FORM 2

THE PATENTS ACT, 1970

(39 of 1970)

&

THE PATENTS RULES, 2003

COMPLETE SPECIFICATION

1. TITLE OF THE INVENTION

SYSTEM AND METHOD TO SEGREGATE THE FRUITS BY MACHINE

LEARNING

2. APPLICANT(S)

NAME – DR. MALLIKHARJUNA RAO K

NATIONALITY - INDIAN
ADDRESS – DEPARTMENT OF DATA SCIENCE AND ARTIFICIAL INTELLIGENCE,
INTERNATIONAL INSTITUTE OF INFORMATION TECHNOLOGY NAYA RAIPUR, PLOT
7, SECTOR 24, ATAL NAGAR, CHHATTISGARH-493661, INDIA
NAME – MR. YATHIN PRAKASH KETHEPALLI
NATIONALITY - INDIAN
ADDRESS – COMPUTER SCIENCE AND ENGINEERING, INTERNATIONAL INSTITUTE
OF INFORMATION TECHNOLOGY NAYA RAIPUR, PLOT 7, SECTOR 24, ATAL NAGAR,
CHHATTISGARH-493661, INDIA
NAME – MS. CHAHAT MITTAL
NATIONALITY - INDIAN
ADDRESS – ELECTRONICS AND COMMUNICATION ENGINEERING INTERNATIONAL
INSTITUTE OF INFORMATION TECHNOLOGY NAYA RAIPUR, PLOT 7, SECTOR 24,
ATAL NAGAR, CHHATTISGARH-493661, INDIA

3. PREAMBLE TO DESCRIPTION

COMPLETE SPECIFICATION -The following specification particularly describes the invention and
the manner in which it is to be performed.

1
 SYSTEM AND METHOD TO SEGREGATE THE FRUITS BY MACHINE
LEARNING

Field of the Invention

[0001] The present invention relates generally to system and method for handling of
agricultural products such as fruits and vegetables. More particularly, method and system to segregate
the agricultural products based on size and quality thereof, using a machine learning mechanism.

Background

[0002] The background description includes information that may be useful in understanding
the present invention. It is not an admission that any of the information provided herein is prior art or
relevant to the presently claimed invention, or that any publication specifically or implicitly referenced
is prior art.

[0003] Generally, vegetables and fruits, which are high in protein, vitamins, dietary fibre are
preferred for human health. Different vegetables and fruits contain a variety of organic acids, aromatic
compounds, and pigment components like red, green, yellow, blue, and purple. These significantly
amplify nutritional value for boosting appetite and facilitating digestion.

[0004] Due to the changing environment, the quality of vegetables and fruits varies. Mainly
quality embodies appearance characteristics, size, freshness and the like. These agricultural products
are sorted into different grades according to the size, shape, texture, colour, and volume to fetch high
prices.

[0005] The fruits of the same kind can also be classified into different grades, according to
the diameter size specifications. The current grading is typically performed by visual inspection and
measuring tools, which are inaccurate, ineffective and require higher human efforts. Additionally, the
equipment required for weight-based grading is expensive and complex, which makes it unsuitable and
lesser acceptable among people.

[0006] Various technological solutions (e.g., fruit-vegetable sorting equipment, fruit

conveying device, fruit grading equipment, etc.) are disclosed in patent literature. Few of the exemplary
documents are discussed below.

[0007] The CN211254175U (By- Hebei Xionghan Agricultural Products Co ltd) relates to a
fruit conveyer belongs to fruit transport means ccomprises` a belt conveyor for conveying the fruits in
boxes, and also comprises a support plate with universal wheels; the belt conveyor is fixed on the upper
2
surface of the support plate; an ultraviolet disinfection box is fixedly arranged on a bracket of the belt
conveyor, and a conveyor belt of the belt conveyor penetrates through the ultraviolet disinfection box;
the support at the discharge end of the belt conveyor extends out of the conveyor belt and is provided
with a material distribution device, the material distribution device comprises two symmetrically
arranged inclined slideways and a T-shaped material distribution plate positioned between the two
inclined slideways, and a vertical plate of the T-shaped material distribution plate is arranged along the
length direction of the belt conveyor and is positioned on the extension line of the central line of the
belt conveyor; the lower end of the support plate is provided with a plurality of lifting electric cylinders,
the fixed ends of the lifting electric cylinders are fixed with the lower end face of the support plate, and
the telescopic ends of the lifting electric cylinders are arranged downwards; the width of the belt
conveyor is two times or more than the width of the fruit box.

[0008] The CN215198272U (By- Jiangxi Reemoon Technology Holdings Co ltd) relates to
a fruit conveying device, which aims to solve the problems that the separated fruits are easy to extrude
each other in the current fruit separation and transfer process, the fruits are damaged and the product
quality is reduced; this fruit conveyer includes the frame, and fixed mounting's sorting passageway and
right-hand member fixed mounting's belt conveyor in the frame, the one end fixed mounting who selects
separately the passageway has the buffering mouth that drops, belt conveyor is last fixed mounting has
the reposition of redundant personnel shelves pole that is used for the reposition of redundant personnel
of fruit. The fruit conveying device can better separate the sorted fruits by adding a plurality of sorting
channels, and reduces mutual contact when sorting materials; this fruit conveyer drops mouth and
buffering brush through the buffering, can be to the better protection of fruit, the integrality of further
protection fruit reduces the injury that causes fruit among the sorting process, better protects.

[0009] However, the technological solutions for segregating fruits and vegetables suffer from
various limitations such as inefficiency, expensiveness, etc. Thus, there remains a need for further
contributions in this area of technology. More specifically, a need exists in the area of technology to
segregate the fruits.

Objects of the Invention

[00010] An object of the present disclosure is to overcome one or more drawbacks associated
with conventional mechanisms.

[00011] Another object of the present disclosure is to separate fruits/vegetables based on

quality.

