WO2019114425A1 - 一种数据处理的方法、装置及设备 - Google Patents

一种数据处理的方法、装置及设备 Download PDF

Info

Publication number
WO2019114425A1
WO2019114425A1 PCT/CN2018/111852 CN2018111852W WO2019114425A1 WO 2019114425 A1 WO2019114425 A1 WO 2019114425A1 CN 2018111852 W CN2018111852 W CN 2018111852W WO 2019114425 A1 WO2019114425 A1 WO 2019114425A1
Authority
WO
WIPO (PCT)
Prior art keywords
merchant
carbon
image
identified
user
Prior art date
Application number
PCT/CN2018/111852
Other languages
English (en)
French (fr)
Inventor
管维刚
邓翔
王康
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
Priority to SG11202001210YA priority Critical patent/SG11202001210YA/en
Publication of WO2019114425A1 publication Critical patent/WO2019114425A1/zh
Priority to US16/805,525 priority patent/US10878239B2/en
Priority to US17/135,988 priority patent/US11106909B2/en

Links

Images

Classifications

    • 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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
    • G06Q30/0208—Trade or exchange of goods or services in exchange for incentives or rewards
    • 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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
    • G06Q30/0217—Discounts or incentives, e.g. coupons or rebates involving input on products or services in exchange for incentives or rewards
    • 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
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements

