US 11,106,909 B2 · Recognizing carbon-saving behaviors from images

Abstract

The present specification discloses a data processing method, apparatus, and equipment. The method includes: obtaining an image sent by a user, wherein the image to is collected by the user for a merchant; identifying carbon-saving behavior of the merchant, comprising processing the image using a trained image recognition model; and determining, based on the carbon-saving behavior, a value representing an amount of carbon saved by the merchant.

Drawings

Drawings are temporarily unavailable. Open the PDF at USPTO

Drawings

Claims15

Dependent claims

A method, comprising:

deploying, at a server, a trained image recognition model that is configured to process images to generate model outputs that identify a category of any object characterized in the images that relates to reducing carbon footprint;
in response to receiving a new image that is collected by a first user for a merchant and that is uploaded by the first user through a user device in data communication with the server:
prompting the first user to enter labeling information for the new image that identifies user-specified categories that relate to reducing carbon footprint for one or more new objects characterized in the new image;
generating, by the server and based on the new image and the labeling information, new training data for use in adjusting the trained image recognition model;
adjusting the trained image recognition model using the new training data including using the user-specified categories as target outputs to be generated by the trained image recognition model from processing the new image;
receiving another image that is collected by a second user for the merchant and that is uploaded by the second user through another user device in data communication with the server;
using the adjusted trained image recognition model to generate another model output that identifies one or more categories that relate to reducing carbon footprint for one or more other objects characterized in the other image;
and
determining, by the server and based on the categories identified for the one or more other objects characterized in the other image, a degree of contribution of the merchant with respect to reducing carbon footprint.

6 more elements

A non-transitory, computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising:

deploying, at a server, a trained image recognition model that is configured to process images to generate model outputs that identify a category of any object characterized in the images that relates to reducing carbon footprint;
in response to receiving a new image that is collected by a first user for a merchant and that is uploaded by the first user through a user device in data communication with the server:
prompting the first user to enter labeling information for the new image that identifies user-specified categories that relate to reducing carbon footprint for one or more new objects characterized in the new image;
generating, by the server and based on the new image and the labeling information, new training data for use in adjusting the trained image recognition model;
adjusting the trained image recognition model using the new training data including using the user-specified categories as target outputs to be generated by the trained image recognition model from processing the new image;
receiving another image that is collected by a second user for the merchant and that is uploaded by the second user through another user device in data communication with the server;
using the adjusted trained image recognition model to generate another model output that identifies one or more categories that relate to reducing carbon footprint for one or more other objects characterized in the other image;
and
determining, by the server and based on the categories identified for the one or more other objects characterized in the other image, a degree of contribution of the merchant with respect to reducing carbon footprint.

6 more elements

A computer-implemented system, comprising:

one or more computers;
and
one or more computer memory devices interoperably coupled with the one or more computers and having tangible, non-transitory, machine-readable media storing one or more instructions that, when executed by the one or more computers, perform one or more operations comprising:
deploying, at a server, a trained image recognition model that is configured to process images to generate model outputs that identify a category of any object characterized in the images that relates to reducing carbon footprint;
in response to receiving a new image that is collected by a first user for a merchant and that is uploaded by the first user through a user device in data communication with the server:
prompting the first user to enter labeling information for the new image that identifies user-specified categories that relate to reducing carbon footprint for one or more new objects characterized in the new image;
generating, by the server and based on the new image and the labeling information, new training data for use in adjusting the trained image recognition model;
adjusting the trained image recognition model using the new training data including using the user-specified categories as target outputs to be generated by the trained image recognition model from processing the new image;
receiving another image that is collected by a second user for the merchant and that is uploaded by the second user through another user device in data communication with the server;
using the adjusted trained image recognition model to generate another model output that identifies one or more categories that relate to reducing carbon footprint for one or more other objects characterized in the other image;
and
determining, by the server and based on the categories identified for the one or more other objects characterized in the other image, a degree of contribution of the merchant with respect to reducing carbon footprint.

9 more elements

Dependencies are inferred from the claim text.

Description7,562 words

Summary964 words

#The present specification relates to the field of computer technologies, and in particular, to a data processing method, apparatus, and equipment.

#Carbon emission is a general term or abbreviation for greenhouse gas emission. People's daily life can directly or indirectly cause carbon emission such as car exhaust emission, thermal power generation, the use of disposable products, etc. With increase of carbon emission, the degree of damage to the environment where people live is increasingly severe.

