is specifically configured to determine, for the at least one image, a first similarity degree between each of the images and a preset merchandise image in the first image library; acquiring a first distinguishing feature of the preset commodity image with the first similarity degree larger than a first threshold value; extracting a second distinguishing feature of each image for the at least one image; determining a second degree of similarity of the first distinguishing feature to the second distinguishing feature; determining the preset commodity image with the highest second similarity degree as the target commodity image matched with the at least one image; the first distinguishing feature and the second distinguishing feature are used for distinguishing preset commodity images of different commodity types.

In one or more alternative embodiments, the apparatus further comprises: a fifth obtaining module, configured to obtain, when the commodity to be checked out includes an identification code, a check-out manner of the commodity to be checked out and commodity attribute information by scanning the identification code; or the first receiving module is used for receiving first feedback information when the commodity to be checked out does not comprise the identification code, wherein the first feedback information is used for indicating the check-out mode of the commodity to be checked out and commodity attribute information; the third determining module is used for determining the commodity total price of the commodity to be checked out according to the check-out mode and the commodity attribute information in the first feedback information; the first output module is used for outputting first prompt information, and the first prompt information is used for indicating that the commodity image of the commodity to be checked out is added into the first image library.

In one or more alternative embodiments, the apparatus further comprises: the first searching module is used for searching whether the checkout videos of the same type of commodities exist in the commodities to be checked out or not through monitoring camera shooting; a sixth obtaining module, configured to obtain, when the checkout video exists, related information of a checkout process of the same type of commodity indicated by the checkout video, where the related information of the checkout process includes a checkout mode and commodity attribute information of the same type of commodity; and the fourth determining module is used for determining the commodity total price of the commodity to be checked out according to the check-out mode and the commodity attribute information of the commodity of the same type.

In one or more alternative embodiments, the apparatus further comprises: the first judging module is used for judging whether the number of the preset commodity images with the first similarity degree larger than a first threshold value is a plurality of; a fifth determining module, configured to determine that a plurality of preset commodity images are similar commodity images if the number of preset commodity images with the first similarity degree greater than a first threshold is multiple; the first determining module is specifically configured to obtain a first distinguishing feature of each similar commodity image; and determining the similar commodity image with the highest second similarity degree as the target commodity image matched with the at least one image.

In one or more alternative embodiments, the commodity attribute information further includes at least one of a date of manufacture, a shelf life, quality eligibility information, and a manufacturer's home, the apparatus further comprising: the second judging module is used for judging whether invalid information exists in the production date, the quality qualified information and the manufacturer; if the production date, the quality qualified information and the invalid information do not exist in the production factory, determining the commodity total price of the commodity to be checked out according to the checking-out mode and the commodity attribute information; or a third judging module, configured to judge whether the commodity to be checked out is an expired product according to the production date and the quality guarantee period; and if the commodity to be checked out is not an expired product, determining the commodity total price of the commodity to be checked out according to the checking out mode and the commodity attribute information.

In one or more alternative embodiments, the checkout mode includes checkout by piece, and the commodity attribute information includes commodity type and price of a single commodity; the second determining module is specifically configured to determine, according to the at least one image, a quantity of each type of commodity included in the commodity to be checked out; and determining the commodity total price according to the sum of the products of the quantity of each type of commodity in the commodity to be checked out and the price of the single commodity of the type of commodity.

In one or more alternative embodiments, the article attribute information further includes a single article weight, the apparatus further comprising: the first detection module is used for detecting the total weight of the commodity to be checked out when the commodity to be checked out comprises a commodity type; a sixth determining module, configured to determine a first commodity number of the commodity to be checked out according to a total commodity weight of the commodity to be checked out and the weight of the single commodity; a seventh determining module, configured to determine a second commodity quantity of the commodity to be checked out according to the at least one image; the second determining module is specifically configured to determine, when the first commodity number is consistent with the second commodity number, the total commodity price according to a product of the first commodity number and a price of a single commodity of the type commodity, or according to a product of the second commodity number and a price of a single commodity of the type commodity.

In one or more alternative embodiments, the article attribute information further includes a single article weight, the apparatus further comprising: an eighth determining module configured to determine, according to the at least one image, a quantity of each type of commodity included in the commodity to be checked out; a ninth determining module, configured to determine a total weight of the first commodity of the commodity to be checked out according to a number of each type of commodity included in the commodity to be checked out and a weight of a single commodity; the second detection module is used for detecting the total weight of a second commodity of the commodity to be checked out; the second determining module is specifically configured to determine, when an absolute value of a difference between the total weight of the first commodity and the total weight of the second commodity is smaller than a second threshold, a total commodity price according to a sum of products of a number of each type of commodity in the commodity to be checked out and a price of a single commodity of the type of commodity.

In one or more alternative embodiments, the checkout mode includes checkout by weight, and the merchandise attribute information includes merchandise type and merchandise price per unit weight; the second determining module is specifically configured to detect a total weight of the commodity to be checked out when the commodity to be checked out includes a commodity type; and determining the commodity total price according to the product of the commodity total weight of the commodity to be checked out and the commodity price per unit weight.

According to an aspect of the present disclosure, there is provided an electronic apparatus including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the instructions stored in the memory to perform the above method.

According to an aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the above-described method.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the technical aspects of the disclosure.

Fig. 1a shows a flow chart of a method of checkout of an article of merchandise according to an embodiment of the disclosure.

Fig. 1b shows an exemplary schematic diagram of a terminal device performing a method of checkout of goods according to an embodiment of the present disclosure.

Fig. 2 illustrates a schematic diagram of an exemplary manner of storing preset merchandise images and associations in a first image store according to an embodiment of the present disclosure.

Fig. 3 illustrates an example of a prompt displayed on a display component or display device of an embodiment of the present disclosure.

Fig. 4 illustrates one example of a prompt for success of feedback in an embodiment of the present disclosure.

FIG. 5 illustrates a block diagram of a checkout device for goods in accordance with an embodiment of the present disclosure

Fig. 6 illustrates a block diagram of an electronic device 1900 according to an embodiment of the disclosure.

Detailed Description

Various exemplary embodiments, features and aspects of the disclosure will be described in detail below with reference to the drawings. In the drawings, like reference numbers indicate identical or functionally similar elements. Although various aspects of the embodiments are illustrated in the accompanying drawings, the drawings are not necessarily drawn to scale unless specifically indicated.

The word "exemplary" is used herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

The term "and/or" is herein merely an association relationship describing an associated object, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, C, and may mean including any one or more elements selected from the group consisting of A, B and C.

Furthermore, numerous specific details are set forth in the following detailed description in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements, and circuits well known to those skilled in the art have not been described in detail in order not to obscure the present disclosure.

The embodiment of the disclosure provides a commodity checkout method, which can be executed by electronic Equipment such as terminal Equipment or a server, wherein the terminal Equipment can be User Equipment (UE), mobile Equipment, a User terminal, a cellular phone, a cordless phone, a personal digital assistant (Personal Digital Assistant, PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device and the like, and the method can be realized by a mode that a processor invokes computer readable instructions stored in a memory. Alternatively, the method may be performed by a server.

Fig. 1a shows a flowchart of a method of checkout of an article of merchandise, according to an embodiment of the present disclosure, as shown in fig. 1a, the method of checkout of an article of merchandise including steps S11-S14:

in step S11, at least one image of the article to be checked out is acquired.

Fig. 1b shows an exemplary schematic diagram of a terminal device performing a method of checkout of goods according to an embodiment of the present disclosure. As shown in fig. 1b, a terminal device performing the method of checkout of an article of merchandise in an embodiment of the present disclosure may include a camera assembly for capturing at least one image of the article to be checked out. Alternatively, the terminal device or the server may be connected to the image capturing device by wire or wirelessly to acquire at least one image captured by the image capturing device. The at least one image may include an image of at least one angle of the item to be checked out.