Definitions

  • the present specification relates to the field of computer technology, and in particular, to a method, device and device for data processing.
  • Carbon emissions are a general term or abbreviation for greenhouse gas emissions. People's daily lives may directly or indirectly contribute to carbon emissions, such as automobile exhaust emissions, thermal power generation, and the use of disposable goods. As carbon emissions increase, the level of damage to the environment in which people live depends on it.
  • the present specification provides a data processing method for solving the problem that the carbon saving amount cannot be effectively quantified in the prior art.
  • This specification provides a method of data processing, including:
  • a value characterizing the carbon savings of the merchant is determined.
  • the present specification provides a data processing device for solving the problem that the carbon saving amount cannot be effectively quantified in the prior art.
  • This specification provides a device for data processing, including:
  • Obtaining a module acquiring an image to be recognized sent by a user, where the image to be identified is collected by the user for a merchant;
  • the identification module identifies the image to be identified by a pre-trained image recognition model to determine a carbon saving behavior of the merchant
  • a determining module determines a value indicative of a carbon saving amount of the merchant based on the carbon saving behavior.
  • the present specification provides a data processing device for solving the problem that the carbon saving amount in the prior art cannot be effectively quantified.
  • the present specification provides a data processing apparatus comprising one or more memories and a processor that stores a program and is configured to perform the following steps by the one or more processors:
  • a value characterizing the carbon savings of the merchant is determined.
  • the present specification provides a data processing method for solving the problem that the carbon saving amount cannot be effectively quantified in the prior art.
  • This specification provides a method of data processing, including:
  • the present specification provides a data processing device for solving the problem that the carbon saving amount cannot be effectively quantified in the prior art.
  • This specification provides a device for data processing, including:
  • An acquisition module collects an image to be identified for the merchant
  • Transmitting module sending the to-be-identified image to a server, so that the server identifies the to-be-identified image by using a pre-trained image recognition model to identify the carbon-saving behavior of the merchant, and according to the carbon-saving behavior And determining a value that characterizes the carbon savings of the merchant.
  • the present specification provides a data processing device for solving the problem that the carbon saving amount in the prior art cannot be effectively quantified.
  • the present specification provides a data processing apparatus comprising one or more memories and a processor that stores a program and is configured to perform the following steps by the one or more processors:
  • the image to be identified may be identified by a pre-trained image recognition model to identify the carbon saving behavior of the merchant. And determining a value indicative of the carbon savings of the merchant based on the identified carbon saving behavior.
  • the carbon saving behavior of the merchant can be identified based on the image to be identified collected by the user for the merchant, thereby effectively quantizing the carbon saving amount of the merchant according to the carbon saving behavior of the identified merchant, and therefore, based on the carbon saving
  • the quantified value allows the merchant to understand its actual carbon saving situation and effectively carry out the subsequent carbon saving work based on the actual carbon saving situation, which can bring about the energy saving and emission reduction work of the society. positive influence.
  • Figure 1 is a schematic diagram of a data processing process provided by the present specification
  • FIG. 2 is a schematic diagram of a user performing image collection on a merchant provided by the present specification
  • FIG. 3 is a schematic diagram of the entire data processing process provided by the present specification.
  • FIG. 4 is a schematic diagram of a device for data processing provided by the present specification.
  • FIG. 5 is a schematic diagram of a device for data processing provided by the present specification.
  • FIG. 6 is a schematic diagram of a device for data processing provided by the present specification.
  • FIG. 7 is a schematic diagram of a device for data processing provided by the present specification.
  • the user can collect the image of the merchant and send the collected image to the server through the terminal, so that the server quantifies the carbon saving behavior implemented by the merchant based on the image sent by the user.
  • the information related to the carbon saving behavior of the merchant included in the image may be collected by the user actively for the carbon saving behavior of the merchant, or may be in the process of collecting other information when the user is active in the merchant.
  • items related to the carbon saving behavior implemented by the merchant are collected. For example, when a user eats in a merchant, non-disposable chopsticks are collected during the process of photographing the dishes.
  • the non-disposable chopsticks mentioned here are items related to the carbon-saving behavior implemented by the merchant.
  • the user can quantify the carbon saving behavior of the merchant through the image collected by the user, which can effectively avoid the merchant to improve the festival. The possibility of falsification of the quantified value of carbon behavior.
  • the execution subject that quantifies the carbon saving amount of the merchant may be a device such as a terminal or a server.
  • a device such as a terminal or a server.
  • the server will be described as an example.
  • FIG. 1 is a schematic diagram of a data processing process provided by the present specification, specifically including the following steps:
  • S100 Acquire an image to be recognized sent by a user.
  • the user can perform image collection on the merchant, obtain the image to be identified, and send the image to be identified to the server, and the server can identify the acquired image to be identified.
  • the image to be identified mentioned herein may be an image collected by the user and containing information related to the carbon saving behavior of the merchant.
  • the image to be identified may be in the form of a video or a picture.
  • the carbon-saving behavior mentioned here can be divided into two categories. One category refers to the positive behavior of the merchants to promote carbon saving, such as not using disposable tableware and using environmentally-friendly furniture. The other type refers to the merchants taking such use once. Tableware, excessive coal burning, etc. do not promote the negative behavior of carbon saving.
  • the image acquisition by the user for the carbon saving behavior of the merchant can be as shown in FIG. 2 .
  • FIG. 2 is a schematic diagram of a user performing image collection on a merchant provided by the present specification.
  • the user can collect the non-disposable tableware provided by the merchant through the held mobile phone, and obtain the image to be recognized, and The image to be identified is sent to the server for identification.
  • S102 Identify, by the pre-trained image recognition model, the image to be identified to identify the carbon saving behavior of the merchant.
  • the server may identify the image to be identified through a pre-trained image recognition model.
  • the image recognition model can be obtained manually based on a large number of collected training samples.
  • the image recognition model mentioned here can adopt a common recognition algorithm such as MobileNet, Faster RCNN, and the recognition algorithm used here. Not limited.
  • the server can identify the carbon saving behavior of the merchant from the acquired image to be identified through the image recognition model.
  • Class behavior For example, when the server recognizes the existence of the chopstick sterilizer from the image to be recognized sent by the user through the pre-trained image recognition model, it can be determined that the carbon-saving behavior of the merchant belongs to the positive behavior of promoting carbon saving.
  • the server determines which type of behavior the merchant's carbon saving behavior belongs to, and can also determine the specific form of the carbon saving behavior implemented by the merchant. For example, when the server identifies the energy saving lamp from the image to be identified through the image recognition model, it may be determined that the specific form of the carbon saving behavior of the restaurant is the positive behavior of using the energy saving lamp; when the server passes the image recognition model, the server When the chopsticks sterilizer is identified in the image to be identified, the specific form of the carbon saving behavior of the restaurant may be determined to provide positive behavior for providing non-disposable chopsticks (because, in general, the restaurant uses a chopstick sterilizer to indicate the catering The store offers non-disposable chopsticks, while the provision of non-disposable chopsticks indicates that the restaurant has increased carbon savings.
  • the server when the server identifies the bamboo furniture from the image to be identified through the image recognition model, it can be determined that the specific form of the carbon-saving behavior of the merchant is the positive behavior of using bamboo furniture (generally, the growth rate of the bamboo) Compared with trees, it is faster, so the use of bamboo furniture can reduce the deforestation of trees, and the reduction of tree felling increases the absorption of greenhouse gases by trees, thereby increasing the carbon savings from the side.
  • the marking prompt may be sent to the user to enable the user to send the image to be recognized. Mark it.
  • the server can determine the carbon saving behavior of the merchant according to the tag information sent by the user.
  • the user performs image acquisition on the chopstick sterilizer and sends the obtained image to be recognized to the server.
  • the server cannot identify the carbon saving behavior of the merchant from the image to be recognized through the pre-trained image recognition model, the user may send a mark prompt to the user, and after the user views the mark prompt sent by the server, the chopstick disinfection machine may be used.
  • the tag information is sent to the server through the terminal, so that the server determines the carbon-saving behavior of the merchant according to the tag information (the type of behavior of the merchant's carbon-saving behavior, and the specific form of the carbon-saving behavior, etc.).
  • the server receives the tag information sent by the user as: a disposable chopstick, it can be determined that the merchant's carbon saving behavior is a negative behavior that does not promote carbon saving, and the specific form is to use disposable tableware.
  • the above image recognition models are usually pre-trained by a large number of training samples, which are usually manually labeled. Therefore, if the image recognition model needs to be further adjusted later, it is necessary to manually identify some training samples by manual labeling, thereby adjusting the image recognition model through the training samples, which is extremely labor intensive. At the same time, the efficiency of model training is reduced.
  • the image recognition model can be trained by using the marker information sent by the user, it is equivalent to the marking work of the training sample by the user, so that the recognition ability of the image recognition model is continuously improved, and the image recognition model is also greatly improved.
  • the labor cost of training the image recognition model is reduced, and the efficiency of model training is improved.
  • S104 Determine, according to the carbon saving behavior, a value that represents the carbon saving amount of the merchant.
  • the server After the server determines the carbon saving behavior of the merchant, it can determine the value of the carbon saving amount that matches the carbon behavior of the merchant. Wherein, when the carbon saving behavior of the merchant belongs to the positive behavior of promoting carbon saving, the value of the carbon saving amount of the merchant may be positive, and when the carbon saving behavior of the merchant belongs to a negative behavior that does not promote carbon saving , the value that indicates the merchant's carbon savings can be negative.
  • the value of the carbon saving amount characterizing the merchant may be in the form of an integral, that is, the server may determine the carbon reduction score representing the carbon saving amount of the merchant according to the carbon saving behavior of the merchant.
  • the server may add the determined carbon savings credit to the merchant's carbon savings account.
  • the carbon savings account mentioned here can be opened in advance by the merchant.
  • the merchant can submit its own merchant information to the server in advance for applying for opening the carbon saving account, and the server can review the merchant information submitted by the merchant, and after determining that the merchant information submitted by the merchant passes the audit, the merchant Open a carbon savings account.
  • the server may further determine the behavior category of the merchant's carbon saving behavior, and then add the carbon saving credit corresponding to the behavior category to the carbon saving account of the merchant. For example, if the server determines that the carbon saving behavior of the merchant belongs to the positive behavior of promoting carbon saving according to the identified carbon saving behavior, the carbon credit corresponding to the positive behavior may be added to the carbon saving account of the merchant, and When it is determined that the carbon saving behavior of the merchant belongs to a negative behavior that does not promote carbon saving, the carbon saving credit corresponding to the negative behavior may be deducted from the carbon saving account of the merchant.
  • the server may also add a carbon credit that matches the specific form to the carbon saving account of the merchant according to the specific form of the carbon behavior after determining the carbon saving behavior of the merchant.
  • different carbon savings points can be corresponding, and merchants can adopt different forms of carbon saving behavior to obtain different carbon savings points.
  • the server determines that the specific form of the carbon saving behavior of the merchant is to use the chopstick sterilizer, the carbon credit score corresponding to the form may be added to the carbon saving account of the merchant.
  • the server determines that the specific form of the carbon saving behavior of the merchant is to use disposable tableware, the carbon credit of the form corresponding to the form may be deducted from the carbon saving account of the merchant.
  • the server may also determine the carbon saving credit of the carbon saving account that needs to be added to the merchant through the specific form, the preset algorithm, and other information.
  • the other information mentioned here may refer to the credit rating of the user, the number of favorable carbon ratings received by the merchant, etc., wherein when the server determines the carbon saving behavior of the merchant based on the image to be identified sent by the user, it is positive for promoting carbon saving. When acting, it can be counted as a carbon-saving praise received by the merchant.
  • the server can also determine the carbon credits by other means, and add the carbon credits to the merchant's carbon savings account, which will not be exemplified here.
  • the server adds the determined carbon saving credit to the carbon saving account of the merchant, and may also determine the contribution of the user who sends the image to be identified, and then add the contribution and/or the contribution to the user's account.
  • the virtual item corresponding to the degree is issued to the user.
  • the server can determine the contribution of the user in a variety of ways. For example, positive carbon saving behaviors may include multiple specific forms, and different specific forms correspond to different contributions. Therefore, the server may determine the corresponding contribution according to the specific form of the determined carbon saving behavior; or according to the user's Credit rating to determine the corresponding contribution. Of course, the server can also determine the contribution of the user in other ways, and will not be exemplified here.
