A cash register management method and system for unmanned shopping malls

By incorporating positioning equipment and scanning cameras in the shopping cart, predicting the product code sequence and scanning the code in the shopping cart, the problem of low efficiency of self-service cash registers in the unmanned shopping malls is solved, and a fast and convenient payment process is achieved.

CN118470870BActive Publication Date: 2024-11-05SHENZHEN ELANDA COMMERCIAL EQUIP CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410693365.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-05-31
Publication Date
2024-11-05
Estimated Expiration
2044-05-31

AI Technical Summary

Technical Problem

The existing self-service cash registers in unmanned shopping malls are not efficient, and customers need to scan codes one by one, which takes a long time, which goes against the original intention of unmanned shopping.

Method used

By obtaining product distribution information in the shopping cart, building a product map, calculating shopping cart motion parameters, predicting product fit to determine the code sequence, scanning code sequence, and generating payment codes after verification by the cash register. Transfer the scanning process to the shopping cart to simplify the verification process of the cash register.

Benefits of technology

It greatly reduces the time-consuming process of cash registering, optimizes the cash registering structure, improves payment efficiency, and realizes a convenient experience of unmanned shopping.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118470870B_ABST
    Figure CN118470870B_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of unmanned cashier management, and specifically discloses a cashier management method and system for unmanned shopping malls, the method comprising obtaining the position of a shopping cart in real time, calculating motion parameters according to the position of the shopping cart; calculating the degree of fit between the shopping cart and each commodity according to the motion parameters, and predicting a code sequence according to the degree of fit; opening a code scanning camera installed on the shopping cart, and when the presence of a commodity is detected, scanning the commodity based on the code sequence, constructing a shopping list indexed by the shopping cart number; and verifying the shopping list according to the cash register. The present invention transfers the code scanning process of the self-service cash register to a shopping cart containing a microprocessor, and the shopping cart first scans the commodity, and then the self-service cash register only needs to verify. The verification process does not need to align with the identification code, nor does it need to be processed one by one in sequence, which greatly reduces the time consumption of the cash register process and optimizes the cash register architecture.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned cash register management, and in particular to a cash register management method and system for unmanned shopping malls. Background Art

[0002] Unmanned shopping malls are a new trend in the development of the retail industry. They integrate artificial intelligence, sensor technology and automation systems to provide a more convenient and efficient shopping experience.

[0003] There are two key points of unmanned shopping malls, one of which is the merchandise loss management solution, and the other is the merchandise checkout solution. The existing merchandise loss management solution can be completed with the help of cameras, and the merchandise checkout solution mostly uses self-service cash registers. However, the working efficiency of self-service cash registers is not high, and customers are required to scan codes one by one, which is time-consuming and inconsistent with the original intention of unmanned shopping malls. How to reduce the time consumption of checkout is the technical problem that the technical solution of the present invention wants to solve. Summary of the invention

[0004] The purpose of the present invention is to provide a cash register management method and system for unmanned shopping malls to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A cash register management method for an unmanned shopping mall, the method comprising:

[0007] Obtaining commodity distribution information in a shopping mall and constructing a commodity map; the commodity map contains a plurality of pixel frames, each of which contains a name label, and the name label points to different commodities;

[0008] Acquire the location of the shopping cart in real time according to the positioning device built into the shopping cart, and calculate the motion parameters according to the acquired location of the shopping cart in real time; the motion parameters include speed and acceleration;

[0009] Calculating the degree of fit between the shopping cart and each product based on the motion parameters, and predicting a code sequence based on the degree of fit; the code sequence is the order of the identification codes of the products;

[0010] The barcode scanning camera installed on the shopping cart is opened, and when the presence of a commodity is detected, the barcode of the commodity is scanned based on the code sequence, and a shopping list with the shopping cart number as an index is constructed; the shopping list includes commodity features and commodity prices;

[0011] The shopping list is verified against the cash register, and when verified, the commodity prices are accumulated, and a payment code is generated and displayed.

[0012] As a further solution of the present invention: the step of obtaining the commodity distribution information in the shopping mall and constructing the commodity map includes:

[0013] Get the floor plan of the mall and build merchandise areas in the floor plan based on shelf placement information;

[0014] Receive the item name and item location uploaded by the cargo clerk, and insert a pixel frame in the commodity area according to the item name and item location; the item location includes the shelf location and the relative location, and the shelf location is used to select the commodity area;

[0015] When there is overlap between pixel frames, a display label is read from a preset label group according to the amount of overlap; wherein the label group includes an overlap amount item and a display label item;

[0016] Output a floor plan containing pixel boxes in real time as a product map.

