WO2019228005A1 - 一种价格信息的处理方法、处理装置和存储介质 - Google Patents

一种价格信息的处理方法、处理装置和存储介质 Download PDF

Info

Publication number
WO2019228005A1
WO2019228005A1 PCT/CN2019/077143 CN2019077143W WO2019228005A1 WO 2019228005 A1 WO2019228005 A1 WO 2019228005A1 CN 2019077143 W CN2019077143 W CN 2019077143W WO 2019228005 A1 WO2019228005 A1 WO 2019228005A1
Authority
WO
WIPO (PCT)
Prior art keywords
currency
price information
recognition model
price
information
Prior art date
Application number
PCT/CN2019/077143
Other languages
English (en)
French (fr)
Inventor
徐达峰
Original Assignee
阿里巴巴集团控股有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 阿里巴巴集团控股有限公司 filed Critical 阿里巴巴集团控股有限公司
Publication of WO2019228005A1 publication Critical patent/WO2019228005A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • G06Q30/0283Price estimation or determination

Definitions

  • the present application relates to the field of information processing technology, and in particular, to a method, a processing device, and a storage medium for processing price information.
  • a user invokes an application module built into a terminal device, selects two currencies to be converted, and enters a price denominated in one currency.
  • the application module converts the price into a Price, and display the converted price information to the user.
  • the embodiments of the present specification provide a method, a processing device, and a storage medium for processing price information, which can automatically identify price information and perform currency conversion.
  • the operation is simple, misoperations are avoided, and user experience is improved.
  • a method for processing price information includes: identifying the first price information from an image containing the first price information related to a first currency; and according to the first price. Information and a conversion relationship between the first currency and a preset second currency, determining second price information related to the second currency; and displaying the second price information.
  • a device for processing price information including: an identifying unit that identifies the first price information from an image containing the first price information related to the first currency; A unit that determines second price information related to the second currency according to the first price information and a conversion relationship between the first currency and a preset second currency; and a display unit that displays the second price information.
  • a storage medium storing a computer-readable program that causes a processor to execute the method according to the first aspect described above.
  • the beneficial effects of the embodiments of the present specification are that it can automatically identify price information and perform currency conversion, which is simple to operate, avoids misoperations, and improves user experience.
  • FIG. 1 is a schematic diagram of a method for processing price information in Embodiment 1 of the present specification
  • FIG. 2 is another schematic diagram of a method for processing price information in Embodiment 1 of the present specification
  • FIG. 3 is a schematic diagram of a price information processing apparatus according to Embodiment 2 of the present specification.
  • first and second are used to distinguish different elements from each other by title, but they do not indicate the spatial arrangement or chronological order of these elements, and these elements should not be used by these terms Restricted.
  • the term “and / or” includes any and all combinations of one or more of the associated listed terms.
  • FIG. 1 is a schematic diagram of a method for processing price information in this embodiment.
  • the method includes:
  • Step 101 Identify the first price information from an image containing the first price information related to the first currency.
  • Step 102 Determine second price information related to the second currency according to the first price information and a conversion relationship between the first currency and a preset second currency.
  • Step 103 Display the second price information.
  • the first price information can be automatically identified from the image and currency conversion can be performed to display the second price information after currency conversion to the user.
  • the operation is simple, misoperations are avoided, and the user experience is improved.
  • the first currency and the second currency are different types of currency, for example, the first currency is the yen and the second currency is the yuan.
  • the first currency may be the currency of the country or region where the user is currently located
  • the second currency may be a preset currency, for example, the currency of the country to which the user belongs or the currency that the user wants to use to measure the price of the product .
  • the first currency can be set by the user or can be automatically acquired by the device. For a specific manner in which the device automatically obtains the first currency, refer to the description below.
  • the first price information related to the first currency is price information denominated in the first currency.
  • the second price information related to the second currency is price information denominated in the second currency.
  • the conversion relationship between the first currency and the second currency is the exchange rate relationship between different currencies.
  • the first price information includes a price, or a price and corresponding discount information. That is, the first price information is information that can be used to determine a first price related to a first currency.
  • the image containing the first price information can be obtained in any manner.
  • a user uses a terminal device to acquire an image of an area in a real scene containing first price information.
  • the real scene here is, for example, an actual life scene including a price tag or a price copy.
  • the price tag here may be, for example, a price tag pasted on a product in a shopping mall, and the price copy may be, for example, a price-related text or picture displayed on a product page on a shopping website.
  • the first price information can be identified from the image in any manner.
  • a recognition method may be performed by using a recognition model obtained by machine learning, but this embodiment is not limited thereto.