  • the server may issue the coupon to the user, or may issue the VIP permission of some services to the user according to the time limit.
  • the server can provide a number of convenient services to the merchant according to the carbon-saving points in the merchant's carbon-saving account. For example, when the server determines that the carbon saving credit in the merchant's carbon saving account exceeds the set point or reaches the set ranking, the information of the merchant may be displayed in the merchant recommendation homepage to further promote the merchant. For another example, when it is determined that the carbon saving credit in the merchant's carbon saving account exceeds the set credit, the merchant's loan amount may be increased. Of course, there are still a lot of convenient services provided by the server to merchants based on the merchant's carbon credits, so I won't give examples here.
  • the carbon saving behavior of the merchant can be identified based on the image to be identified collected by the user for the merchant, the carbon saving amount of the merchant is effectively determined according to the carbon saving behavior of the identified merchant. Quantitative, therefore, based on the value quantified for carbon savings, the merchant can understand his actual carbon savings, and based on the actual carbon savings learned, the subsequent carbon-saving work can be carried out effectively, and thus can be a society.
  • the energy saving and emission reduction work has brought about a positive impact.
  • the server can use the tag information sent by the user and the image to be recognized that does not recognize the carbon saving behavior to train and adjust the image recognition model, thereby greatly reducing the labor cost for training the image recognition model and improving The efficiency of model training.
  • the server can provide convenience services for the merchant according to the carbon-saving points in the merchant's carbon-saving account, therefore, with the carbon-saving accounts in each
  • the popularity of merchants and the incentives brought about by carbon credits in carbon-saving accounts can further promote positive carbon-saving behaviors to be more effectively promoted, thus having a more positive impact on the environment on which people depend. .
  • the server since the server needs to quantify the carbon saving amount of the merchant according to the image to be recognized sent by the user, the server needs to determine the to-be-identified after receiving the image to be recognized sent by the user through the step S100 shown in FIG. Which merchant the image belongs to, and then based on the image to be identified, determines the value that represents the carbon savings of the merchant.
  • the server determines the merchant corresponding to the image to be identified above. For example, when the user evaluates the merchant through the mobile phone, the collected image to be identified may be sent to the server through the evaluation page of the merchant, so that the server adds the determined carbon credit score to the user evaluation according to the image to be identified. In the merchant's carbon savings account.
  • the collected image to be recognized may be sent to the server.
  • the server may add the carbon saving credit corresponding to the carbon saving behavior to the carbon saving account of the receiving merchant when the user settles according to the carbon saving behavior identified from the image to be identified.
  • the terminal when collecting the carbon saving behavior of the merchant, the terminal may determine the location information on which the carbon saving behavior is collected, and then send the collected image to be identified and the determined location information to the server, and the server may be based on The carbon credit score determined by the image to be identified is added to the carbon saving account of the merchant corresponding to the location information.
  • the merchants corresponding to the above-mentioned image to be identified may also be determined by other means, and are not illustrated here.
  • the terminal may send the collected image to be identified, the merchant identifier, and the location information on which the image to be identified is collected to the server, and the server may determine where the merchant corresponding to the merchant identifier is located.
  • the server may determine where the merchant corresponding to the merchant identifier is located.
  • the purpose of this move is that some merchants may collect fraudulent images from other images that are not related to themselves (such as collecting images of other merchants to be identified). It can be seen from the above method that even if some merchants collect fraudulent image recognition frauds of other merchants, the server adds the determined carbon credits to the location information based on the location information on which the image to be identified is collected. Corresponding merchants' carbon savings accounts, thus effectively reducing the possibility of merchants implementing fraud.
  • the server since the above-mentioned tag information obtained by the server is subjectively obtained by the user, this causes the server to determine the carbon saving behavior of the merchant through the tag information, and the server may have an error according to the incorrect tag information. Determining the carbon-saving behavior and determining the value of the carbon-saving amount that characterizes the merchant may cause losses to the merchant or other merchants.
  • the server when the server needs to determine the carbon saving behavior of the merchant according to the marking information sent by the user, the reference value corresponding to the carbon saving behavior may be multiplied and determined.
  • the trust factor is determined and the product of the two is determined as the value that characterizes the merchant's carbon savings.
  • the server can determine the trust coefficient in many ways. For example, different carbon-saving behaviors (or different specific forms of carbon-saving behavior) can correspond to different trust factors.
  • the server may determine a corresponding trust coefficient according to the determined carbon saving behavior of the merchant (or a specific form of the carbon saving behavior), and then determine the carbon saving character of the merchant according to the trust coefficient and the reference value corresponding to the carbon behavior. The value of the quantity.
  • the trust factor mentioned here can be determined manually. For those images that the server cannot identify the carbon-saving behavior (or the specific form of carbon-saving behavior) through the image recognition model, the server administrator can send according to the user first. Marking information to determine the carbon-saving behavior (or the specific form of carbon-saving behavior) that the user has marked for these images to be identified, and then, for the different carbon-saving behaviors marked by the user (different specific forms of carbon-saving behavior), Manually identifying the image to be identified corresponding to the carbon behavior (or the specific form) to determine the accuracy rate of the user marking the carbon saving behavior (or the specific form), and determining the accuracy according to the determined accuracy rate.
  • the server can determine the trust coefficient based on the determined carbon saving behavior (or the specific form of the carbon saving behavior), and can also determine the trust coefficient according to the user information of the user and/or the merchant information of the merchant.
  • the user information mentioned here and the merchant information of the merchant may refer to the credit rating of the user or the merchant, and the existing carbon credits in the carbon saving account.
  • FIG. 3 is a schematic diagram of the entire data processing process provided by the present specification.
  • the user can obtain a certain reward by performing image collection on the carbon saving behavior implemented by the merchant, and the merchant can obtain a certain carbon credit by the user to collect the image to be recognized for the merchant. Therefore, through this kind of incentive mechanism, more merchants can be encouraged to implement positive carbon-saving behaviors, thus forming a benign cycle, which will have a positive impact on energy conservation and emission reduction in the whole society.
  • the data processing method provided by one or more embodiments of the present specification is based on the same idea, and the present specification further provides a corresponding data processing device, as shown in FIGS. 4 and 5.
  • FIG. 4 is a schematic diagram of a device for data processing provided by the present specification, specifically including:
  • the obtaining module 401 is configured to acquire an image to be identified sent by the user, where the image to be identified is collected by the user for a merchant;
  • the identification module 402 identifies the image to be identified by using a pre-trained image recognition model to determine a carbon saving behavior of the merchant;
  • the determining module 403 determines a value representative of the carbon saving amount of the merchant according to the carbon saving behavior.
  • the device also includes:
  • the receiving module 404 when the carbon saving behavior of the merchant is not recognized from the image to be recognized by the image recognition model, receiving the marking information corresponding to the image to be recognized sent by the user, the marking information Including a carbon saving behavior of the merchant marked by the user for the image to be identified;
  • the determining module 403 determines, according to the received tag information, a value that represents the carbon saving amount of the merchant.
  • the determining module 403 is configured to determine a carbon saving behavior included in the marking information, determine a reference value corresponding to the carbon saving behavior, and determine a value representing a carbon saving amount of the merchant according to a product of the reference value and a trust coefficient .
  • the device also includes:
  • the adjustment module 405 adjusts the image recognition model according to the image to be recognized and the mark information.
  • the determining module 403 determines a contribution degree of the user; provides the virtual item corresponding to the contribution degree to the user, and/or adds the contribution degree to an account of the user.
  • a value indicative of the carbon savings of the merchant includes: a carbon savings integral that characterizes the carbon savings of the merchant;
  • the device also includes:
  • Adding module 406 adds the carbon savings credit to the merchant's carbon savings account.
  • FIG. 5 is a schematic diagram of a device for data processing provided by the present specification, specifically including:
  • the collecting module 501 collects an image of the merchant as an image to be identified
  • the sending module 502 is configured to send the to-be-identified image to the server, so that the server identifies the carbon-saving behavior of the merchant from the to-be-identified image through a pre-trained image recognition model, and determines according to the carbon-saving behavior A value that characterizes the carbon savings of the merchant.
  • the device also includes:
  • the receiving module 503 is configured to receive a mark prompt sent by the server, where the mark prompt is sent to the user when the server does not identify the carbon saving behavior of the merchant from the image to be identified by using the image recognition model;
  • the sending module 502 receives the marking information input by the user according to the marking prompt, and sends the marking information to the server, so that the server determines the carbon saving of the merchant according to the marking information. behavior.
  • the present specification also provides a device for data processing, as shown in FIG.
  • the device includes one or more memories and a processor that stores the program and is configured to perform the following steps by the one or more processors:
  • a value characterizing the carbon savings of the merchant is determined.
  • the present specification also provides a device for data processing, as shown in FIG.
  • the device includes one or more memories and a processor that stores the program and is configured to perform the following steps by the one or more processors:
  • the image to be identified may be identified by a pre-trained image recognition model to identify the carbon saving of the merchant. Behavior, and based on the identified carbon-saving behavior, determine the value of the carbon savings that characterize the merchant.
  • the carbon saving behavior of the merchant can be identified based on the image to be identified collected by the user for the merchant, thereby effectively quantizing the carbon saving amount of the merchant according to the carbon saving behavior of the identified merchant, and therefore, based on the carbon saving
  • the quantified value allows the merchant to understand its actual carbon saving situation and effectively carry out the subsequent carbon saving work based on the actual carbon saving situation, which can bring about the energy saving and emission reduction work of the society. positive influence.
  • PLD Programmable Logic Device
  • FPGA Field Programmable Gate Array
  • HDL Hardware Description Language
  • the controller can be implemented in any suitable manner, for example, the controller can take the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (eg, software or firmware) executable by the (micro)processor.
  • computer readable program code eg, software or firmware
  • examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, The Microchip PIC18F26K20 and the Silicone Labs C8051F320, the memory controller can also be implemented as part of the memory's control logic.
  • the controller can be logically programmed by means of logic gates, switches, ASICs, programmable logic controllers, and embedding.
  • Such a controller can therefore be considered a hardware component, and the means for implementing various functions included therein can also be considered as a structure within the hardware component.
  • a device for implementing various functions can be considered as a software module that can be both a method of implementation and a structure within a hardware component.
  • the system, device, module or unit illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product having a certain function.
  • a typical implementation device is a computer.
  • the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or A combination of any of these devices.
  • embodiments of the present specification can be provided as a method, system, or computer program product. Accordingly, the description may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment in combination of software and hardware. Moreover, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
  • computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.
  • a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
  • processors CPUs
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • the memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory.
  • RAM random access memory
  • ROM read only memory
  • Memory is an example of a computer readable medium.
  • Computer readable media includes both permanent and non-persistent, removable and non-removable media.
  • Information storage can be implemented by any method or technology.
  • the information can be computer readable instructions, data structures, modules of programs, or other data.
  • Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory. (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disk read only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, Magnetic tape cartridges, magnetic tape storage or other magnetic storage devices or any other non-transportable media can be used to store information that can be accessed by a computing device.
  • computer readable media does not include temporary storage of computer readable media, such as modulated data signals and carrier waves.
  • program modules include routines, programs, objects, components, data structures, and the like that perform particular tasks or implement particular abstract data types.
  • One or more embodiments of the present specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are connected through a communication network.
  • program modules can be located in both local and remote computer storage media including storage devices.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Multimedia (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Tourism & Hospitality (AREA)
  • Educational Administration (AREA)
  • Human Resources & Organizations (AREA)
  • Primary Health Care (AREA)
  • Image Analysis (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本说明书公开一种数据处理的方法、装置及设备，该方法中在获取到用户针对商户采集到的待识别图像后，可以通过预先训练的图像识别模型，对该待识别图像进行识别，以识别该商户的节碳行为，并根据识别出的节碳行为，确定表征该商户的节碳量的值。

