Adjusting parameters of weighing device for reducing average giveaway rate when packaging an article

Patent metadata

Field	Value
Publication number	US-12188809-B2
Application number	US-202117350699-A
Country	US
Kind code	B2
Filing date	Jun 17, 2021
Priority date	Jun 17, 2021
Publication date	Jan 7, 2025
Grant date	Jan 7, 2025

Abstract

Reducing an average give-away rate of a weighing device by determining a weight of a product of a weighing device that includes an article, determining one or more conditions of an environment of the weighing device, determining a state of the environment of the weighing device, wherein the state relates to an average give-away rate of the environment of the weighing device, determining a reward value for the state of the environment of the weighing device, wherein the reward value is based at least in part on the weight of the product, and generating a set of parameters for the weighing device based at least in part on the environment, the state, and the reward.

First claim

What is claimed is:

1. A computer implemented method for reducing an average give-away rate of a weighing device, the method comprising:
determining a weight of a product of a weighing device that includes an article;
determining one or more conditions of an environment of the weighing device;
determining a state of the environment of the weighing device, wherein the state relates to an average give-away rate of the environment of the weighing device;
determining a change in the environment of the weighing device by identifying and comparing variations in, at least in part, the one or more conditions of the environment of the weighing device and the average give-away rate over a defined time period;
based on the determined change, determining a reward value for the state of the environment of the weighing device, wherein the reward value is based at least in part on the weight of the product, the reward value being associated with a reduction of the average give-away rate without changing a mechanical design of an existing weighing hardware equipment of the weighing device;
iteratively generating a set of parameters for the weighing device based on the one or more conditions of the environment of the weighing device, the reward value, and the state of the environment of the weighing device;
the iteratively generating of the set of parameters being for each state associated with the environment of the weighing device, which includes considering a physical environment and attribute characteristics of a packaged product and setting an average give-away rate change as a reward and punishment function to provide timely feedback and timely adjustment of the set of parameters; and
determining the reward for the state by dividing the reward value by a number of adjusted parameters based on positive and negative values, which are utilized to determine the average give-away rate.

2. The computer implemented method according to claim 1 , further comprising:
modifying one or more parameters of the set of parameters for the weighing device based at least in part on the reward value for the state of the environment of the weighing device.

3. The computer implemented method according to claim 2 , further comprising:
collecting iterative feedback data of the environment of the weighing device, wherein the feedback data relates to the environment of the weighing device;
identifying an optimal set of parameters for the weighing device based on the iterative feedback data, wherein the optimal set of parameters result in the average give-away rate of the weighing device meeting a target give-away rate, wherein the target give-away rate is based at least in part on a target weight of the product; and
modifying the one or more parameters of the set of parameters for the weighing device based on the optimal set of parameters.

4. The computer implemented method according to claim 2 , wherein the reward value for the state of the environment of the weighing device is based at least in part on the average give-away rate of the state, an overall average give-away rate of the weighing device, and an amount of modified parameters for the state of the environment of the weighing device.

5. The computer implemented method according to claim 1 , further comprising:
generating an initial set of parameters for the weighing device;
determining a weight of one or more products associated with the initial set of parameters;
determining that a pass rate for the one or more products of the weighing device exceeds a threshold pass rate; and
determining an overall average give-away rate of the weighing device for the one or more products based at least in part on the weight of the one or more products.

6. The computer implemented method according to claim 1 , wherein determining the one or more conditions of the environment of the weighing device, further comprises:
collecting a set of physical environment data from one or more sensors associated with the environment of the weighing device;
collecting a set of product attribute data from the one or more sensors associated with the environment of the weighing device, wherein the set of product attribute data corresponds to physical attributes of the article of the product; and
generating a set of conditions corresponding to the environment of the weighing device based at least in part on the set of physical environment data and the set of product attribute data.

7. The computer implemented method according to claim 1 , wherein generating the set of parameters for the weighing device based on the one or more conditions of the environment of the weighing device, the reward value, and the state of the environment of the weighing device, comprises:
selecting one or more parameter candidates of a Deep Q-Network (DQN) algorithm based at least in part on the reward value.

8. A computer program product for reducing an average give-away rate of a weighing device, the computer program product comprising one or more computer readable storage devices and collectively stored program instructions on the one or more computer readable storage devices, the stored program instructions comprising:
program instructions to determine a weight of a product of a weighing device that includes an article;
program instructions to determine one or more conditions of an environment of the weighing device;
program instructions to determine a state of the environment of the weighing device, wherein the state relates to an average give-away rate of the environment of the weighing device;
program instructions to determine a change in the environment of the weighing device by identifying and comparing variations in, at least in part, the one or more conditions of the environment of the weighing device and the average give-away rate over a defined time period;
based on the determined change, program instructions to determine a reward value for the state of the environment of the weighing device, wherein the reward value is based at least in part on the weight of the product, the reward value being associated with a reduction of the average give-away rate without changing a mechanical design of an existing weighing hardware equipment of the weighing device;
program instructions to iteratively generate a set of parameters for the weighing device based on the one or more conditions of the environment of the weighing device, the reward value, and the state of the environment of the weighing device;
program instructions to the iterative generation of the set of parameters for each state associated with the environment of the weighing device, which includes considering a physical environment and attribute characteristics of a packaged product and setting an average give-away rate change as a reward and punishment function to provide timely feedback and timely adjustment of the set of parameters; and
program instructions to determine the reward for the state by dividing the reward value by a number of adjusted parameters based on positive and negative values, which are utilized to determine the average give-away rate.

9. The computer program product according to claim 8 , the stored program instructions further comprising:
program instructions to modify one or more parameters of the set of parameters for the weighing device based at least in part on the reward value for the state of the environment of the weighing device.

10. The computer program product according to claim 9 , the stored program instructions further comprising:
program instructions to collect iterative feedback data of the environment of the weighing device, wherein the feedback data relates to the environment of the weighing device;
program instru

Assignees

• IBM

Inventors

• Luo Deng Xin
• Yang Xiang Yu
• Wang Yong
• Wang Ye
• Yuan Zhong Fang
• Pan Yu

Classifications

• G06F18/217 Primary

  Validation; Performance evaluation; Active pattern learning techniques · CPC title

• G01G19/417

  with provision for checking computing part of balance · CPC title

• G06N3/02

  Neural networks · CPC title

• G01G19/62

  Over or under weighing apparatus · CPC title

• G01G19/52

  Weighing apparatus combined with other objects, e.g. furniture (with walking sticks A45B3/08) · CPC title