[0017] As a further solution of the present invention: the step of obtaining the position of the shopping cart in real time according to the positioning device built into the shopping cart, and calculating the motion parameters according to the real-time obtained position of the shopping cart comprises:

[0018] The location of the shopping cart is obtained periodically according to the positioning device built into the shopping cart, and a movement point corresponding to the location of the shopping cart is marked in the product map; the location of the shopping cart contains a unique number pointing to the shopping cart;

[0019] Based on the number, the shopping cart positions of the same shopping cart at each moment are counted to obtain a set of movement points;

[0020] Connect the motion points obtained at adjacent moments to obtain a motion line segment, obtain the length of the motion line segment, and divide the length by the time interval in the timing acquisition process to obtain the motion speed;

[0021] Arrange the movement speeds in chronological order, calculate the change in movement speed, and obtain the movement acceleration by dividing the change in movement speed by the time interval in the timing acquisition process.

[0022] As a further solution of the present invention: the step of calculating the degree of fit between the shopping cart and each product based on the motion parameters and predicting the code sequence based on the degree of fit includes:

[0023] Read the movement speed and movement acceleration in real time, and determine the intention degree according to the movement speed and movement acceleration;

[0024] Querying a pixel frame within a preset range with the shopping cart position as the center, and outputting a product list; the name of the product list contains a timestamp, and the timestamp is the reading time of the motion speed and motion acceleration; the product list includes a product name item and a distance item;

[0025] Obtain all product tables within the preset backtracking time, and calculate the fit of each product based on all product tables;

[0026] The commodities are arranged in descending order according to the degree of fit, and the identification codes of the commodities arranged in descending order are read as the code sequence.

[0027] As a further solution of the present invention: the process of determining the intention degree is:

[0028] ;

[0029] The calculation process of the distance term is:

[0030] ;

[0031] The calculation process of the fit degree is:

[0032] ;

[0033] In the above content, For intention, , and is the preset correction factor, is the movement speed, is the motion acceleration; and is the length and width of a pixel box, is a point in the pixel box, is the coordinate corresponding to the location of the shopping cart; is the fit of product A, is the number of commodity tables within the lookback time, For the The intention of the product table, For the The distance in the product table.

[0034] As a further solution of the present invention: the steps of verifying the shopping list according to the cash register, accumulating the commodity prices, and generating and displaying the payment code when the verification is passed include:

[0035] When a shopping cart enters the checkout range, the shopping list of the shopping cart is read;

[0036] Turn on the camera, take pictures in real time, and traverse the pictures according to the product features in the shopping list;

[0037] When there is a matching area in the image, the data item corresponding to the image feature is verified;

[0038] When all data items in the shopping list are verified, the product prices are accumulated and the payment code is generated and displayed.

[0039] The technical solution of the present invention also provides a cash register management system for unmanned shopping malls, the system comprising:

[0040] A commodity map construction module is used to obtain commodity distribution information in a shopping mall and construct a commodity map; the commodity map contains a plurality of pixel frames, each of which contains a name label, and the name label points to different commodities;

[0041] A position analysis module, used to obtain the position of the shopping cart in real time according to a positioning device built into the shopping cart, and calculate motion parameters according to the real-time acquired position of the shopping cart; the motion parameters include speed and acceleration;

[0042] A code sequence prediction module, used to calculate the fit between the shopping cart and each commodity according to the motion parameters, and predict the code sequence according to the fit; the code sequence is the order of the identification codes of the commodities;

[0043] A shopping list building module is used to open a barcode scanning camera installed on a shopping cart, and when a product is detected, the product is scanned based on the code sequence to build a shopping list indexed by the shopping cart number; the shopping list includes product features and product prices;

[0044] The verification and accumulation module is used to verify the shopping list according to the cash register. When the verification is passed, the commodity prices are accumulated and the payment code is generated and displayed.

[0045] As a further solution of the present invention: the commodity map construction module includes:

[0046] A merchandise area construction unit is used to obtain a floor plan of the shopping mall and construct merchandise areas in the floor plan according to shelf placement information;

[0047] A pixel frame insertion unit is used to receive the item name and item location uploaded by the cargo clerk, and insert a pixel frame in the commodity area according to the item name and item location; the item location includes a shelf location and a relative location, and the shelf location is used to select the commodity area;

[0048] A label reading unit, used for reading a display label in a preset label group according to the amount of overlap when there is overlap between pixel frames; wherein the label group includes an overlap amount item and a display label item;

[0049] Output a floor plan containing pixel boxes in real time as a product map.