Description

一种数据处理的方法、装置及设备 技术领域
本说明书涉及计算机技术领域，尤其涉及一种数据处理的方法、装置及设备。
背景技术
碳排放，是关于温室气体排放的一个总称或简称。人们的日常生活都可能直接或间接的促使碳排放的发生，如汽车尾气排放、火力发电、一次性商品的使用等。随着碳排放的日益加剧，人们赖以生存的环境的破坏程度也在逐渐增加。
当前，人们正通过多种途径减少碳排放的发生，如，研发并推广更为清洁的电动汽车，建设更多的风力、水力发电站，制造并使用更为环保的消耗品等。然而，目前并没有有效的节碳量量化准则，使人们对自己实际生活中的节碳情况进行了解，进而也就无法基于实际生活中的节碳情况对后续的节碳工作进行更为有效的开展。
基于此，如何对人们的日常生活中的节碳量进行有效量化则是一个亟待解决的问题。
发明内容
本说明书提供一种数据处理的方法，用以解决现有技术中节碳量无法有效量化的问题。
本说明书提供了一种数据处理的方法，包括：
获取用户发送的待识别图像，所述待识别图像是所述用户针对商户采集的；
通过预先训练的图像识别模型，对所述待识别图像进行识别，以识别所述商户的节碳行为；
根据所述节碳行为，确定表征所述商户的节碳量的值。
本说明书提供一种数据处理的装置，用以解决现有技术中节碳量无法有效量化的问题。
本说明书提供了一种数据处理的装置，包括：
获取模块，获取用户发送的待识别图像，所述待识别图像是所述用户针对商户采集 的；
识别模块，通过预先训练的图像识别模型，对所述待识别图像进行识别，以确定商户的节碳行为；
确定模块，根据所述节碳行为，确定表征所述商户的节碳量的值。
本说明书提供一种数据处理的设备，用以解决现有技术中节碳量无法有效量化的问题。
本说明书提供了一种数据处理的设备，包括一个或多个存储器以及处理器，所述存储器存储程序，并且被配置成由所述一个或多个处理器执行以下步骤：
获取用户发送的待识别图像，所述待识别图像是所述用户针对商户采集的；
通过预先训练的图像识别模型，对所述待识别图像进行识别，以识别所述商户的节碳行为；
根据所述节碳行为，确定表征所述商户的节碳量的值。
本说明书提供一种数据处理的方法，用以解决现有技术中节碳量无法有效量化的问题。
本说明书提供了一种数据处理的方法，包括：
采集针对商户的待识别图像；
将所述待识别图像发送给服务器，以使服务器通过预先训练的图像识别模型，对所述待识别图像进行识别，以识别所述商户的节碳行为，并根据所述节碳行为，确定表征所述商户的节碳量的值。
本说明书提供一种数据处理的装置，用以解决现有技术中节碳量无法有效量化的问题。
本说明书提供了一种数据处理的装置，包括：
采集模块，采集针对商户的待识别图像；
发送模块，将所述待识别图像发送给服务器，以使服务器通过预先训练的图像识别模型，对所述待识别图像进行识别，以识别所述商户的节碳行为，并根据所述节碳行为，确定表征所述商户的节碳量的值。
本说明书提供一种数据处理的设备，用以解决现有技术中节碳量无法有效量化的问 题。
本说明书提供了一种数据处理的设备，包括一个或多个存储器以及处理器，所述存储器存储程序，并且被配置成由所述一个或多个处理器执行以下步骤：
采集针对商户的待识别图像；
将所述待识别图像发送给服务器，以使服务器通过预先训练的图像识别模型，对所述待识别图像进行识别，以识别所述商户的节碳行为，并根据所述节碳行为，确定表征所述商户的节碳量的值。
本说明书采用的上述至少一个技术方案能够达到以下有益效果：
在本说明书一个或多个实施例中，在获取到用户针对商户采集到的待识别图像后，可以通过预先训练的图像识别模型，对该待识别图像进行识别，以识别该商户的节碳行为，并根据识别出的节碳行为，确定表征该商户的节碳量的值。
由于可以基于用户针对商户采集的待识别图像，对商户的节碳行为进行识别，从而根据识别出的商户的节碳行为，对该商户的节碳量进行有效的量化，因此，基于针对节碳量所量化出的值，可使商户了解自身的实际节碳情况，并基于了解到的实际节碳情况对后续的节碳工作进行有效的开展，进而可为社会的节能减排工作带来了积极的影响。
附图说明
此处所说明的附图用来提供对本说明书的进一步理解，构成本说明书的一部分，本说明书的示意性实施例及其说明用于解释本说明书，并不构成对本说明书的不当限定。在附图中：
图1为本说明书提供的数据处理过程的示意图；
图2为本说明书提供的用户对商户进行图像采集的示意图；
图3为本说明书提供的整个数据处理过程的示意图；
图4为本说明书提供的一种数据处理的装置示意图；
图5为本说明书提供的一种数据处理的装置示意图；
图6为本说明书提供的一种数据处理的设备示意图；
图7为本说明书提供的一种数据处理的设备示意图。
具体实施方式
本说明书中，用户可以采集商户的图像，并将采集到的图像通过终端发送给服务器，以使服务器基于用户发送的图像，对商户实施的节碳行为进行量化。其中，该图像中包括的与该商户的节碳行为相关的信息，可以是用户主动针对该商户的节碳行为进行采集的，也可以是用户在该商户中活动时，采集其他信息的过程中顺带采集到了与该商户实施的节碳行为相关的物品。例如，用户在商户中就餐时，拍摄菜肴的过程中采集到了非一次性筷子，这里提到的非一次性筷子即是与商户实施的节碳行为相关的物品。
由于用户通过欺诈的手段，主动帮助商户提高节碳行为的量化值的动机较小，所以，通过用户针对商户采集到的图像对商户的节碳行为进行量化，可以有效的避免商户为提高自身节碳行为的量化值而进行作假的可能。
在本说明书中，对商户的节碳量进行量化的执行主体可以是终端、服务器等设备，为了方便对本说明书提供的数据处理方法进行说明，下面将仅以服务器为例进行描述。
为了使本技术领域的人员更好地理解本说明书一个或多个实施例中的技术方案，下面将结合本说明书一个或多个实施例中的附图，对本说明书一个或多个实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本说明书一部分实施例，而不是全部的实施例。基于本说明书中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都应当属于本说明书保护的范围。
图1为本说明书提供的数据处理过程的示意图，具体包括以下步骤：
S100：获取用户发送的待识别图像。
在本说明书中，用户可以对商户进行图像采集，得到待识别图像，并将该待识别图像发送给服务器，服务器可以对获取到的待识别图像进行识别。其中，这里提到的待识别图像可以是指用户采集到的，包含商户的节碳行为相关信息的图像，该待识别图像的形式可以是视频形式的，也可以是图片形式的。而这里提到的节碳行为可以分为两类，一类是指商户采取了诸如不使用一次性餐具、使用环保家具等促进节碳的积极行为，另一类是指商户采取了诸如使用一次性餐具、过度燃煤等不促进节碳的消极行为。而用户针对商户的节碳行为进行图像采集可以如图2所示。
图2为本说明书提供的用户对商户进行图像采集的示意图。
假设，用户在商户中就餐时，发现商户提供的餐具均为非一次性餐具，则该用户可 以通过持有的手机对该商户所提供的非一次性餐具进行图像采集，得到待识别图像，并将该待识别图像发送给服务器进行识别。
S102：通过预先训练的图像识别模型，对所述待识别图像进行识别，以识别所述商户的节碳行为。
服务器在获取到用户通过终端发送的待识别图像后，可以通过预先训练的图像识别模型，对该待识别图像进行识别。其中，该图像识别模型可以通过人工的方式，基于采集到的大量训练样本得到的，这里提到的图像识别模型可以采用诸如MobileNet、Faster RCNN等常用的识别算法，在此对所采用的识别算法不作限定。
通过上述步骤S100可知，商户的节碳行为可以分为两类，因此，在本说明书中，服务器可以通过该图像识别模型，从获取到的待识别图像中识别出商户的节碳行为具体属于哪类行为。例如，当服务器通过预先训练的图像识别模型，从用户发送的待识别图像中识别出存在筷子消毒机时，则可以确定商户的节碳行为属于促进节碳的积极行为。
服务器除了可以通过用户发送的待识别图像，确定出商户的节碳行为属于哪类行为之外，还可以确定出该商户实施的节碳行为的具体形式。例如，服务器通过该图像识别模型，从待识别图像中识别出节能灯时，可以确定出餐饮店实施节碳行为的具体形式为使用节能灯的积极行为；当服务器通过该图像识别模型，从该待识别图像中识别出筷子消毒机时，则可以确定出该餐饮店实施节碳行为的具体形式为提供非一次性筷子的积极行为(因为一般来说，餐饮店使用筷子消毒机能够表明该餐饮店提供的是非一次性筷子，而提供非一次性筷子则表明该餐饮店提高了节碳量)。
再例如，服务器通过该图像识别模型，从待识别图像中识别出竹制家具时，则可以确定商户实施节碳行为的具体形式为使用竹制家具的积极行为(一般来说，竹子的生长速度相比于树木来说较快，所以，使用竹子家具可以降低树木的砍伐，树木砍伐量降低则提高了树木对温室气体的吸收量，进而从侧面提高了节碳量)。
在本说明书中，若服务器通过预先训练的图像识别模型，无法从获取到的待识别图像中识别出商户的节碳行为时，则可以向用户发送标记提示，以使用户对发送的待识别图像进行标记。而服务器则可以根据用户发送的标记信息，确定该商户的节碳行为。
例如，假设用户对筷子消毒机进行图像采集，并将得到的待识别图像发送到服务器。而若服务器无法通过预先训练的图像识别模型，从该待识别图像中识别出商户的节碳行为时，则可以向用户发送标记提示，用户查看到服务器发送的标记提示后，可以将筷子 消毒机这一标记信息通过终端发送给服务器，以使服务器根据该标记信息，确定出商户的节碳行为(商户的节碳行为具体属于哪类行为，以及节碳行为的具体形式等)。例如，当服务器接收到用户发送的标记信息为：一次性筷子时，则可以确定出商户的节碳行为属于不促进节碳的消极行为，具体形式为使用一次性餐具。
通常情况下，上述图像识别模型通常都是人为通过大量的训练样本预先训练出来的，而这些训练样本通常都是人工进行标注的。因此，若后续需要对该图像识别模型进一步调整，则需要再次通过人工标注的方式，确定出一些训练样本，从而通过这些训练样本对该图像识别模型进行调整，这样则会极大的耗费人力成本，同时降低了模型训练的效率。
