Automatic settlement method, device, system and storage medium

Abstract

The present invention discloses an automatic settlement method, device, system and storage medium, and relates to the field of data processing technology. The automatic settlement method includes: identifying a user matching the user image information in a tracking image acquired in a picking area; determining a first correspondence between the user ID, coordinates and acquisition time of the tracking image according to the identified user's position in the tracking image and the shooting time of the tracking image; identifying the picking image acquired by a picking camera located in a container to determine the items picked up and placed in the picking image; determining a second correspondence between the items picked up and placed in the picking image, the coordinates of the picking image acquisition area and the acquisition time of the picking image; binding the items picked up and placed with the user ID of the user located in the picking image acquisition area at the same time according to the first correspondence and the second correspondence; and settling according to the items bound to the user ID.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an automatic settlement method, device, system and storage medium. Background Art

[0002] In traditional convenience stores, libraries and other scenarios, people need to go to the checkout counter to settle the bill after selecting goods or books in order to purchase or borrow them. When there are a large number of people, people need to queue up, resulting in a long waiting time.

[0003] At present, some scenarios use Radio Frequency Identification (RFID) to identify items to achieve self-service checkout. Summary of the invention

[0004] After analysis, the inventors found that the labeling operation of RFID tags is relatively complicated and cumbersome, and the cost of the RFID system is relatively high and the reusability is relatively low, which increases the cost of automatic settlement and reduces deployment efficiency.

[0005] A technical problem to be solved by the embodiments of the present invention is: how to reduce the cost of automatic settlement and improve deployment efficiency.

[0006] According to a first aspect of some embodiments of the present invention, there is provided an automatic settlement method, comprising: acquiring a user identification and user image information of a corresponding user; identifying a user matching the user image information in an acquired tracking image within a picking area, and determining the user identification of the identified user; determining a first correspondence between the user identification, coordinates and acquisition time of the tracking image of the identified user according to the position of the identified user in the tracking image and the shooting time of the tracking image; identifying a picking image captured by a picking camera located in a container to determine items picked up and placed in the picking image; determining a second correspondence between the items picked up and placed in the picking image, the coordinates of the picking image acquisition area and the acquisition time of the picking image according to the coordinates of the picking image acquisition area acquired in advance and the shooting time of the picking image; binding the items picked up and placed with the user identification of the user who is located in the picking image acquisition area at the same time according to the first correspondence and the second correspondence; and settling according to the items bound to the user identification.

[0007] In some embodiments, the picking images are captured in response to a gravity sensor located in the cargo bin sensing a weight change.

[0008] In some embodiments, gesture recognition is performed on a picking image captured by a picking camera located at a container to determine the items to be picked up and placed in the picking image.

[0009] In some embodiments, the automatic checkout method also includes: identifying the user face image collected at the entrance to obtain a corresponding user ID; after identifying the user face image, the first user image information in the tracking image collected from the area adjacent to the entrance in the picking area is matched with the user ID.

[0010] In some embodiments, the tracking image is collected by a tracking camera, and the shooting angle of the tracking camera is fixed.

[0011] In some embodiments, the automatic settlement method further includes: determining the coordinates of the picking image acquisition area according to the position of the picking image acquisition area in the tracking image.

[0012] In some embodiments, the tracking image is a video frame.

[0013] In some embodiments, settlement based on items bound to user identifiers includes: collecting a departure image in an area outside the picking area and adjacent to an exit; identifying a user whose user image information matches the user's user image information in the departure image, and determining that the user corresponding to the corresponding user identifier has left; and settling the items bound to the user identifier of the departing user.

[0014] According to a second aspect of some embodiments of the present invention, there is provided an automatic settlement device, comprising: a user information acquisition module, configured to acquire a user identification and user image information of a corresponding user; a user matching module, configured to identify a user matching the user image information in a tracking image acquired within a picking area, and determine the user identification of the identified user; a first correspondence determination module, configured to determine a first correspondence between the user identification, coordinates and acquisition time of the identified user according to the position of the identified user in the tracking image and the shooting time of the tracking image; an item identification module, configured to identify the item located in the tracking image; The picking image captured by the picking camera of the container is identified to determine the items picked up and placed in the picking image; the second correspondence determination module is configured to determine the second correspondence between the items picked up and placed in the picking image, the coordinates of the picking image acquisition area and the acquisition time of the picking image based on the coordinates of the picking image acquisition area acquired in advance and the shooting time of the picking image; the item binding module is configured to bind the items picked up and placed with the user identification of the user who is in the picking image acquisition area at the same time according to the first correspondence and the second correspondence; the settlement module is configured to settle according to the items bound to the user identification.