[0050] As a further solution of the present invention: the location analysis module includes:

[0051] A movement point marking unit, used to obtain the location of the shopping cart according to the positioning device built into the shopping cart at regular intervals, and mark the movement point corresponding to the location of the shopping cart in the commodity map; the shopping cart location contains a unique number pointing to the shopping cart;

[0052] A movement point counting unit, used for counting the shopping cart positions of the same shopping cart at various times based on the number, to obtain a movement point set;

[0053] A speed calculation unit is used to connect the motion points obtained at adjacent moments to obtain a motion segment, obtain the length of the motion segment, and obtain the motion speed by dividing the length by the time interval in the timing acquisition process;

[0054] The acceleration calculation unit is used to arrange the movement speed in time sequence, calculate the change of the movement speed, and obtain the movement acceleration by dividing the change of the movement speed by the time interval in the timing acquisition process.

[0055] As a further solution of the present invention: the code sequence prediction module includes:

[0056] An intention degree determination unit, used for reading the motion speed and motion acceleration in real time, and determining the intention degree according to the motion speed and motion acceleration;

[0057] A product list output unit is used to query a pixel frame within a preset range with the shopping cart position as the center, and output a product list; the name of the product list contains a timestamp, and the timestamp is the reading time of the motion speed and motion acceleration; the product list includes a product name item and a distance item;

[0058] A fit calculation unit, used to obtain all product tables within a preset backtracking time, and calculate the fit of each product based on all product tables;

[0059] The arrangement and reading unit is used to arrange the commodities in descending order according to the degree of fit, and read the identification codes of the commodities in descending order as the code sequence.

[0060] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention transfers the code scanning process of the self-service cash register to a shopping cart containing a microprocessor. The shopping cart first scans the code of the product, and then the self-service cash register only needs to verify it. The verification process does not require alignment with the identification code, nor does it require processing one by one in sequence, which greatly reduces the time consumption of the cash register process and optimizes the cash register architecture. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention.

[0062] Figure 1 This is a flowchart of the cash register management method for unmanned shopping malls.

[0063] Figure 2 This is the first sub-process flowchart of the cash register management method for unmanned shopping malls.

[0064] Figure 3 This is the second sub-process flowchart of the cash register management method for unmanned shopping malls.

[0065] Figure 4 This is the third sub-process flowchart of the cash register management method for unmanned shopping malls.

[0066] Figure 5 This is the fourth sub-process flowchart of the cash register management method for unmanned shopping malls.

[0067] Figure 6 This is the structural diagram of the cash register management system for unmanned shopping malls. DETAILED DESCRIPTION

[0068] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0069] Figure 1 The flowchart of the cash register management method for unmanned shopping malls is as follows. In an embodiment of the present invention, a cash register management method for unmanned shopping malls includes:

[0070] Step S100: Obtaining commodity distribution information in a shopping mall and constructing a commodity map; the commodity map contains a plurality of pixel frames, each of which contains a name label, and the name label points to different commodities;

[0071] The shopping mall mentioned in the present application is an area with the same management party, such as a supermarket, where all goods in the supermarket have the same management party; the distribution information of goods in the shopping mall is obtained, and the product distribution information is which locations have which goods, thereby constructing a product distribution map, called a product map; the focus of the product map is the location of the goods, and the location of the goods is represented in the map, and an area is obtained, called a pixel box; since in real scenes, the shelves are mostly rectangular shelves, the pixel box is generally a rectangular box; while determining the pixel box, a name attribute is inserted into the pixel box to indicate which product the pixel box corresponds to; the final product map is a map containing multiple pixel boxes, and different pixel boxes have different names, corresponding to different products.

[0072] Step S200: obtaining the location of the shopping cart in real time according to a positioning device built into the shopping cart, and calculating motion parameters according to the real-time acquired location of the shopping cart; the motion parameters include speed and acceleration;

[0073] The focus of the technical solution of the present invention is to transfer the code scanning process to the shopping cart, which means that the shopping cart needs to have a built-in microprocessor to complete some tasks; in an example of the technical solution of the present invention, the microprocessor needs to have data transmission function, image acquisition function, image recognition function and positioning function, which are all conventional functions, and a built-in microprocessor in the shopping cart is sufficient.

[0074] In the case where a microprocessor is provided in the default shopping cart, the position of the shopping cart is acquired in real time, and the position of the shopping cart is analyzed, so that the speed and acceleration can be calculated in real time. The speed and acceleration are collectively referred to as motion parameters.