The image pickup assembly or the image pickup apparatus may be disposed at a position where the commodity to be checked out in the check out area can be photographed, and may be disposed so as to be able to collect images at a certain frequency. In this case, the captured image may be an image of the article to be checked out. Optionally, as shown in fig. 1b, the terminal device may further comprise a gravity detection component for detecting the gravity force experienced by the checkout area. Alternatively, the terminal device or server may be connected with the gravity detection device either by wire or wirelessly to detect the gravity experienced by the checkout area by the gravity detection device. It may be arranged to drive the camera assembly or the camera device to capture images at a frequency after detecting that the weight force experienced by the checkout area is greater than a certain threshold, to reduce the cost required to capture (and transmit) the images. The present disclosure is not limited to the manner in which the image of the article to be checked out is acquired.

In step S12, a target commodity image matching at least one image is determined from the first image library.

The first image library may store preset commodity images corresponding to various types of commodities. Each image of the commodity to be checked out can comprise at least one commodity image of the commodity type, and a preset commodity image in the first image library matched with any commodity image in the images of the commodity to be checked out can be used as a target commodity image. For example, the commodity A to be checked out, the commodity B to be checked out and the commodity C to be checked out are placed in an image collecting area (the image collecting area can be larger than or equal to the area of the checking out area), 2 images are collected from different angles, the image 1 comprises the commodity image A and the commodity image B (the image of the commodity C to be checked out is blocked), the image 2 comprises the commodity image A, the commodity image B and the commodity image C, then the image 1 is matched with a preset commodity image in a first image library to obtain a target commodity image A and a target commodity image B, and the image 2 is matched with the preset commodity image in the first image library to obtain a target commodity image A and a target commodity image B, and the target commodity image C, namely the target commodity image matched with the image of the commodity to be checked out is the target commodity image A, the target commodity image B and the target commodity image C.

The "matching" method may be various, for example, by identifying, by a neural network method, the similarity degree between the preset commodity image stored in the first image library and the image of the commodity to be checked out, and when the similarity degree value is higher than a certain threshold value, considering that the image of the commodity to be checked out is matched with the target commodity image, or may be by comparing the values of the pixels of the image of the commodity to be checked out and the target commodity image, and when the difference of the values of the pixels of the corresponding positions is smaller than a certain threshold value, considering that the image of the commodity to be checked out is matched with the target commodity image. The present disclosure is not limited in the specific manner in which the target merchandise image that matches the image of the merchandise to be checked out is determined.

In step S13, according to the preset association relationship, the checkout mode and the commodity attribute information corresponding to the target commodity image are acquired.

The preset association relationship may be established when preset commodity images corresponding to various types of commodities are stored in the first image library, and may be an association relationship of preset commodity images, a checkout mode and commodity attribute information. The corresponding checkout mode of the target commodity image can comprise checkout by a piece and checkout by weight. The commodity attribute information corresponding to the target commodity image may include a commodity type, a single commodity price, a unit weight commodity price, a single commodity weight, and the like corresponding to the target commodity image. The present disclosure is not limited to the specific type of checkout mode and merchandise attribute information.

In step S14, the commodity total price of the commodity to be checked out is determined according to the check-out manner and the commodity attribute information.

As shown in fig. 1b, the terminal device for executing the method for checking out the commodity according to the embodiment of the present disclosure may further include a display component for displaying the total commodity price of the commodity to be checked out. Alternatively, the terminal device or the server may be connected with the display device by wire or wirelessly to display the total price of the commodity to be checked out. When the commodity total price is displayed, commodity attribute information and/or a checkout mode can be displayed together. The customer may determine the total price of the merchandise and make a payment by viewing the content displayed on the display assembly or display device.

Exemplary methods of determining a target merchandise image from a first image library that matches at least one image according to embodiments of the present disclosure are described below.

In one possible implementation, step S12 includes:

determining a first similarity degree of each image and a preset commodity image in a first image library aiming at least one image;

acquiring a first distinguishing feature of a preset commodity image with a first similarity degree larger than a first threshold value;

extracting a second distinguishing feature of each image for at least one image;

determining a second degree of similarity of the first distinguishing feature to the second distinguishing feature;

determining a second preset commodity image with highest similarity as a target commodity image matched with at least one image;

the first distinguishing feature and the second distinguishing feature are used for distinguishing preset commodity images of different commodity types.

For example, the preset merchandise images in the first image library may include a plurality of merchandise images of the merchandise type "YY brand biscuits", for example, the image numbers are 000201-000205, and a plurality of merchandise images of the merchandise type "XX brand milk", for example, the image numbers are 000111-000115. The image number of at least one image of the article to be checked out is, for example, 000121 to 000125. The first degree of similarity of each image with image numbers 000121-000125 to each image with image numbers 000201-000205, 000111-000115 can be determined, respectively. The first degree of similarity may be a value of the value range 0,100 and the first threshold may be equal to 75, for example. The preset commodity image whose first degree of similarity is greater than the first threshold value may be an image whose image number is 000201. Those skilled in the art will appreciate that the first threshold may be set in other ways as long as the user's needs are satisfied, which is not limited by the present disclosure.

The first distinguishing feature of the image with image number 000201 and the second distinguishing feature of each of the images with image numbers 000121-000125 may be further acquired. The first distinguishing feature and the second distinguishing feature may be used to distinguish preset merchandise images of different merchandise types, for example, may be an identifier, such as a trademark, a merchandise surface pattern, or the like, that can uniquely distinguish the merchandise in the image from other merchandise.

Based on the acquired first and second distinguishing features, a second degree of similarity of the first and second distinguishing features may be determined. The second similarity degree may be a value of a value range of [0,100], and the higher the value of the second similarity degree, the more similar the distinguishing feature of the preset commodity image and the commodity image of the commodity to be checked out can be considered. The second preset merchandise image having the highest degree of similarity may be an image having an image number of 000201. The preset merchandise image with the image number 000201 may be determined as the target merchandise image matching with at least one image.

In one possible implementation manner, after determining, for at least one image, a first similarity degree between each image and a preset commodity image in the first image library, the method further includes:

judging whether the number of the preset commodity images with the first similarity degree larger than a first threshold value is a plurality of;

if the number of the preset commodity images with the first similarity degree larger than the first threshold value is a plurality of, determining that the plurality of preset commodity images are similar commodity images;

the acquiring the first distinguishing feature of the preset commodity image with the first similarity degree larger than the first threshold value comprises the following steps:

acquiring a first distinguishing characteristic of each similar commodity image;

determining the second preset commodity image with the highest similarity degree as the target commodity image matched with at least one image comprises the following steps:

and determining the second similar commodity image with the highest similarity degree as a target commodity image matched with at least one image.

For example, the preset merchandise images in the first image library may include a plurality of merchandise images of the merchandise type "YY brand biscuits", for example, the image numbers are 000201-000205, and a plurality of merchandise images of the merchandise type "XX brand milk", for example, the image numbers are 000111-000115. The image number of at least one image of the article to be checked out is, for example, 000121 to 000125.

By comparing the magnitude relation between the first similarity and the first threshold, it can be determined that three preset commodity images with the first similarity greater than the first threshold are images with image numbers of 000201, 000205 and 000111 respectively. In this case, it may be judged that the number of the preset commodity images for which the first degree of similarity is determined to be larger than the first threshold value is plural, and the images of which the image numbers are 000201, 000205, 000111 may be determined to be the similar commodity images. When the first distinguishing feature of the preset commodity image with the first similarity degree larger than the first threshold value is acquired, the first distinguishing feature of each similar commodity image can be acquired. When the second preset commodity image with the highest similarity is determined as the target commodity image matched with at least one image, the second similar commodity image with the highest similarity can be determined as the target commodity image matched with at least one image. The method for obtaining the first distinguishing feature and the second distinguishing feature may be referred to the above description, and will not be described herein. The second similar commodity image having the highest degree of similarity may be an image having an image number of 000201. The similar merchandise image with the image number 000201 may be determined as the target merchandise image matching with the at least one image.

In one possible implementation, in a case that the target commodity image matching the at least one image cannot be determined from the first image library, the method further includes:

under the condition that the commodity to be checked out comprises the identification code, acquiring a checking out mode of the commodity to be checked out and commodity attribute information in a mode of scanning the identification code; or (b)

Receiving first feedback information when the commodity to be checked out does not comprise the identification code, wherein the first feedback information is used for indicating a check-out mode of the commodity to be checked out and commodity attribute information;

determining the commodity total price of the commodity to be checked out according to the check-out mode and commodity attribute information in the first feedback information;

and outputting first prompt information, wherein the first prompt information is used for indicating that the commodity image of the commodity to be checked out is added into a first image library.