[0015] According to a third aspect of some embodiments of the present invention, there is provided an automatic settlement device, comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute any one of the aforementioned automatic settlement methods based on instructions stored in the memory.

[0016] According to a fourth aspect of some embodiments of the present invention, there is provided an automatic settlement system, comprising: any one of the aforementioned automatic settlement devices; a tracking camera for capturing tracking images or tracking videos including tracking images; and a picking camera located in a container for capturing picking images.

[0017] In some embodiments, the automatic checkout system also includes: a facial recognition camera located at the entrance of the picking area, for collecting user facial images.

[0018] According to a fifth aspect of some embodiments of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any one of the aforementioned automatic settlement methods.

[0019] Some embodiments of the above invention have the following advantages or beneficial effects: the embodiments of the present invention can determine the user's position based on the tracking image, and determine the items to be picked up and placed based on the picking image. Then, based on the matching result of the position of the acquisition area of ​​the picking image and the user's position at the same time, the user who picks up and places the item is determined to achieve the association between the user and the item. Therefore, the user can achieve real-time update of the items to be settled in the process of picking up and placing the items, without the need for centralized inventory, thereby improving the settlement efficiency. In addition, this method does not require additional processing of each item, is easy to deploy and has low cost.

[0020] Further features and advantages of the present invention will become apparent from the following detailed description of exemplary embodiments of the present invention with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0022] Figure 1 Schematic diagram of the process of automatic settlement method according to some embodiments of the present invention.

[0023] Figure 2 is an exemplary tracking image according to some embodiments of the present invention.

[0024] Figure 3Schematic diagram of a flow chart of a method for identifying a user when a user enters a picking area according to some embodiments of the present invention.

[0025] Figure 4 Schematic diagram of a flow chart of an identification method when a user picks an item according to some embodiments of the present invention.

[0026] Figure 5 Schematic diagram of a flow chart of a settlement method when a user leaves a picking area according to some embodiments of the present invention.

[0027] Figure 6 Schematic diagram of the structure of an automatic settlement device according to some embodiments of the present invention.

[0028] Figure 7 Schematic diagram of the structure of an automatic settlement system according to some embodiments of the present invention.

[0029] Figure 8 A schematic diagram of the deployment of an automatic settlement system according to some embodiments of the present invention.

[0030] Fig. 9 Schematic diagram of the structure of automatic settlement devices according to other embodiments of the present invention.

[0031] Fig.10 Schematic diagram of the structure of automatic settlement devices according to some other embodiments of the present invention. DETAILED DESCRIPTION

[0032] In this application, all actions to obtain signals, information or data are carried out in compliance with the relevant data protection laws and policies of the country where they are located and with the authorization given by the owner of the corresponding device.

[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present invention and its application or use. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] The relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

[0035] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0036] Technologies, methods, and apparatus known to ordinary technicians in the relevant field may not be discussed in detail, but where appropriate, such technologies, methods, and apparatus should be considered part of the authorization specification.

[0037] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0038] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0039] Figure 1 FIG. 1 is a flow chart of an automatic settlement method according to some embodiments of the present invention. Figure 1 As shown, the automatic settlement method of this embodiment includes steps S102 to S114.

[0040] In step S102, a user identification and user image information of a corresponding user are obtained. The user image information may be the user image itself or an image feature of the user image.

[0041] The user image is a full-body or partial image of the user that is collected. The user image information may include, for example, the user's head and shoulder information, facial information, clothing information, body shape information, etc.

[0042] In some embodiments, the profile image information may be head-shoulder image information corresponding to the head-shoulder image. The head-shoulder image may be obtained, for example, by taking a bird's-eye view of the camera set at a high position. Using the head-shoulder image information may reduce the amount of data that needs to be processed during the tracking process and improve computational efficiency.

[0043] In some embodiments, the correspondence between the user identification and the user image information may be pre-stored in the database, or may be collected after the user enters the picking area. The picking area may include, for example, closed areas such as stores and libraries, where users can pick up and place items and settle accounts.