[0075] Step S300: Calculating the degree of fit between the shopping cart and each product based on the motion parameters, and predicting a code sequence based on the degree of fit; the code sequence is the order of the identification codes of the products;

[0076] Speed ​​and acceleration reflect the preferences of customers using shopping carts for different products. The slower the speed, the more the customer is observing the surrounding products, which is considered to be a higher preference for the surrounding products. When the acceleration is a positive value, the greater the acceleration, the faster the customer is moving away from the surrounding products, which is considered to be a lower preference for the surrounding products. When the acceleration is a negative value, the smaller the acceleration, the more the customer suddenly stops at a certain product, which is considered to be a higher preference for the surrounding products. The degree of preference is represented by the fit between the shopping cart and the product.

[0077] From the above content, it can be seen that the fit degree represents the user's preference for each product. The products are sorted according to the fit degree, and the identification codes of the sorted products are read to obtain the code sequence.

[0078] The application of the code sequence is described as follows:

[0079] The identification code is the unique number of the product, which can be a barcode or a QR code. The scanning and recognition process is actually a comparison process. First, all the codes and their corresponding product information are counted. For a certain product, after the identification code of the product is photographed, all the codes are traversed according to the photographed identification code. After the match is successful, the product information can be obtained; in this process, the code sequence affects the arrangement order of all the codes counted in advance, which can greatly improve the scanning speed; in practical applications, the code sequence is determined according to the fit, and the code of the more likely product is at the front. When traversing, it is possible that only a few codes need to be compared to successfully match, which greatly improves efficiency. Under the framework of the present invention, the scanning task is transferred to the shopping cart. The performance of the microprocessor in the shopping cart is not high. The comparison process based on the code sequence can significantly improve the efficiency. For example, on a device with higher performance, it may only be optimized from 0.5 seconds to 0.1 seconds, while on a device with lower performance, it is optimized from 2s to 0.5s.

[0080] Step S400: opening a barcode scanning camera installed on the shopping cart, and when detecting the presence of a commodity, scanning the commodity based on the code sequence, and constructing a shopping list indexed by the shopping cart number; the shopping list includes commodity features and commodity prices;

[0081] In combination with the above description, the code scanning task of the present application is completed by the shopping cart. The code scanning camera installed on the shopping cart is opened. When the presence of goods is detected, the goods are scanned based on the code sequence. After the scanning is successful, the product information is recorded and a shopping list is created; the product information includes at least two types, one is the product price, and the other is the product features. The product features are visual features, which are pre-stored in the database. When the scanning is successful, they can be directly read. For this application, they are pre-set known data.

[0082] Step S500: Verify the shopping list according to the cash register, and when the verification is passed, accumulate the commodity prices, generate and display the payment code;

[0083] After scanning the code of the product in the shopping cart, the cash register only needs to verify the product. Compared with the scanning process, the verification process is simpler and faster, which improves the payment efficiency. The verification process only needs to traverse the product features and match the pictures taken by the cash register.

[0084] The focus of this application is to transfer the original cash register's code scanning query task to the shopping cart, which greatly reduces the cash register's workload, builds a split cash register architecture, and reduces the cash register's time consumption.

[0085] Figure 2 This is a flowchart of the first sub-process of the cash register management method for unmanned shopping malls. The steps of obtaining the commodity distribution information in the shopping mall and constructing a commodity map include:

[0086] Step S101: Obtain a floor plan of the shopping mall, and construct a commodity area in the floor plan according to shelf placement information;

[0087] Step S102: receiving the item name and item location uploaded by the cargo clerk, and inserting a pixel frame in the commodity area according to the item name and item location; the item location includes a shelf location and a relative location, and the shelf location is used to select the commodity area;

[0088] Step S103: when there is overlap between pixel frames, reading a display label from a preset label group according to the amount of overlap; wherein the label group includes an overlap amount item and a display label item;

[0089] Step S104: Output the floor plan containing the pixel frame in real time as a commodity map.

[0090] The above content specifically limits the process of constructing the commodity map. First, obtain the floor plan of the shopping mall and query the shelf placement information. The shelf is the support for placing commodities, and the area corresponding to the shelf is marked in the floor plan; then, receive the name and location of the item uploaded by the merchandiser, and further divide the area corresponding to the shelf to obtain a pixel frame; since commodities may overlap up and down when they are placed, it is reflected in the commodity map as the intersection between the pixel frames. In the technical solution of the present invention, a parameter called display label is introduced to indicate how many commodities a certain pixel frame corresponds to.

