WO2019096228A1 - 一种基于神经网络的无人售货方法和设备 - Google Patents
一种基于神经网络的无人售货方法和设备 Download PDFInfo
- Publication number
- WO2019096228A1 WO2019096228A1 PCT/CN2018/115738 CN2018115738W WO2019096228A1 WO 2019096228 A1 WO2019096228 A1 WO 2019096228A1 CN 2018115738 W CN2018115738 W CN 2018115738W WO 2019096228 A1 WO2019096228 A1 WO 2019096228A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- user
- neural network
- item
- preset
- shopping mall
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07G—REGISTERING THE RECEIPT OF CASH, VALUABLES, OR TOKENS
- G07G1/00—Cash registers
- G07G1/0036—Checkout procedures
- G07G1/0045—Checkout procedures with a code reader for reading of an identifying code of the article to be registered, e.g. barcode reader or radio-frequency identity [RFID] reader
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/08—Payment architectures
- G06Q20/20—Point-of-sale [POS] network systems
- G06Q20/208—Input by product or record sensing, e.g. weighing or scanner processing
Definitions
- the present application relates to the field of data processing, and in particular, to a neural network based unattended method and apparatus.
- the present application proposes a neural network-based unmanned sales method and equipment, which performs unmanned sales in an automated manner, greatly improving efficiency, reducing the use cost, and facilitating the flow of people. Smooth circulation, which enhances the user experience.
- the embodiment of the present application provides a neural network-based unmanned vending method, which is applied to a shopping mall, wherein a location of the shopping mall corresponding to the exit is provided with a camera, and the commodity in the shopping mall is provided with a passive tag, and the method includes:
- the “identifying the picture based on a neural network corresponding to the item identification for each user to determine the item selected by the user” includes:
- the payment information input by the user is acquired, and each of the pictures is identified based on a neural network corresponding to the product identification to determine the user. Selected item.
- the preset process of completing payment includes: a release process
- the preset warning process includes: performing an alarm by means of an audible and visual alarm, and/or notifying the guard, and/or notifying the user that the item is lost.
- the neural network is based on training all of the merchandise in the mall as a sample.
- the passive tag comprises: a barcode; wherein the barcode corresponds to information about the item, the information comprising: price information.
- the embodiment of the present application provides a neural network-based unmanned vending device, which is applied to a shopping mall, wherein a position of the shopping mall corresponding to the exit is provided with a camera, and the goods in the shopping mall are provided with a passive tag, and the device includes:
- a photographing module configured to capture a picture of a product selected by each user through the camera
- An identification module configured to identify the image based on a neural network corresponding to the product identification for each of the users to determine an item selected by the user;
- a judging module configured to determine whether the item that the user has paid is consistent with the selected item
- the first processing module is configured to execute a preset completion payment process when the determination result is consistent
- the second processing module is configured to execute a preset alert process when the determination result is inconsistent.
- the identification module is configured to:
- the payment information input by the user is acquired, and each of the pictures is identified based on a neural network corresponding to the product identification to determine the user. Selected item.
- the preset process of completing payment includes: a release process
- the preset warning process includes: performing an alarm by means of an audible and visual alarm, and/or notifying the guard, and/or notifying the user that the item is lost.
- the neural network is based on training all of the merchandise in the mall as a sample.
- the passive tag comprises: a barcode; wherein the barcode corresponds to information about the item, the information comprising: price information.
- the present application proposes a neural network-based unmanned vending method and apparatus, which is applied to a shopping mall, wherein a location of the shopping mall corresponding to the exit is provided with a camera, and the goods in the shopping mall are provided with passive tags.
- the method includes: capturing, by the camera, a picture of an item selected by each user; for each of the users, identifying the picture based on a neural network corresponding to the item identification to determine an item selected by the user; determining that the user has Whether the paid item is consistent with the selected item; if the judgment result is consistent, the preset completion payment process is executed; if the judgment result is inconsistent, the preset warning process is executed.
- Unmanned sales in this automated way greatly improve efficiency, reduce the cost of use, and facilitate the smooth flow of people, thereby improving the user experience.
- FIG. 1 is a schematic flow chart of a method for unmanned vending based on a neural network according to an embodiment of the present application
- FIG. 2 is a schematic structural diagram of an unmanned vending apparatus based on a neural network according to an embodiment of the present application.
- the term “comprising” or “including” may be used in the various embodiments of the present disclosure to indicate the existence of the disclosed function, operation or element, and does not limit one or more functions, operations or elements. increase.
