Reducing data transfer to machine learning accelerator hardware
US-11662986-B1 · May 30, 2023 · US
US12561539B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-12561539-B2 |
| Application number | US-202418942689-A |
| Country | US |
| Kind code | B2 |
| Filing date | Nov 9, 2024 |
| Priority date | Dec 23, 2021 |
| Publication date | Feb 24, 2026 |
| Grant date | Feb 24, 2026 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
The disclosure includes a fixed retail scanner including a data reader, comprising a main board including one or more processors including a system processor, one or more camera modules, and an artificial intelligence (AI). The system processor is configured to transmit image data received from the one or more camera modules responsive to one or more event triggers detected by the system processor, and wherein the AI accelerator is configured to perform analysis based on an AI engine local to the AI accelerator in response to the event trigger. A remote server may also be operably coupled to the fixed retail scanner through the multi-port network switch, the remote server having a remote AI engine stored therein, wherein the local AI engine within the fixed retail scanner is a simplified AI model relative to the remote AI engine within the remote server.
Opening claim text (preview).
What is claimed: 1 . A fixed retail scanner, comprising: a housing having at least one window disposed therein; a main board including one or more processors including a system processor disposed within the housing; one or more camera modules disposed within the housing and operably coupled with the system processor; and an on-board artificial intelligence (AI) accelerator operably coupled with the system processor, wherein the system processor is configured to transmit image data received from the one or more camera modules responsive to one or more event triggers detected by the system processor, and wherein the AI accelerator is configured to perform AI analysis based on an AI engine local to the AI accelerator in response to the event trigger and a determined event trigger type. 2 . The fixed retail scanner of claim 1 , wherein the fixed retail scanner is a single plane scanner wherein the housing and window is oriented in one of a horizontal or vertical plane. 3 . The fixed retail scanner of claim 1 , wherein the fixed retail scanner is a bioptic scanner wherein the housing includes a horizontal base having a horizontal window, and a vertical bonnet having a vertical window. 4 . The fixed retail scanner of claim 1 , wherein the AI accelerator is disposed on the main board. 5 . The fixed retail scanner of claim 1 , wherein the one or more camera modules includes a first color camera module configured to capture color images, wherein a first preponderance of color metric is determined for a first image captured by a first color camera module and provided to the AI engine local to the AI accelerator for the AI analysis to validate and/or identify an item. 6 . The fixed retail scanner of claim 5 , wherein the one or more camera modules includes a second color camera module configured to capture color images, wherein a second preponderance of color metric is determined for a second image captured by a second color camera module and provided to the AI engine local to the AI accelerator for the AI analysis. 7 . The fixed retail scanner of claim 6 , wherein the first and second images are time correlated images. 8 . The fixed retail scanner of claim 6 , wherein the first color camera module is located within a horizontal housing of a bi-optic scanner, and the second color camera module is located within a vertical housing of the bi-optic scanner. 9 . The fixed retail scanner of claim 1 , wherein the AI accelerator initiates a different response depending on the determined event trigger type. 10 . The fixed retail scanner of claim 9 , wherein the different response includes a number of frames of image data sent to the AI engine for the AI analysis. 11 . The fixed retail scanner of claim 9 , wherein the different response includes a type of data provided to the AI engine for the AI analysis. 12 . The fixed retail scanner of claim 11 , wherein the type of data includes temperature data for an item detected from a temperature sensor proximate the fixed retail scanner. 13 . The fixed retail scanner of claim 11 , wherein the type of data includes sound data detected from a microphone proximate the fixed retail scanner. 14 . The fixed retail scanner of claim 11 , wherein the type of data includes at least one of a low resolution frame, a high resolution frame, a cropped image, a descriptor, histogram data, or color metrics of an image. 15 . The fixed retail scanner of claim 9 , wherein the different response includes data from different camera views provided to the AI engine for the AI analysis. 16 . The fixed retail scanner of claim 9 , wherein the different response includes loading a different trained AI engine for the AI analysis. 17 . The fixed retail scanner of claim 1 , wherein the one or more event trigger includes one or more of an item entering a field-of-view, an item being detected at a pre-determined position within the field-of view, detection of a portion of a user's body within the field-of-view, a successful decode of an item, detecting presence of an item without decoding a barcode, detecting motion within the field-of-view, detecting a weight on a weigh platter of the scanner. 18 . A method of operating a fixed retail scanner, comprising: capturing image data, via one or more camera modules having a field-of-view through at least one window disposed in a housing; transmitting the image data to an on-board artificial intelligence (AI) accelerator disposed within the housing responsive to one or more event triggers detected by a system processor; and perform AI analysis, via the AI accelerator, based on a local AI engine in response to the event trigger and a determined event trigger type. 19 . The method of claim 18 , further comprising the AI accelerator initiating a different response depending on the determined event trigger type. 20 . The method of claim 19 , wherein the different response includes loading a different trained AI engine for the AI analysis by the AI accelerator depending on the determined event trigger type.
the scanner having more than one scanning window, e.g. two substantially orthogonally placed scanning windows for integration into a check-out counter of a super-market · CPC title
2D bar codes · CPC title
using fuzzy logic or natural solvers, such as neural networks, genetic algorithms and simulated annealing · CPC title
Photodetector array or CCD scanning · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.