[00012] An exemplary object of present invention is to segregate the fruits based on size.

3
[00013] Yet another object of foreclosed invention is to monitor a ripening status of the fruits.

[00014] Another object of the present disclosure is to monitor a current ambience parameter
of the fruits kept in a container.

[00015] An exemplary object of present invention is to discard over ripened fruits.

[00016] An yet another object of foreclosed invention is to enable real-time monitoring of

current ambience parameter.

Summary

[00017] The present invention relates generally to system and method for handling of
agricultural products such as fruits and vegetables. More particularly, method and system to segregate
the agricultural products based on size and quality thereof, using a machine learning mechanism.

[00018] The following presents a simplified summary of various aspects of this disclosure in
order to provide a basic understanding of such aspects. This summary is not an extensive overview of
all contemplated aspects, and is intended to neither identify key or critical elements nor delineate the
scope of such aspects. Its purpose is to present some concepts of this disclosure in a simplified form as
a prelude to the more detailed description that is presented later.

[00019] The following paragraphs provide additional support for the claims of the subject
application.

[00020] In an aspect the present disclosure provides a system to segregate the fruits, the system
comprising: a conveyor unit that comprises: a first end that is arranged to receive the fruits from a user;
a second end; a body that extends from the first end to the second end, wherein the body comprises a
first rotating belt to enable a movement of the received fruits from the first end to the second end; and
a separator element is disposed at the second end to segregate the good quality fruits and the average
quality fruits from the received fruits; and a first motor that is coupled with the separator element,
wherein the first motor transforms the separator element between a first position and a second position;
a first image sensor that is disposed at a first pre-set distance from the body, wherein the first image
sensor captures an image of the received fruits; a bifurcation unit, which is disposed at the second end,
wherein the bifurcation unit comprises: a first segregator arm that is arranged to receive the good quality
fruits, wherein the first segregator comprises: a first primary end; and a first secondary end; a first
mid-section that extends from the first primary end to the first secondary end, wherein the first mid-
section comprises a second rotating belt to enable a movement of the received good quality fruits from
the first primary end to the first secondary end; a first partition element is disposed at the first secondary
end to segregate the received good quality fruits into the large size good quality fruits and the small size
4
good quality fruits; and a second motor that is coupled with the first partition element, wherein the
second motor transforms the first partition element between a third position and a fourth position; a
second image sensor that is disposed at a second pre-set distance from the first mid-section, wherein
the second image sensor captures an image of the received good quality fruits; and a first division unit
that is disposed at the secondary end, wherein the first division unit is coupled with: a first container
that is arranged to receive the large size good quality fruits; and a second container that is arranged to
receive the small size good quality fruits; a second segregator arm that is arranged to receive the average
quality fruits, wherein the second segregator comprises: a second primary end; and a second
secondary end; a second mid-section that extends from the second primary end to the second secondary
end, wherein the second mid-section comprises a third rotating belt to enable a movement of the
received average quality fruits from the second primary end to the second secondary end; a second
partition element is disposed at the second secondary end to segregate the received average quality fruits
into the large size average quality fruits and the small size average quality fruits; a third motor that is
coupled with the second partition element, wherein the third motor transforms the second partition
element between a fifth position and a sixth position; a third image sensor that is disposed at a third pre-
set distance from the second mid-section, wherein the third image sensor captures an image of the
received average quality fruits; and a second division unit that is disposed at the second secondary end,
wherein the second division unit is coupled with: a third container that is arranged to receive the large
size average quality fruits; and a fourth container that is arranged to receive the small size average
quality fruits; and a controller device that is arranged to: acquire the captured image of, the received
fruits, the received good quality fruits and the received average quality fruits, from the first image
sensor, the second image sensor and the third image sensor, respectively; analyse the acquired image of
the fruits to determine the first quality fruits and the second quality fruits; analyse the determined first
quality fruits to identify, the large size first quality fruits and the small size first quality fruits; analyse
the determined second quality fruits to identify, the large size second quality fruits and the small size
second quality fruits; and control a supply of electrical energy to the first motor, the second motor and
the third motor, to segregate the fruits.

[00021] In an embodiment, the each amongst the first container, the second container, the third
container and the fourth container, comprises a sensing module to determine a current ambience
parameter, a fan assembly, a control unit and a memory unit to store an optimum ambience parameter
database.

[00022] In an embodiment, the sensing module comprises a temperature sensor, a humidity

sensor, a gas sensor, to determine a current temperature, a current humidity and a current gas
concentration, respectively.

5
[00023] In an embodiment, the fan assembly is activated based on the determined current
temperature, the current humidity and the current gas concentration, respectively.

[00024] In an embodiment, the determined, current temperature, current humidity and current
gas concentration, corresponding to the first container, the second container, the third container and the
fourth container, is transmitted to a cloud server by the each control unit.

[00025] In an embodiment, the each amongst the first container, the second container, the third
container and the fourth container, comprises an alert unit, which is activated based on the determined
current gas concentration.

[00026] In an embodiment, the conveyor unit comprises an openable duct to dispose the bad
quality fruits.

[00027] In an embodiment, the conveyor unit is coupled with a waste collection container to
receive the bad quality fruits.

[00028] In an embodiment, the first division unit is coupled with a second conveyor to
bifurcate the identified large size good quality fruits and the identified small size good quality fruits.

[00029] In an embodiment, the second division unit is coupled with a third conveyor to
bifurcate the identified large size average quality fruits and the identified small size average quality
fruits.

Brief Description of the Drawings

[00030] The features and advantages of the present disclosure would be more clearly
understood from the following description taken in conjunction with the accompanying drawings in
which:

[00031] Fig. 1 illustrates a system architecture to segregate the fruits and

components/elements thereof, in accordance to embodiments of present disclosure.

[00032] Fig. 2 illustrates exemplary functional units to segregate the fruits, in accordance with
embodiments of the present disclosure.