- the terms “comprising,” “having,” “,” It should not be understood that the existence or addition of one or more features, numbers, steps, operations, components or components of one or more other features, numbers, steps, operations, components, components or combinations of the foregoing are excluded. Or the possibility of a combination of the foregoing.
- the expression “or” or “at least one of A or / and B” includes any or all combinations of the simultaneously listed characters.
- the expression “A or B” or “at least one of A or / and B” may include A, may include B, or may include both A and B.
- first and second may modify various constituent elements in the various embodiments, but the corresponding constituent elements may not be limited.
- the above statements do not limit the order and/or importance of the elements.
- the above statements are only used for the purpose of distinguishing one element from another.
- the first user device and the second user device indicate different user devices, although both are user devices.
- a first element could be termed a second element, and a second element could be termed a first element, without departing from the scope of the various embodiments of the present disclosure.
- the first constituent element can be directly connected to the second constituent element and can be “connected” between the first constituent element and the second constituent element.
- the third component On the contrary, when a constituent element is “directly connected” to another constituent element, it is understood that there is no third constituent element between the first constituent element and the second constituent element.
- the term "user” as used in various embodiments of the present disclosure may indicate a person using an electronic device or a device using an electronic device (eg, an artificial intelligence electronic device).
- Embodiment 1 of the present application discloses a method for unmanned vault based on a neural network, which is applied to a shopping mall, wherein a position of the shopping mall corresponding to the exit is provided with a camera, and the goods in the shopping mall are provided with passive tags, as shown in FIG. 1 .
- the method includes:
- Step 101 Capture, by the camera, a picture of an item selected by each user;
- Step 102 Identify, for each user, the picture based on a neural network corresponding to the item identification to determine the item selected by the user;
- Step 103 Determine whether the product that the user has paid is consistent with the selected product
- Step 104 If the determination result is consistent, performing a preset process of completing the payment;
- Step 105 If the judgment result is inconsistent, execute a preset alert process.
- the description is based on the complete flow
- the user determines the selected item by scanning the barcode already existing on the item, and pays with the scanned item when paying, while when exiting the store (supermarket), Then, through the neural network, the image of the goods brought out of the supermarket is image-recognized to verify whether the goods to be paid are the goods to be taken out; if the verification result is not correct, the warning is performed.
- the “recognizing the picture based on the neural network corresponding to the item identification to determine the item selected by the user for each user in step 102” includes:
- the payment information input by the user is acquired, and each of the pictures is identified based on a neural network corresponding to the product identification to determine the user. Selected item.
- the product in the shopping mall is pre-set with a passive tag, specifically, for example, a barcode, or a two-dimensional code, etc., to confirm the selected item and the price of the selected item, and subsequently based on this
- the payment information is generated, and the payment information may be, for example, a barcode, a two-dimensional code or a character string, etc., for example, may be a 6-digit number, for example, may be 256982 or other embodiments, or may be a letter combination.
- the user can display the payment information by displaying the barcode generated by the payment, the two-dimensional code, and the like on the mobile phone and scanning by the preset scanner. It can also be entered manually for the user.
- the preset process of completing payment includes: a release process
- the preset warning process includes: performing an alarm by means of an audible and visual alarm, and/or notifying the guard, and/or notifying the user that the item is lost.
- the foregoing process is performed at an exit, and the one-way door may be disposed at the exit.
- the one-way door is opened to perform the release operation, and if In case of inconsistency, the goods may be paid, but they are lost when they arrive at the exit, which requires the user to re-acquire the goods, and the other is to take more goods. In this case, it is necessary to give a warning, such as notifying the guard, or Control the one-way door is closed.
- the neural network is based on training all of the merchandise in the mall as a sample.
- the passive tag comprises: a barcode; wherein the barcode corresponds to information about the item, the information comprising: price information.
- this is pre-set on the package of each product of the barcode itself, and the subsequent user can identify the barcode through the preset application for identification on the mobile phone, thereby saving cost and eliminating the need for additional labels.
- Embodiment 2 of the present application further discloses a neural network-based unmanned vending device, which is applied to a shopping mall, wherein a position of the shopping mall corresponding to the exit is provided with a camera, and the goods in the shopping mall are provided with a passive tag, and the device include:
- the photographing module 201 is configured to capture a picture of a product selected by each user through the camera;
- the identification module 202 is configured to identify, according to each user, a neural network based on the corresponding item identification to determine the item selected by the user;
- the determining module 203 is configured to determine whether the item that the user has paid is consistent with the selected item
- the first processing module 204 is configured to execute a preset process of completing payment when the determination result is consistent;
- the second processing module 205 is configured to execute a preset alert process when the determination result is inconsistent.