#Currently, people are reducing carbon emission in many ways, such as developing and promoting cleaner electric vehicles, building more wind and hydroelectric power stations, and manufacturing and using more environment-friendly consumables. Currently, however, there are no effective criteria for carbon-saving quantification that can enable people to understand the carbon-saving condition in real life. Thus, it is difficult to carry out more effective subsequent carbon-saving work based on the carbon-saving condition in real life.

Brief description of the drawings7 figures

#The accompanying drawings described here are used to provide a further understanding of the present specification and constitute a part of the present specification. The illustrative implementations of the present specification and descriptions thereof are intended to describe the present specification, and do not constitute limitations to the present specification. In the accompanying drawings:

#FIG. 1 is a schematic diagram illustrating a data processing process, according to an implementation of the present specification;

#FIG. 2 is a schematic diagram illustrating image collection by a user for a merchant, according to an implementation of the present specification;

Detailed description6,406 words

#In the present specification, a user can collect an image of a merchant and send the collected image to a server by using an end-user equipment, so the server quantifies carbon-saving behavior of the merchant based on the image sent by the user. Information included in the image and related to the carbon-saving behavior of the merchant can be collected by the user actively for the carbon-saving behavior of the merchant. Or when the user is active in the merchant, items related to the carbon-saving behavior of the merchant are incidentally collected in the process of collecting other information. For example, when a user is having a meal in the merchant, non-disposable chopsticks are collected when the user takes a photo of the food. The non-disposable chopsticks mentioned here are the items related to the carbon-saving behavior of the merchant.

#The motivation of the user for helping the merchant to increase the quantified value of the carbon-saving behavior in a deceptive way is relatively low, so the possibility of the merchant to cheat in order to increase the quantified value of the carbon-saving behavior can be effectively reduced by using the image collected by the user for the merchant to quantify the carbon-saving behavior of the merchant.

#In the present specification, an execution body for quantifying of the merchant can be an end-user equipment, a server, or other equipments. To facilitate description of the data processing method provided in the present specification, a server is used as an example in the following description.

Facts

Application

17/135,988Filed 28 Dec 2020 · continuation

Priority

CN 201711334828.014 Dec 2017

Published

US 2021/0117675 A122 Apr 2021

Granted

31 Aug 2021

Term ends

25 Oct 2038

Estimated · how

20 years from earliest known nonprovisional domestic filing plus recorded patent term adjustment. Maintenance-fee lapses, terminal disclaimers and statutory extensions have not been checked. The continuity chain may be incomplete; this is not an enforceability determination.

Classification6 codes

G06Q 30/0208
Discounts or incentives, e.g. coupons or rebates: trade or exchange of goods or services in exchange for incentives or rewards
G06Q 30/0217
Discounts or incentives, e.g. coupons or rebates: involving input on products or services in exchange for incentives or rewards
G06V 10/70
Arrangements for image or video recognition or understanding: using pattern recognition or machine learning
G06V 20/00
Scenes

Family

PCT/CN2018/111852Parent of this continuation · filed 25 Oct 2018

Application16/805,525Parent of this continuation · filed 28 Feb 2020

US 2021/0117675 A1Pre-grant publication · published 22 Apr 2021

US 10,878,239 B2Parent of this continuation

US 2020/0202126 A1Published application

US 11,106,909 B2This patent

From the US filing history. Foreign family members aren’t listed.

Timeline

14 Dec 2017Priority claimedCN 201711334828.0
28 Dec 2020Application filedUS 17/135,988
27 Jan 2021Assigned to Alibaba Group Holding Limitedassignment of assignor's interest
27 Jan 2021Assigned to Advantageous New Technologies Co., Ltd.assignment of assignor's interest
27 Jan 2021Assigned to Advanced New Technologies Co., Ltd.assignment of assignor's interest
22 Apr 2021PublishedUS 2021/0117675 A1
31 Aug 2021GrantedUS 11,106,909 B2
12 Oct 2026TodayWithin its term
25 Oct 2038Term endsEstimated

Recognizing carbon-saving behaviors from images

Life of this patent

Recognizing carbon-saving behaviors from images

Life of this patent

Life of this patent

Abstract

Drawings

Drawings

Claims15

Description7,562 words

Drawings

Classification6 codes

Life of this patent

Description7,562 words