[00033] Fig. 3 illustrates exemplary complete working model to segregate the fruits, in
accordance with embodiments of the present disclosure.

[00034] Fig. 4 illustrates exemplary tabular data to depict quality of fruits, in accordance with
embodiments of the present disclosure.

6
[00035] Fig. 5 illustrates exemplary tabular data to depict current ambience parameter of fruits
in a container, in accordance with embodiments of the present disclosure.

[00036] Fig. 6 illustrates exemplary machine learning protocol to segregate the fruits based on
quality, in accordance with embodiments of the present disclosure.

Detailed Description

[00037] In the following detailed description of the invention, reference is made to the
accompanying drawings that form a part hereof, and in which is shown, by way of illustration, specific
embodiments in which the invention may be practiced. In the drawings, like numerals describe
substantially similar components throughout the several views. These embodiments are described in
sufficient detail to claim those skilled in the art to practice the invention. Other embodiments may be
utilized and structural, logical, and electrical changes may be made without departing from the scope
of the present invention. The following detailed description is, therefore, not to be taken in a limiting
sense, and the scope of the present invention is defined only by the appended claims and equivalents
thereof.

[00038] The use of the terms “a” and “an” and “the” and “at least one” and similar referents
in the context of describing the invention (especially in the context of the following claims) are to be
construed to cover both the singular and the plural, unless otherwise indicated herein or clearly
contradicted by context. The use of the term “at least one” followed by a list of one or more items (for
example, “at least one of A and B”) is to be construed to mean one item selected from the listed items
(A or B) or any combination of two or more of the listed items (A and B), unless otherwise indicated
herein or clearly contradicted by context. The terms “comprising,” “having,” “including,” and
“containing” are to be construed as open-ended terms (i.e., meaning “including, but not limited to,”)
unless otherwise noted. Recitation of ranges of values herein are merely intended to serve as a shorthand
method of referring individually to each separate value falling within the range, unless otherwise
indicated herein, and each separate value is incorporated into the specification as if it were individually
recited herein. All methods described herein can be performed in any suitable order unless otherwise
indicated herein or otherwise clearly contradicted by context. The use of any and all examples, or
exemplary language (e.g., “such as”) provided herein, is intended merely to better illuminate the
invention and does not pose a limitation on the scope of the invention unless otherwise claimed. No
language in the specification should be construed as indicating any non-claimed element as essential to
the practice of the invention.

7
[00039] The present invention relates generally to system and method for handling of
agricultural products such as fruits and vegetables. More particularly, method and system to segregate
the agricultural products based on size and quality thereof, using a machine learning mechanism.

[00040] Referring now to the invention in more detail, in Fig. 1 there is shown a system
architecture 100 to segregate the fruits and components/elements thereof, in accordance to embodiments
of present disclosure. Referring now to the invention in more detail, in Fig. 1 there is shown a conveyor
unit 102, a first image sensor 104, a bifurcation unit 106, a controller device 128 and other known
components of a fruit/vegetable conveyor device/apparatus. Data communication means to
communicate with different components or external computing environment, and an electrical energy
source to provide electrical energy to the one or more components of system architecture 100. It can be
appreciated that the aforementioned components of system architecture 100 are communicably coupled
with each other.

[00041] In an embodiment, the conveyor unit 102 can be arranged to receive the fruits (not
limited to reception of the fruits) from a user and transport the received fruits from one location to
another, with or without human intervention. The conveyor unit 102 allows quick and efficient transport
for a wide variety of materials (which may include fruits, vegetables, etc.). The conveyor unit 102 may
comprise a first end 102-A, a second end 102-B, a body 102-C, a separator element 102-D, a first motor
102-E and other known components of a belt conveyor device/apparatus.

[00042] In an embodiment, the first end 102-A can be arranged to receive the fruits from the
user or any other means, wherein the received fruits can be of distinct size and quality.

[00043] In an embodiment, the second end 102-B can be spaced apart from the first end 102-
A, wherein the space can be a distance between the first end 102-A and the second end 102-B. The
second end 102-B may be associated with numerous components, which can be utilized in separation
of the received fruits, based on the distinct factors (such as quality, etc.).

[00044] In an embodiment, the body 102-C may extend from the first end 102-A to the second
end 102-B, wherein the body 102-C may comprise a first rotating belt to enable movement of the
received fruits from the first end 102-A to the second end 102-B. The fruits can be conveyed directly
on the first rotating belt so both regular and irregular shaped objects, large or small, light and heavy,
can be transported successfully. The first rotating belt can also be manufactured with curved sections
that may use tapered rollers and curved belting to convey products around a corner.

[00045] In an embodiment, the separator element 102-D can be disposed at the second end
102-B to segregate the first quality fruits (interchangeably referred as good quality fruits) and the second

8
quality fruits (interchangeably referred as average quality fruits) from the received fruits based on an
analysis performed (for determining a quality of the received fruits) by the controller device 128. The
separator element 102-D can be pivotally affixed at the second end 102-B and can be moved between
a first position and a second position to enable restricted movement of the received fruits, based on the
determined quality of the fruits.

[00046] In an embodiment, the first motor 102-E can be coupled with the separator element
102-D, wherein the first motor 102-E may transform the separator element 102-D between the first
position and the second position (based on signal received from the controller device 128) to allow the
movement of the received fruits based on the determined quality. The first motor 102-E may rotate in
clockwise and anti-clockwise to enable the movement of the separator element 102-D. The first motor
102-E can be a conventional electric motor. Central components of the first motor 102-E can be an
immovable stator, with a stable magnetic field, a rotor (also anchor) and a pole changer (polwender.The
first motor 102-E can be selected from a stepper motor, a DC motor, a servo motor, etc.