- the identification module 202 is configured to:
- the payment information input by the user is acquired, and each of the pictures is identified based on a neural network corresponding to the product identification to determine the user. Selected item.
- the preset process of completing payment includes: a release process
- the preset alerting process includes: alerting by means of an audible and visual alarm, and/or notifying the guard, and/or notifying the user that the item is lost.
- the neural network is based on training all of the merchandise in the mall as a sample.
- the passive tag comprises: a barcode; wherein the barcode corresponds to information about the item, the information comprising: price information.
- Embodiment 3 of the present application further discloses a computer storage medium, wherein the computer storage medium stores a computer program, and is applied to a shopping mall, wherein a position of the shopping mall corresponding to the exit is provided with a camera, and the goods in the shopping mall are passively disposed.
- a tag the computer program configured to perform the following process:
- the image is identified based on a neural network corresponding to the product identification to determine the product selected by the user;
- the “identifying the picture based on a neural network corresponding to the item identification for each user to determine the item selected by the user” includes:
- the payment information input by the user is acquired, and each of the pictures is identified based on a neural network corresponding to the product identification to determine the user. Selected item.
- the preset process of completing payment includes: a release process
- the preset warning process includes: performing an alarm by means of an audible and visual alarm, and/or notifying the guard, and/or notifying the user that the item is lost.
- the neural network is based on training all of the merchandise in the mall as a sample.
- the passive tag comprises: a barcode; wherein the barcode corresponds to information about the item, the information comprising: price information.
- the present application proposes a neural network-based unmanned vending method and apparatus, which is applied to a shopping mall, wherein a location of the shopping mall corresponding to the exit is provided with a camera, and the goods in the shopping mall are provided with passive tags.