而在本说明书中，由于可以利用用户发送的标记信息对图像识别模型进行训练，相当于由用户来完成对训练样本的标记工作，这样在不断提高图像识别模型识别能力的同时，也极大的降低了训练该图像识别模型所消耗的人力成本，提高了模型训练的效率。
S104：根据所述节碳行为，确定表征所述商户的节碳量的值。
服务器确定出商户的节碳行为后，可以确定出与该节碳行为相匹配的，表征商户的节碳量的值。其中，当该商户的节碳行为属于促进节碳的积极行为时，则表征该商户的节碳量的值可以是正值，而当该商户的节碳行为属于不促进节碳的消极行为时，则表征该商户的节碳量的值可以是负值。
在本说明书中，表征该商户的节碳量的值可以是积分形式的，即，服务器可以根据该商户的节碳行为，确定出表征该商户的节碳量的节碳积分。服务器可将确定出的节碳积分添加至该商户的节碳账户中。其中，这里提到的节碳账户可以是该商户事先开通的。该商户事先可以将自身的商户信息提交给服务器，以用于申请开通节碳账户，服务器可以对该商户提交的商户信息进行审核，并在确定该商户提交的商户信息通过审核后，对该商户开设节碳账户。
服务器在确定出商户的节碳行为后，可以进一步确定出的商户的节碳行为所属的行为类别，进而将该行为类别对应的节碳积分添加至该商户的节碳账户中。例如，假设服务器根据识别出的节碳行为，确定该商户的节碳行为属于促进节碳的积极行为时，则可将该积极行为对应的节碳积分添加至该商户的节碳账户中，而当确定该商户的节碳行为属于不促进节碳的消极行为时，则可从该商户的节碳账户中扣除该消极行为对应的节碳积分。
服务器也可以在确定出该商户的节碳行为后，根据该节碳行为的具体形式，将与该具体形式相匹配的节碳积分添加至该商户的节碳账户中。换句话说，对于不同的具体形式，可以对应不同的节碳积分，商户采取不同的形式的节碳行为，可以获取不同的节碳积分。例如，服务器确定出该商户的节碳行为的具体形式为使用筷子消毒机时，则可将这一形式对应的节碳积分添加至该商户的节碳账户中。再例如，服务器确定出该商户的节碳行为的具体形式为使用一次性餐具时，则可以将这一形式对应的节碳积分从该商户的节碳账户中扣除。
服务器在确定出商户的节碳行为的具体形式后，也可以通过该具体形式、预设的算法以及其他信息，确定出需要添加至该商户的节碳账户的节碳积分。这里提到的其他信息可以是指用户的信用等级、商户受到的节碳好评次数等信息，其中，当服务器根据一个用户发送的待识别图像，确定出商户的节碳行为是促进节碳的积极行为时，则可以算作是该商户受到的一次节碳好评。
当然，服务器也可以通过其他的方式，确定出节碳积分，并将该节碳积分添加至该商户的节碳账户中，在此就不一一举例说明了。
服务器将确定出的节碳积分添加至该商户的节碳账户的同时，也可以确定出发送待识别图像的用户的贡献度，进而向该用户的账户中添加该贡献度和/或将该贡献度对应的虚拟物品发放给该用户。
服务器可以通过多种方式确定该用户的贡献度。例如，积极的节碳行为可以包括多种具体形式，不同的具体形式对应不同的贡献度，因此，服务器可以根据确定出的节碳行为的具体形式，确定相应的贡献度；或是根据用户的信用等级，确定相应的贡献度。当然，服务器也可以通过其他的方式，确定用户的贡献度，在此就不一一举例说明了。
上述提到的贡献度的形式可以有很多，如，积分形式、红包形式等。而上述提到的虚拟物品的形式也可以有很多，如，服务器可将优惠券发放给用户，也可以将一些业务的VIP权限按时限发放给用户。
为了进一步促进商户实施积极的节碳行为，服务器可以根据商户的节碳账户中的节碳积分，向该商户提供诸多便利服务。例如，服务器在确定该商户的节碳账户中的节碳积分超过设定积分或到达设定排名时，则可以将该商户的信息在商户推荐首页中展示，以进一步推广该商户。再例如，当确定该商户的节碳账户中的节碳积分超过设定积分时，则可以提高该商户的贷款额度。当然，服务器根据商户的节碳积分向商户提供的便利服 务还有很多，在此就不一一举例说明了。
从上述方法中可以看出，由于可以基于用户针对商户采集的待识别图像，对商户的节碳行为进行识别，从而根据识别出的商户的节碳行为，对该商户的节碳量进行有效的量化，因此，基于针对节碳量所量化出的值，可使商户了解自身的实际节碳情况，并基于了解到的实际节碳情况对后续的节碳工作进行有效的开展，进而可为社会的节能减排工作带来了积极的影响。
并且，服务器可以利用用户发送的标记信息以及未识别出节碳行为的待识别图像，对图像识别模型进行训练、调整，这样则极大的降低了训练该图像识别模型所消耗的人力成本，提高了模型训练的效率。
不仅如此，由于商户的节碳行为可以使商户获取到相应的节碳积分，进而服务器可以根据商户的节碳账户中的节碳积分，为商户提供便利服务，因此，随着节碳账户在各商户间的普及，以及节碳账户中节碳积分所带来的奖励机制，可以进一步促使积极的节碳行为能够得到更为有效的推广，从而对人们赖以生存的环境产生更为积极的影响。
在本说明书中，由于服务器需要根据用户发送的待识别图像量化商户的节碳量，因此，服务器在通过图1所示的步骤S100接收到用户发送的待识别图像后，需要确定出该待识别图像属于哪一商户，继而基于该待识别图像，确定出表征该商户的节碳量的值。在本说明书中，服务器确定与上述待识别图像相对应的商户的方式可以有很多。例如，用户通过手机对商户进行评价时，可以通过该商户的评价页面将采集到的待识别图像发送给服务器，以使服务器根据该待识别图像，将确定出的节碳积分添加至用户评价的商户的节碳账户中。
再例如，用户通过电子支付的方式进行结账时，可以将采集到的待识别图像发送给服务器。服务器可以根据从该待识别图像中识别出的节碳行为，将该节碳行为对应的节碳积分添加至用户结账时收款商户的节碳账户中。
再例如，终端在采集商户的节碳行为时，可以确定出采集节碳行为所基于的位置信息，进而将采集到的待识别图像以及确定出的位置信息发送给服务器，而服务器则可以将基于该待识别图像确定出的节碳积分添加至该位置信息对应的商户的节碳账户中。当然，还可以通过其他的方式，确定与上述待识别图像相对应的商户，在此就不一一举例说明了。
在本说明书中，终端可以将采集到的待识别图像、商户标识以及采集该待识别图像 所基于的位置信息发送给服务器，而服务器则可以在确定该位置信息与该商户标识对应的商户所处的位置相匹配时，再对该待识别图像进行识别，并根据识别出的节碳行为，将该节碳行为对应的节碳积分添加至该商户的节碳账户中。
此举的目的在于，一些商户可能会在别处采集与自身并不相关的待识别图像(如采集其他商户的待识别图像)实施欺诈行为。而通过上述方法可以看出，即使一些商户采集了其他商户的待识别图像实施欺诈，服务器也会基于采集该待识别图像时所基于的位置信息，将确定出的节碳积分添加至该位置信息对应的商户的节碳账户中，从而有效的降低了商户实施欺诈的可能。
在本说明书中，由于服务器得到的上述标记信息是用户基于主观而得出的，这就使得服务器通过该标记信息确定出的商户的节碳行为存在错误的可能，而服务器根据错误的标记信息所确定出的节碳行为，确定表征该商户的节碳量的值，则可能会给该商户或是其他的商户带来损失。
为了降低上述问题所带来的不利影响，在本说明书中，当服务器需要根据用户发送的标记信息确定该商户的节碳行为时，可以将该节碳行为所对应的基准值乘以确定出的信任系数，并将两者的乘积确定为表征该商户的节碳量的值。
其中，服务器确定信任系数的方式可以有很多。例如，不同的节碳行为(或节碳行为的不同具体形式)，可以对应不同的信任系数。服务器可以根据确定出的商户的节碳行为(或节碳行为的具体形式)，确定出相应的信任系数，进而根据该信任系数以及该节碳行为对应的基准值，确定表征该商户的节碳量的值。
这里提到的信任系数可以由人工进行确定，对于那些服务器无法通过图像识别模型识别出节碳行为(或节碳行为的具体形式)的待识别图像来说，服务器的管理人员可以先根据用户发送的标记信息，确定出用户针对这些待识别图像所标记出的节碳行为(或节碳行为的具体形式)，而后，针对用户标记出的不同节碳行为(节碳行为的不同具体形式)，对该节碳行为(或该具体形式)所对应的待识别图像进行人工识别，以确定出用户标记该节碳行为(或该具体形式)的准确率，进而根据确定出的准确率，确定出该节碳行为(或具体形式)所对应的信任系数。
当然，服务器不仅可以基于确定出的节碳行为(或节碳行为的具体形式)，来确定信任系数，还可以根据用户的用户信息和/或商户的商户信息，确定出该信任系数。其中，这里提到的用户信息以及商户的商户信息可以是指用户或商户的信用等级、节碳账户中 现有节碳积分等信息。至于其他确定信任系数的方式，在此就不一一举例说明了。
为了进一步说明本说明书提供的数据处理方法，下面将通过一个具体的实例，对整个数据处理过程进行说明，如图3所示。
图3为本说明书提供的整个数据处理过程的示意图。
从图3可以看出，用户可以通过对商户实施的节碳行为进行图像采集，得到一定的奖励，而商户则可以通过用户针对该商户所采集的待识别图像，获取一定的节碳积分。所以，通过这种奖励机制，可以促使更多的商户实施积极的节碳行为，从而形成一个良性的循环，给整个社会的节能减排带来积极的影响。
以上为本说明书的一个或多个实施例提供的数据处理方法，基于同样的思路，本说明书还提供了相应的数据处理的装置，如图4、5所示。
图4为本说明书提供的一种数据处理的装置示意图，具体包括：
获取模块401，获取用户发送的待识别图像，所述待识别图像是所述用户针对商户采集的；
识别模块402，通过预先训练的图像识别模型，对所述待识别图像进行识别，以确定商户的节碳行为；
确定模块403，根据所述节碳行为，确定表征所述商户的节碳量的值。
所述装置还包括：
接收模块404，当通过所述图像识别模型未从所述待识别图像中识别出所述商户的节碳行为时，接收所述用户发送的所述待识别图像对应的标记信息，所述标记信息包括所述用户针对所述待识别图像标记的所述商户的节碳行为；
所述确定模块403，根据接收到的所述标记信息，确定表征所述商户的节碳量的值。
所述确定模块403，确定所述标记信息包括的节碳行为；确定所述节碳行为对应的基准值；根据所述基准值以及信任系数的乘积，确定表征所述商户的节碳量的值。