[0044] In step S104, a user matching the user image information is identified in the acquired tracking image within the picking area, and a user ID of the identified user is determined.

[0045] In some embodiments, the tracking image is a video frame. Thus, a video can be taken in the picking area and the same user in the video can be tracked by analyzing each frame.

[0046] In step S106, a first corresponding relationship between the user identifier and coordinates of the identified user and the acquisition time of the tracking image is determined according to the position of the identified user in the tracking image and the shooting time of the tracking image.

[0047] In step S108, the picking image captured by the picking camera located at the container is identified to determine the items to be picked up and placed in the picking image.

[0048] In step S110, a second correspondence between the items picked up and placed in the picking image, the coordinates of the picking image acquisition area and the acquisition time of the picking image is determined based on the pre-acquired coordinates of the picking image acquisition area and the shooting time of the picking image.

[0049] In some embodiments, the picking image is collected in response to a gravity sensor located in the same container sensing a weight change. Thus, the picking camera located in the container can only collect images when a user performs a picking and placing action, saving energy consumption and system overhead.

[0050] The coordinates of the user and the coordinates of the image acquisition area are in the same coordinate system. In some embodiments, the coordinates of the user and the coordinates of the image acquisition area are in the image coordinate system of the tracking image. Figure 2 As shown, assume that the upper left corner of the tracking image is the origin (0, 0) of the image coordinate system of the tracking image collected at 12:15:01. By matching the head and shoulder image information of users U1 and U2 in the tracking image, it is determined that user U1 is located at point (300, 200) and user U2 is located at point (100, 400) at 12:15:01. The dotted area in front of shelf S1 is the image acquisition area of ​​camera C1 on shelf S1. In the picking image collected by camera C1 at 12:15:01, an item is picked up by a user. Since the center coordinates of the image acquisition area of ​​camera C1 are pre-stored as (301, 200), by matching the coordinates of each user at 12:15:01, it is found that user U1 is located near the image acquisition area of ​​camera C1 at this moment. Therefore, it can be determined that user U1 has picked up the item.

[0051] In some embodiments, the image coordinate system of the tracking image may also be mapped to other coordinate systems. The coordinates of the user and the coordinates of the image acquisition area are located in the mapped other coordinate systems. For example, when multiple tracking cameras are used to acquire tracking images, the image coordinate systems of the tracking images acquired by different tracking cameras may be mapped to a unified coordinate system.

[0052] In step S112, the items to be picked up and placed are bound to the user identifiers of the users who are in the picking image acquisition area at the same time according to the first corresponding relationship and the second corresponding relationship.

[0053] In step S114, settlement is performed according to the items bound to the user ID.

[0054] Through the method of the above embodiment, the user's position can be determined based on the tracking image, and the items to be picked up and placed can be determined based on the picking image. Then, based on the matching result of the position of the collection area of ​​the picking image and the user's position at the same time, the user who picks up and places the item can be determined to achieve the association between the user and the item. Thus, the user can achieve real-time update of the items to be settled in the process of picking up and placing the items, without the need for centralized inventory, thereby improving the settlement efficiency. In addition, this method does not require additional processing of each item, is easy to deploy and has low cost.

[0055] Reference below Figure 3 An embodiment of the identification process when a user enters a picking area is described.

[0056] Figure 3 FIG. 1 is a flow chart of a method for identifying a user when a user enters a picking area according to some embodiments of the present invention. Figure 3 As shown, the user identification method of this embodiment includes steps S302 to S304.

[0057] In step S302, the user face image collected at the entrance is recognized to obtain the corresponding user identification. When performing face recognition, the collected user face image can be matched with the face image corresponding to the user identification pre-stored in the database to identify the identity of the user at the entrance.

[0058] In some embodiments, a gate can be set at the entrance. After the identity of the user is identified, the gate can be opened to allow the user to pass through.

[0059] In step S304, after the user's face image is recognized, the first user image information in the tracking image collected from the area adjacent to the entrance in the picking area is matched with the user identification.

[0060] When the face recognition of the user is successfully performed and the user enters the picking area, the user image can be collected immediately. The user image collected at this time belongs to the user who has just passed the verification, so the user image information can correspond to the user identification.

[0061] The first user image information after the user face image is recognized refers to the user image information of the first user who appears in the area adjacent to the entrance in the picking area after the user face image is recognized. Thus, the user identification and the user image can be accurately matched.