  • the conversion relationship between the first currency and the second currency may also be displayed at the same time, that is, the exchange rate information may be displayed at the same time.
  • FIG. 2 is another schematic diagram of a method for processing price information in this embodiment. As shown in FIG. 2, in addition to the above steps 101-103, the method may further include:
  • Step 201 Use a training sample to train an identification model for identifying the first price information.
  • the above step 101 can recognize the first price information from the image based on the recognition model.
  • This step 201 is optional. In addition, this step 201 may be performed in advance. That is, the recognition model is trained and obtained before actual recognition.
  • the training samples may be a large number of pictures containing price information or the like.
  • Pictures containing similar information can be, for example, other pictures containing numbers, such as pictures containing mathematical formulas, pictures of calendars, and the like.
  • the method may further include:
  • Step 202 Add an image containing the first price information to the training sample, and retrain the recognition model based on the added training sample to obtain an updated recognition model.
  • the updated identification model obtained in the above step 202 may be provided to step 101 for identifying the first price information from the image based on the updated identification model.
  • step 202 is optional, and step 101 may be performed directly after step 201 without performing step 202.
  • step 202 may be performed directly after obtaining the image containing the first price information, or step 202 may be performed when the first price information cannot be identified from the image containing the first price information.
  • the above recognition model may be a model based on a convolutional neural network, or may be another model.
  • the method may further include steps (not shown): testing the recognition model using a test sample, adding the image to the test sample, and re-recognizing the recognition model based on the added test sample. Test to get the updated recognition model. This step is optional.
  • test sample may also be a large number of pictures containing price information or the like.
  • the image may be added to the test sample directly after the image containing the first price information is obtained, or the image may be added to the test only when the first price information cannot be identified from the image. In the sample.
  • the test result based on the updated recognition model that meets the preset conditions can also be used.
  • the first price information is re-identified from the image.
  • the method may further include the steps of obtaining positioning information of the user, determining the first currency according to the positioning information, and acquiring the conversion relationship based on the determined first currency and a preset second currency.
  • the first currency can be automatically obtained by the device, which further simplifies the operation and avoids misoperation. This step is optional.
  • the country or region where the user is currently located is determined, and the first currency is the currency of the country or region.
  • the conversion relationship can be obtained by querying a server providing a real-time exchange rate information service, for example.
  • the foregoing method may be implemented on one device, for example, may be implemented on one terminal device. It can also be implemented on multiple devices in a distributed manner, for example, it can be performed jointly on a terminal device and a server. However, this embodiment is not limited to the above examples, and may also be executed on other types of devices.
  • the above steps 101-103 can be implemented, for example, by: identifying the first price information and obtaining positioning information in the first device (such as a terminal device), and aggregating the two types of information,
  • the aggregated information is sent to a second device (such as a server) that provides currency conversion services.
  • the second device may extract positioning information and first price information from the aggregated information, determine a first currency based on the positioning information, and obtain the first currency and the second currency based on the first currency and a preset second currency.
  • the conversion relationship between currencies, and according to the extracted first price information and the conversion relationship determine the second price information related to the second currency, and send the second price information to the first device for display.
  • this embodiment is not limited to this, and may be implemented in other similar manners.
  • steps 201-202, 101-103 can be implemented, for example, as follows: steps 201-202 can be performed on a third device (such as a server) and on a first device (such as a terminal device) Perform steps 101-103.
  • steps 201-202 can be performed on a third device (such as a server) and on a first device (such as a terminal device) Perform steps 101-103.
  • the step of testing the recognition model, adding the image to a test sample, and retesting the recognition model based on the added test sample to obtain an updated recognition model may also be performed on the third device.
  • the step of re-identifying the first price information from the image may be performed on the first device.
  • the identification model or the updated identification model may be sent from the third device to the first device after being obtained, and the first device may identify the first price information based on the received identification model or the updated identification model.
  • the first device may send an image containing the first price information to a third device for addition to the training samples and / or test samples.
  • this embodiment is not limited to this, and may be implemented in other similar manners.
  • the second device and the third device may be the same device or different devices.
  • the terminal device when the first device is a terminal device and the third device is a server, the terminal device can be set to send an image containing the first price information from the terminal device to the server without the user's permission. It can be set to send the image from the terminal device to the server only if the user allows it, otherwise the image cannot be sent.