所述装置还包括：
调整模块405，根据所述待识别图像以及所述标记信息，对所述图像识别模型进行调整。
所述确定模块403，确定所述用户的贡献度；为所述用户提供所述贡献度对应的虚 拟物品，和/或，向所述用户的账户添加所述贡献度。
表征所述商户的节碳量的值包括：表征所述商户的节碳量的节碳积分；
所述装置还包括：
添加模块406，向所述商户的节碳账户中添加所述节碳积分。
图5为本说明书提供的一种数据处理的装置示意图，具体包括：
采集模块501，采集商户的图像作为待识别图像；
发送模块502，将所述待识别图像发送给服务器，以使服务器通过预先训练的图像识别模型，从所述待识别图像中识别所述商户的节碳行为，并根据所述节碳行为，确定表征所述商户的节碳量的值。
所述装置还包括：
接收模块503，接收所述服务器发送的标记提示，所述标记提示是所述服务器未通过所述图像识别模型从所述待识别图像中识别出所述商户的节碳行为时向用户发送的；
所述发送模块502，接收所述用户根据所述标记提示输入的标记信息，并将所述标记信息发送给所述服务器，以使所述服务器根据所述标记信息，确定所述商户的节碳行为。
基于上述说明的数据处理的方法，本说明书还对应提供了一种用于数据处理的设备，如图6所示。该设备包括一个或多个存储器以及处理器，所述存储器存储程序，并且被配置成由所述一个或多个处理器执行以下步骤：
获取用户发送的待识别图像，所述待识别图像是所述用户针对商户采集的；
通过预先训练的图像识别模型，对所述待识别图像进行识别，以识别所述商户的节碳行为；
根据所述节碳行为，确定表征所述商户的节碳量的值。
基于上述说明的数据处理的方法，本说明书还对应提供了一种用于数据处理的设备，如图7所示。该设备包括一个或多个存储器以及处理器，所述存储器存储程序，并且被配置成由所述一个或多个处理器执行以下步骤：
采集商户的图像作为待识别图像；
将所述待识别图像发送给服务器，以使服务器通过预先训练的图像识别模型，从所述待识别图像中识别所述商户的节碳行为，并根据所述节碳行为，确定表征所述商户的节碳量的值。
在本说明书的一个或多个实施例中，在获取到用户针对商户采集到的待识别图像后，可以通过预先训练的图像识别模型，对该待识别图像进行识别，以识别该商户的节碳行为，并根据识别出的节碳行为，确定表征该商户的节碳量的值。
由于可以基于用户针对商户采集的待识别图像，对商户的节碳行为进行识别，从而根据识别出的商户的节碳行为，对该商户的节碳量进行有效的量化，因此，基于针对节碳量所量化出的值，可使商户了解自身的实际节碳情况，并基于了解到的实际节碳情况对后续的节碳工作进行有效的开展，进而可为社会的节能减排工作带来了积极的影响。
在20世纪90年代，对于一个技术的改进可以很明显地区分是硬件上的改进(例如，对二极管、晶体管、开关等电路结构的改进)还是软件上的改进(对于方法流程的改进)。然而，随着技术的发展，当今的很多方法流程的改进已经可以视为硬件电路结构的直接改进。设计人员几乎都通过将改进的方法流程编程到硬件电路中来得到相应的硬件电路结构。因此，不能说一个方法流程的改进就不能用硬件实体模块来实现。例如，可编程逻辑器件(Programmable Logic Device,PLD)(例如现场可编程门阵列(Field Programmable Gate Array，FPGA))就是这样一种集成电路，其逻辑功能由用户对器件编程来确定。由设计人员自行编程来把一个数字系统“集成”在一片PLD上，而不需要请芯片制造厂商来设计和制作专用的集成电路芯片。而且，如今，取代手工地制作集成电路芯片，这种编程也多半改用“逻辑编译器(logic compiler)”软件来实现，它与程序开发撰写时所用的软件编译器相类似，而要编译之前的原始代码也得用特定的编程语言来撰写，此称之为硬件描述语言(Hardware Description Language，HDL)，而HDL也并非仅有一种，而是有许多种，如ABEL(Advanced Boolean Expression Language)、AHDL(Altera Hardware Description Language)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL(Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM、RHDL(Ruby Hardware Description Language)等，目前最普遍使用的是VHDL(Very-High-Speed Integrated Circuit Hardware Description Language)与Verilog。本领域技术人员也应该清楚，只需要将方法流程用上述几种硬件描述语言稍作逻辑编程并编程到集成电路中，就可以很容易得到实现该逻辑方法流程的硬件电 路。
控制器可以按任何适当的方式实现，例如，控制器可以采取例如微处理器或处理器以及存储可由该(微)处理器执行的计算机可读程序代码(例如软件或固件)的计算机可读介质、逻辑门、开关、专用集成电路(Application Specific Integrated Circuit，ASIC)、可编程逻辑控制器和嵌入微控制器的形式，控制器的例子包括但不限于以下微控制器：ARC 625D、Atmel AT91SAM、Microchip PIC18F26K20以及Silicone Labs C8051F320，存储器控制器还可以被实现为存储器的控制逻辑的一部分。本领域技术人员也知道，除了以纯计算机可读程序代码方式实现控制器以外，完全可以通过将方法步骤进行逻辑编程来使得控制器以逻辑门、开关、专用集成电路、可编程逻辑控制器和嵌入微控制器等的形式来实现相同功能。因此这种控制器可以被认为是一种硬件部件，而对其内包括的用于实现各种功能的装置也可以视为硬件部件内的结构。或者甚至，可以将用于实现各种功能的装置视为既可以是实现方法的软件模块又可以是硬件部件内的结构。
上述实施例阐明的系统、装置、模块或单元，具体可以由计算机芯片或实体实现，或者由具有某种功能的产品来实现。一种典型的实现设备为计算机。具体的，计算机例如可以为个人计算机、膝上型计算机、蜂窝电话、相机电话、智能电话、个人数字助理、媒体播放器、导航设备、电子邮件设备、游戏控制台、平板计算机、可穿戴设备或者这些设备中的任何设备的组合。
为了描述的方便，描述以上装置时以功能分为各种单元分别描述。当然，在实施本说明书时可以把各单元的功能在同一个或多个软件和/或硬件中实现。
本领域内的技术人员应明白，本说明书的实施例可提供为方法、系统、或计算机程序产品。因此，本说明书可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本说明书可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本说明书是参照根据本说明书一个或多个实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理 设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
在一个典型的配置中，计算设备包括一个或多个处理器(CPU)、输入/输出接口、网络接口和内存。
内存可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)。内存是计算机可读介质的示例。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括，但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带，磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质，可用于存储可以被计算设备访问的信息。按照本文中的界定，计算机可读介质不包括暂存电脑可读媒体(transitory media)，如调制的数据信号和载波。
还需要说明的是，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、商品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、商品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、商品或者设备中还存在另外的相同要素。
本说明书可以在由计算机执行的计算机可执行指令的一般上下文中描述，例如程序模块。一般地，程序模块包括执行特定任务或实现特定抽象数据类型的例程、程序、对象、组件、数据结构等等。也可以在分布式计算环境中实践本说明书的一个或多个实施例，在这些分布式计算环境中，由通过通信网络而被连接的远程处理设备来执行任务。在分布式计算环境中，程序模块可以位于包括存储设备在内的本地和远程计算机存储介质中。
本说明书中的各个实施例均采用递进的方式描述，各个实施例之间相同相似的部分互相参见即可，每个实施例重点说明的都是与其他实施例的不同之处。尤其，对于系统实施例而言，由于其基本相似于方法实施例，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。
上述对本说明书特定实施例进行了描述。其它实施例在所附权利要求书的范围内。在一些情况下，在权利要求书中记载的动作或步骤可以按照不同于实施例中的顺序来执行并且仍然可以实现期望的结果。另外，在附图中描绘的过程不一定要求示出的特定顺序或者连续顺序才能实现期望的结果。在某些实施方式中，多任务处理和并行处理也是可以的或者可能是有利的。
以上所述仅为本说明书的一个或多个实施例而已，并不用于限制本说明书。对于本领域技术人员来说，本说明书的一个或多个实施例可以有各种更改和变化。凡在本说明书的一个或多个实施例的精神和原理之内所作的任何修改、等同替换、改进等，均应包含在本说明书的权利要求范围之内。