[0062] Through the method of the above embodiment, the user image information of the user in the picking area can be accurately determined.

[0063] Reference below Figure 4 An embodiment of the identification process when a user picks an item is described.

[0064] Figure 4 FIG. 1 is a flow chart of a method for identifying items when a user picks an item according to some embodiments of the present invention. Figure 4 As shown, the identification method of this embodiment includes steps S402 to S406.

[0065] In step S402, in response to the gravity sensor located in the container sensing the weight change, a shooting instruction is sent to the camera located in the same container. The shooting instruction can be sent directly to the camera by the gravity sensor through a wireless network, Bluetooth, an electrical signal, etc., or the gravity sensor can be fed back to the server through the network, and then the server sends the shooting instruction to the camera through the network. The server can also monitor the weight value of the gravity sensor and send the shooting instruction to the camera through the network when the monitored weight value changes.

[0066] In step S404, the camera located in the same container takes pictures in response to the shooting instruction to obtain a picking image.

[0067] In step S406, gesture recognition is performed on the picking image captured by the camera to determine the items to be picked up and placed in the picking image.

[0068] Since the shooting angle of the camera placed on the shelf is relatively fixed, when the user takes or places items on the shelf, the movements and angles of the hands and arms are similar, so it is possible to identify which items are taken or placed by the user.

[0069] Reference below Figure 5 An embodiment of the checkout process when a user leaves a picking area is described.

[0070] Figure 5 FIG. 1 is a flow chart of a settlement method when a user leaves a picking area according to some embodiments of the present invention. Figure 5 As shown, the settlement method of this embodiment includes steps S502 to S506.

[0071] In step S502, an exit image is collected in an area outside the picking area and adjacent to the exit.

[0072] In some embodiments, after picking up items, the user comes to the gate machine and triggers the gate machine to open through infrared sensing or manual button. In response to the gate machine opening, the camera located outside the exit can collect the exit image.

[0073] In step S504, a user matching the user image information of the user is identified in the user image information in the departure image, and it is determined that the user corresponding to the corresponding user identifier has left.

[0074] In step S506, the items bound to the user ID of the user who left are settled. For example, the amount corresponding to the items bound to the user ID is calculated and deducted from the account corresponding to the user ID; or the items bound to the user ID are recorded in the user's usage list or borrowing list.

[0075] Through the method of the above embodiment, the settlement operation can be triggered by the user's departure.

[0076] Reference below Figure 6 An embodiment of the automatic settlement device of the present invention is described.

[0077] Figure 6 Schematic diagram of the structure of the automatic settlement device according to some embodiments of the present invention. Figure 6 As shown, the automatic settlement device 600 of this embodiment includes: a user information acquisition module 6100, configured to acquire a user identification and user image information of a corresponding user; a user matching module 6200, configured to identify a user matching the user image information in the acquired tracking image within the picking area, and determine the user identification of the identified user; a first correspondence determination module 6300, configured to determine a first correspondence between the user identification, coordinates and acquisition time of the tracking image of the identified user according to the position of the identified user in the tracking image and the shooting time of the tracking image; an item recognition module 6400, configured to identify the item located in the container; The picking image captured by the selection camera is identified to determine the items picked up and placed in the picking image; the second correspondence determination module 6500 is configured to determine the second correspondence between the items picked up and placed in the picking image, the coordinates of the picking image acquisition area and the acquisition time of the picking image based on the coordinates of the picking image acquisition area acquired in advance and the shooting time of the picking image; the item binding module 6600 is configured to bind the items picked up and placed with the user identification of the user who is in the picking image acquisition area at the same time according to the first correspondence and the second correspondence; the settlement module 6700 is configured to settle according to the items bound to the user identification.

[0078] In some embodiments, the picking images are captured in response to a gravity sensor located in the cargo bin sensing a weight change.

[0079] In some embodiments, the item identification module 6400 is further configured to perform gesture recognition on the picking image captured by the picking camera located in the container to determine the items to be picked up and placed in the picking image.

[0080] In some embodiments, the automatic settlement device 600 also includes: a face recognition module 6800, which is configured to identify the user face image collected at the entrance and obtain the corresponding user identification; after identifying the user face image, the first user image information in the tracking image collected from the area adjacent to the entrance in the picking area is matched with the user identification.