[0091] Figure 3 The second sub-flow chart of the cash register management method for unmanned shopping malls, wherein the steps of obtaining the location of the shopping cart in real time according to the positioning device built into the shopping cart and calculating the motion parameters according to the real-time obtained location of the shopping cart include:

[0092] Step S201: obtaining the location of the shopping cart regularly according to the positioning device built into the shopping cart, and marking a movement point corresponding to the location of the shopping cart in the commodity map; the location of the shopping cart contains a unique number pointing to the shopping cart;

[0093] Step S202: Counting the shopping cart positions of the same shopping cart at each time based on the number to obtain a movement point set;

[0094] Step S203: Connect the motion points acquired at adjacent moments to obtain a motion line segment, obtain the length of the motion line segment, and obtain the motion speed by dividing the length by the time interval in the timing acquisition process;

[0095] Step S204: Arrange the movement speeds in chronological order, calculate the change in movement speed, and obtain the movement acceleration by dividing the change in movement speed by the time interval in the timing acquisition process.

[0096] The above content specifically describes the process of determining motion parameters. There are mainly two types of motion parameters, one is speed and the other is acceleration. The solution for obtaining the location of the shopping cart in this application is to obtain it at a fixed time, and obtain the location once every certain period of time. Therefore, the location of the shopping cart is discrete. The location of the shopping cart obtained in the map is called a motion point.

[0097] It is not suitable to use the derivative calculation scheme for discrete data. Therefore, this application adopts the segmented calculation method, as follows:

[0098] Connect the moving points to get a line segment. Divide the length of the line segment by the time in the timing acquisition process to get the movement speed. Then divide the difference in movement speed by the time to get the movement acceleration.

[0099] Figure 4 The third sub-flow chart of the cash register management method for unmanned shopping malls, wherein the steps of calculating the fit between the shopping cart and each commodity based on the motion parameters and predicting the code sequence based on the fit include:

[0100] Step S301: reading the movement speed and movement acceleration in real time, and determining the intention degree according to the movement speed and movement acceleration;

[0101] The movement speed and acceleration are read in real time to determine the intention of the customer using the shopping cart towards the surrounding products (product list), which is represented by the intention degree, with one intention degree corresponding to one moment.

[0102] Step S302: querying a pixel frame within a preset range with the shopping cart position as the center, and outputting a product list; the name of the product list contains a timestamp, which is the reading time of the motion speed and motion acceleration; the product list includes a product name item and a distance item;

[0103] With the current position of the shopping cart as the center and a preset value as the radius, a circle is constructed, and the pixel boxes in the circle are queried. Each pixel box corresponds to a product. All products are counted and stored in the form of a table, which is called a product table. The product table is the product table at the current moment (the moment when the shopping cart position is obtained), so it is necessary to insert a timestamp in the name of the product table.

[0104] In addition, each data item in the product table includes two contents: one is the product name, which can be directly obtained from the name label, and the other is the product distance, which is the spatial distance calculated based on the shopping cart position and the pixel frame.

[0105] Step S303: Obtain all product tables within a preset backtracking time, and calculate the fit degree of each product based on all product tables;

[0106] Step S304: Arrange the products in descending order according to the degree of fit, and read the identification codes of the products in descending order as the code sequence;

[0107] Finally, the product tables within a period of time, such as half a minute, are counted, and multiple product tables are compared to determine the fit of each product. The identification codes of the products are queried in descending order of fit to obtain the code sequence.

[0108] Among them, the code sequence determined according to multiple commodity tables is very robust and is the code sequence of commodities within a range.

[0109] Specifically, the process of determining the intention degree is as follows:

[0110] ;

[0111] The calculation process of the distance term is:

[0112] ;

[0113] The calculation process of the fit degree is:

[0114] ;

[0115] In the above content, For intention, , and is the preset correction factor, is the movement speed, is the motion acceleration; and is the length and width of a pixel box, is a point in the pixel box, is the coordinate corresponding to the location of the shopping cart; is the fit of product A, is the number of commodity tables within the lookback time, For the The intention of the product table, For the The distance in the product table.

[0116] The description of the above calculation process is as follows:

[0117] The key to determining intention is , which is inversely proportional to the speed. When the speed is smaller, it is considered that the customer has a higher preference for the surrounding products. At this time, the intention becomes larger. When the acceleration is a positive value, the greater the acceleration, it means that the customer is accelerating away from the surrounding products. It is considered that the customer has a lower preference for the surrounding products and the intention becomes smaller. When the acceleration is a negative value, the smaller the acceleration, it means that the customer suddenly stops at a certain product. It is considered that the customer has a higher preference for the surrounding products and the intention becomes larger. Use By compounding the function, the range of intentionality can be between 0 and 1.