  • price information can be automatically identified and currency conversion can be performed, the operation is simple, misoperations are avoided, and the user experience is improved.
  • FIG. 3 is a schematic diagram of a price information processing apparatus 300 in this embodiment. The same parts of the second embodiment as those of the first embodiment are not described again.
  • the price information processing device 300 includes an identification unit 301, a determination unit 302, and a display unit 303.
  • the identification unit 301 identifies the first price information from an image containing the first price information related to the first currency; the determination unit 302 determines according to the first price information and a conversion relationship between the first currency and the second currency The second price information related to the second currency; the display unit 303 displays the second price information.
  • the first price information may include a price and / or corresponding discount information.
  • the processing device 300 may further include a positioning unit 304, a currency determination unit 305, and a conversion relationship acquisition unit 306.
  • the positioning unit 304 acquires positioning information; the currency determination unit 305 determines the first currency according to the positioning information; the conversion relationship acquisition unit 306 acquires the conversion relationship based on the determined first currency and a preset second currency.
  • the above-mentioned positioning unit 304, currency determination unit 305, and conversion relationship acquisition unit 306 are optional components.
  • the processing device 300 may further include a training unit 307, which uses the training samples to train an identification model for identifying the first price information.
  • the above-mentioned training unit 307 is an optional component.
  • the recognition model may be a convolutional neural network model.
  • the processing device 300 may further include an adding unit 308, which adds the image containing the first price information to the training sample, and retrains the recognition model based on the added training sample to obtain Updated recognition model.
  • the above-mentioned adding unit 308 is an optional component.
  • the processing device 300 may further include a test unit 309, which uses the test sample to test the recognition model, and the adding unit 308 may also add an image including the first price to the test sample, and based on the adding The subsequent test samples retest the recognition model to obtain an updated recognition model.
  • a test unit 309 which uses the test sample to test the recognition model
  • the adding unit 308 may also add an image including the first price to the test sample, and based on the adding The subsequent test samples retest the recognition model to obtain an updated recognition model.
  • test unit 309 is an optional component.
  • the processing device 300 may further include an image obtaining unit 310 that obtains an image including the first price information.
  • the adding unit 308 can also obtain the image from the image obtaining unit 310.
  • the image acquisition unit 310 described above is an optional component.
  • Embodiment 1 The functions of the above units may be implemented in a specific manner described in Embodiment 1.
  • the foregoing units may be implemented by one device, or may be implemented by multiple devices.
  • the foregoing units may be implemented by one device, or may be implemented by multiple devices.
  • the price information processing device of this embodiment can automatically identify the price information and perform currency conversion.
  • the operation is simple, misoperations are avoided, and the user experience is improved.
  • the embodiment of the present specification further provides a computer-readable program, which causes the processor to execute the method described in Embodiment 1.
  • the embodiment of the present specification also provides a storage medium storing a computer-readable program, wherein the storage medium storing the computer-readable program causes the processor to execute the method according to the first embodiment.
  • the price information processing device described in combination with the embodiments of the present specification may be directly embodied as hardware, a software module executed by a processor, or a combination of the two.
  • one or more of the functional block diagrams and / or one or more combinations of the functional block diagrams shown in the drawings may correspond to each software module of a computer program flow, or to each hardware module.
  • These software modules can respectively correspond to the steps shown in the drawings.
  • These hardware modules can be implemented by using a field programmable gate array (FPGA) to cure these software modules.
  • FPGA field programmable gate array
  • a software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.
  • a storage medium may be coupled to the processor so that the processor can read information from and write information to the storage medium; or the storage medium may be a component of the processor.
  • the processor and the storage medium may reside in an ASIC.
  • the software module can be stored in the memory of the electronic device, or it can be stored in a memory card that can be inserted into the electronic device.
  • the software module may be stored in the MEGA-SIM card or a large-capacity flash memory device.
  • One or more of the functional block diagrams described in the drawings and / or one or more combinations of the functional block diagrams may be implemented as a general-purpose processor, digital signal processor (DSP), or dedicated integration for performing the functions described in this application. Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or any suitable combination thereof.
  • ASICs Application Specific integrated circuits
  • FPGAs Field Programmable Gate Arrays
  • One or more of the functional block diagrams and / or one or more combinations of functional block diagrams described with reference to the drawings may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, One or more microprocessors in conjunction with DSP communications or any other such configuration.
  • processing methods and processing devices in the embodiments of the present specification may be implemented in a uniprocessor environment, or may be implemented in a distributed manner in a multiprocessor environment.

