BRN 2.44% 20.0¢ brainchip holdings ltd

LG

  1. 550 Posts.
    lightbulb Created with Sketch. 2212
    Peter recently talked about predictions for products in 2022 (see link below). One of these included a washing machine that monitors waste water for pollutants.

    From a search of US patents, there is one company who has been granted several patents over the last few years relating to monitoring levels of pollutants / contaminants in washing machines, namely LG. Note that this can't be conclusively used to verify they are the customer Peter was referring to, as there is a gap of up to 18 months where you can't see recent applications. However, this being said, IMO customers will be trialling Akida in more rigorously tested product ideas to start with to determine how well it works. They are less likely to try using Akida in an area they are not familiar with as other issues may crop up which will impede on their time to market, giving competitors a chance of getting there first. Rather, they are more likely to try a chip like Akida in a proven market offering, a product in which they have tested all of the other components thoroughly, meaning the key new thing they are testing is the ability of the Akida to perform machine learning at the edge.

    On top of this, Brainchip have said in the past that a large South Korean company had done a huge amount of testing for the older version of the Akida technology. While most on here have assumed this was Samsung (which is also a fair call given the large number of links to Samsung over time such as testing neuromorphic cameras and patents for fridges that smell food ripeness), there's always a possibility Brainchip were referring to LG, or alternatively Samsung + LG. If they successfully approached one large South Korean company, who's to say they were unsuccessfuly with other South Korean companies. Brainchip have had success with multiple companies in Japan (Renesas, MegaChips, MagikEye...), so there's a fair chance many companies in each country were approached at the same time to make business trips more efficient.

    A large majority of the recent patents for washing machines which refer to pollution or contaminants are from LG. Several of these refer to cameras recognition, using a microphone to recognise a wake-word etc. I've listed a couple of these below.

    Pure speculation, DYOR


    Peter's predictions for 2022:
    https://vmblog.com/archive/2021/12/23/brainchip-2022-predictions-2022-a-breakthrough-year-for-ai.aspx#.YdIpr2hBxZe

    In 2022, I believe we will see more progress, and more promises realized, than any year so far. Here is what I and my colleagues in AI expect to see:
    4. AI will become more commonplace in everyday products; refrigerators that can smell if any food is about to go off to prevent food poisoning, washing machines that monitor waste water for pollutants,

    Patent 1 - talks extensively about identifying, classifying and response to types of contaminants. Includes mention of responding to a wake-word from a microphone:
    https://appft.uspto.gov/netacgi/nph-Parser?Sect1=PTO2&Sect2=HITOFF&p=1&u=%2Fnetahtml%2FPTO%2Fsearch-adv.html&r=1&f=G&l=50&d=PG01&S1=20210189626&OS=20210189626&RS=20210189626

    United States Patent Application20210189626
    1Kind CodeA1
    2KIM; Sang Won ; et al.June 24, 2021
    WASHING MACHINE, CONTROL METHOD OF WASHING MACHINE AND SERVER FOR SUPPORTING WASHING

    Abstract

    Disclosed is a washing machine that performs a washing process in response to a type of a contaminant in laundry in a 5G environment, a method for controlling a washing machine, and a server for supporting washing. The washing machine according to an embodiment of the present disclosure may include a processor, a memory operably coupled to the processor and for storing at least one code executed in the processor, and a driver for controlling rotation of an inner tub so as to perform a washing operation on laundry. The memory may store a code to, when executed by the processor, cause the processor to identify a type of a contaminant in the laundry, determine a first washing process corresponding to the type of the contaminant, and control the driver based on the first washing process.


    Assignee:LG ELECTRONICS INC.
    Filed:April 20, 2020
    Claims

    1. A washing machine, comprising: an inner tube; a processor; a memory operably coupled to the processor, the memory configured to store codes to be executed in the processor; and a driver configured to control rotation of the inner tub so as to perform a washing operation on laundry inserted into the inner tub, wherein the memory stores a code configured to, when executed by the processor, cause the processor to: identify a type of a contaminant in the laundry, determine a first washing process corresponding to the type of the contaminant, and control the driver based on the first washing process.

    2. The washing machine according to claim 1, wherein the memory further stores a code configured to cause the processor to acquire and determine the first washing process from the memory or a washing support server.

    3. The washing machine according to claim 2, wherein the memory further stores a code configured to cause the processor to: request a search server for a washing method associated with the type of the contaminant, in response to a result of the first washing process not being acquired from the memory or the washing support server, and acquire the washing method from the search server as a response to the request.

    4. The washing machine according to claim 3, wherein laundry information comprises at least one of a garment type of the laundry, a material type of the laundry, a color type of the laundry or an area of the contaminant, and wherein the memory further stores a code configured to cause the processor to: request the search server for a washing method associated with the laundry information together with the type of the contaminant, and acquire, from the search server, a washing method that is selected by satisfying a set condition among search results acquired from the search server, as a response to the request.

    5. The washing machine according to claim 1, further comprising: a microphone configured to capture speech; and a camera configured to capture an image of the laundry, wherein the memory further stores a code configured to cause the processor to identify the type of the contaminant based on at least one of the speech inputted via the microphone or the image of the laundry captured by the camera.

    6. The washing machine according to claim 5, wherein the memory further stores a code configured to cause the processor to: further identify, based on at least one of the speech or the image, laundry information comprising at least one of a garment type of the laundry, a material type of the laundry, a color type of the laundry or an area of the contaminant, and determine the first washing process further in response to the laundry information.

    7. The washing machine according to claim 5, wherein the memory further stores a code configured to cause the processor to: estimate a color of the contaminant based on a result of the type of the contaminant being identified from the speech inputted via the microphone, determine a similarity between a color of the laundry identified from the image of the laundry photographed by the camera and the color of the contaminant, change a color depth used for identifying the type of contaminant based on the similarity, and determine an area of the contaminant based on the changed color depth.