Claims (18)

  1. 一种数据处理的方法，包括：
    获取用户发送的待识别图像，所述待识别图像是所述用户针对商户采集的；
    通过预先训练的图像识别模型，对所述待识别图像进行识别，以识别所述商户的节碳行为；
    根据所述节碳行为，确定表征所述商户的节碳量的值。
  2. 如权利要求1所述的方法，所述方法还包括：
    当通过所述图像识别模型未从所述待识别图像中识别出所述商户的节碳行为时，接收所述用户发送的所述待识别图像对应的标记信息，所述标记信息包括所述用户针对所述待识别图像标记的所述商户的节碳行为；
    根据接收到的所述标记信息，确定表征所述商户的节碳量的值。
  3. 如权利要求2所述的方法，根据接收到的所述标记信息，确定表征所述商户的节碳量的值，具体包括：
    确定所述标记信息包括的节碳行为；
    确定所述节碳行为对应的基准值；
    根据所述基准值以及信任系数的乘积，确定表征所述商户的节碳量的值。
  4. 如权利要求2所述的方法，所述方法还包括：
    根据所述待识别图像以及所述标记信息，对所述图像识别模型进行调整。
  5. 如权利要求1所述的方法，所述方法还包括：
    确定所述用户的贡献度；
    为所述用户提供所述贡献度对应的虚拟物品，和/或，向所述用户的账户添加所述贡献度。
  6. 如权利要求1所述的方法，表征所述商户的节碳量的值包括：表征所述商户的节碳量的节碳积分；
    所述方法还包括：
    向所述商户的节碳账户中添加所述节碳积分。
  7. 一种数据处理的方法，包括：
    采集商户的图像作为待识别图像；
    将所述待识别图像发送给服务器，以使服务器通过预先训练的图像识别模型，从所述待识别图像中识别所述商户的节碳行为，并根据所述节碳行为，确定表征所述商户的节碳量的值。
  8. 如权利要求7所述的方法，所述方法还包括：
    接收所述服务器发送的标记提示，所述标记提示是所述服务器未通过所述图像识别模型从所述待识别图像中识别出所述商户的节碳行为时发送的；
    接收所述用户根据所述标记提示输入的标记信息，并将所述标记信息发送给所述服务器，以使所述服务器根据所述标记信息，确定所述商户的节碳行为。
  9. 一种数据处理的装置，包括：
    获取模块，获取用户发送的待识别图像，所述待识别图像是所述用户针对商户采集的；
    识别模块，通过预先训练的图像识别模型，对所述待识别图像进行识别，以确定商户的节碳行为；
    确定模块，根据所述节碳行为，确定表征所述商户的节碳量的值。
  10. 如权利要求9所述的装置，所述装置还包括：
    接收模块，当通过所述图像识别模型未从所述待识别图像中识别出所述商户的节碳行为时，接收所述用户发送的所述待识别图像对应的标记信息，所述标记信息包括所述用户针对所述待识别图像标记的所述商户的节碳行为；
    所述确定模块，根据接收到的所述标记信息，确定表征所述商户的节碳量的值。
  11. 如权利要求10所述的装置，所述确定模块，确定所述标记信息包括的节碳行为；确定所述节碳行为对应的基准值；根据所述基准值以及信任系数的乘积，确定表征所述商户的节碳量的值。
  12. 如权利要求10所述的装置，所述装置还包括：
    调整模块，根据所述待识别图像以及所述标记信息，对所述图像识别模型进行调整。
  13. 如权利要求9所述的装置，所述确定模块，确定所述用户的贡献度；为所述用户提供所述贡献度对应的虚拟物品，和/或，向所述用户的账户添加所述贡献度。
  14. 如权利要求9所述的装置，表征所述商户的节碳量的值包括：表征所述商户的节碳量的节碳积分；
    所述装置还包括：
    添加模块，向所述商户的节碳账户中添加所述节碳积分。
  15. 一种数据处理的装置，包括：
    采集模块，采集商户的图像作为待识别图像；
    发送模块，将所述待识别图像发送给服务器，以使服务器通过预先训练的图像识别模型，从所述待识别图像中识别所述商户的节碳行为，并根据所述节碳行为，确定表征 所述商户的节碳量的值。
  16. 如权利要求15所述的装置，所述装置还包括：
    接收模块，接收所述服务器发送的标记提示，所述标记提示是所述服务器未通过所述图像识别模型从所述待识别图像中识别出所述商户的节碳行为时发送的；
    所述发送模块，接收所述用户根据所述标记提示输入的标记信息，并将所述标记信息发送给所述服务器，以使所述服务器根据所述标记信息，确定所述商户的节碳行为。
  17. 一种数据处理的设备，包括一个或多个存储器以及处理器，所述存储器存储程序，并且被配置成由所述一个或多个处理器执行以下步骤：
    获取用户发送的待识别图像，所述待识别图像是所述用户针对商户采集的；
    通过预先训练的图像识别模型，对所述待识别图像进行识别，以识别所述商户的节碳行为；
    根据所述节碳行为，确定表征所述商户的节碳量的值。
  18. 一种数据处理的设备，包括一个或多个存储器以及处理器，所述存储器存储程序，并且被配置成由所述一个或多个处理器执行以下步骤：
    采集针对商户的待识别图像；
    将所述待识别图像发送给服务器，以使服务器通过预先训练的图像识别模型，对所述待识别图像进行识别，以识别所述商户的节碳行为，并根据所述节碳行为，确定表征所述商户的节碳量的值。
PCT/CN2018/111852 2017-12-14 2018-10-25 一种数据处理的方法、装置及设备 WO2019114425A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
SG11202001210YA SG11202001210YA (en) 2017-12-14 2018-10-25 Data processing method, apparatus, and equipment
US16/805,525 US10878239B2 (en) 2017-12-14 2020-02-28 Recognizing carbon-saving behaviors from images
US17/135,988 US11106909B2 (en) 2017-12-14 2020-12-28 Recognizing carbon-saving behaviors from images