Landscapes

  • Business, Economics & Management (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
  • Image Processing (AREA)

Abstract

本说明书实施例提供一种价格信息的处理方法、处理装置和存储介质。该方法包括:从包含与第一货币相关的第一价格信息的图像中识别该第一价格信息;根据该第一价格信息以及该第一货币与预设的第二货币之间的转换关系,确定与该第二货币相关的第二价格信息;以及显示该第二价格信息。

Description

一种价格信息的处理方法、处理装置和存储介质 技术领域
本申请涉及信息处理技术领域,特别涉及一种价格信息的处理方法、处理装置、存储介质。
背景技术
近年来,用户在境外活动的时间日益增长。在境外活动时,用户常常存在如下的需求:将以当地货币计价的价格信息转换为以其常用货币计价的价格信息,即,进行相应的货币转换(也称为汇率转换)。
在以往的技术中,用户调用内置于终端设备的应用模块,选择要进行转换的两种货币,输入以其中一种货币计价的价格,该应用模块将该价格转换为以另一种货币计价的价格,并向用户显示转换后的价格信息。
应该注意,上面对技术背景的介绍只是为了方便对本发明的技术方案进行清楚、完整的说明,并方便本领域技术人员的理解而阐述的。不能仅仅因为这些方案在本发明的背景技术部分进行了阐述而认为上述技术方案为本领域技术人员所公知。
发明内容
发明人发现,在以往的技术中,用户需要通过复杂的手动操作来获得转换后的价格信息,操作繁琐且可能出现误操作,用户体验较差。
为了解决上述问题,本说明书实施例提供一种价格信息的处理方法、处理装置和存储介质,能够自动识别价格信息并进行货币转换,操作简单,且避免了误操作,提升用户体验。
根据本说明书实施例的第一方面,提供一种价格信息的处理方法,该方法包括:从包含与第一货币相关的第一价格信息的图像中识别该第一价格信息;根据该第一价格信息以及该第一货币与预设的第二货币之间的转换关系,确定与该第二货币相关的第二价格信息;以及显示该第二价格信息。
根据本说明书实施例的第二方面,提供一种价格信息的处理装置,该装置包括:识别单元,其从包含与第一货币相关的第一价格信息的图像中识别该第一价格信息;确定 单元,其根据该第一价格信息以及该第一货币与预设的第二货币之间的转换关系,确定与该第二货币相关的第二价格信息;以及显示单元,其显示该第二价格信息。
根据本说明书实施例的第三方面,提供一种存储有计算机可读程序的存储介质,该计算机可读程序使得处理器执行根据上述第一方面所述的方法。
本说明书实施例的有益效果在于,能够自动识别价格信息并进行货币转换,操作简单,且避免了误操作,提升用户体验。
参照后文的说明和附图,详细公开了本发明的特定实施方式,指明了本发明的原理可以被采用的方式。应该理解,本发明的实施方式在范围上并不因而受到限制。在所附权利要求的精神和条款的范围内,本发明的实施方式包括许多改变、修改和等同。
针对一种实施方式描述和/或示出的特征可以以相同或类似的方式在一个或更多个其它实施方式中使用,与其它实施方式中的特征相组合,或替代其它实施方式中的特征。
应该强调,术语“包括/包含”在本文使用时指特征、整件、步骤或组件的存在,但并不排除一个或更多个其它特征、整件、步骤或组件的存在或附加。
附图说明
所包括的附图用来提供对本说明书实施例的进一步的理解,其构成了说明书的一部分,用于例示本发明的实施方式,并与文字描述一起来阐释本发明的原理。显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。在附图中:
图1是本说明书实施例1的价格信息的处理方法的一个示意图;
图2是本说明书实施例1的价格信息的处理方法的另一个示意图;
图3是本说明书实施例2的价格信息的处理装置的一个示意图。
具体实施方式
参照附图,通过下面的说明书,本发明的前述以及其它特征将变得明显。在说明书和附图中,具体公开了本发明的特定实施方式,其表明了其中可以采用本发明的原则的部分实施方式,应了解的是,本发明不限于所描述的实施方式,相反,本发明包括落入所附权利要求的范围内的全部修改、变型以及等同物。
在本说明书实施例中,术语“第一”、“第二”等用于对不同元素从称谓上进行区分,但并不表示这些元素的空间排列或时间顺序等,这些元素不应被这些术语所限制。术语“和/或”包括相关联列出的术语的一种或多个中的任何一个和所有组合。
在本说明书实施例中,单数形式“一”、“该”等包括复数形式,应广义地理解为“一种”或“一类”而并不是限定为“一个”的含义;此外术语“所述”应理解为既包括单数形式也包括复数形式,除非上下文另外明确指出。此外术语“根据”应理解为“至少部分根据……”,术语“基于”应理解为“至少部分基于……”,除非上下文另外明确指出。
下面结合附图对本说明书实施例的具体实施方式进行说明。
实施例1
本实施例1提供一种价格信息的处理方法。图1是本实施例的价格信息的处理方法的一个示意图。
如图1所述,该方法包括:
步骤101,从包含与第一货币相关的第一价格信息的图像中识别该第一价格信息;
步骤102,根据该第一价格信息以及该第一货币与预设的第二货币之间的转换关系,确定与该第二货币相关的第二价格信息;
步骤103,显示该第二价格信息。
通过本实施例的上述方法,能够从图像中自动识别第一价格信息并进行货币转换,以将货币转换后的第二价格信息显示给用户,操作简单,且避免了误操作,提升用户体验。