For example, if the target commodity image matching the at least one image is not determined from the first image library, it may be considered that the commodity to be checked out is not entered in the first image library, that is, the commodity image of the commodity to be checked out is not added to the first image library. The payment terminal may not be able to complete the checkout of the goods faster because it may not continue to perform subsequent steps. In this case, in order to reduce waiting time of the customer, the checkout may be performed by a checkout method existing in the related art.

For example, if the commodity to be checked out is a commodity printed or attached with an identification code, the checking out mode of the commodity to be checked out and the commodity attribute information may be obtained by scanning the identification code, so that the payment terminal may normally execute step S14 to determine the commodity total price of the commodity to be checked out. If the commodity to be checked out is a commodity without the identification code, the check out mode of the commodity and the commodity attribute information can be provided to the payment terminal by manually inputting the first feedback information, so that the payment terminal can normally execute the step S14 according to the check out mode and the commodity attribute information in the first feedback information, and the commodity total price of the commodity to be checked out is determined.

Further, the payment terminal may output first prompt information for indicating that the commodity image of the commodity to be checked out is added to the first image library. The first prompt information may be output to a server or other terminal device used by the administrator, and may include various forms of image prompts, text prompts, voice prompts, and the like. After receiving the first prompt information, the server or other terminal equipment can determine the association relationship between the commodity image of the commodity to be checked out and the check-out mode and the commodity attribute information of the commodity to be checked out according to the first prompt information, and then store the commodity image and the association relationship of the commodity to be checked out into the first image library.

searching whether the checkout videos of the same type of commodities exist in the commodities to be checked out or not through monitoring camera shooting;

under the condition that the checkout video exists, acquiring related information of the checkout process of the same type of commodity indicated by the checkout video, wherein the related information of the checkout process comprises the checkout mode and commodity attribute information of the same type of commodity;

and determining the commodity total price of the commodity to be checked out according to the check-out mode and the commodity attribute information of the commodity of the same type.

For example, if a customer M cannot determine a target commodity image matched with at least one image of a commodity to be checked out when checking out, and checking out is completed by manually scanning an identification code or by manually inputting a checking out mode required for checking out and commodity attribute information, the relevant information of the checking out process of the commodity to be checked out of the customer M may be recorded as a checking out video by a monitoring camera (for example, an imaging component or an imaging device). After that, if the other customer N fails to determine the target commodity image matched with the at least one image of the commodity to be checked out, and the commodity to be checked out of the customer N is the same type of commodity as the commodity to be checked out of the customer M, whether the check out record of the same type of commodity as the commodity to be checked out of the customer N exists or not can be searched out through the monitoring camera, and if the check out record exists, the check out mode and commodity attribute information of the commodity of the same type of commodity as the commodity to be checked out of the customer N are obtained through the related information of the check out process indicated by the check out record. After the checkout mode and the commodity attribute information of the commodities of the same type are acquired, the commodity total price of the commodities to be checked out can be determined according to the checkout mode and the commodity attribute information of the commodities of the same type.

In one possible implementation manner, the commodity attribute information further includes at least one of a production date, a quality guarantee period, quality qualification information, and a manufacturer, and after acquiring a checkout mode and commodity attribute information corresponding to the target commodity image according to a preset association relationship, the method further includes:

judging whether invalid information exists in the production date, the quality qualified information and the manufacturer; if the production date, the quality qualified information and the invalid information do not exist in the production factory, determining the commodity total price of the commodity to be checked out according to the checking-out mode and the commodity attribute information; or (b)

Judging whether the commodity to be checked out is an expired product according to the production date and the quality guarantee period; if the commodity to be checked out is not an expired product, determining the commodity total price of the commodity to be checked out according to the checking out mode and the commodity attribute information.

For example, when a merchant purchases a commodity, information such as a date of production, a shelf life, quality qualification information, a manufacturer, etc. of the commodity may be obtained according to a package, a purchase channel, etc. of the commodity. Such information may be used as commodity attribute information. Those skilled in the art will readily recognize that a commodity lacking any one of date of manufacture, quality-qualifying information, and manufacturer's home may be considered as a triple-nothing commodity, and that the quality of the triple-nothing commodity is difficult to guarantee. Therefore, after the checkout mode and the commodity attribute information corresponding to the target commodity image are acquired, it is possible to judge whether or not the production date, the quality-qualified information, and the invalid information exists in the manufacturer's home based on the commodity attribute information.

If the production date, the quality qualified information and the invalid information does not exist in the manufacturer, the commodity total price of the commodity to be checked out can be determined according to the check-out mode and the price of the single commodity, the price of the commodity per unit weight and the like in the commodity attribute information. If at least one of the production date, the quality qualified information and the production factory has invalid information, a second prompt message can be output, and the second prompt message indicates that the commodity to be checked out is three non-products. The second prompt information may be in other forms such as a picture form or a sound form, so that the second prompt information may be displayed to the customer through the payment terminal. Through the second prompt information, the customer can clearly know the quality of the commodity to be checked out.

Further, the expiration date of the commodity can be determined according to the production date and the quality guarantee period, and whether the commodity is an expired product can be determined according to the actual date of checkout. If the commodity to be checked out is not an expired product, the commodity total price of the commodity to be checked out can be determined according to the check out mode and the price of the single commodity, the price of the commodity with unit weight and the like of the commodity attribute information. If the commodity to be checked out is an expired product, third prompt information can be output, and the third prompt information indicates that the commodity to be checked out is the expired product. The third prompt information may be in a form of a picture or a sound, etc., so that the third prompt information may be displayed to the customer through the payment terminal. Through the third prompt information, the customer can clearly know whether the commodity to be checked out is out of date.

The first image library may be preset, and may be used to store an image of a commodity being sold (preset commodity image) and an association relationship between the image and the checkout mode and the commodity attribute information. Before a certain type of commodity starts to be sold, a preset commodity image and an association relation of the commodity can be stored in a first image library. An exemplary manner in which the embodiments of the present disclosure store the preset merchandise images and the association relationship in the first image bank is described below.

As shown in fig. 2, in one possible implementation manner, the method further includes step S21 to step S24:

in step S21, acquiring a commodity image of at least one commodity type, wherein each commodity type corresponds to at least one commodity image;

in step S22, for each commodity type, screening at least one commodity image corresponding to the commodity type to obtain a preset commodity image with image quality meeting a first preset condition;

In step S23, acquiring a checkout mode and merchandise attribute information of each preset merchandise image, and establishing an association relationship among the preset merchandise images, the checkout mode and the merchandise attribute information;

in step S24, each preset commodity image and the association relationship are stored in the first image library.

For example, in step S21, the at least one commodity type may be a type of commodity that is determined to be sold. The commodity image of the type of commodity may be first acquired by a camera assembly or camera device. For example, when the commodity type includes "strawberry", "XX brand milk", commodity images of "strawberry", "XX brand milk" are acquired, respectively. For each type of merchandise, multiple merchandise images may be acquired from multiple angles, respectively. For example, for commodity type "strawberry", the image numbers of the plurality of collected commodity images may be 000101 to 000110 (ten pieces in total). For commodity type "XX brand milk", the image number of the plurality of collected commodity images may be 000111-000120 (ten in total).

After acquiring the merchandise image of at least one merchandise type, in step S22, the acquired merchandise image may be screened to obtain a preset merchandise image with image quality meeting the first preset condition. The first preset condition may be that the resolution of the image is greater than a certain threshold value, or the like, or may be set as other conditions, as long as the first preset condition can be used as a criterion of image quality, and the specific setting manner of the first preset condition is not limited in the present disclosure. For example, for a plurality of commodity images with the serial numbers of 000101-000110 of commodity type "strawberry", the preset commodity image satisfying the first preset condition obtained by screening may be a plurality of commodity images with the serial numbers of 000101-000105; for the plurality of commodity images with the serial numbers of 000111-000120 of commodity type XX brand milk, the preset commodity images meeting the first preset condition obtained by screening can be the plurality of commodity images with the serial numbers of 000111-000115.