[0081] In some embodiments, the tracking image is collected by a tracking camera, and the shooting angle of the tracking camera is fixed.

[0082] In some embodiments, the automatic settlement device 600 further includes: a picking image acquisition area coordinate determination module 6900, which is configured to determine the coordinates of the picking image acquisition area according to the position of the picking image acquisition area in the tracking image.

[0083] In some embodiments, the tracking image is a video frame.

[0084] In some embodiments, the settlement module 6700 is further configured to collect a departure image in an area outside the picking area and adjacent to the exit; identify a user whose user image information matches the user's user image information in the departure image, and determine that the user corresponding to the corresponding user ID has left; and settle the items bound to the user ID of the departing user.

[0085] Reference below Figure 7 and Figure 8 An embodiment of the automatic settlement system of the present invention is described.

[0086] Figure 7 Schematic diagram of the structure of the automatic settlement system according to some embodiments of the present invention. Figure 7 As shown, the automatic settlement system 70 of this embodiment includes: an automatic settlement device 710, and its specific implementation method can refer to Figure 6 The automatic checkout device 600 in the embodiment; the tracking camera 720, used to collect tracking images or tracking videos including tracking images; and the picking camera 730, located in the container, used to collect picking images.

[0087] In some embodiments, the automatic checkout system 70 further includes: a face recognition camera 740, located at the entrance of the picking area, for collecting user facial images.

[0088] Figure 8 It is a schematic diagram of the deployment of an automatic checkout system according to some embodiments of the present invention, wherein the schematic diagram shows a top view of a self-service supermarket.

[0089] In scene 80, a face recognition camera 81 is set at the entrance 801. The face recognition camera 81 obtains a face image and transmits it to a server (not shown) for recognition, wherein an automatic settlement device is deployed on the server. The server determines the user ID based on the face image. After the user completes face recognition at the entrance 801, he walks into the supermarket along the entrance passage 802. The entrance tracking camera 82 located at the top of the entrance passage 802 collects the user's user image and transmits it to the server, so that the server can determine the corresponding relationship between the user ID and the user's user image information.

[0090] When the user is inside the supermarket, the tracking camera 83 installed on the top of the supermarket collects the user's user image to track and locate the user. When the user picks up an item in front of the shelf 803, in response to the weight sensor on the shelf 803 detecting the weight change, the picking camera 84 located on the same shelf collects the picking image and transmits it to the server. The server identifies the items picked up and placed in the picking image and the corresponding location information. In addition, the server determines which user picked up the item by matching the user's location and the location of the item picked up and placed, so as to bind the user ID and the corresponding item.

[0091] When the user is about to leave the supermarket, the tracking camera 85 located at the exit channel collects the user's image and sends it to the server. The server confirms that the corresponding user has left and settles the items bound by the user.

[0092] Fig. 9 Schematic diagram of the structure of the automatic settlement device according to some other embodiments of the present invention. Fig. 9 As shown, the automatic settlement device 90 of this embodiment includes: a memory 910 and a processor 920 coupled to the memory 910, and the processor 920 is configured to execute the automatic settlement method in any one of the aforementioned embodiments based on the instructions stored in the memory 910.

[0093] The memory 910 may include, for example, a system memory, a fixed non-volatile storage medium, etc. The system memory may store, for example, an operating system, an application program, a boot loader, and other programs.

[0094] Fig.10 This is a schematic diagram of the structure of an automatic settlement device according to some other embodiments of the present invention. Fig.10As shown, the automatic settlement device 100 of this embodiment includes: a memory 1010 and a processor 1020, and may also include an input / output interface 1030, a network interface 1040, a storage interface 1050, etc. These interfaces 1030, 1040, 1050 and the memory 1010 and the processor 1020 may be connected, for example, via a bus 1060. Among them, the input / output interface 1030 provides a connection interface for input / output devices such as a display, a mouse, a keyboard, and a touch screen. The network interface 1040 provides a connection interface for various networked devices. The storage interface 1050 provides a connection interface for external storage devices such as SD cards and USB flash drives.

[0095] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein the program implements any one of the aforementioned automatic settlement methods when executed by a processor.