在本实施例中,第一货币、第二货币是不同类型的货币,例如,第一货币是日元、第二货币是人民币。
在本实施例中,第一货币可以是用户当前所处的国家或地区的货币,第二货币可以是预设的货币,例如,用户所属国的货币或者用户想要用于衡量商品价格的货币。该第一货币可由用户设置,也可以由设备自动获取。关于设备自动获取第一货币的具体方式,可参见后述的说明。
与第一货币相关的第一价格信息是以第一货币计价的价格信息。同样地,与第二货币相关的第二价格信息是以第二货币计价的价格信息。这样,第一货币与第二货币之间的转换关系即不同货币之间的汇率关系。
在本实施例中,该第一价格信息包括价格,或者,价格以及相应的折扣信息。也就是说,该第一价格信息是能够用于确定与第一货币相关的第一价格的信息。
例如,通过将价格和折扣相乘,得到以第一货币表示的实际价格。
在本实施例中,包含第一价格信息的图像可通过任意方式获得。例如,用户使用终端设备对包含第一价格信息的实景中的区域进行图像采集而获得。这里的实景例如是包含价签或者价格文案等的实际生活场景。这里的价签例如可以是商场中商品上粘贴的价签,价格文案例如可以是购物网站上在商品页面中显示的与价格相关的文字或图片等。
在本实施例中,在上述步骤101中,可以使用任意方式从图像中识别第一价格信息。例如,可以通过使用机器学习而获得的识别模型进行识别的方式,但本实施例不以此作为限制。
在本实施例中,在上述步骤103中,还可以同时显示第一货币与第二货币之间的转换关系,即,可以同时显示汇率信息。
图2是本实施例的价格信息的处理方法的另一个示意图。如图2所示,除上述步骤101-103以外,该方法还可以包括:
步骤201,使用训练样本训练用于识别该第一价格信息的识别模型。
由此,上述步骤101能够基于该识别模型从图像中识别第一价格信息。
该步骤201是可选的。另外,该步骤201可以是预先进行的。也就是说,在实际的识别之前预先训练并得到识别模型。
在本实施例中,上述训练样本可以是大量包含价格信息或类似信息的图片。包含类似信息的图片例如可以是包含数字的其他图片,例如包含数学公式的图片、日历的图片等。
在本实施例中,如图2所示,该方法还可以包括:
步骤202,将包含第一价格信息的图像添加到上述训练样本中,基于添加后的训练样本对识别模型进行重新训练,以获得更新后的识别模型。
由此,能够利用该图像向训练样本提供反馈样本,从而提高基于更新后的识别模型进行识别时的识别度。
上述步骤202中获得的更新后的识别模型可被提供给步骤101,用于基于该更新后的识别模型从该图像中识别第一价格信息。
该步骤202是可选的,可不执行步骤202而在步骤201后直接执行步骤101。
另外,在实施步骤202时,可以在获得包含第一价格信息的图像后直接实施步骤202,也可以在无法从包含第一价格信息的图像中识别第一价格信息的情况下实施步骤202。
在本实施例中,上述识别模型可以是基于卷积神经网络的模型,也可以是其他模型。
在本实施例中,该方法还可以包括步骤(未图示):使用测试样本对该识别模型进行测试,将该图像添加到测试样本中,并且基于添加后的测试样本对该识别模型进行重新测试,以获得更新后的识别模型。该步骤为可选的步骤。
由此,能够利用该图像向测试样本提供反馈样本,从而提高基于更新后的识别模型进行识别时的识别度。
在本实施例中,测试样本也可以是大量包含价格信息或类似信息的图片。
在本实施例中,可以在获得包含第一价格信息的图像后直接将该图像添加到测试样本中,也可以在无法从该图像中识别第一价格信息的情况下才将该图像添加到测试样本中。
如果采用在无法从该图像中识别第一价格信息的情况下才将该图像添加到训练样本和/或测试样本中的方案,还可在基于更新后的识别模型的测试结果满足预设条件的情况下重新从该图像中识别第一价格信息。由此,能够提高从该图像中识别出该第一价格信息的可能性。
在本实施例中,该方法还可包括步骤:获取用户的定位信息,根据该定位信息确定该第一货币,并基于确定的该第一货币和预设的第二货币获取该转换关系。由此,能够由设备自动获取该第一货币,进一步简化了操作并避免误操作。该步骤是可选的步骤。
例如,根据用户的定位信息,确定该用户当前所处的国家或地区,该第一货币则是该国家或地区的货币。
该转换关系例如可以通过向提供实时汇率信息服务的服务器查询而获得。
在本实施例中,上述方法可以在一个设备上实现,例如可以在一个终端设备中实现。也可以分布式地在多个设备上实现,例如可以在终端设备和服务器上共同执行。但本实施例不限于上述示例,也可以在其他类型的设备上执行。
在多个设备上实现时,上述步骤101-103例如可通过如下方式实现:可在第一设备(例如终端设备)中识别第一价格信息并获取定位信息,并将该两种信息聚合,将聚合 后的信息发送到提供货币转换服务的第二设备(例如服务器)。该第二设备可从聚合后的信息中提取出定位信息和第一价格信息,根据该定位信息确定第一货币,并基于该第一货币和预设的第二货币获取第一货币与第二货币之间的转换关系,并且,根据提取出的第一价格信息以及该转换关系,确定与第二货币相关的第二价格信息,将该第二价格信息发送到第一设备进行显示。但本实施例不以此作为限制,也可以采用其他类似的方式实现。