After screening to obtain preset commodity images with image quality meeting the first preset condition, in step S23, a checkout mode and commodity attribute information of each preset commodity image may be obtained, and an association relationship among the preset commodity images, the checkout mode and the commodity attribute information may be established. For example, the checkout mode of the commodity type "strawberry" may be a checkout mode of checkout by weight, and the commodity attribute information of the commodity type "strawberry" may include: commodity type "strawberry", commodity price per unit weight "50.00 yuan/kg". The checkout mode of the commodity type XX brand milk can be a checkout mode of checking out according to a piece, and commodity attribute information of the commodity type XX brand milk can comprise: commodity type "XX brand milk", single commodity price "8.00 yuan/piece", single commodity weight "500 g/piece". In this case, the association relationship of the preset commodity image, the checkout mode, and the commodity attribute information of the commodity types "strawberry", "XX brand milk" that can be established is shown in table 1 below.

TABLE 1

After the association relationship among the preset commodity image, the checkout mode, and the commodity attribute information is established, each preset commodity image and the association relationship may be stored in the first image library in step S24. In this case, when the target commodity image matching with at least one image is determined from the first image library, the checkout mode and commodity attribute information corresponding to the target commodity image can be obtained according to each preset commodity image and the association relationship stored in the first image library.

Further, before the first image library is formally put into use, the accuracy of the target commodity image determined from the first image library may be tested, and whether the first image library needs to be adjusted may be determined according to the test result.

Exemplary methods of testing the accuracy of a target commodity image determined from a first image library according to embodiments of the present disclosure are described below.

In one possible implementation, the method further includes:

acquiring at least one test image of a test commodity;

determining a third similarity degree between the test image and a preset commodity image in the first image library;

and adjusting the first image library when the third similarity degree is smaller than or equal to a third threshold value. .

For example, the type of the commodity can be selected as the test commodity according to the commodity type corresponding to the preset commodity image newly stored in the first image library. After the test merchandise is selected, the test merchandise may be placed in a checkout area such that the camera assembly or camera device may acquire at least one test image. By comparing the test image with the preset commodity image in the first image library, a third degree of similarity between the test image and the preset commodity image in the first image library can be determined.

The third threshold may be preset, and by comparing the magnitude relation between the third similarity and the third threshold, it is determined whether the first image library needs to be adjusted. The third threshold may be preset according to a value of the third similarity degree and a user requirement, and the specific selection manner of the third threshold is not limited in the disclosure.

If the third similarity is greater than the third threshold, the similarity between the preset commodity image of at least one type of commodity in the first image library and the test image is considered to be higher, and whether the first image library can determine whether the target commodity image is not finally determined or not can be determined temporarily, and the first image library can be not adjusted. Otherwise, if the third similarity is smaller than or equal to the third threshold, the similarity between the preset commodity images and the test images of all types of commodities in the first image library is considered to be low, and at this time, the first image library cannot necessarily determine the target commodity image, and adjustment of the first image library is required.

The test merchandise may be merchandise to be sold, and when the third similarity between the test image and the preset merchandise image in the first image library is low, the first image library may be considered as the possibility that the matching of the target merchandise image is not completed, so that the first image library may be adjusted. In this way, the accuracy of the target commodity image determined from the first image library can be improved.

In one possible implementation, the method further includes:

when the third similarity is greater than a third threshold, acquiring a third distinguishing feature of a preset commodity image of which the third similarity is greater than the third threshold;

extracting a fourth distinguishing feature of the test image;

determining a fourth degree of similarity of the third distinguishing feature to the fourth distinguishing feature;

adjusting the first image library when the fourth similarity degree is less than or equal to a fourth threshold value;

wherein the third discriminating characteristic and the fourth discriminating characteristic are used to discriminate merchandise images of different merchandise types.

For example, as can be seen from the above description, when the third similarity is greater than the third threshold, the first image library is not adjusted for the moment if it can be determined that the target commodity image has not been finally determined. In order to determine whether the first image library needs to be adjusted, a third distinguishing feature of a preset commodity image with a third similarity degree larger than a third threshold value and a fourth distinguishing feature of the test image can be further acquired. The third and fourth distinguishing features may be used to distinguish preset merchandise images of different merchandise types, and may be referred to above as examples of the first and second distinguishing features. The manner of obtaining the third distinguishing feature and the fourth distinguishing feature may refer to the above examples of the manner of obtaining the first distinguishing feature and the second distinguishing feature, which are not described herein.

From the acquired third and fourth distinguishing features, a fourth degree of similarity of the third and fourth distinguishing features may be determined. The higher the value of the fourth degree of similarity, the more similar the distinguishing features of the preset merchandise image and the merchandise image of the test merchandise can be considered. The fourth threshold may be preset, and by comparing the magnitude relation between the fourth similarity degree and the fourth threshold, it is determined whether the first image library needs to be adjusted. The fourth threshold may be preset according to the value of the fourth similarity degree and the user requirement, and the specific selection manner of the fourth threshold is not limited in the disclosure.

If the fourth similarity is determined to be greater than the fourth threshold, the first image library may be considered to have a higher similarity of the distinguishing features of the preset merchandise image of the at least one type of merchandise to the distinguishing features of the test image, and the target merchandise image may be determined from the first image library without adjusting the first image library. Otherwise, if the fourth similarity is determined to be less than or equal to the fourth threshold, it may be considered that the similarity between the distinguishing features of the preset commodity images of all types of commodities in the first image library and the distinguishing features of the test image is relatively low, and at this time, the first image library cannot necessarily determine the target commodity image, and adjustment needs to be performed on the first image library.

The test merchandise may be merchandise to be sold, the third similarity degree of the third difference feature of the preset merchandise image is larger than the third threshold value, and when the fourth similarity degree of the fourth difference feature of the test image is low, the first image library may be considered to be the possibility that the matching of the target merchandise image is not completed, so that the first image library may be adjusted. In this way, the accuracy of the target commodity image determined from the first image library can be improved.

Exemplary methods of adjusting the first image library according to embodiments of the present disclosure are described below.

In one possible implementation, the adjusting the first image library includes:

receiving second feedback information, wherein the second feedback information is used for indicating the actual type of the tested commodity;

acquiring a checkout mode and commodity attribute information of the test image according to the second feedback information;

establishing an association relation among the test image, the checkout mode and the commodity attribute information;

and storing the test image and the association relation in a first image library.

For example, when testing the accuracy of the target commodity image determined from the first image library, the terminal device or the server performing the commodity checkout method according to the embodiments of the present disclosure may provide a service to the staff member to adjust the first image library with the help of the staff member when the adjustment of the first image library is required.

For example, when the third degree of similarity is less than or equal to the third threshold, or the fourth degree of similarity is less than or equal to the fourth threshold, the corresponding control may be displayed on the display component or the display device and a prompt, such as a screen blinking, playing a voice prompt, or the like, may be performed to seek assistance of the staff member. If the adjustment to the first image library is determined when the third similarity is less than or equal to the third threshold, the display component or the display device may, for example, display a selection control of a commodity type corresponding to the preset commodity image with a higher third similarity, a selection control indicating that none of the currently displayed commodity types is an actual type of the test commodity, and an information input box. For example, the image number of at least one test image of the test commodity may be 000131-000140 (ten total), and the commodity types corresponding to the preset commodity image with the highest third degree of the test image in the first image library are commodity type "XX brand milk" and commodity type "YY brand biscuits", respectively. Fig. 3 illustrates an example of a prompt displayed on a display component or display device of an embodiment of the present disclosure.

If the displayed commodity type is just the actual type of the tested commodity, the staff can trigger a selection control corresponding to the commodity type identical to the actual type of the tested commodity according to the actual type of the tested commodity, and the display component or the display equipment can generate corresponding second feedback information according to the triggering operation. The second feedback information may indicate an actual type of the test article. As shown in FIG. 3, if a worker confirms that the actual type of the test commodity is XX brand milk, and triggers a selection control corresponding to the commodity type XX brand milk, the display page can display prompt information of successful feedback. Fig. 4 illustrates one example of a prompt for success of feedback in an embodiment of the present disclosure.