[0118] The distance calculation process is very simple, which is the average distance between all pixels in the pixel box and the shopping cart position.

[0119] Regarding the final fit, the fit is directly proportional to the intention of the product at a certain moment and inversely proportional to the distance of the product. For a certain product, the intention at each moment in a period of time is divided by its distance, and then the sum is multiplied by the preset correction coefficient to get the fit.

[0120] Figure 5 The fourth sub-flow diagram of the cash register management method for unmanned shopping malls, wherein the steps of verifying the shopping list according to the cash register, accumulating the commodity prices, and generating and displaying the payment code when the verification is passed include:

[0121] Step S501: when a shopping cart enters the checkout range, the shopping list of the shopping cart is read;

[0122] Step S502: Turn on the camera, take pictures in real time, and traverse the taken pictures according to the characteristics of the goods in the shopping list;

[0123] Step S503: When there is a matching area in the picture, the data item corresponding to the image feature passes the verification;

[0124] Step S504: When all data items in the shopping list pass verification, the commodity prices are accumulated, and a payment code is generated and displayed.

[0125] In one example of the technical solution of the present invention, when the cash register detects that a shopping cart is present nearby, it queries the shopping list corresponding to the shopping cart; at the same time, it turns on the camera, obtains pictures in real time, reads image features in the shopping list, and matches them with the obtained pictures. If all the goods in the shopping list appear in the picture (all data items are matched successfully and pass the verification), the prices of the goods are accumulated, and a payment code is generated and displayed.

[0126] The advantage of the above verification process is that the product is verified based on product characteristics. It is possible that customers only need to flip the product a few times to pass the verification. There is no need to scan the code of each product one by one, which is extremely efficient.

[0127] Figure 6 1 is a structural diagram of a cash register management system for an unmanned shopping mall. In an embodiment of the present invention, a cash register management system for an unmanned shopping mall, the system 10 includes:

[0128] The commodity map construction module 11 is used to obtain commodity distribution information in the mall and construct a commodity map; the commodity map contains a plurality of pixel frames, each of which contains a name label, and the name label points to different commodities;

[0129] The position analysis module 12 is used to obtain the position of the shopping cart in real time according to the positioning device built into the shopping cart, and calculate the motion parameters according to the real-time acquired position of the shopping cart; the motion parameters include speed and acceleration;

[0130] The code sequence prediction module 13 is used to calculate the fit between the shopping cart and each product according to the motion parameters, and predict the code sequence according to the fit; the code sequence is the order of the identification codes of the products;

[0131] The shopping list building module 14 is used to open the code scanning camera installed on the shopping cart, and when the presence of a commodity is detected, the commodity is scanned based on the code sequence to build a shopping list with the shopping cart number as the index; the shopping list includes commodity features and commodity prices;

[0132] The verification and accumulation module 15 is used to verify the shopping list according to the cash register, and when the verification is passed, the commodity prices are accumulated and the payment code is generated and displayed.

[0133] Furthermore, the commodity map construction module 11 includes:

[0134] A merchandise area construction unit is used to obtain a floor plan of the shopping mall and construct merchandise areas in the floor plan according to shelf placement information;

[0135] A pixel frame insertion unit is used to receive the item name and item location uploaded by the cargo clerk, and insert a pixel frame in the commodity area according to the item name and item location; the item location includes a shelf location and a relative location, and the shelf location is used to select the commodity area;

[0136] A label reading unit, used for reading a display label in a preset label group according to the amount of overlap when there is overlap between pixel frames; wherein the label group includes an overlap amount item and a display label item;

[0137] Output a floor plan containing pixel boxes in real time as a product map.

[0138] Specifically, the location analysis module 12 includes:

[0139] A movement point marking unit, used to obtain the location of the shopping cart according to the positioning device built into the shopping cart at regular intervals, and mark the movement point corresponding to the location of the shopping cart in the commodity map; the shopping cart location contains a unique number pointing to the shopping cart;

[0140] A movement point counting unit, used for counting the shopping cart positions of the same shopping cart at various times based on the number, to obtain a movement point set;

[0141] A speed calculation unit is used to connect the motion points obtained at adjacent moments to obtain a motion segment, obtain the length of the motion segment, and obtain the motion speed by dividing the length by the time interval in the timing acquisition process;

[0142] The acceleration calculation unit is used to arrange the movement speed in time sequence, calculate the change of the movement speed, and obtain the movement acceleration by dividing the change of the movement speed by the time interval in the timing acquisition process.