在多个设备上实现时,上述步骤201-202、101-103例如可通过如下方式实现:可在第三设备(例如服务器)上执行步骤201-202,在第一设备(例如终端设备上)执行步骤101-103。另外,上述对该识别模型进行测试,将该图像添加到测试样本中,并且基于添加后的测试样本对该识别模型进行重新测试,以获得更新后的识别模型的步骤也可在上述第三设备上执行。在基于更新后的识别模型的测试结果满足预设条件的情况下重新从该图像中识别第一价格信息的步骤可在第一设备上执行。识别模型或更新后的识别模型在被获得后可从第三设备被发送到第一设备,第一设备可基于接收到的识别模型或更新后的识别模型识别第一价格信息。第一设备可将包含第一价格信息的图像发送到第三设备用于添加到到训练样本和/或测试样本。但本实施例不以此作为限制,也可以采用其他类似的方式实现。
上述第二设备和第三设备可以是同一设备,也可以是不同的设备。
在本实施例中,在上述第一设备为终端设备,上述第三设备为服务器的情况下,可将终端设备设置无需用户允许即可从终端设备向服务器发送包含第一价格信息的图像,也可设置为在用户允许的情况下才能从终端设备向服务器发送该图像,否则不能发送该图像。
通过本实施例的价格信息的处理方法,能够自动识别价格信息并进行货币转换,操作简单,且避免了误操作,提升用户体验。
实施例2
本实施例2提供一种价格信息的处理装置。图3是本实施例的价格信息的处理装置300的一个示意图。本实施例2中与实施例1相同的部分不再赘述。
如图3所示,价格信息的处理装置300包括识别单元301、确定单元302和显示单元303。识别单元301从包含与第一货币相关的第一价格信息的图像中识别该第一价格信息;确定单元302根据该第一价格信息以及该第一货币与第二货币之间的转换关系, 确定与该第二货币相关的第二价格信息;显示单元303显示该第二价格信息。
在本实施例中,该第一价格信息可包括价格和/或相应的折扣信息。
在本实施例中,处理装置300还可包括:定位单元304、货币确定单元305和转换关系获取单元306。定位单元304获取定位信息;货币确定单元305根据该定位信息确定该第一货币;转换关系获取单元306基于确定的该第一货币和预设的第二货币获取该转换关系。
上述定位单元304、货币确定单元305和转换关系获取单元306是可选的部件。
在本实施例中,处理装置300还可包括训练单元307,训练单元307使用训练样本训练用于识别第一价格信息的识别模型。
上述训练单元307是可选的部件。
在本实施例中,该识别模型可以为卷积神经网络模型。
在本实施例中,处理装置300还可包括添加单元308,添加单元308将包含第一价格信息的图像添加到该训练样本中,基于添加后的训练样本对该识别模型进行重新训练,以获得更新后的识别模型。
上述添加单元308是可选的部件。
在本实施例中,处理装置300还可包括测试单元309,测试单元309使用测试样本对识别模型进行测试,添加单元308还可将包含第一价格的图像添加到该测试样本中,并且基于添加后的测试样本对该识别模型进行重新测试,以获得更新后的识别模型。
上述测试单元309是可选的部件。
在本实施例中,处理装置300还可包括图像取得单元310,该图像取得单元310取得包含第一价格信息的图像。并且,添加单元308还可从图像取得单元310获得该图像。
上述图像取得单元310是可选的部件。
上述各单元的功能可通过实施例1中所述的具体方式实现。此外,上述各单元可通过一个设备实现,也可通过多个设备实现,相应的具体实现方式可参见实施例1。此处不再赘述。
通过本实施例的价格信息的处理装置,能够自动识别价格信息并进行货币转换,操作简单,且避免了误操作,提升用户体验。
本说明书实施例还提供一种计算机可读程序,该计算机可读程序使得处理器执行实施例1所述的方法。
本说明书实施例还提供一种存储有计算机可读程序的存储介质,其中,存储有计算机可读程序的存储介质,该计算机可读程序使得处理器执行实施例1所述的方法。
结合本说明书实施例描述的价格信息的处理装置可直接体现为硬件、由处理器执行的软件模块或二者组合。例如,附图中所示的功能框图中的一个或多个和/或功能框图的一个或多个组合,既可以对应于计算机程序流程的各个软件模块,亦可以对应于各个硬件模块。这些软件模块,可以分别对应于附图所示的各个步骤。这些硬件模块例如可利用现场可编程门阵列(FPGA)将这些软件模块固化而实现。
软件模块可以位于RAM存储器、闪存、ROM存储器、EPROM存储器、EEPROM存储器、寄存器、硬盘、移动磁盘、CD-ROM或者本领域已知的任何其它形式的存储介质。可以将一种存储介质耦接至处理器,从而使处理器能够从该存储介质读取信息,且可向该存储介质写入信息;或者该存储介质可以是处理器的组成部分。处理器和存储介质可以位于ASIC中。该软件模块可以存储在电子设备的存储器中,也可以存储在可插入电子设备的存储卡中。例如,若电子设备(例如移动终端)采用的是较大容量的MEGA-SIM卡或者大容量的闪存装置,则该软件模块可存储在该MEGA-SIM卡或者大容量的闪存装置中。
针对图描述的功能框图中的一个或多个和/或功能框图的一个或多个组合,可以实现为用于执行本申请所描述功能的通用处理器、数字信号处理器(DSP)、专用集成电路(ASIC)、现场可编程门阵列(FPGA)或其它可编程逻辑器件、分立门或晶体管逻辑器件、分立硬件组件、或者其任意适当组合。针对附图描述的功能框图中的一个或多个和/或功能框图的一个或多个组合,还可以实现为计算设备的组合,例如,DSP和微处理器的组合、多个微处理器、与DSP通信结合的一个或多个微处理器或者任何其它这种配置。
此外,本说明书实施例的处理方法、处理装置可在单处理器环境中实现,也可在多处理器的环境中分布式地实现。
以上结合具体的实施方式对本发明进行了描述,但本领域技术人员应该清楚,这些描述都是示例性的,并不是对本发明保护范围的限制。本领域技术人员可以根据本发明的原理对本发明做出各种变型和修改,这些变型和修改也在本发明的范围内。