[00047] In an embodiment, the first image sensor 104 (e.g., Raspberry Pi Camera, 3D scanner,
CMOS camera, IR camera, DSLR camera etc.) can be disposed at a first pre-set distance from the body
102-C, wherein the first image sensor 104 may capture an image of the received fruits. The captured
image can be analysed by the controller device 128 to segregate the received fruits based on quality.
The first image sensor 104 can be a sensor that may detect and convey information which can be used
to make an image. The first image sensor 104 can be used in electronic imaging devices of both analog
and digital types, which may include digital cameras, camera modules, a night vision camera, etc.

[00048] In an embodiment, the bifurcation unit 106 can be disposed at the second end 102-B
to receive the segregated fruits (good quality fruits and average quality fruits), based on the determined
quality. The bifurcation unit 106 may comprise a first segregator arm 108, a second segregator arm 118
and other known components of a Y-shaped conveyor device/apparatus.

[00049] In an embodiment, the first segregator arm 108 can be arranged to receive the good
quality fruits, which can be segregated from the received fruits, upon transformation of the separator
element 102-D at the first position (using the first motor 102-E). When the separator element 102-D is
at the first position, the path towards the second segregator arm 118 may be blocked, thereby enabling
the movement of the good quality fruits towards the first segregator arm 108. The first segregator arm
108 may comprise a first primary end 108-A, a first secondary end 108-B, a first mid-section 108-C, a
first partition element 108-D, a second motor 108-E, a second image sensor 110 and a first division unit
112.

9
[00050] In an embodiment, the first primary end 108-A can be arranged to receive the good
quality fruits from the conveyor unit 102, which may enable the movement of the good quality fruits
towards the first primary end 108-A, upon transformation of the separator element 102-D at the first
position.

[00051] In an embodiment, the first secondary end 108-B can be spaced apart from the first
primary end 108-A, wherein the space can be a distance between the first primary end 108-A and the
first secondary end 108-B. The first secondary end 108-B may be associated with numerous
components, which can be utilized in separation of the received good quality fruits, based on size.

[00052] In an embodiment, the first mid-section 108-C may extend from the first primary end
108-A to the first secondary end 108-B, wherein the first mid-section 108-C may comprise a second
rotating belt to enable a movement of the received good quality fruits from the first primary end 108-A
to the first secondary end 108-B. The good quality fruits can be conveyed directly on the second rotating
belt so that both large or small good quality fruits can be transported successfully. The second rotating
belt can also be manufactured with curved sections that may use tapered rollers and curved belting to
convey products around a corner.

[00053] In an embodiment, the first partition element 108-D can be disposed at the first
secondary end 108-B to segregate the first size first quality fruits (interchangeably referred as large size
good quality fruits) and the second size first quality fruits (interchangeably referred as small size good
quality fruits) from the received good quality fruits based on analysis performed (for determining a size
of the received good quality fruits) by the controller device 128. The first partition element 108-D can
be pivotally affixed at the first secondary end 108-B and can move between a third position and a fourth
position to enable restricted movement of the received good quality fruits, based on the determined size
of the received good quality fruits.

[00054] In an embodiment, the second motor 108-E can be coupled with the first partition
element 108-D, wherein the second motor 108-E may transform the first partition element 108-D
between the third position and the fourth position, based on signal received from the controller device
128, to allow the movement of the received good quality fruits based on the determined size. The second
motor 108-E may rotate clockwise and anti-clockwise to enable the movement of the first partition
element 108-D. The second motor 108-E can be a conventional electric motor, a stepper motor, a DC
motor, a servo motor, etc.

[00055] In an embodiment, the second image sensor 110 can be disposed at a second pre-set
distance from the first mid-section 108-C, wherein the second image sensor 110 may capture image of

10
the received good quality fruits. The captured image can be analysed by the controller device 128 to
segregate the received good quality fruits based on the size (small or large). The second image sensor
110 can be a sensor that may detect and convey information which can be used to make image. The
second image sensor 110 can be used in electronic imaging devices of both analog and digital types,
which may include digital cameras, camera modules, a night vision camera, etc. The second image
sensor 110 can be a charge-coupled device (CCD) or an active-pixel sensor (CMOS sensor).

[00056] In an embodiment, the first division unit 112 can be arranged to enable the movement
of the large size good quality fruits in a first direction, and the small size good quality fruits in a second
direction. The first division unit 112 may be associated with a first left conveyor belt and a first right
conveyor belt for transferring the large size good quality fruits in the first direction and small size good
quality fruits in the second direction. The first division unit 112 can be coupled with a first container
114, which may be placed in the first direction to receive the large size good quality fruits, which can
be packed within the first container 114. The first division unit 112 can be coupled with a second
container 116, which may be placed in the second direction to receive the small size good quality fruits.

[00057] In an embodiment, the second segregator arm 118 can be arranged to receive the
average or poor quality fruits, which can be segregated from the received fruits, upon transformation of
the separator element 102-D at the second position (using the first motor 102-E). When the separator
element 102-D is at the second position, the path towards the first segregator arm 108 may be blocked,
thereby enabling the movement of the average quality fruits towards the second segregator arm 118.
The second segregator arm 118 may comprise a second primary end 118-A, a second secondary end
118-B, a second mid-section 118-C, a second partition element 118-D, a third motor 118-E, a third
image sensor 120 and a second division unit 122.

[00058] In an embodiment, the second primary end 118-A can be arranged to receive the
average quality fruits from the conveyor unit 102, which may enable the movement of the average
quality fruits towards the second primary end 118-A, upon transformation of the separator element 102-
D at the second position.

[00059] In an embodiment, the second secondary end 118-B can be spaced apart from the
second primary end 118-A, wherein the space can be a distance between the second primary end 118-
A and the second secondary end 118-B. The second secondary end 118-B may be associated with
numerous components, which can be utilized in separation of the received average quality fruits, based
on size.

11
[00060] In an embodiment, the second mid-section 118-C may extend from the second
primary end 118-A to the second secondary end 118-B, wherein the second mid-section 118-C may
comprise a third rotating belt to enable a movement of the received average quality fruits from the
second primary end 118-A to the second secondary end 118-B. The average quality fruits can be
conveyed directly on the third rotating belt so that both large or small average quality fruits can be
transported successfully. The third rotating belt can also be manufactured with curved sections that may
use tapered rollers and curved belting to convey products around a corner.