    8. The washing machine according to claim 5, wherein the memory further stores a code configured to cause the processor to: start control of the driver based on a second washing process performed before identifying the type of the contaminant, determine the first washing process based on the type of the contaminant identified from the speech inputted via the microphone, and compare the first washing process to the second washing process.

    9. The washing machine according to claim 1, further comprising: a speaker; a microphone configured to capture speech; and a camera configured to capture an image of the laundry, wherein the memory further stores a code configured to cause the processor to inquire about the type of the contaminant through the speaker, in response to a result of comparing a first type of the contaminant identified from speech inputted via the microphone and a second type of the contaminant identified from the image of the laundry captured by the camera.

    10. The washing machine according to claim 1, further comprising: a speaker; a microphone configured to capture speech; and a camera configured to capture an image of the laundry, wherein the memory further stores a code configured to cause the processor to: identify, in response to a wake-up word recognized from speech inputted via the microphone, a garment type of the laundry together with the type of the contaminant based on the speech, and determine the first washing process based on the type of the contaminant and the garment type of the laundry.


    [0044] The washing support server 130 may be, for example, an artificial intelligence (AI) server, and may be a database server that provides big data required for applying an AI algorithm (for example, a contaminant recognition algorithm) and various pieces of service information based on the big data.



    Patent 2:
    https://appft.uspto.gov/netacgi/nph-Parser?Sect1=PTO2&Sect2=HITOFF&u=%2Fnetahtml%2FPTO%2Fsearch-adv.html&r=1&f=G&l=50&d=PG01&p=1&S1=20200002868&OS=20200002868&RS=20200002868
    United States Patent Application20200002868
    1Kind CodeA1
    2YANG; JiyounJanuary 2, 2020
    METHOD AND APPARATUS FOR CONTROLLING DETERGENT QUANTITY

    Abstract

    Provided are a washing machine based on artificial intelligence and a method of controlling a detergent quantity thereof. The method of controlling a detergent quantity of a washing machine based on artificial intelligence (AI) includes obtaining information about a kind of detergent from an external information collector; applying the information about a kind of detergent to a pre-learned artificial neural network (ANN) model; determining a kind of the detergent based on the application result; receiving appropriate detergent quantity information from the server according to the determined kind of detergent; and determining whether a supplied detergent quantity satisfies an appropriate detergent quantity. Thereby, it can be guided to use an appropriate quantity of detergent according to a laundry amount. An AI device may be connected to a drone (unmanned aerial vehicle (UAV)), a robot, an augmented reality (AR) device, a virtual reality (VR) device, a device related to a 5G service, and the like.


    Claims

    1. A method of controlling a detergent quantity of a washing machine based on artificial intelligence (AI), the method comprising: obtaining information about a kind of detergent from an external information collector; applying the information about a kind of detergent to a pre-learned artificial neural network (ANN) model; determining a kind of the detergent based on the application result; receiving predetermined detergent quantity information from the server according to a laundry amount based on the determined kind of detergent; and determining whether the detergent quantity supplied through a detergent inlet is less than the predetermined detergent quantity based on the detergent quantity information.

    2. The method of claim 1, wherein the predetermined detergent quantity is a value determined in advance by a manufacturer of the detergent according to the laundry amount.

    3. The method of claim 1, wherein the external information collector comprises at least one of a camera or a microphone.

    4. The method of claim 1, further comprising obtaining information about a kind of the detergent from a message received from a user terminal.

    5. The method of claim 1, further comprising displaying information of an insufficient detergent quantity through a display of the washing machine or outputting information of an insufficient detergent quantity through a speaker of the washing machine, when the detergent quantity is less than the predetermined detergent quantity.

    6. The method of claim 1, further comprising: when the detergent quantity exceeds the predetermined detergent quantity, supplying the detergent corresponding to the predetermined quantity of detergent together with the washing water to the inner tub of the washing machine; and storing the remaining detergent, except for the supplied detergent in a detergent storage of the washing machine.

    10. The method of claim 1, wherein the neural network model is stored in an artificial intelligence (AI) device, and wherein the applying of the information comprises: transmitting a feature value related to information about a kind of detergent to the AI device; and obtaining a result in which information about a kind of detergent is applied to the artificial neural network model from the AI device.

    11. The method of claim 1, wherein the artificial neural network model is stored in a network, and wherein the applying of the information comprises: transmitting information about a kind of the detergent to the network; and obtaining a result in which information about a kind of the detergent is applied to the artificial neural network model from the network.

    12. A washing machine based on artificial intelligence, the washing machine comprising: a controller; a memory; a communication circuit; a processor; and an external information collector, wherein information about a kind of detergent is obtained from the external information collector, and by applying the information about the kind of detergent to a pre-learned Artificial Neural Network (ANN), the kind of detergent is determined, and it is determined whether a quantity of detergent supplied through a detergent inlet is less than the predetermined detergent quantity based on predetermined detergent quantity information according to a laundry amount and a kind of detergent received through the communication circuit.


 
watchlist Created with Sketch. Add BRN (ASX) to my watchlist
(20min delay)
Last
20.0¢
Change
-0.005(2.44%)
Mkt cap ! $371.1M
Open High Low Value Volume
20.5¢ 20.5¢ 19.5¢ $843.2K 4.220M

Buyers (Bids)

No. Vol. Price($)
5 71948 20.0¢
 

Sellers (Offers)

Price($) Vol. No.
20.5¢ 644737 16
View Market Depth
Last trade - 16.10pm 26/07/2024 (20 minute delay) ?
BRN (ASX) Chart
arrow-down-2 Created with Sketch. arrow-down-2 Created with Sketch.