Claims (15)

  1. 一种价格信息的处理方法,所述方法包括:
    从包含与第一货币相关的第一价格信息的图像中识别所述第一价格信息;
    根据所述第一价格信息以及所述第一货币与预设的第二货币之间的转换关系,确定与所述第二货币相关的第二价格信息;以及
    显示所述第二价格信息。
  2. 根据权利要求1所述的方法,
    所述第一价格信息包括价格,或者,价格以及相应的折扣信息。
  3. 根据权利要求1所述的方法,所述方法还包括:
    获取用户的定位信息,根据所述定位信息确定所述第一货币,并基于确定的所述第一货币和预设的第二货币获取所述转换关系。
  4. 根据权利要求1所述的方法,所述方法还包括:
    使用训练样本训练用于识别所述第一价格信息的识别模型。
  5. 根据权利要求4所述的方法,
    所述识别模型为卷积神经网络模型。
  6. 根据权利要求4或5所述的方法,所述方法还包括:
    将所述图像添加到所述训练样本中,基于添加后的训练样本对所述识别模型进行重新训练,以获得更新后的识别模型。
  7. 根据权利要求4或5所述的方法,所述方法还包括:
    使用测试样本对所述识别模型进行测试,将所述图像添加到所述测试样本中,并且基于添加后的测试样本对所述识别模型进行重新测试,以获得更新后的识别模型。
  8. 一种价格信息的处理装置,所述装置包括:
    识别单元,其从包含与第一货币相关的第一价格信息的图像中识别所述第一价格信息;
    确定单元,其根据所述第一价格信息以及所述第一货币与预设的第二货币之间的转换关系,确定与所述第二货币相关的第二价格信息;以及
    显示单元,其显示所述第二价格信息。
  9. 根据权利要求8所述的装置,
    所述第一价格信息包括价格,或者,价格以及相应的折扣信息。
  10. 根据权利要求8所述的装置,所述装置还包括:
    定位单元,其获取用户的定位信息;
    货币确定单元,其根据所述定位信息确定所述第一货币;以及
    转换关系获取单元,基于确定的所述第一货币和预设的第二货币获取所述转换关系。
  11. 根据权利要求10所述的装置,所述装置还包括:
    训练单元,其使用训练样本训练用于识别所述第一价格信息的识别模型。
  12. 根据权利要求11所述的装置,
    所述识别模型为卷积神经网络模型。
  13. 根据权利要求11或12所述的装置,所述装置还包括:
    添加单元,其将所述图像添加到所述训练样本中,基于添加后的训练样本对所述识别模型进行重新训练,以获得更新后的识别模型。
  14. 根据权利要求11或12所述的装置,所述装置还包括:
    测试单元,其使用测试样本对所述识别模型进行测试,
    并且所述添加装置还将所述图像添加到所述测试样本中,并且基于添加后的测试样本对所述识别模型进行重新测试,以获得更新后的识别模型。
  15. 一种存储有计算机可读程序的存储介质,所述计算机可读程序使得处理器执行根据权利要求1至7中任一项所述的方法。
PCT/CN2019/077143 2018-05-31 2019-03-06 一种价格信息的处理方法、处理装置和存储介质 WO2019228005A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810549476.9 2018-05-31
CN201810549476.9A CN108921592A (zh) 2018-05-31 2018-05-31 一种价格信息的处理方法、处理装置和存储介质