[00061] In an embodiment, the second partition element 118-D can be disposed at the second
secondary end 118-B to segregate the first size second quality fruits (interchangeably referred as large
size average quality fruits and the second size second quality fruits (interchangeably referred as small
size average quality fruits) from the received average quality fruits based on an analysis performed (for
determining a size of the received average quality fruits) the controller device 128. The second partition
element 118-D can be pivotally affixed at the second secondary end 118-B and can be moved between
a fifth position and a sixth position to enable restricted movement of the received average quality fruits,
based on the determined size of the received average quality fruits.

[00062] In an embodiment, the third motor 118-E can be coupled with the second partition
element 118-D, wherein the third motor 118-E may transform the second partition element 118-D
between the fifth position and the sixth position (based on signal received from the controller device
128) to allow the movement of the received average quality fruits based on the determined size. The
third motor 118-E may rotate in clockwise and anti-clockwise enable the movement of the second
partition element 118-D. The third motor 118-E can be a conventional electric motor. The third motor
118-E can be selected from a stepper motor, a DC motor, a servo motor, etc.

[00063] In an embodiment, the third image sensor 120 can be disposed at a third pre-set
distance from the second mid-section 118-C, wherein the third image sensor 120 may capture an image
of the received average quality fruits. The captured image can be analysed by the controller device 128
to segregate the received average quality fruits based on the size (small or large). The third image sensor
120 can be a sensor that may detect and convey information which can be used to make an image.

[00064] In an embodiment, the second division unit 122 can be arranged to enable the
movement of the large size average quality fruits in a third direction and enable the movement of the
small size average quality fruits in a fourth direction. The second division unit 122 may be associated
with a third left conveyor belt and a fourth right conveyor belt for moving the, large size average quality
fruits in the third direction and small size average quality fruits in the fourth direction. The second
division unit 122 can be coupled with a third container 124, which may be placed in the third direction
12
to receive the large size average quality fruits, which can be packed within the third container 124 and
can be further processed for selling. The second division unit 122 can be coupled with a fourth container
126, which may be placed in the fourth direction to receive the small size average quality fruits, which
can be packed within the fourth container 126 and can be further processed for selling.

[00065] In an embodiment, to determine size of fruits the controller device 128 may remove
background from each of the received image and define counter (i.e., outer perimeter of fruit) to
determine size. Further, the controller device 128 may utilize pre-stored rules to categorise fruits as
either small (e.g., counter corresponds to smaller sized fruit) and large/big if the counter corresponds to
large fruit. Similarly, controller device 128 may determine surface irregularities (e.g., presence of
spotting, wrinkle, surface cut etc.) to enable categorization of fruits as good quality or poor quality.

[00066] In an embodiment, the controller device 128 (e.g., Raspberry Pi 4 Model B) can be
arranged to enable segregation of fruits based on various factors such as quality and size. The controller
device 128 may acquire the captured image of, the received fruits, the received good quality fruits and
the received average quality fruits, from the first image sensor 104, the second image sensor 110 and
the third image sensor 120, respectively, in a run-time or near run-time manner through known
communication means (wired or wireless). The controller device 128 may analyse the acquired image
of the fruits to determine the primary quality fruits (which can be of good quality) and the secondary
quality fruits (which can be of average quality) by applying a machine learning protocol (utilizing a
pre-saved database comprising multiple fruits images) which can be selected from artificial neural
network (ANN), convolutional neural network (CNN), hybrid markov model (HMM), artificial
intelligence (AI), deep learning, etc. The controller device 128 may analyse the determined primary
quality fruits to identify, the first size primary quality fruits (interchangeably referred as large size first
quality fruits) and the second size primary quality fruits (interchangeably referred as small size first
quality fruits) by applying a machine learning technique (which can be selected from ANN, CNN,
HMM, AI, deep learning, etc.). The controller device 128 may analyse the determined secondary quality
fruits to identify, the first size secondary quality fruits (interchangeably referred as large size second
quality fruits) and the second size secondary quality fruits (interchangeably referred as small size second
quality fruits) by applying a machine learning model (which can be selected from ANN, CNN, HMM,
AI, deep learning, etc.). The controller device 128 may control a supply of electrical energy to the first
motor 102-E, the second motor 108-E and the third motor 118-E, to segregate the fruits by altering the
position of the separator element 102-D (between first position and second position), the first partition
element 108-D (between third position and fourth position) and the second partition element 118-D
(between fourth position and sixth position), respectively.

13
[00067] In an aspect, the known fruit sorting mechanism involves separation of fruits based
on any one of the criteria, which includes quality or size. The known fruit sorting mechanisms are
limited to sorting and grading of fruits. The present disclosure provides and multi-prong approach to
sort fruits based on both the criteria, that is quality and size, which makes grading more successful in
terms of time and human effort. A ripening status of the fruits of numerous quality and size is
continuously monitored, wherein the determined ripening status are transmitted over a cloud server
using a blockchain technology.

[00068] In an embodiment, the each amongst the first container 114, the second container
116, the third container 124 and the fourth container 126, may comprise a fan assembly and a sensing
module to determine a current ambience parameter (such as temperature, humidity, gas concentration
by), as temperature and humidity can be a vital factor for ripening of the fruits and gas concentration
(such as concentration of ethylene) may indicate a ripening status of the fruits.

[00069] In an embodiment, the sensing module may comprise a temperature sensor (e.g.,
DHT 11 sensor), a humidity sensor (e.g., DHT 11 sensor), a gas sensor (e.g., MQ3 sensor), to determine
a current temperature, a current humidity and a current gas concentration, respectively, wherein the
current temperature and current humidity may affect the quality of the fruits by causing ripening. The
current gas concentration may indicate a current ripening status, based on which the control unit may
control activation/deactivation of then fan assembly.