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201711334828.0 2017-12-14
CN201711334828.0A CN108229337B (zh) 2017-12-14 2017-12-14 一种数据处理的方法、装置及设备

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US16/805,525 Continuation US10878239B2 (en) 2017-12-14 2020-02-28 Recognizing carbon-saving behaviors from images

Publications (1)

Publication Number Publication Date
WO2019114425A1 true WO2019114425A1 (zh) 2019-06-20

Family

ID=62649515

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/111852 WO2019114425A1 (zh) 2017-12-14 2018-10-25 一种数据处理的方法、装置及设备

Country Status (5)

Country Link
US (2) US10878239B2 (zh)
CN (2) CN108229337B (zh)
SG (1) SG11202001210YA (zh)
TW (1) TWI713908B (zh)
WO (1) WO2019114425A1 (zh)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108229337B (zh) 2017-12-14 2021-03-30 创新先进技术有限公司 一种数据处理的方法、装置及设备
CN109146030B (zh) * 2018-08-17 2021-02-19 创新先进技术有限公司 一种低碳消费的识别方法、装置及电子设备
CN110009296A (zh) * 2019-02-11 2019-07-12 阿里巴巴集团控股有限公司 理赔业务的处理方法及装置
CN115146980A (zh) * 2019-10-24 2022-10-04 支付宝(杭州)信息技术有限公司 对象评估方法及装置
CN111401759B (zh) * 2020-03-20 2022-08-23 支付宝(杭州)信息技术有限公司 数据处理方法、装置、电子设备及存储介质
CN111353883A (zh) * 2020-05-22 2020-06-30 浙江网商银行股份有限公司 一种为商户提供服务的方法和装置
CN113505837A (zh) * 2021-07-14 2021-10-15 同济大学 一种基于Faster-RCNN的测量标志自动提取方法

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103745238A (zh) * 2013-11-15 2014-04-23 中国科学院遥感与数字地球研究所 基于AdaBoost和主动形状模型的受电弓识别方法
CN106709525A (zh) * 2017-01-05 2017-05-24 北京大学 一种相机测量食物营养成分方法
CN108229337A (zh) * 2017-12-14 2018-06-29 阿里巴巴集团控股有限公司 一种数据处理的方法、装置及设备

Family Cites Families (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070219862A1 (en) * 2006-03-20 2007-09-20 Casella Waste Systems, Inc. System and method for identifying and processing recyclables
KR20110006903A (ko) * 2009-07-15 2011-01-21 엘지전자 주식회사 탄소 배출량을 계산하는 단말기 및 탄소 모니터링 방법
US20110055092A1 (en) * 2009-09-01 2011-03-03 Qwest Communications International, Inc. Electronic Systems and Methods for Aggregating and Distributing Environmental Credits
TW201118789A (en) * 2009-09-09 2011-06-01 Univ Trobe Method and system for energy management
JP5429690B2 (ja) * 2009-09-14 2014-02-26 株式会社リコー 画像形成装置及び消費電力報知方法
US20120101883A1 (en) * 2010-05-04 2012-04-26 Pervez Akhter System and Method for Rewarding Smart Phone Users Personal Companion
CN102243684A (zh) * 2010-05-13 2011-11-16 上海杰远环保科技有限公司 一种基于图像识别功能实现的节能环保指引方法及系统
JP5502662B2 (ja) * 2010-09-01 2014-05-28 東芝テック株式会社 店舗システム及び商品コード読取装置
TWI569214B (zh) * 2011-01-04 2017-02-01 Chunghwa Telecom Co Ltd The system and method of purchasing stored value points
US20130035973A1 (en) * 2011-08-01 2013-02-07 Infosys Limited Assessing green it maturity and providing green it recommendations
US20150189233A1 (en) * 2012-04-30 2015-07-02 Goggle Inc. Facilitating user interaction in a video conference
TW201347538A (zh) * 2012-05-08 2013-11-16 Univ Nat Chiao Tung 互動視訊平台系統及方法
KR20130140285A (ko) * 2012-06-14 2013-12-24 이철희 모바일 단말기를 통한 재활용품 수거 방법 및 그 시스템
CN104836780B (zh) * 2014-02-12 2017-03-15 腾讯科技（深圳）有限公司 数据交互方法、验证终端、服务器和系统
CN105744218B (zh) 2014-12-11 2019-04-26 小米科技有限责任公司 垃圾清理方法及装置
CN104732654A (zh) * 2015-03-30 2015-06-24 苏州朗米尔照明科技有限公司 基于图像识别技术的有偿节能灯回收行为关联方法
CN105205466B (zh) * 2015-09-21 2018-06-15 广州地理研究所 一种基于夜间灯光影像的能源碳排放量遥感估算方法
CN106846621A (zh) * 2017-02-20 2017-06-13 湖南大学 “互联网+”包装瓶智能回收系统及方法
CN106874954A (zh) * 2017-02-20 2017-06-20 佛山市络思讯科技有限公司 一种信息获取的方法以及相关装置
CN107256386A (zh) * 2017-05-23 2017-10-17 东南大学 基于深度学习的人类行为分析方法
CN107247946B (zh) * 2017-07-06 2021-01-26 北京安宁威尔科技发展有限公司 行为识别方法及装置
US10025950B1 (en) * 2017-09-17 2018-07-17 Everalbum, Inc Systems and methods for image recognition

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103745238A (zh) * 2013-11-15 2014-04-23 中国科学院遥感与数字地球研究所 基于AdaBoost和主动形状模型的受电弓识别方法
CN106709525A (zh) * 2017-01-05 2017-05-24 北京大学 一种相机测量食物营养成分方法
CN108229337A (zh) * 2017-12-14 2018-06-29 阿里巴巴集团控股有限公司 一种数据处理的方法、装置及设备

Also Published As

Publication number Publication date
US20200202126A1 (en) 2020-06-25
US11106909B2 (en) 2021-08-31
US20210117675A1 (en) 2021-04-22
CN113139524A (zh) 2021-07-20
SG11202001210YA (en) 2020-03-30
TWI713908B (zh) 2020-12-21
US10878239B2 (en) 2020-12-29
CN108229337B (zh) 2021-03-30
CN108229337A (zh) 2018-06-29
TW201928804A (zh) 2019-07-16

Similar Documents

Publication Publication Date Title
WO2019114425A1 (zh) 一种数据处理的方法、装置及设备
WO2019196545A1 (zh) 保险欺诈识别的数据处理方法、装置、设备及服务器
CN107153641A (zh) 评论信息确定方法、装置、服务器及存储介质
WO2019084810A1 (zh) 一种信息处理方法及终端、计算机存储介质
WO2021103909A1 (zh) 风险预测和风险预测模型的训练方法、装置及电子设备
WO2020238229A1 (zh) 交易特征生成模型的训练、交易特征的生成方法和装置
CN108241737A (zh) 用于提供地点信息的系统和支持该系统的电子装置和方法
US11675821B2 (en) Method for capturing and updating database entries of CRM system based on voice commands
WO2019136909A1 (zh) 基于深度学习的语音活体检测方法、服务器及存储介质
CN110263157A (zh) 一种数据风险预测方法、装置及设备
WO2019128527A1 (zh) 一种社交内容风险识别方法、装置以及设备
US20200349415A1 (en) Method for capturing and storing contact information from a physical medium using machine learning
US11948558B2 (en) Messaging system with trend analysis of content
CN107622413A (zh) 一种价格敏感度计算方法、装置及其设备
CN107679457A (zh) 用户身份校验方法及装置
CN107451918B (zh) 资产数据管理方法及装置
WO2019037649A1 (zh) 一种针对使用共享物品的用户评估方法、装置及设备
CN105791446A (zh) 一种民间借贷处理方法、装置及系统
CN108572988A (zh) 一种房产评估数据生成方法和装置
KR20220018461A (ko) 음성을 분석하여 이벤트를 생성하는 플랫폼을 운용하는 서버
WO2019052430A1 (zh) 移动终端的自助服务方法及装置
CN110046231A (zh) 一种客服信息处理方法、服务器和系统
WO2020155831A1 (zh) 数据标签生成、模型训练、事件识别方法和装置
Zamora et al. Noise-sensing using smartphones: Determining the right time to sample
US20150331889A1 (en) Method of Image Tagging for Identifying Regions and Behavior Relationship between Different Objects

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: 18889810

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: 18889810

Country of ref document: EP

Kind code of ref document: A1