The first image library may be adjusted according to the actual type of the test article indicated in the second feedback information, for example, a checkout mode and article attribute information of the test article may be obtained according to the actual type of the test article indicated in the second feedback information, and an association relationship between at least one test image of the test article and the checkout mode and article attribute information may be established. The test image and the association may then be stored in a first image library. The new association may be combined with the existing association in the first image library.

For example, the commodity type indicated by the second feedback information may be "XX brand milk", and the combined association relationship is adjusted to be shown in table 2 according to the feedback information (table 2 does not show the checkout mode of the commodity type "YY brand biscuit" and the association relationship between the commodity attribute information and the commodity image).

TABLE 2

If all the displayed commodity types are not the actual types of the test commodity, the staff can trigger a selection control for indicating that the currently displayed commodity types are not the actual types of the test commodity, manually input the commodity types of the test commodity through an information input box, and the display assembly or the display equipment can generate corresponding second feedback information according to the input operation. For example, if a worker confirms that the actual type of test item is "CC brand milk," a selection control that is not "above" may be triggered and "CC brand milk" manually entered in the information entry box. The display assembly or display device may generate second feedback information indicating that the actual type of the test article is "CC brand milk. The display page can display prompt information of successful feedback.

Examples of adjusting the first image library according to the actual type of the test article indicated in the second feedback information may be referred to the above related description, and will not be described herein.

In this way, when the first image library does not meet the requirement, the second feedback information can be acquired, the association relation between the image of the test commodity and the checkout mode and the commodity attribute information can be established according to the second feedback information, and the first image library is adjusted by adding the image of the test commodity and the association relation in the first image library. Since the second feedback information indicates the actual type of the test article, the association is accurate, and the accuracy of determining the target article image from the adjusted first image library can be made higher than before adjustment.

The above is given as an example of the need to make adjustments to the first image library being determined when the third degree of similarity is less than or equal to a third threshold. It should be understood by those skilled in the art that if it is determined that the first image library needs to be adjusted when the fourth similarity degree is less than or equal to the fourth threshold, the implementation manner may refer to the above example of the manner of adjusting the first image library when the third similarity degree is less than or equal to the third threshold, and replace the selection control of the commodity type corresponding to the preset commodity image displayed by the display component or the display device with the selection control of the commodity type corresponding to the third distinguishing feature with the fourth similarity degree. In addition, the method for adjusting the first image library may be the same, and will not be described herein.

After the adjustment of the first image library is completed, the steps of acquiring at least one test image of the test article and thereafter may be continued until the first image library meets the requirements. In this case, it can be considered that the accuracy of determining the target commodity image from the first image library is high. At this time, the terminal device or the server performing the method of checkout of the goods according to the embodiment of the present disclosure may provide the service to the customer, that is, perform steps S11 to S14. In providing service to customers, it is known from the above description that the customer needs to be provided with the total price of the goods via the display assembly or display device.

According to different checkout modes, the acquisition modes of the commodity total prices of the commodities to be checked out are different. An exemplary manner of obtaining the total commodity price of the commodity to be checked out according to the embodiment of the present disclosure is described below when checking out by piece and checking out by weight, respectively.

An exemplary manner of obtaining the total price of the article to be checked out in accordance with the embodiments of the present disclosure when checking out by piece is described below.

In one possible implementation, the checkout mode includes checkout by piece, and the commodity attribute information includes commodity type and price of a single commodity;

determining the commodity total price of the commodity to be checked out according to the checking out mode and the commodity attribute information, wherein the method comprises the following steps:

Determining the quantity of each type of commodity included in the commodity to be checked out according to at least one image;

and determining the total price of the commodity according to the sum of the products of the quantity of each type of commodity in the commodity to be checked and the price of the single commodity of the type of commodity.

For example, the target commodity image to which at least one image of the commodity to be checked out matches may be more than one commodity-type image, and the commodity of each commodity type included in the at least one image may be more than one. For example, the target commodity image determined in step S12 may include a commodity image of commodity type "XX brand milk", a commodity image of commodity type "YY brand cookie". According to the checkout mode of each commodity type in the first image library and the association relation between the commodity attribute information and the commodity image, in step S13, it may be determined that the commodity type to be checked out includes "XX brand milk", where the checkout mode is to check out according to a piece and the price of a single commodity is "8.00 yuan/piece". The commodity type to be checked out can be determined to also comprise a YY brand biscuit, and the check out mode is that the check out is carried out by pieces, and the price of a single commodity is 10.00 yuan/piece.

Since each type of commodity included in the commodity to be checked out is checked out by piece, the commodity total price of the commodity to be checked out can be determined by determining the number of each type of commodity and then calculating the sum of the products of the number of each type of commodity and the price of the corresponding single commodity. Wherein the number of each type of merchandise may be determined by identifying the merchandise in at least one image. For example, it may be determined in step S14 that there are 2 "XX brand milk" and 1 "YY brand biscuits" based on at least one image. The total price of the article to be checked out is 8.00 x 2+10.00 x 1 = 18 (yuan).

Considering that in at least one image of the commodity to be checked out, the condition that the commodity with larger volume shields the commodity with smaller volume may occur, or under certain angles, the condition that the commodity with the same volume shields may also occur. Errors may occur in the number of each type of item included in the item to be checked out determined from the at least one image when occlusion occurs. The commodity checkout method of the embodiment of the present disclosure may further check the number of each type of commodity obtained from at least one image or the total commodity weight of the commodity to be checked out, so as to determine whether at least one image is occluded, and respond when it is determined that occlusion occurs.

An exemplary method of verifying the quantity of each type of merchandise derived from at least one image is described below.

In one possible implementation, the merchandise attribute information further includes a single piece merchandise weight, the method further comprising:

Detecting the total weight of the commodity to be checked out when the commodity to be checked out comprises a commodity type;

determining the first commodity quantity of the commodity to be checked out according to the commodity total weight of the commodity to be checked out and the weight of the single commodity;

determining a second commodity quantity of the commodity to be checked out according to the at least one image;

and under the condition that the first commodity quantity is consistent with the second commodity quantity, determining the commodity total price according to the product of the first commodity quantity and the price of the single commodity of the commodity, or according to the product of the second commodity quantity and the price of the single commodity of the commodity.

For example, the target commodity image determined in step S12 may include a commodity image of a commodity type "XX brand milk", the obtained checkout manner in step S13 may be checkout by piece, and in the obtained commodity attribute information, the commodity type to be checked out may include "XX brand milk", the price of a single commodity of "XX brand milk" may be "8.00 yuan/piece", and the weight of a single commodity of "XX brand milk" may be "500 g/piece".

According to the above-mentioned checkout mode and commodity attribute information, it can be determined that the commodity to be checked out includes only one commodity type, and the checkout mode of this commodity type is checked out by piece, in which case the gravity force applied to the checkout area can be detected by the gravity detection component or the gravity detection device, and the commodity total weight of the commodity to be checked out can be obtained according to the detection result. According to the detected total weight of the commodities and the weight of the single commodity of the commodity type only included in the commodity to be checked out, the commodity number of the commodity type, namely the first commodity number of the commodity to be checked out, can be determined. For example, when the total weight of the commodity is 1000g, the first commodity amount may be determined to be 1000g/500 g=2 (pieces).

Based on at least one image of the item to be checked out, the number of items in the image, i.e. the second number of items of the item to be checked out, can be identified. For example, a second merchandise quantity of 2 may be determined. Since the first commodity number is consistent with the second commodity number, the commodity total price can be determined according to the product of the first commodity number and the price of the single commodity of the type commodity or according to the product of the second commodity number and the price of the single commodity of the type commodity. For example, the total commodity price is determined to be 8.00 x 2 = 16.00 (yuan).

In one possible implementation, the method further includes: and outputting fourth prompt information for indicating to reacquire at least one image of the commodity to be checked out under the condition that the number of the first commodity is inconsistent with the number of the second commodity.