[00070] In an embodiment, the fan assembly can be activated based on the determined current
temperature, the current humidity and the current gas concentration, respectively, by analysing the
optimum ambience parameter database. The control unit may apply a machine learning approach (which
can be selected from ANN, CNN, HMM, AI. deep learning, etc.) for activating/deactivating and
controlling the speed of the fan assembly, to prevent the ripening of the fruits.

[00071] In an embodiment, the determined, current temperature, current humidity and current
gas concentration, corresponding to the first container 114, the second container 116, the third container
124 and the fourth container 126, is transmitted to a cloud server by the each control unit, to enable
regular monitoring by a person or by means of automation. The current ambience parameter (the
determined, current temperature, current humidity and current gas concentration) corresponding to the
each amongst the first container 114, the second container 116, the third container 124 and the fourth
container 126 (or any other container) using a blockchain technology, which can be a type of digital
ledger technology (DLT) that consists of growing list of records, called blocks, that are securely linked
together using cryptography.

14
[00072] The fan assembly comprises a fan and a control unit (e.g., ESP-8266 Node), wherein
the fan assembly can be configured to adjust the current ambience parameter. The control unit (e.g.,
ESP-8266 Node) can be arranged to receive the determined current ambience parameter and control the
fan, if the determined ambience parameter is greater than a pre-set condition. For example, if determined
alcohol concentration (determined through MQ-3) is greater than 225 PPM or temperature is greater
than 30°F or humidity is greater than 90% or data of MQ-135 is greater than 60 PPM, then the control
unit may activate fan to control ambience through removal of excessive heat, moisture and ethyl alcohol
may slower down ripping process and extend life of fruits by maintaining freshness. Thus, present
disclosure may reduce fruit wastage and thereby reduce economic loss to relevant stakeholder such as
framer, logistic partner, etc.

[00073]

[00074] In an embodiment, each amongst the first container 114, the second container 116,
the third container 124 and the fourth container 126, may comprise an alert unit, which is activated
based on the determined current gas concentration, wherein the activation of the alert unit may indicate
an over ripening status of the fruits. Based on the activation of the alert unit, a worker may dispose of
the over ripped fruits, from first container 114, second container 116, third container 124 or fourth
container 126.

[00075] In an embodiment, the conveyor unit 102 may comprise an openable duct to dispose
the third quality fruits (interchangeably referred as bad quality fruits), which can be identified along
with the identification of the good quality fruits and the average quality fruits by application of the
machine learning protocol. The controller device 128 may control opening/closing of the openable duct
for disposal of bad quality fruits. The ripping status may also provide valuable feedback about current
condition of fruit. If fruit is over ripe, then fruit can be consumed rapidly or put under reduced price.
Upon detection of sufficient ripeness, the cloud server may suggest nearby vendor (e.g., super market,
fruit store etc. ) at where the fruit can be sold out.

[00076] In an embodiment, the conveyor unit 102 can be coupled with a waste collection
container to receive the bad quality fruits, which could be disposed, as the gas produced by the bad
quality fruits may affect the good quality fruits and average quality fruits. The waste collection container
can be either carried manually or through means of automation for disposal of the bad quality fruits.

[00077] In an embodiment, the first division unit 112 can be coupled with a second conveyor
(possessing two separate arms) to bifurcate the identified first size primary quality fruits (which may
be large size good quality fruits) and the identified second size primary quality fruits (which can be

15
small size good quality fruits). The second conveyor may comprise a belt to carry the received large
size good quality fruits to the first container 114 and the received small size good quality fruits to the
second container 116.

[00078] In an embodiment, the second division unit 122 can be coupled with a third conveyor
(possessing two separate arms) to bifurcate the identified first size secondary quality fruits (which can
be large size average quality fruits) and the identified second size secondary quality fruits (which can
be small size average quality fruits). The third conveyor may comprise a carrier belt to carry the received
large size average quality fruits to the third container 124 and the received small size average quality
fruits to the fourth container 126.

[00079] Fig. 2 illustrates exemplary functional units to segregate the fruits, in accordance with
embodiments of the present disclosure. As illustrated, the functional unit 200 can comprise an
acquisition unit 202, a first analysis unit 204, a second analysis unit 206, a third analysis unit 208, a
supply control unit 210. The functional units 200 can be executed by processor of the controller device
128.

[00080] In an embodiment, the acquisition unit 202 can be configured to acquire the captured
image of, the received fruits, the received good quality fruits and the received average quality fruits,
from the first image sensor 104, the second image sensor 110 and the third image sensor 120,
respectively, in a run-time or near run-time manner through known communication means (wired or
wireless).

[00081] In an embodiment, the first analysis unit 204 can be configured to analyse the
acquired image of the fruits to determine the first quality fruits (which can be of good quality) and the
second quality fruits (which can be of average quality) by applying a machine learning protocol
(utilizing a pre-saved database comprising multiple fruits images) which can be selected from artificial
neural network (ANN), convolutional neural network (CNN), hybrid markov model (HMM), artificial
intelligence (AI), deep learning, etc.

[00082] In an embodiment, the second analysis unit 206 can be configured to analyse the
determined first quality fruits to identify, the large size first quality fruits and the small size first quality
fruits by applying a machine learning technique (which can be selected from ANN, CNN, HMM, AI,
deep learning, etc.).

[00083] In an embodiment, the third analysis unit 208 can be configured to analyse the
determined second quality fruits to identify, the large size second quality fruits and the small size second

16
quality fruits by applying a machine learning model (which can be selected from ANN, CNN, HMM,
AI, deep learning, etc.).

[00084] In an embodiment, the supply control unit 210 can be configured to control a supply
of electrical energy to the first motor 102-E, the second motor 108-E and the third motor 118-E, to
segregate the fruits by altering the position of the separator element 102-D (between first position and
second position), the first partition element 108-D (between third position and fourth position) and the
second partition element 118-D (between fourth position and sixth position), respectively.