- the method includes: capturing, by the camera, a picture of an item selected by each user; for each of the users, identifying the picture based on a neural network corresponding to the item identification to determine an item selected by the user; determining that the user has Whether the paid item is consistent with the selected item; if the judgment result is consistent, the preset completion payment process is executed; if the judgment result is inconsistent, the preset warning process is executed.
- Unmanned sales in this automated way greatly improve efficiency, reduce the cost of use, and facilitate the smooth flow of people, thereby improving the user experience.
- modules in the apparatus in the implementation scenario may be distributed in the apparatus for implementing the scenario according to the implementation scenario description, or may be correspondingly changed in one or more devices different from the implementation scenario.
- the modules of the above implementation scenarios may be combined into one module, or may be further split into multiple sub-modules.
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Control Of Vending Devices And Auxiliary Devices For Vending Devices (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Cash Registers Or Receiving Machines (AREA)
Abstract
一种基于神经网络的无人售货方法和设备,应用于商场,其中所述商场对应出口的位置设置有摄像头,所述商场中的商品设置有无源标签,该方法包括:通过所述摄像头拍摄各用户选择的商品的图片;针对各所述用户,基于对应商品识别的神经网络对所述图片进行识别,以确定所述用户选择的商品;判断所述用户已支付的商品与所选的商品是否一致;若判断结果为一致,则执行预设的完成支付的流程;若判断结果为不一致,则执行预设的警示流程。以此自动化的方式进行无人售货,大大提高了效率,降低了使用成本,且利于人流的顺畅流通,进而提升了用户的使用体验。
Description
相关申请的交叉引用
本申请要求于2017年11月15日提交中国专利局的申请号为201711127805.2、名称为“一种基于神经网络的无人售货方法和设备”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
本申请涉及数据处理领域,特别涉及一种基于神经网络的无人售货方法和设备。
目前,商店或者超市等,在进行销售时,在结算时都是依赖于收银员来进行的,在这种方式下,由于是依赖人工的方式来继续的,一则成本较高,且随着社会的发展,人力的成本将越来越高,另外,人工的方式导致效率比较低下,特别是在大型的超市,往往结算时用户需要排很久的队,导致用户的体验特别不好,另外,也导致人流无法顺畅流通,导致大量本应该出去的人出不去,或者放弃购物,或者导致想购物的人进不来,特别是在商场的面积相对不足的情况下更是如此。
发明内容
针对现有技术中的缺陷,本申请提出了一种基于神经网络的无人售货方法和设备,以自动化的方式进行无人售货,大大提高了效率,降低了使用成本,且利于人流的顺畅流通,进而提升了用户的使用体验。
具体地,本申请提出了以下具体的实施例:
本申请实施例提出了一种基于神经网络的无人售货方法,应用于商场,其中所述商场对应出口的位置设置有摄像头,所述商场中的商品设置有无源标签,该方法包括:
通过所述摄像头拍摄各用户选择的商品的图片;
针对各所述用户,基于对应商品识别的神经网络对所述图片进行识别,以确定所述用户选择的商品;
判断所述用户已支付的商品与所选的商品是否一致;
若判断结果为一致,则执行预设的完成支付的流程;
若判断结果为不一致,则执行预设的警示流程。
在一个具体的实施例中,所述“针对各所述用户,基于对应商品识别的神经网络对所述图片进行识别,以确定所述用户选择的商品”包括:
针对各所述用户,当所述用户的位置处于预设的监控位置时,获取所述用户输入的支付信息,且基于对应商品识别的神经网络对各所述图片进行识别,以确定所述用户选择的 商品。
在一个具体的实施例中,所述预设的完成支付的流程包括:放行流程;
所述预设的警示流程包括:以声光报警的方式进行报警、和/或通知警卫、和/或通知所述用户商品丢失。
在一个具体的实施例中,所述神经网络是基于将所述商场中所有商品作为样本进行训练得到的。
在一个具体的实施例中,所述无源标签包括:条形码;其中,所述条形码对应有所在商品的信息,所述信息包括:价格信息。
本申请实施例提出了一种基于神经网络的无人售货设备,应用于商场,其中所述商场对应出口的位置设置有摄像头,所述商场中的商品设置有无源标签,该设备包括:
拍摄模块,配置成通过所述摄像头拍摄各用户选择的商品的图片;
识别模块,配置成针对各所述用户,基于对应商品识别的神经网络对所述图片进行识别,以确定所述用户选择的商品;
判断模块,配置成判断所述用户已支付的商品与所选的商品是否一致;
第一处理模块,配置成当判断结果为一致时,执行预设的完成支付的流程;