For example, if the second commodity number is inconsistent with the first commodity number, it may be considered that at least one image is occluded by the commodity. The prompting can be performed through the display component or the display device, for example, fourth prompting information is output, and the fourth prompting information is used for indicating to reacquire at least one image of the commodity to be checked out, so that the customer can adjust the placement position of the commodity to be checked out in the checking area according to the fourth prompting information. Step S14 may not be performed at this time. After the customer adjusts the placement position of the commodity to be checked out, the steps S11 and the following steps are executed again. The fourth prompting information may be in a picture form, a sound form or other forms, and the disclosure is not limited thereto.

The error information can be displayed to the customer through outputting the fourth prompt information so that the customer can process the error information, and the purpose of ensuring the calculation accuracy of the commodity total price through interaction is achieved.

An exemplary method of verifying the total weight of the article to be checked out is described below.

determining the total weight of a first commodity of the commodity to be checked out according to the quantity of each type of commodity included in the commodity to be checked out and the weight of the single commodity;

detecting the total weight of a second commodity of the commodity to be checked out;

and determining the commodity total price according to the sum of the products of the quantity of each type of commodity in the commodities to be checked out and the price of the single commodity of the type of commodity under the condition that the absolute value of the difference between the total weight of the first commodity and the total weight of the second commodity is smaller than a second threshold value.

For example, the number of each type of merchandise may be determined by identifying the merchandise in at least one image. The total weight of the goods to be checked out, i.e., the total weight of the first goods, can be obtained by the sum of the products of the number of each type of goods included in the goods to be checked out and the weight of the single goods. The gravity force applied to the checkout area can be detected by the gravity detection component or the gravity detection equipment, and the total commodity weight of the commodity to be checked out, namely the total weight of the second commodity, is obtained according to the detection result. If there is no occlusion in at least one of the images, the values of the total weight of the first commodity and the total weight of the second commodity should be approximated, and a second threshold value may be preset such that the deviation of the total weight of the first commodity and the total weight of the second commodity is considered to be within an allowable range when the absolute value of the difference between the total weight of the first commodity and the total weight of the second commodity is less than or equal to the second threshold value. Therefore, if the absolute value of the difference between the total weight of the first commodity and the total weight of the second commodity is larger than the second threshold value, the condition that at least one image is blocked by the commodity can be determined. The second threshold may be preset according to the accuracy of the gravity detection component or the gravity detection device, and the specific selection manner of the second threshold is not limited in the present disclosure.

For example, in step S13, the obtained checkout manner may be checkout by piece, and in the obtained commodity attribute information, the types of commodities to be checked out may include "XX brand milk" and "YY brand biscuits", the price of single commodity of "XX brand milk" may be "8.00 yuan/piece", the weight of single commodity of "XX brand milk" may be "500 g/piece", the price of single commodity of "YY brand biscuits" may be "10.00 yuan/piece", and the weight of single commodity of "YY brand biscuits" may be "250 g/piece".

Based on at least one image, it may be determined, for example, that there are 1 "XX brand milk" and 2 "YY brand biscuits," the total weight of the first commodity may be 500g by 1+250g by 2=1000 g. The total weight of the second commodity may be, for example, 999g, and the absolute value of the difference between the total weight of the first commodity and the total weight of the second commodity may be equal to 1g assuming that the second threshold is set to 5 g. Since the absolute value of the difference between the total weight of the first commodity and the total weight of the second commodity is smaller than the second threshold value, the commodity total price can be determined according to the sum of the products of the number of each type of commodity in the commodities to be checked out and the price of the single commodity of the type of commodity. For example, the total commodity price is determined to be 8.00×1+10.00×2=28.00 (yuan).

In one possible implementation, the method further includes:

and outputting fifth prompt information for indicating to reacquire at least one image of the commodity to be checked out under the condition that the absolute value of the difference between the total weight of the first commodity and the total weight of the second commodity is greater than or equal to a second threshold value.

For example, if the absolute value of the difference between the total weight of the first commodity and the total weight of the second commodity is greater than or equal to the second threshold, it may be determined that at least one image is considered to be occluded by the commodity. The prompting can be performed through the display component or the display device, for example, fifth prompting information is output, and the fifth prompting information is used for indicating to reacquire at least one image of the commodity to be checked out, so that the customer can adjust the placement position of the commodity to be checked out in the check out area according to the fifth prompting information. Step S14 may not be performed at this time. After the customer adjusts the placement position of the commodity to be checked out, the steps S11 and the following steps are executed again. The fifth prompting information may be in a picture form, or may be in a sound form or the like, which is not limited in the present disclosure.

The information of errors in the number of the commodities to be checked out can be transmitted to the customer through outputting the fifth prompt information, so that the customer can process the information, and the purpose of ensuring the accuracy of the commodity total price through interaction is achieved.

An exemplary manner of obtaining the total commodity price of the commodity to be checked out according to the embodiments of the present disclosure when checking out by weight is described below.

In one possible implementation, the checkout mode includes checkout by weight, and the commodity attribute information includes commodity type and commodity price per unit weight;

and determining the total price of the commodity according to the product of the total weight of the commodity to be checked and the commodity price per unit weight.

For example, the target merchandise image to which at least one image of the merchandise to be checked out matches may include an image of a merchandise type. For example, the target commodity image determined in step S12 may include a commodity image of commodity type "strawberry". In step S13, the obtained checkout mode may be checkout according to weight, and the obtained commodity attribute information may include "strawberry", where the commodity price per unit weight of "strawberry" may be "50.00 yuan/kg".

The gravity force applied to the checkout area can be detected by the gravity detection component or the gravity detection equipment, and the total commodity weight of the commodity to be checked out can be obtained according to the detection result. Since the commodity to be checked out includes one commodity type, the commodity total price can be obtained by multiplying the commodity total weight of the commodity to be checked out by the commodity price per unit weight. For example, when the total weight of the commodity to be checked out is 1kg, the commodity total price may be 50.00 yuan/kg 1 kg=50 (yuan).

In one possible implementation, the method further includes:

and outputting sixth prompt information when the checkout mode corresponding to the commodity attribute information of the target commodity image comprises checkout according to weight and the commodity attribute information comprises more than two commodity prices per unit weight, wherein the sixth prompt information is used for indicating that the commodity type of the commodity to be checked out does not meet the checkout condition. For example, the target merchandise image to which at least one image of the merchandise to be checked out matches may be more than one merchandise type image. For example, the target commodity image determined in step S12 may include a commodity image of commodity type "strawberry", a commodity image of commodity type "grape". In step S13, the obtained checkout mode may be checkout according to weight, and the obtained commodity attribute information may include "strawberry", "grape", and "strawberry" with a commodity price per unit weight of "50.00 yuan/kg", and "grape" with a commodity price per unit weight of "25.00 yuan/kg". Since the commodity attribute information of the commodity to be checked out comprises more than two commodity prices per unit weight, the commodity to be checked out can be prompted through the display component or the display device, for example, a sixth prompt message is output, and the sixth prompt message is used for indicating that the commodity type of the commodity to be checked out does not meet the check out condition, so that a customer can adjust the commodity to be checked out in the check out area according to the sixth prompt message, and the commodity attribute information of the commodity to be checked out after adjustment can comprise one commodity price per unit weight. Step S14 may not be performed at this time. After the customer adjusts the commodity to be checked out, the steps S11 and thereafter are performed again. The sixth prompt information may be in a form of a screen, a sound, or the like, which is not limited in this disclosure.

Because two commodities with different commodity prices per unit weight are difficult to check out according to weight at the same time, information that the commodity price per unit weight of the commodity to be checked out does not meet the requirement can be transmitted to a customer through prompt, so that the customer can process the commodity, and the purpose that the total commodity price can be determined based on the total weight of the commodity obtained through detection is achieved through interaction.

In one possible implementation, the method further includes:

when the checkout mode corresponding to the commodity attribute information of the target commodity image comprises checkout according to a piece and checkout according to weight, outputting seventh prompt information, wherein the seventh prompt information is used for indicating that the commodity type of the commodity to be checked out does not meet the checkout condition.