[00085] Fig. 3 illustrates exemplary complete working model to segregate the fruits, in
accordance with embodiments of the present disclosure. The operating mechanism is divided into three
phases as shown in the illustration. Fruits are separated in the first phase using layer 1 of the system
architecture 100. By keeping track of the current ambience parameter throughout the second phase,
layer 2 assists in the continual evaluation of fruits. The third phase, which includes layer 3, gives
customers a platform to view the pricing, expiration date, and current ambience parameter. The solution
offers a cutting-edge replacement for conventional warehousing systems that addresses many
drawbacks. By automating the regulation of warehouse environment factors, this helps to reduce
physical labour, fruit loss, and seller decision-making when selling fruits. Manual errors are almost
eliminated as a result.

[00086] Fig. 4 illustrates exemplary tabular data to depict quality of fruits, in accordance with
embodiments of the present disclosure. As illustrated, fruits can be rated on a scale of 1 for quality. If
any of the rotten fruit has a quality value higher than 0.8, it can be removed from the remaining fruits
and thrown (called waste). The following criteria can be used to categorise fresh fruits: I) Fruit is
deemed to be of "Average quality" if its quality level is greater than 0.3 and less than 0.6. II) Fresh fruit
is deemed to be of "Good quality" if its quality level exceeds 0.6.

[00087] Fig. 5 illustrates exemplary tabular data to depict current ambience parameter of
fruits in a reservoir (i.e., first container 114, second container 116, third container 124 or fourth
container 126), in accordance with embodiments of the present disclosure. As illustrated, the data
includes ethylene level in ppm using MQ3 sensor (can detect alcohol concentrations between 25 and
500 parts per million), temperature and humidity in degree Celsius and percentage using DHT-11 sensor
(ranges between 0 and 50 degrees Celsius with +-2 degrees accuracy and humidity ranges between 20%
and 100% with 5% accuracy), and various harmful gases for pesticide detection using MQ135 sensor
(can detect ammonia gas, sulphur, benzene, toluene, hydrogen, carbon dioxide, smoke from 10 – 1000
parts per million).

17
[00088] Fig. 6 illustrates exemplary machine learning protocol to segregate the fruits based
on quality, in accordance with embodiments of the present disclosure. As illustrated, the fruit image is
provided as input to the resulting convolution neural network model. The pixel values will differ
because the intensities of the ripe and unripe regions of the fruit are varied. The present disclosure looks
at each input image pixel in an effort to identify these variations and returns whether the fruit is likely
to be fresh or ripe. By choosing the proper threshold value, the present disclosure may then decide if
the fruit is fresh or not. The threshold value can be determined automatically by creating a loss function
that reduces error magnitude and increases evaluation metric score.

[00089] Example embodiments herein have been described above with reference to block
diagrams and flowchart illustrations of methods and apparatuses. It will be understood that each block
of the block diagrams and flowchart illustrations, and combinations of blocks in the block diagrams and
flowchart illustrations, respectively, can be implemented by various means including hardware,
software, firmware, and a combination thereof. For example, in one embodiment, each block of the
block diagrams and flowchart illustrations, and combinations of blocks in the block diagrams and
flowchart illustrations can be implemented by computer program instructions. These computer program
instructions may be loaded onto a general purpose computer, special purpose computer, or other
programmable data processing apparatus to produce a machine, such that the instructions which execute
on the computer or other programmable data processing apparatus create means for implementing the
functions specified in the flowchart block or blocks.

[00090] Throughout the present disclosure, the term ‘processing means’ or ‘microprocessor’
or ‘processor’ or ‘processors’ includes, but is not limited to, a general purpose processor (such as, for
example, a complex instruction set computing (CISC) microprocessor, a reduced instruction set
computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, a
microprocessor implementing other types of instruction sets, or a microprocessor implementing a
combination of types of instruction sets) or a specialized processor (such as, for example, an application
specific integrated circuit (ASIC), a field programmable gate array (FPGA), a digital signal processor
(DSP), or a network processor).

[00091] The term “non-transitory storage device” or “storage” or “memory,” as used herein
relates to a random access memory, read only memory and variants thereof, in which a computer can
store data or software for any duration.

[00092] Operations in accordance with a variety of aspects of the disclosure is described

above would not have to be performed in the precise order described. Rather, various steps can be
handled in reverse order or simultaneously or not at all.
18
While several implementations have been described and illustrated herein, a variety of other means
and/or structures for performing the function and/or obtaining the results and/or one or more of the
advantages described herein may be utilized, and each of such variations and/or modifications is deemed
to be within the scope of the implementations described herein. More generally, all parameters,
dimensions, materials, and configurations described herein are meant to be exemplary and that the
actual parameters, dimensions, materials, and/or configurations will depend upon the specific
application or applications for which the teachings is/are used. Those skilled in the art will recognize,
or be able to ascertain using no more than routine experimentation, many equivalents to the specific
implementations described herein. It is, therefore, to be understood that the foregoing implementations
are presented by way of example only and that, within the scope of the appended claims and equivalents
thereto, implementations may be practiced otherwise than as specifically described and claimed.
Implementations of the present disclosure are directed to each individual feature, system, article,
material, kit, and/or method described herein. In addition, any combination of two or more such
features, systems, articles, materials, kits, and/or methods, if such features, systems, articles, materials,
kits, and/or methods are not mutually inconsistent, is included within the scope of the present disclosure.

Advantages of the Invention

[00093] An advantage of the present disclosure is to overcome one or more drawbacks

associated with conventional mechanisms.

[00094] Another advantage of the present disclosure is to separate fruits based on quality.

[00095] An exemplary advantage of present invention is to segregate the fruits based on size.

[00096] Yet another advantage of foreclosed invention is to monitor a ripening status of the
fruits.