[0143] In addition, the code sequence prediction module 13 includes:

[0144] An intention degree determination unit, used for reading the motion speed and motion acceleration in real time, and determining the intention degree according to the motion speed and motion acceleration;

[0145] A product list output unit is used to query a pixel frame within a preset range with the shopping cart position as the center, and output a product list; the name of the product list contains a timestamp, and the timestamp is the reading time of the motion speed and motion acceleration; the product list includes a product name item and a distance item;

[0146] A fit calculation unit, used to obtain all product tables within a preset backtracking time, and calculate the fit of each product based on all product tables;

[0147] The arrangement and reading unit is used to arrange the commodities in descending order according to the degree of fit, and read the identification codes of the commodities in descending order as the code sequence.

[0148] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A cash register management method for unmanned shopping malls, characterized in that: The method comprises: Obtaining commodity distribution information in a shopping mall and constructing a commodity map; the commodity map contains a plurality of pixel frames, each of which contains a name label, and the name label points to different commodities; Acquire the location of the shopping cart in real time according to the positioning device built into the shopping cart, and calculate the motion parameters according to the acquired location of the shopping cart in real time; the motion parameters include speed and acceleration; Calculating the degree of fit between the shopping cart and each product based on the motion parameters, and predicting a code sequence based on the degree of fit; the code sequence is the order of the identification codes of the products; The barcode scanning camera installed on the shopping cart is opened, and when the presence of a commodity is detected, the barcode of the commodity is scanned based on the code sequence, and a shopping list with the shopping cart number as an index is constructed; the shopping list includes commodity features and commodity prices; Verify the shopping list against the cash register, and when verified, accumulate the commodity prices, generate and display the payment code; Among them, regarding fit and code sequence: The fit degree indicates the user's preference for each product. The products are sorted by the fit degree, and the identification codes of the sorted products are read to obtain the code sequence. The identification code is the unique number of the product. In actual application, the code sequence is determined according to the fit degree, and the code of the more likely product is at the front.

2. The cash register management method for unmanned shopping malls according to claim 1, characterized in that: The steps of obtaining the commodity distribution information in the mall and constructing the commodity map include: Get the floor plan of the mall and build merchandise areas in the floor plan based on shelf placement information; Receive the item name and item location uploaded by the cargo clerk, and insert a pixel frame in the commodity area according to the item name and item location; the item location includes the shelf location and the relative location, and the shelf location is used to select the commodity area; When there is overlap between pixel frames, a display label is read from a preset label group according to the amount of overlap; wherein the label group includes an overlap amount item and a display label item; Output a floor plan containing pixel boxes in real time as a product map.

3. The cash register management method for unmanned shopping malls according to claim 1, characterized in that: The step of obtaining the location of the shopping cart in real time according to the positioning device built into the shopping cart and calculating the motion parameters according to the location of the shopping cart obtained in real time comprises: The location of the shopping cart is obtained periodically according to the positioning device built into the shopping cart, and a movement point corresponding to the location of the shopping cart is marked in the product map; the location of the shopping cart contains a unique number pointing to the shopping cart; Based on the number, the shopping cart positions of the same shopping cart at each moment are counted to obtain a set of movement points; Connect the motion points obtained at adjacent moments to obtain a motion line segment, obtain the length of the motion line segment, and divide the length by the time interval in the timing acquisition process to obtain the motion speed; Arrange the movement speeds in chronological order, calculate the change in movement speed, and obtain the movement acceleration by dividing the change in movement speed by the time interval in the timing acquisition process.

4. The cash register management method for unmanned shopping malls according to claim 1, characterized in that: The step of calculating the degree of fit between the shopping cart and each product according to the motion parameters and predicting the code sequence according to the degree of fit includes: Read the movement speed and movement acceleration in real time, and determine the intention degree according to the movement speed and movement acceleration; Querying a pixel frame within a preset range with the shopping cart position as the center, and outputting a product list; the name of the product list contains a timestamp, and the timestamp is the reading time of the motion speed and motion acceleration; the product list includes a product name item and a distance item; Obtain all product tables within the preset backtracking time, and calculate the fit of each product based on all product tables; The commodities are arranged in descending order according to the degree of fit, and the identification codes of the commodities arranged in descending order are read as the code sequence.