For example, since the items checked out by piece and checked out by weight are difficult to check out simultaneously, if the items checked out by piece and checked out by weight are placed together in the image acquisition area, the user may be prompted to adjust the items to be checked out. For example, a seventh hint information may be output that indicates that the article type of the article to be checked out does not satisfy the check out condition. The customer can adjust the commodity to be checked out in the check out area according to the seventh prompt information, so that the adjusted commodity to be checked out can only comprise one check out mode. Step S14 may not be performed at this time. After the customer adjusts the commodity to be checked out, the steps S11 and thereafter are performed again. The seventh prompt information may be in a form of a screen, a sound, or the like, which is not limited in this disclosure.

The information that the checkout mode of the commodity to be checked out does not meet the requirement can be transmitted to the customer through the prompt, so that the customer can process the commodity, and the purpose that the total commodity price can be determined based on the total commodity weight obtained through detection is achieved through interaction.

It will be appreciated that the above-mentioned method embodiments of the present disclosure may be combined with each other to form a combined embodiment without departing from the principle logic, and are limited to the description of the present disclosure. It will be appreciated by those skilled in the art that in the above-described methods of the embodiments, the particular order of execution of the steps should be determined by their function and possible inherent logic.

In addition, the disclosure further provides a commodity checkout device, an electronic device, a computer readable storage medium and a program, which can be used for realizing any commodity checkout method provided by the disclosure, and corresponding technical schemes and descriptions and corresponding records of method parts are omitted.

Fig. 5 shows a block diagram of a checkout device for goods, as shown in fig. 5, according to an embodiment of the present disclosure, the device comprising:

a first acquiring module 51, configured to acquire at least one image of a commodity to be checked out;

A first determining module 52, configured to determine a target commodity image matching the at least one image from a first image library;

a second obtaining module 53, configured to obtain a checkout mode and merchandise attribute information corresponding to the target merchandise image according to a preset association relationship;

and a second determining module 54, configured to determine a total commodity price of the commodity to be checked out according to the check-out manner and the commodity attribute information.

In one or more alternative embodiments, the first determining module 52 is specifically configured to determine, for the at least one image, a first similarity degree between each of the images and a preset merchandise image in the first image library; acquiring a first distinguishing feature of the preset commodity image with the first similarity degree larger than a first threshold value; extracting a second distinguishing feature of each image for the at least one image; determining a second degree of similarity of the first distinguishing feature to the second distinguishing feature; determining the preset commodity image with the highest second similarity degree as the target commodity image matched with the at least one image; the first distinguishing feature and the second distinguishing feature are used for distinguishing preset commodity images of different commodity types.

In one or more alternative embodiments, the apparatus further comprises: the first judging module is used for judging whether the number of the preset commodity images with the first similarity degree larger than a first threshold value is a plurality of; a fifth determining module, configured to determine that a plurality of preset commodity images are similar commodity images if the number of preset commodity images with the first similarity degree greater than a first threshold is multiple; the first determining module 52 is specifically configured to obtain a first distinguishing feature of each of the similar merchandise images; and determining the similar commodity image with the highest second similarity degree as the target commodity image matched with the at least one image.

In one or more alternative embodiments, the checkout mode includes checkout by piece, and the commodity attribute information includes commodity type and price of a single commodity; the second determining module 54 is specifically configured to determine, according to the at least one image, a quantity of each type of commodity included in the commodity to be checked out; and determining the commodity total price according to the sum of the products of the quantity of each type of commodity in the commodity to be checked out and the price of the single commodity of the type of commodity.

In one or more alternative embodiments, the article attribute information further includes a single article weight, the apparatus further comprising: the first detection module is used for detecting the total weight of the commodity to be checked out when the commodity to be checked out comprises a commodity type; a sixth determining module, configured to determine a first commodity number of the commodity to be checked out according to a total commodity weight of the commodity to be checked out and the weight of the single commodity; a seventh determining module, configured to determine a second commodity quantity of the commodity to be checked out according to the at least one image; the second determining module 54 is specifically configured to determine, when the first number of products is consistent with the second number of products, the total price of the products according to the product of the first number of products and the price of the single product of the type of products, or according to the product of the second number of products and the price of the single product of the type of products.

In one or more alternative embodiments, the article attribute information further includes a single article weight, the apparatus further comprising: an eighth determining module configured to determine, according to the at least one image, a quantity of each type of commodity included in the commodity to be checked out; a ninth determining module, configured to determine a total weight of the first commodity of the commodity to be checked out according to a number of each type of commodity included in the commodity to be checked out and a weight of a single commodity; the second detection module is used for detecting the total weight of a second commodity of the commodity to be checked out; the second determining module 54 is specifically configured to determine, when the absolute value of the difference between the total weight of the first commodity and the total weight of the second commodity is smaller than a second threshold, the total commodity price according to the sum of the products of the number of each type of commodity in the commodity to be checked out and the price of the single commodity of the type of commodity.

In one or more alternative embodiments, the checkout mode includes checkout by weight, and the merchandise attribute information includes merchandise type and merchandise price per unit weight; the second determining module 54 is specifically configured to detect a total weight of the commodity to be checked out when the commodity to be checked out includes a commodity type; and determining the commodity total price according to the product of the commodity total weight of the commodity to be checked out and the commodity price per unit weight.

In some embodiments, functions or modules included in an apparatus provided by the embodiments of the present disclosure may be used to perform a method described in the foregoing method embodiments, and specific implementations thereof may refer to descriptions of the foregoing method embodiments, which are not repeated herein for brevity.

The disclosed embodiments also provide a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the above-described method. The computer readable storage medium may be a volatile or nonvolatile computer readable storage medium.

The embodiment of the disclosure also provides an electronic device, which comprises: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the instructions stored in the memory to perform the above method.

Embodiments of the present disclosure also provide a computer program product comprising computer readable code, or a non-transitory computer readable storage medium carrying computer readable code, which when run in a processor of an electronic device, performs the above method.

The electronic device may be provided as a terminal, server or other form of device.

Fig. 6 illustrates a block diagram of an electronic device 1900 according to an embodiment of the disclosure. For example, electronic device 1900 may be provided as a server or terminal device. Referring to FIG. 6, electronic device 1900 includes a processing component 1922 that further includes one or more processors and memory resources represented by memory 1932 for storing instructions, such as application programs, that can be executed by processing component 1922. The application programs stored in memory 1932 may include one or more modules each corresponding to a set of instructions. Further, processing component 1922 is configured to execute instructions to perform the methods described above.

The electronic device 1900 may also include a power component 1926 configured to perform power management of the electronic device 1900, and a wired or wireless network interface 1950 configured to configure the electronic device The device 1900 is connected to a network, and an input output (I/O) interface 1958. Electronic device 1900 may operate an operating system based on memory 1932, such as the Microsoft Server operating system (Windows Server) ^TM ) Apple Inc. developed graphical user interface based operating System (Mac OS X ^TM ) Multi-user multi-process computer operating system (Unix) ^TM ) Unix-like operating system (Linux) of free and open source code ^TM ) Unix-like operating system (FreeBSD) with open source code ^TM ) Or the like.

In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as memory 1932, including computer program instructions executable by processing component 1922 of electronic device 1900 to perform the methods described above.

The present disclosure may be a system, method, and/or computer program product. The computer program product may include a computer readable storage medium having computer readable program instructions embodied thereon for causing a processor to implement aspects of the present disclosure.

The computer readable storage medium may be a tangible device that can hold and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: portable computer disks, hard disks, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static Random Access Memory (SRAM), portable compact disk read-only memory (CD-ROM), digital Versatile Disks (DVD), memory sticks, floppy disks, mechanical coding devices, punch cards or in-groove structures such as punch cards or grooves having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media, as used herein, are not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., optical pulses through fiber optic cables), or electrical signals transmitted through wires.

The computer readable program instructions described herein may be downloaded from a computer readable storage medium to a respective computing/processing device or to an external computer or external storage device over a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers and/or edge servers. The network interface card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium in the respective computing/processing device.

Computer program instructions for performing the operations of the present disclosure can be assembly instructions, instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, c++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may be executed entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present disclosure are implemented by personalizing electronic circuitry, such as programmable logic circuitry, field Programmable Gate Arrays (FPGAs), or Programmable Logic Arrays (PLAs), with state information of computer readable program instructions, which can execute the computer readable program instructions.

Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. 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-readable program instructions.