[00097] Another advantage of the present disclosure is to monitor a current ambience

parameter of the fruits kept in a container.

[00098] An exemplary advantage of present invention is to discard over ripened fruits.

[00099] An yet another advantage of foreclosed invention is to enable real-time monitoring of

current ambience parameter.

19
Claims

I/We Claim:

1. A system to segregate the fruits, the system comprising:

a conveyor unit that comprises:
a first end that is arranged to receive the fruits from a user;
a second end;
a body that extends from the first end to the second end, wherein the
body comprises a first rotating belt to cause a movement of the
received fruits from the first end to the second end; and
a separator element is disposed at the second end to segregate the first
quality fruits and the second quality fruits from the received fruits; and
a first motor that is coupled with the separator element, wherein the
first motor causes a movement of the separator element between a first
position and a second position;

a first image sensor that is disposed at a first pre-set distance from the body,
wherein the first image sensor captures an image of the received fruits;

a bifurcation unit, which is disposed at the second end, wherein the bifurcation
unit comprises:

a first segregator arm that is arranged to receive the first quality fruits,
wherein the first segregator comprises:

a first primary end; and

a first secondary end;

a first mid-section that extends from the first primary end to

the first secondary end, wherein the first mid-section
comprises a second rotating belt to cause a movement of the
received first quality fruits from the first primary end to the
first secondary end;

a first partition element is disposed at the first secondary end

to segregate the received first quality fruits into the first size
first quality fruits and the second size first quality fruits; and
a second motor that is coupled with the first partition element,
wherein the second motor cause a movement of the first
20
 partition element between a third position and a fourth
position;

a second image sensor that is disposed at a second pre-set

distance from the first mid-section, wherein the second image
sensor captures an image of the received first quality fruits;
and

a first division unit that is disposed at the secondary end,

wherein the first division unit is coupled with:

a first container that is arranged to receive the first

size first quality fruits; and

a second container that is arranged to receive the

second size first quality fruits;

a second segregator arm that is arranged to receive the second quality

fruits, wherein the second segregator comprises:

a second primary end; and

a second secondary end;

a second mid-section that extends from the second primary

end to the second secondary end, wherein the second mid-
section comprises a third rotating belt to cause a movement of
the received second quality fruits from the second primary
end to the second secondary end;

a second partition element is disposed at the second secondary

end to segregate the received second quality fruits into the
first size second quality fruits and the second size second
quality fruits;
a third motor that is coupled with the second partition element,
wherein the third motor cause a movement of the second
partition element between a fifth position and a sixth position;

a third image sensor that is disposed at a third pre-set distance

from the second mid-section, wherein the third image sensor
captures an image of the received second quality fruits; and

21
 a second division unit that is disposed at the second secondary
end, wherein the second division unit is coupled with:

a third container that is arranged to receive the first

size second quality fruits; and

a fourth container that is arranged to receive the

second size second quality fruits; and

a controller device that is arranged to:

acquire the captured image of, the received fruits, the received
first quality fruits and the received second quality fruits, from
the first image sensor, the second image sensor and the third
image sensor, respectively;

determine the primary quality fruits and the secondary quality

fruits by processing the acquired image of the fruits;

examine the determined primary quality fruits to identify, the

first size primary quality fruits and the second size primary
quality fruits;

examine the determined second quality fruits to identify, the

first size secondary quality fruits and the second size
secondary quality fruits; and

control a supply of electrical energy to the first motor, the

second motor and the third motor, to segregate the fruits.

2. The system as claimed in claim 1, wherein the each amongst the first container, the second
container, the third container and the fourth container, comprises a sensing module to determine
a current ambience parameter, a fan assembly, a control unit and a memory unit to store an
ambience parameter database.
3. The system as claimed in claim 2, wherein the sensing module comprises a temperature sensor,
a humidity sensor, a gas sensor, to determine a current temperature, a current humidity and a
current gas concentration, respectively.
4. The system as claimed in claim 2, wherein the fan assembly is activated based on the
determined current temperature, the current humidity and the current gas concentration,
respectively.

22
 5. The system as claimed in claim 3, wherein the determined, current temperature, current
humidity and current gas concentration, corresponding to the first container, the second
container, the third container and the fourth container, is transmitted to a cloud server by each
control unit.
6. The system as claimed in claim 3, wherein the each amongst the first container, the second
container, the third container and the fourth container, comprises an alert unit, which is
activated based on the determined current gas concentration.
7. The system as claimed in claim 1, wherein the conveyor unit comprises an openable duct to
dispose the third quality fruits.
8. The system as claimed in claim 7, wherein the conveyor unit is coupled with a waste collection
container to receive the third quality fruits.
9. The system as claimed in claim 1, wherein the first division unit is coupled with a second
conveyor to bifurcate the identified first size primary quality fruits and the identified second
size primary quality fruits.
10. The system as claimed in claim 1, wherein the second division unit is coupled with a third
conveyor to bifurcate the identified first size secondary quality fruits and the identified second
size secondary quality fruits.

Dated Dec 29, 2022 Kumar Tushar Srivastava

IN/PA- 3973
Agent for the Applicant

23
 SYSTEM AND METHOD TO SEGREGATE THE FRUITS BY MACHINE
LEARNING

Abstract

The present invention relates to segregation of the fruits by machine learning. The method may include;
segregating, the good quality fruits and the average quality fruits from the received fruits, by utilizing
a separator element; segregating, the large size good quality fruits and the small size good quality fruits
from the segregated good quality fruits; segregating, the large size average quality fruits and the small
size average quality fruits from the segregated average quality fruits; storing, the segregated large size
good quality fruits and the segregated small size good quality fruits, in a first container and a second
container, respectively; storing, the segregated large size average quality fruits and the segregated small
size average quality fruits, in a third container and a fourth container, respectively.

Fig. 1

Dated Dec 29, 2022 Kumar Tushar Srivastava

IN/PA- 3973
Agent for the Applicant

24