Publications (1)

Publication Number Publication Date
WO2019228005A1 true WO2019228005A1 (zh) 2019-12-05

Family

ID=64410703

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/077143 WO2019228005A1 (zh) 2018-05-31 2019-03-06 一种价格信息的处理方法、处理装置和存储介质

Country Status (3)

Country Link
CN (1) CN108921592A (zh)
TW (1) TW202004609A (zh)
WO (1) WO2019228005A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108921592A (zh) * 2018-05-31 2018-11-30 阿里巴巴集团控股有限公司 一种价格信息的处理方法、处理装置和存储介质
CN113095898A (zh) * 2020-01-08 2021-07-09 阿里巴巴集团控股有限公司 一种处理方法、装置、设备和机器可读介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105989512A (zh) * 2015-02-10 2016-10-05 黄金富知识产权咨询(深圳)有限公司 一种商品销售系统和相应方法
CN107219920A (zh) * 2017-05-15 2017-09-29 北京小米移动软件有限公司 基于场景的ar眼镜识别方法、装置和ar眼镜
CN107292248A (zh) * 2017-06-05 2017-10-24 广州诚予国际市场信息研究有限公司 一种基于图像识别技术的商品管理方法及系统
CN107492185A (zh) * 2017-07-27 2017-12-19 上海青橙实业有限公司 基于移动终端的货币识别方法和装置
CN108921592A (zh) * 2018-05-31 2018-11-30 阿里巴巴集团控股有限公司 一种价格信息的处理方法、处理装置和存储介质

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105279235A (zh) * 2015-09-25 2016-01-27 联想(北京)有限公司 一种显示方法及电子设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105989512A (zh) * 2015-02-10 2016-10-05 黄金富知识产权咨询(深圳)有限公司 一种商品销售系统和相应方法
CN107219920A (zh) * 2017-05-15 2017-09-29 北京小米移动软件有限公司 基于场景的ar眼镜识别方法、装置和ar眼镜
CN107292248A (zh) * 2017-06-05 2017-10-24 广州诚予国际市场信息研究有限公司 一种基于图像识别技术的商品管理方法及系统
CN107492185A (zh) * 2017-07-27 2017-12-19 上海青橙实业有限公司 基于移动终端的货币识别方法和装置
CN108921592A (zh) * 2018-05-31 2018-11-30 阿里巴巴集团控股有限公司 一种价格信息的处理方法、处理装置和存储介质

Also Published As

Publication number Publication date
CN108921592A (zh) 2018-11-30
TW202004609A (zh) 2020-01-16

Similar Documents

Publication Publication Date Title
US11610394B2 (en) Neural network model training method and apparatus, living body detecting method and apparatus, device and storage medium
US10936672B2 (en) Automatic document negotiation
US20220012488A1 (en) Receipt identification method, apparatus, electronic device and computer-readable storage medium
CN109800320B (zh) 一种图像处理方法、设备及计算机可读存储介质
US11373251B1 (en) System and method to augment electronic documents with externally produced metadata to improve processing
CN105338148B (zh) 一种根据频域能量对音频信号进行检测的方法和装置
US20170103397A1 (en) Video identification method and computer program product thereof
CN112396054A (zh) 文本提取方法、装置、电子设备及存储介质
US9292579B2 (en) Method and system for document data extraction template management
US20140330566A1 (en) Providing social-graph content based on a voice print
WO2017114167A1 (zh) 终端真伪验证方法、装置及系统
CN112233690B (zh) 双录方法、装置、终端及存储介质
WO2019228005A1 (zh) 一种价格信息的处理方法、处理装置和存储介质
WO2020024714A1 (zh) 医保结算方法及装置和电子设备
WO2020057305A1 (zh) 一种风险商户发现方法和装置
JP2019536122A (ja) 情報インタラクションのための方法および装置
CN104780282A (zh) 对电话会议中的发言内容进行分类的方法和设备
CN107992484A (zh) 一种评测ocr系统的性能的方法、设备及存储介质
Liang Subjective norms and customer adoption of mobile banking: Taiwan and Vietnam
CN107205095A (zh) 语音信息的播放方法、装置及终端
CN107391543B (zh) 一种无线热点的类型识别方法和装置
CN112183417A (zh) 一种置业顾问服务能力评价系统及方法
CN109409875B (zh) 一种账单校验方法、装置及电子设备
US8654942B1 (en) Multi-device video communication session
WO2017045312A1 (zh) 办卡数据处理方法及装置

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: 19811834

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: 19811834

Country of ref document: EP

Kind code of ref document: A1