These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, 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, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable medium having the instructions stored therein includes an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The computer program product may be realized in particular by means of hardware, software or a combination thereof. In an alternative embodiment, the computer program product is embodied as a computer storage medium, and in another alternative embodiment, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK), or the like.

The foregoing description of various embodiments is intended to highlight differences between the various embodiments, which may be the same or similar to each other by reference, and is not repeated herein for the sake of brevity.

It will be appreciated by those skilled in the art that in the above-described method of the specific embodiments, the written order of steps is not meant to imply a strict order of execution but rather should be construed according to the function and possibly inherent logic of the steps.

If the technical scheme of the application relates to personal information, the product applying the technical scheme of the application clearly informs the personal information processing rule before processing the personal information and obtains the autonomous agreement of the individual. If the technical scheme of the application relates to sensitive personal information, the product applying the technical scheme of the application obtains individual consent before processing the sensitive personal information, and simultaneously meets the requirement of 'explicit consent'. For example, a clear and remarkable mark is set at a personal information acquisition device such as a camera to inform that the personal information acquisition range is entered, personal information is acquired, and if the personal voluntarily enters the acquisition range, the personal information is considered as consent to be acquired; or on the device for processing the personal information, under the condition that obvious identification/information is utilized to inform the personal information processing rule, personal authorization is obtained by popup information or a person is requested to upload personal information and the like; the personal information processing rule may include information such as a personal information processor, a personal information processing purpose, a processing mode, and a type of personal information to be processed.

The foregoing description of the embodiments of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the improvement of technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method of checkout of a commodity, comprising:

acquiring at least one image of a commodity to be checked out;

determining a target commodity image matched with the at least one image from a first image library;

acquiring a checkout mode and commodity attribute information corresponding to the target commodity image according to a preset association relation;

determining the commodity total price of the commodity to be checked out according to the checking out mode and the commodity attribute information;

searching whether the checkout video of the same type of commodity of the commodity to be checked out exists or not through monitoring camera shooting under the condition that the target commodity image matched with the at least one image is not determined from the first image library;

Acquiring related information of a checkout process of the same type of commodity indicated by the checkout video under the condition that the checkout video exists, wherein the related information of the checkout process comprises a checkout mode and commodity attribute information of the same type of commodity;

2. The method of claim 1, wherein prior to the acquiring the at least one image of the item to be checked out, the method further comprises:

acquiring commodity images of at least one commodity type, wherein each commodity type corresponds to at least one commodity image;

screening at least one commodity image corresponding to each commodity type to obtain a preset commodity image with image quality meeting a first preset condition;

acquiring a checkout mode and commodity attribute information of each preset commodity image, and establishing an association relationship among the preset commodity images, the checkout mode and the commodity attribute information;

and storing each preset commodity image and the association relation in the first image library.

3. The method of claim 2, wherein determining a target merchandise image from the first image library that matches the at least one image comprises:

determining a first similarity degree of each image and a preset commodity image in the first image library aiming at the at least one image;

acquiring a first distinguishing feature of the preset commodity image with the first similarity degree larger than a first threshold value;

extracting a second distinguishing feature of each image for the at least one image;

determining the preset commodity image with the highest second similarity degree as the target commodity image matched with the at least one image;

4. A method according to any one of claims 1-3, wherein in the event that a target merchandise image matching the at least one image is not determined from the first image library, the method further comprises:

under the condition that the commodity to be checked out comprises an identification code, acquiring a checking out mode and commodity attribute information of the commodity to be checked out in a mode of scanning the identification code; or (b)

Receiving first feedback information when the commodity to be checked out does not comprise the identification code, wherein the first feedback information is used for indicating a check-out mode and commodity attribute information of the commodity to be checked out;

determining the commodity total price of the commodity to be checked out according to the check-out mode and the commodity attribute information in the first feedback information;

and outputting first prompt information, wherein the first prompt information is used for indicating that the commodity image of the commodity to be checked out is added into the first image library.

5. A method according to claim 3, wherein after determining a first degree of similarity of each of the images to a preset merchandise image in a first image library for the at least one image, the method further comprises:

if the number of the preset commodity images with the first similarity degree larger than a first threshold value is a plurality of, determining that the preset commodity images are similar commodity images;

the acquiring the first distinguishing feature of the preset commodity image with the first similarity degree larger than a first threshold value comprises the following steps:

The determining the target commodity image with the highest second similarity degree as the target commodity image matched with the at least one image comprises the following steps:

and determining the similar commodity image with the highest second similarity degree as the target commodity image matched with the at least one image.

6. The method according to claim 1, wherein the commodity attribute information further includes at least one of a date of manufacture, a shelf life, quality qualification information, and a manufacturer's home, and the method further includes, after acquiring the checkout mode and commodity attribute information corresponding to the target commodity image according to a preset association relationship:

Judging whether the commodity to be checked out is an expired product or not according to the production date and the quality guarantee period; and if the commodity to be checked out is not an expired product, determining the commodity total price of the commodity to be checked out according to the checking out mode and the commodity attribute information.

7. The method of claim 1, wherein the checkout mode includes checkout by piece, and the merchandise attribute information includes a merchandise type and a price of a single merchandise;

the determining the commodity total price of the commodity to be checked out according to the check out mode and the commodity attribute information comprises the following steps:

determining the quantity of each type of commodity included in the commodity to be checked out according to the at least one image;

and determining the commodity total price according to the sum of the products of the quantity of each type of commodity in the commodity to be checked out and the price of the single commodity of the type of commodity.

8. The method of claim 7, wherein the commodity attribute information further comprises a single-piece commodity weight, the method further comprising:

determining a first commodity quantity of the commodity to be checked out according to the commodity total weight of the commodity to be checked out and the weight of the single commodity;

the determining the commodity total price according to the sum of the products of the quantity of each type of commodity in the commodity to be checked out and the price of the single commodity of the type of commodity comprises:

And under the condition that the first commodity quantity is consistent with the second commodity quantity, determining the commodity total price according to the product of the first commodity quantity and the price of the single commodity of the type commodity or the product of the second commodity quantity and the price of the single commodity of the type commodity.

9. The method of claim 7, wherein the commodity attribute information further comprises a single-piece commodity weight, the method further comprising:

determining the total weight of a first commodity of the commodity to be checked out according to the quantity of each type of commodity included in the commodity to be checked out and the weight of a single commodity;

and under the condition that the absolute value of the difference between the total weight of the first commodity and the total weight of the second commodity is smaller than a second threshold value, determining the commodity total price according to the sum of the products of the quantity of each type of commodity in the commodities to be checked out and the price of the single commodity of the type of commodity.

10. The method of claim 1, wherein the checkout mode includes checkout by weight, and the commodity attribute information includes commodity type and commodity price per unit weight;

and determining the commodity total price according to the product of the commodity total weight of the commodity to be checked out and the commodity price per unit weight.

11. A checkout device for merchandise, comprising:

the first acquisition module is used for acquiring at least one image of the commodity to be checked out;

the first determining module is used for determining a target commodity image matched with the at least one image from the first image library;

the second acquisition module is used for acquiring a checkout mode and commodity attribute information corresponding to the target commodity image according to a preset association relation;

the second determining module is used for determining the commodity total price of the commodity to be checked out according to the checking out mode and the commodity attribute information;

the first searching module is used for searching whether the checkout videos of the same type of commodities of the commodity to be checked out exist or not through monitoring camera shooting under the condition that the target commodity image matched with the at least one image cannot be determined from the first image library;

A sixth obtaining module, configured to obtain, when the checkout video exists, related information of a checkout process of the same type of commodity indicated by the checkout video, where the related information of the checkout process includes a checkout mode and commodity attribute information of the same type of commodity;

and the fourth determining module is used for determining the commodity total price of the commodity to be checked out according to the check-out mode and the commodity attribute information of the commodity of the same type.

12. An electronic device, comprising:

a processor;

a memory for storing processor-executable instructions;

wherein the processor is configured to invoke the instructions stored in the memory to perform the method of any of claims 1 to 10.

13. A computer readable storage medium having stored thereon computer program instructions, which when executed by a processor, implement the method of any of claims 1 to 10.