第二处理模块,配置成当判断结果为不一致时,执行预设的警示流程。
在一个具体的实施例中,所述识别模块,配置成:
针对各所述用户,当所述用户的位置处于预设的监控位置时,获取所述用户输入的支付信息,且基于对应商品识别的神经网络对各所述图片进行识别,以确定所述用户选择的商品。
在一个具体的实施例中,所述预设的完成支付的流程包括:放行流程;
所述预设的警示流程包括:以声光报警的方式进行报警、和/或通知警卫、和/或通知所述用户商品丢失。
在一个具体的实施例中,所述神经网络是基于将所述商场中所有商品作为样本进行训练得到的。
在一个具体的实施例中,所述无源标签包括:条形码;其中,所述条形码对应有所在商品的信息,所述信息包括:价格信息。
以此,本申请提出了一种基于神经网络的无人售货方法和设备,应用于商场,其中所述商场对应出口的位置设置有摄像头,所述商场中的商品设置有无源标签,该方法包括:通过所述摄像头拍摄各用户选择的商品的图片;针对各所述用户,基于对应商品识别的神经网络对所述图片进行识别,以确定所述用户选择的商品;判断所述用户已支付的商品与所选的商品是否一致;若判断结果为一致,则执行预设的完成支付的流程;若判断结果为 不一致,则执行预设的警示流程。以此自动化的方式进行无人售货,大大提高了效率,降低了使用成本,且利于人流的顺畅流通,进而提升了用户的使用体验。
为了更清楚地说明本申请实施例的技术方案,下面将对实施例中所需要使用的附图作简单地介绍,应当理解,以下附图仅示出了本申请的某些实施例,因此不应被看作是对范围的限定,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他相关的附图。
图1为本申请实施例提出的一种基于神经网络的无人售货方法的流程示意图;
图2为本申请实施例提出的一种基于神经网络的无人售货设备的结构示意图。
在下文中,将更全面地描述本公开的各种实施例。本公开可具有各种实施例,并且可在其中做出调整和改变。然而,应理解:不存在将本公开的各种实施例限于在此公开的特定实施例的意图,而是应将本公开理解为涵盖落入本公开的各种实施例的精神和范围内的所有调整、等同物和/或可选方案。
在下文中,可在本公开的各种实施例中使用的术语“包括”或“可包括”指示所公开的功能、操作或元件的存在,并且不限制一个或更多个功能、操作或元件的增加。此外,如在本公开的各种实施例中所使用,术语“包括”、“具有”及其同源词仅意在表示特定特征、数字、步骤、操作、元件、组件或前述项的组合,并且不应被理解为首先排除一个或更多个其它特征、数字、步骤、操作、元件、组件或前述项的组合的存在或增加一个或更多个特征、数字、步骤、操作、元件、组件或前述项的组合的可能性。
在本公开的各种实施例中,表述“或”或“A或/和B中的至少一个”包括同时列出的文字的任何组合或所有组合。例如,表述“A或B”或“A或/和B中的至少一个”可包括A、可包括B或可包括A和B二者。
在本公开的各种实施例中使用的表述(诸如“第一”和“第二”等)可修饰在各种实施例中的各种组成元件,不过可不限制相应组成元件。例如,以上表述并不限制所述元件的顺序和/或重要性。以上表述仅用于将一个元件与其它元件区别开的目的。例如,第一用户装置和第二用户装置指示不同用户装置,尽管二者都是用户装置。例如,在不脱离本公开的各种实施例的范围的情况下,第一元件可被称为第二元件,同样地,第二元件也可被称为第一元件。
应注意到:如果描述将一个组成元件“连接”到另一组成元件,则可将第一组成元件直接连接到第二组成元件,并且可在第一组成元件和第二组成元件之间“连接”第三组成元件。相反地,当将一个组成元件“直接连接”到另一组成元件时,可理解为在第一组成 元件和第二组成元件之间不存在第三组成元件。
在本公开的各种实施例中使用的术语“用户”可指示使用电子装置的人或使用电子装置的装置(例如,人工智能电子装置)。
在本公开的各种实施例中使用的术语仅用于描述特定实施例的目的并且并非意在限制本公开的各种实施例。如在此所使用,单数形式意在也包括复数形式,除非上下文清楚地另有指示。除非另有限定,否则在这里使用的所有术语(包括技术术语和科学术语)具有与本公开的各种实施例所属领域普通技术人员通常理解的含义相同的含义。所述术语(诸如在一般使用的词典中限定的术语)将被解释为具有与在相关技术领域中的语境含义相同的含义并且将不被解释为具有理想化的含义或过于正式的含义,除非在本公开的各种实施例中被清楚地限定。
实施例1
本申请实施例1公开了一种基于神经网络的无人售货方法,应用于商场,其中所述商场对应出口的位置设置有摄像头,所述商场中的商品设置有无源标签,如图1所示,该方法包括:
步骤101、通过所述摄像头拍摄各用户选择的商品的图片;
步骤102、针对各所述用户,基于对应商品识别的神经网络对所述图片进行识别,以确定所述用户选择的商品;
步骤103、判断所述用户已支付的商品与所选的商品是否一致;
步骤104、若判断结果为一致,则执行预设的完成支付的流程;
步骤105、若判断结果为不一致,则执行预设的警示流程。
具体地,在一个实施例中,基于完整流程来进行说明,用户通过扫描商品上已有的条形码确定所选取的商品,支付时以扫描的商品来进行支付,而在出商店(超市)时,则通过神经网络来对带出超市的商品进行图像识别,以验证是否支付的商品即为带出的商品;若验证结果不对,则进行警示。
具体的实施例中,步骤102中的所述“针对各所述用户,基于对应商品识别的神经网络对所述图片进行识别,以确定所述用户选择的商品”包括:
针对各所述用户,当所述用户的位置处于预设的监控位置时,获取所述用户输入的支付信息,且基于对应商品识别的神经网络对各所述图片进行识别,以确定所述用户选择的商品。
具体地,在该应用场景中,商场中的商品上预设有无源标签,具体地例如可以为条形码,或者二维码等等,确认所选的商品以及所选商品的价格,后续基于此进行支付,支付后会生成有支付信息,该支付信息例如可以为条形码,二维码或者字符串等等,例如可以 为6位数字,例如可以为256982或者其他的实施例,还可以为字母组合或者字母与数字的组合等等,后续在输入支付信息时,用户可以将基于支付生成的条形码,二维码等等在手机上显示并被预设的扫描器所扫描,以此输入支付信息,还可以为用户手动输入。
在一个具体的实施例中,所述预设的完成支付的流程包括:放行流程;