5. The cash register management method for unmanned shopping malls according to claim 4, characterized in that: The determination process of the intention degree is: ; The calculation process of the distance term is: ; The calculation process of the fit degree is: ; In the above content, For intention, , and is the preset correction factor, is the movement speed, is the motion acceleration; and is the length and width of a pixel box, is a point in the pixel box, is the coordinate corresponding to the location of the shopping cart; is the fit of product A, is the number of commodity tables within the lookback time, For the The intention of the product table, For the The distance in the product table.

6. The cash register management method for unmanned shopping malls according to claim 1, characterized in that: The steps of verifying the shopping list according to the cash register, accumulating the commodity prices, and generating and displaying the payment code when the verification is passed include: When a shopping cart enters the cash register range of the cash register, the shopping list of the shopping cart is read; Turn on the camera, take pictures in real time, and traverse the pictures according to the product features in the shopping list; When there is a matching area in the image, the data item corresponding to the image feature is verified; When all data items in the shopping list are verified, the product prices are accumulated and the payment code is generated and displayed.

7. A cash register management system for unmanned shopping malls, characterized in that: The system comprises: A commodity map construction module is used to obtain commodity distribution information in a shopping mall and construct a commodity map; the commodity map contains a plurality of pixel frames, each of which contains a name label, and the name label points to different commodities; A position analysis module, used to obtain the position of the shopping cart in real time according to a positioning device built into the shopping cart, and calculate motion parameters according to the real-time acquired position of the shopping cart; the motion parameters include speed and acceleration; A code sequence prediction module, used to calculate the fit between the shopping cart and each commodity according to the motion parameters, and predict the code sequence according to the fit; the code sequence is the order of the identification codes of the commodities; A shopping list building module is used to open a barcode scanning camera installed on a shopping cart, and when a product is detected, the product is scanned based on the code sequence to build a shopping list indexed by the shopping cart number; the shopping list includes product features and product prices; The verification and accumulation module is used to verify the shopping list according to the cash register. When the verification is passed, the commodity prices are accumulated and the payment code is generated and displayed; Among them, regarding fit and code sequence: The fit degree indicates the user's preference for each product. The products are sorted by the fit degree, and the identification codes of the sorted products are read to obtain the code sequence. The identification code is the unique number of the product. In actual application, the code sequence is determined according to the fit degree, and the code of the more likely product is at the front.

8. The cash register management system for unmanned shopping malls according to claim 7, characterized in that: The commodity map construction module includes: A merchandise area construction unit is used to obtain a floor plan of the shopping mall and construct merchandise areas in the floor plan according to shelf placement information; A pixel frame insertion unit is used to receive the item name and item location uploaded by the cargo clerk, and insert a pixel frame in the commodity area according to the item name and item location; the item location includes a shelf location and a relative location, and the shelf location is used to select the commodity area; A label reading unit, used for reading a display label in a preset label group according to the amount of overlap when there is overlap between pixel frames; wherein the label group includes an overlap amount item and a display label item; Output a floor plan containing pixel boxes in real time as a product map.

9. The cash register management system for unmanned shopping malls according to claim 7, characterized in that: The location analysis module comprises: A movement point marking unit, used to obtain the location of the shopping cart according to the positioning device built into the shopping cart at regular intervals, and mark the movement point corresponding to the location of the shopping cart in the commodity map; the shopping cart location contains a unique number pointing to the shopping cart; A movement point counting unit, used for counting the shopping cart positions of the same shopping cart at various times based on the number, to obtain a movement point set; A speed calculation unit is used to connect the motion points obtained at adjacent moments to obtain a motion segment, obtain the length of the motion segment, and obtain the motion speed by dividing the length by the time interval in the timing acquisition process; The acceleration calculation unit is used to arrange the movement speed in time sequence, calculate the change of the movement speed, and obtain the movement acceleration by dividing the change of the movement speed by the time interval in the timing acquisition process.

10. The cash register management system for unmanned shopping malls according to claim 7, characterized in that: The code sequence prediction module comprises: An intention degree determination unit, used for reading the motion speed and motion acceleration in real time, and determining the intention degree according to the motion speed and motion acceleration; A product list output unit is used to query a pixel frame within a preset range with the shopping cart position as the center, and output a product list; the name of the product list contains a timestamp, and the timestamp is the reading time of the motion speed and motion acceleration; the product list includes a product name item and a distance item; A fit calculation unit, used to obtain all product tables within a preset backtracking time, and calculate the fit of each product based on all product tables; The arrangement and reading unit is used to arrange the commodities in descending order according to the degree of fit, and read the identification codes of the commodities in descending order as the code sequence.