[0096] It should be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable non-transient storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0097] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0098] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0099] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0100] 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, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An automatic settlement method, comprising: Recognize the user's facial image collected at the entrance and obtain the corresponding user ID; After the user's face image is recognized, the first user image information in the tracking image collected from the area adjacent to the entrance in the picking area is matched with the user identifier, wherein the tracking image is collected by a tracking camera with a fixed shooting angle; Obtaining a user ID and user image information of a corresponding user; identifying a user matching the user image information in the acquired tracking image within the picking area, and determining a user identifier of the identified user; Determining a first correspondence between a user identifier and coordinates of the identified user and a capture time of the tracking image according to a position of the identified user in the tracking image and a capture time of the tracking image; Recognize the picking images captured by the picking cameras located in the container to determine the items to be picked up and placed in the picking images; Determining a second correspondence between the items picked and placed in the picking image, the coordinates of the picking image acquisition area, and the acquisition time of the picking image based on the pre-acquired coordinates of the picking image acquisition area and the shooting time of the picking image, wherein the coordinates of the user and the coordinates of the image acquisition area belong to the same coordinate system, or the image coordinate system of the tracking image is mapped to the coordinate system in which the coordinates of the user and the coordinates of the image acquisition area are located; According to the first corresponding relationship and the second corresponding relationship, the picked-up and placed items are bound to the user identifiers of users who are in the picking image acquisition area at the same time; Settlement is performed based on the items bound to the user ID.

2. The automatic settlement method according to claim 1, wherein: The picking image is captured in response to a gravity sensor located at the cargo bin sensing a weight change.

3. The automatic settlement method according to claim 1, wherein: Gesture recognition is performed on the picking images captured by the picking cameras located in the container to determine the items to be picked up and placed in the picking images.

4. The automatic settlement method according to claim 1, further comprising: According to the position of the picked image acquisition area in the tracking image, the coordinates of the picked image acquisition area are determined.

5. The automatic settlement method according to claim 1, wherein: The tracking images are video frames.

6. The automatic settlement method according to claim 1, wherein: The settlement according to the items bound to the user identification includes: Collect departure images in an area outside the picking area and adjacent to the exit; identifying a user matching the user image information of the user in the leaving image, and determining that the user corresponding to the corresponding user identifier has left; Settle the items bound to the user ID of the user who left.

7. An automatic settlement device, comprising: A face recognition module is configured to recognize a user face image collected at the entrance and obtain a corresponding user identification; After the user's face image is recognized, the first user image information in the tracking image collected from the area adjacent to the entrance in the picking area is matched with the user identifier, wherein the tracking image is collected by a tracking camera with a fixed shooting angle; A user information acquisition module, configured to acquire a user identification and user image information of a corresponding user; A user matching module configured to identify a user matching the user image information in the acquired tracking image within the picking area, and determine a user identifier of the identified user; a first correspondence determination module configured to determine a first correspondence between a user identifier and coordinates of the identified user and a capture time of the tracking image according to a position of the identified user in the tracking image and a capture time of the tracking image; An item recognition module is configured to recognize a picking image captured by a picking camera located at a container to determine an item to be picked up and placed in the picking image; A second correspondence determination module is configured to determine a second correspondence between the items picked and placed in the picking image, the coordinates of the picking image acquisition area, and the acquisition time of the picking image based on the pre-acquired coordinates of the picking image acquisition area and the shooting time of the picking image, wherein the coordinates of the user and the coordinates of the image acquisition area belong to the same coordinate system, or the image coordinate system of the tracking image is mapped to the coordinate system where the coordinates of the user and the coordinates of the image acquisition area are located; an item binding module, configured to bind the picked-up and placed items with user identifiers of users who are in the picking image acquisition area at the same time according to the first corresponding relationship and the second corresponding relationship; The settlement module is configured to settle the items according to the items bound to the user identification.

8. An automatic settlement device, comprising: Memory; as well as A processor coupled to the memory, the processor being configured to execute the automatic settlement method according to any one of claims 1 to 6 based on instructions stored in the memory.

9. An automatic settlement system comprising: The automatic settlement device according to claim 7 or 8; A tracking camera, used for collecting tracking images or tracking videos including tracking images; as well as The picking camera is located in the container and is used to capture picking images.

10. The automatic settlement system according to claim 9, further comprising: The facial recognition camera is located at the entrance of the picking area and is used to collect user facial images.

11. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the automatic settlement method according to any one of claims 1 to 6.

Images