所述预设的警示流程包括:以声光报警的方式进行报警、和/或通知警卫、和/或通知所述用户商品丢失。
具体地,例如上述流程是在出口处执行,该出口处可以设置单向门,在确认支付信息对应的商品与被识别出的商品一致时,则打开单向门,执行放行的操作,而若是不一致时,则可能商品支付了,但是在到达出口时丢失了,这样需要用户重新去获取该商品,还一种则是多拿了商品,这种情况则是需要进行警示,例如通知警卫,或者控制单向门处于关闭状态。
在一个具体的实施例中,所述神经网络是基于将所述商场中所有商品作为样本进行训练得到的。
在一个具体的实施例中,所述无源标签包括:条形码;其中,所述条形码对应有所在商品的信息,所述信息包括:价格信息。
具体地,这是考虑到条形码本身各商品的包装上都会预设有,后续用户可以通过手机上预设的识别用的应用程序对条形码进行识别,从而节约成本,不需要额外的标签。
实施例2
本申请实施例2还公开了一种基于神经网络的无人售货设备,应用于商场,其中所述商场对应出口的位置设置有摄像头,所述商场中的商品设置有无源标签,该设备包括:
拍摄模块201,配置成通过所述摄像头拍摄各用户选择的商品的图片;
识别模块202,配置成针对各所述用户,基于对应商品识别的神经网络对所述图片进行识别,以确定所述用户选择的商品;
判断模块203,配置成判断所述用户已支付的商品与所选的商品是否一致;
第一处理模块204,配置成当判断结果为一致时,执行预设的完成支付的流程;
第二处理模块205,配置成当判断结果为不一致时,执行预设的警示流程。
在一个具体的实施例中,所述识别模块202,配置成:
针对各所述用户,当所述用户的位置处于预设的监控位置时,获取所述用户输入的支付信息,且基于对应商品识别的神经网络对各所述图片进行识别,以确定所述用户选择的商品。
在一个具体的实施例中,所述预设的完成支付的流程包括:放行流程;
所述预设的警示流程包括:以声光报警的方式进行报警、和/或通知警卫、和/或通知所 述用户商品丢失。
在一个具体的实施例中,所述神经网络是基于将所述商场中所有商品作为样本进行训练得到的。
在一个具体的实施例中,所述无源标签包括:条形码;其中,所述条形码对应有所在商品的信息,所述信息包括:价格信息。
实施例3
本申请实施例3还公开了一种计算机存储介质,该计算机存储介质中存储有计算机程序,应用于商场,其中所述商场对应出口的位置设置有摄像头,所述商场中的商品设置有无源标签,所述计算机程序配置成执行以下流程:
流程A、通过所述摄像头拍摄各用户选择的商品的图片;
流程B、针对各所述用户,基于对应商品识别的神经网络对所述图片进行识别,以确定所述用户选择的商品;
流程C、判断所述用户已支付的商品与所选的商品是否一致;
流程D、若判断结果为一致,则执行预设的完成支付的流程;
流程E、若判断结果为不一致,则执行预设的警示流程。
在一个具体的实施例中,所述“针对各所述用户,基于对应商品识别的神经网络对所述图片进行识别,以确定所述用户选择的商品”包括:
针对各所述用户,当所述用户的位置处于预设的监控位置时,获取所述用户输入的支付信息,且基于对应商品识别的神经网络对各所述图片进行识别,以确定所述用户选择的商品。
在一个具体的实施例中,所述预设的完成支付的流程包括:放行流程;
所述预设的警示流程包括:以声光报警的方式进行报警、和/或通知警卫、和/或通知所述用户商品丢失。
在一个具体的实施例中,所述神经网络是基于将所述商场中所有商品作为样本进行训练得到的。
在一个具体的实施例中,所述无源标签包括:条形码;其中,所述条形码对应有所在商品的信息,所述信息包括:价格信息。
以此,本申请提出了一种基于神经网络的无人售货方法和设备,应用于商场,其中所述商场对应出口的位置设置有摄像头,所述商场中的商品设置有无源标签,该方法包括:通过所述摄像头拍摄各用户选择的商品的图片;针对各所述用户,基于对应商品识别的神经网络对所述图片进行识别,以确定所述用户选择的商品;判断所述用户已支付的商品与所选的商品是否一致;若判断结果为一致,则执行预设的完成支付的流程;若判断结果为 不一致,则执行预设的警示流程。以此自动化的方式进行无人售货,大大提高了效率,降低了使用成本,且利于人流的顺畅流通,进而提升了用户的使用体验。
本领域技术人员可以理解附图只是一个优选实施场景的示意图,附图中的模块或流程并不一定是实施本申请所必须的。
本领域技术人员可以理解实施场景中的装置中的模块可以按照实施场景描述进行分布于实施场景的装置中,也可以进行相应变化位于不同于本实施场景的一个或多个装置中。上述实施场景的模块可以合并为一个模块,也可以进一步拆分成多个子模块。
上述本申请序号仅仅为了描述,不代表实施场景的优劣。
以上公开的仅为本申请的几个具体实施场景,但是,本申请并非局限于此,任何本领域的技术人员能思之的变化都应落入本申请的保护范围。
Claims (10)
- 一种基于神经网络的无人售货方法,其特征在于,应用于商场,其中所述商场对应出口的位置设置有摄像头,所述商场中的商品设置有无源标签,该方法包括:通过所述摄像头拍摄各用户选择的商品的图片;针对各所述用户,基于对应商品识别的神经网络对所述图片进行识别,以确定所述用户选择的商品;判断所述用户已支付的商品与所选的商品是否一致;若判断结果为一致,则执行预设的完成支付的流程;若判断结果为不一致,则执行预设的警示流程。
- 如权利要求1所述的一种基于神经网络的无人售货方法,其特征在于,所述“针对各所述用户,基于对应商品识别的神经网络对所述图片进行识别,以确定所述用户选择的商品”包括:针对各所述用户,当所述用户的位置处于预设的监控位置时,获取所述用户输入的支付信息,且基于对应商品识别的神经网络对各所述图片进行识别,以确定所述用户选择的商品。
- 如权利要求1所述的一种基于神经网络的无人售货方法,其特征在于,所述预设的完成支付的流程包括:放行流程;所述预设的警示流程包括:以声光报警的方式进行报警、和/或通知警卫、和/或通知所述用户商品丢失。
- 如权利要求1所述的一种基于神经网络的无人售货方法,其特征在于,所述神经网络是基于将所述商场中所有商品作为样本进行训练得到的。
- 如权利要求1所述的一种基于神经网络的无人售货方法,其特征在于,所述无源标签包括:条形码;其中,所述条形码对应有所在商品的信息,所述信息包括:价格信息。
- 一种基于神经网络的无人售货设备,其特征在于,应用于商场,其中所述商场对应出口的位置设置有摄像头,所述商场中的商品设置有无源标签,该设备包括:拍摄模块,配置成通过所述摄像头拍摄各用户选择的商品的图片;识别模块,配置成针对各所述用户,基于对应商品识别的神经网络对所述图片进行识别,以确定所述用户选择的商品;判断模块,配置成判断所述用户已支付的商品与所选的商品是否一致;第一处理模块,配置成当判断结果为一致时,执行预设的完成支付的流程;第二处理模块,配置成当判断结果为不一致时,执行预设的警示流程。
- 如权利要求6所述的一种基于神经网络的无人售货设备,其特征在于,所述识别模块,配置成:针对各所述用户,当所述用户的位置处于预设的监控位置时,获取所述用户输入的支付信息,且基于对应商品识别的神经网络对各所述图片进行识别,以确定所述用户选择的商品。
- 如权利要求6所述的一种基于神经网络的无人售货设备,其特征在于,所述预设的完成支付的流程包括:放行流程;所述预设的警示流程包括:以声光报警的方式进行报警、和/或通知警卫、和/或通知所述用户商品丢失。
- 如权利要求6所述的一种基于神经网络的无人售货设备,其特征在于,所述神经网络是基于将所述商场中所有商品作为样本进行训练得到的。
- 如权利要求6所述的一种基于神经网络的无人售货设备,其特征在于,所述无源标签包括:条形码;其中,所述条形码对应有所在商品的信息,所述信息包括:价格信息。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711127805.2A CN107918983A (zh) | 2017-11-15 | 2017-11-15 | 一种基于神经网络的无人售货方法和设备 |
CN201711127805.2 | 2017-11-15 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2019096228A1 true WO2019096228A1 (zh) | 2019-05-23 |
Family
ID=61896388
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2018/115738 WO2019096228A1 (zh) | 2017-11-15 | 2018-11-15 | 一种基于神经网络的无人售货方法和设备 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN107918983A (zh) |
WO (1) | WO2019096228A1 (zh) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107918983A (zh) * | 2017-11-15 | 2018-04-17 | 深圳码隆科技有限公司 | 一种基于神经网络的无人售货方法和设备 |
CN108647671B (zh) * | 2018-06-28 | 2023-12-22 | 武汉市哈哈便利科技有限公司 | 一种光学标识视觉识别方法及基于该方法的无人售货柜 |
CN109190705A (zh) * | 2018-09-06 | 2019-01-11 | 深圳码隆科技有限公司 | 无人售货方法、装置及系统 |
WO2021072699A1 (en) * | 2019-10-17 | 2021-04-22 | Shenzhen Malong Technologies Co., Ltd. | Irregular scan detection for retail systems |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106683294A (zh) * | 2016-12-14 | 2017-05-17 | 深圳市易捷通科技股份有限公司 | 一种零售收银防盗防损的收银设备及方案 |
CN106781121A (zh) * | 2016-12-14 | 2017-05-31 | 朱明� | 基于视觉分析的超市自助结账智能系统 |
CN107330684A (zh) * | 2017-07-06 | 2017-11-07 | 广州联业商用机器人科技股份有限公司 | 一种云端智能管控无人商店及其自动结算方法 |
CN107918983A (zh) * | 2017-11-15 | 2018-04-17 | 深圳码隆科技有限公司 | 一种基于神经网络的无人售货方法和设备 |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN204480327U (zh) * | 2015-02-13 | 2015-07-15 | 苏州健生源医药连锁有限公司 | 一种无人值守药房自主购药系统 |
US9747512B2 (en) * | 2015-06-25 | 2017-08-29 | Toshiba Tec Kabushiki Kaisha | Article recognition apparatus and image processing method for article recognition apparatus |
CN205451124U (zh) * | 2016-02-17 | 2016-08-10 | 中国工商银行股份有限公司 | 一种商场快速支付系统 |
CN106373296A (zh) * | 2016-09-19 | 2017-02-01 | 北京火星盒子科技有限公司 | 检验已支付商品的系统、蓝牙扫描设备和校验终端设备 |
CN106340137A (zh) * | 2016-11-14 | 2017-01-18 | 贵州师范学院 | 一种基于深度学习的自动称重机及其程序控制方法 |
CN106779690A (zh) * | 2017-01-17 | 2017-05-31 | 深圳市百姓通商网络科技有限公司 | 无人值守自动结账商店及其实现方法 |
CN107230137A (zh) * | 2017-05-31 | 2017-10-03 | 北京小米移动软件有限公司 | 商品信息获取方法及装置 |
-
2017
- 2017-11-15 CN CN201711127805.2A patent/CN107918983A/zh active Pending
-
2018
- 2018-11-15 WO PCT/CN2018/115738 patent/WO2019096228A1/zh active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106683294A (zh) * | 2016-12-14 | 2017-05-17 | 深圳市易捷通科技股份有限公司 | 一种零售收银防盗防损的收银设备及方案 |
CN106781121A (zh) * | 2016-12-14 | 2017-05-31 | 朱明� | 基于视觉分析的超市自助结账智能系统 |
CN107330684A (zh) * | 2017-07-06 | 2017-11-07 | 广州联业商用机器人科技股份有限公司 | 一种云端智能管控无人商店及其自动结算方法 |
CN107918983A (zh) * | 2017-11-15 | 2018-04-17 | 深圳码隆科技有限公司 | 一种基于神经网络的无人售货方法和设备 |
Also Published As
Publication number | Publication date |
---|---|
CN107918983A (zh) | 2018-04-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2019096228A1 (zh) | 一种基于神经网络的无人售货方法和设备 | |
WO2020042966A1 (zh) | 漏扫识别方法、装置、自助收银终端及系统 | |
US10600043B2 (en) | Automated checkout system through mobile shopping units | |
US11151427B2 (en) | Method and apparatus for checkout based on image identification technique of convolutional neural network | |
CN108269371B (zh) | 商品自动结算方法、装置、自助收银台 | |
US20230013957A1 (en) | Non-Scan Loss Verification at Self-Checkout Terminal | |
WO2019095884A1 (zh) | 一种基于图像识别技术的无人售货方法、装置、电子设备及计算机存储介质 | |
US20170011606A1 (en) | Systems, Devices, and/or Methods for Managing Transactions | |
WO2019096222A1 (zh) | 一种基于身份识别和商品识别的无人售货方法和设备 | |
US20090272801A1 (en) | Deterring checkout fraud | |
US11488126B2 (en) | Cashier fraud detecting system and method and product image selection generation for artificial neural network learning related applications | |
US10372998B2 (en) | Object recognition for bottom of basket detection | |
US20100253787A1 (en) | Method for Object Recognition and Communication of Associated Label and Other Information | |
TW201214339A (en) | Auditing video analytics through essence generation | |
JP2004127013A (ja) | 販売時点情報管理装置 | |
WO2021179137A1 (zh) | 结算方法、装置和系统 | |
JP2022519191A (ja) | セルフチェックアウト端末でスキャンの不規則性を検出するためのシステムおよび方法 | |
US20230368625A1 (en) | Self-checkout verification systems and methods | |
US20150317642A1 (en) | Process to query electronic sales receipts with a portable computerized device | |
WO2021179138A1 (zh) | 商超货架上商品的分析方法和系统 | |
WO2019096200A1 (zh) | 一种基于电子标签的无人售货方法和设备 | |
CN111428743B (zh) | 商品识别方法、商品处理方法、装置及电子设备 | |
EP3629276A1 (en) | Context-aided machine vision item differentiation | |
US9865148B2 (en) | Shopping party locator systems and methods | |
CN110765825A (zh) | 物品摆放状态获取方法和系统 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 18879148 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 18879148 Country of ref document: EP Kind code of ref document: A1 |