FORM 2
THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENTS RULES, 2006
COMPLETE SPECIFICATION
[See section 10, Rule 13]
1.TITLE OF THE INVENTION: DATA ANALYTICS SYSTEM FOR EFFICIENT
COOKING PROCESS
2. APPLICANT:
I. Name: INTELLILOGOS CONSULTING LLP
Nationality: Indian
Address: 202 Mary Anne heights, 3rd Golibar Road, Santa Cruz East, Mumbai, 400055
3. PREAMBLE TO THE DESCRIPTION
THE FOLLOWING SPECIFICATION PARTICULARLY DESCRIBES THE INVENTION
AND THE MANNER IN WHICH IT IS TO BE PERFORMED
2
FIELD OF INVENTION
The present invention pertains to the field of kitchen appliances and more particularly, to a data
analytics system that collects relevant data pertaining to cooking process and provide insights for
efficiently carrying out the cooking process.
CROSS-REFERENCE TO PARENT APPLICATION
This is a patent of addition to Indian patent number 439625 dated 27/02/2018, which relates to a
a monitoring system for a pressure cooking vessel that enables the cook to perform faster
cooking while saving fuel and at the same time conduct his/her other chores while dispensing
with the requirement to monitor the operation of the pressure cooking vessel.
BACKGROUND OF THE INVENTION
Pressure cooking vessels form the fundamental bedrock of any household in India. More than
60% of households have such pressure vessels for the reason that the same save a lot of time as
well as fuel in cooking. Pressure cooking vessels also enable cooks to reduce the efforts for
cooking, thereby enabling them to run multiple tasks while cooking in the kitchen.
A pressure cooking vessel has a pressure control valve, which operates to release any excess
pressure that is formed within the vessel. The trick to efficient cooking using the pressure
cooking vessel is that different number of pressure release operations, also referred to as whistles
in common cooking parlance, are required for cooking different types of food articles. One
common problem in a typical pressure cooking vessel is that the cook needs to constantly
monitor the number of whistles for a particular food item to cook properly. Typically, this is
carried out manually such that the cook counts the number of whistles before switching off the
heat supply to the pressure cooking vessel. The issue with such manual counting is that it is
prone to error. For instance, sometimes the cook may count the number incorrectly as he may
forget the numbers while counting. This could have the following repercussions:
3
1. If the cook counts less than the actual number of whistles, additional cooking gas is used
and the food item may be over-cooked.
2. If the food is not cooked properly then the process needs to be repeated, which also
results in usage of more gas and also wastage of time.
Moreover, the cooking process involves a lot of experience based decision making. In a
conventional cooking process, the knowledge gained from cooking experience remains limited to
the cook or at best those to whom the cook decides to share the knowledge with.. Even
otherwise, every cook will gain new experiences as they encounter different cooking conditions,
such as high-altitude cooking, or all-weather cooking and the like. Thus, even when an
experienced cook encounters a different cooking condition, his/her cooking efficiency may be
affected. Hence, there exists a need for a solution that can enhance the efficiency of cooking
process by providing necessary guidance to the cook when required. .
OBJECTS OF THE DISCLOSURE
In view of the foregoing disadvantages inherent in the prior art, the general purpose of the
present invention is to enhance the efficiency in a cooking process.
Accordingly, an objective of the present invention is to provide a data analytics and an AI-based
system that provides guidance to cooks about the cooking process by collecting data from
different cooking processes.
Another objective of the present invention is to provide a data analytics system that enables an
efficient cooking process irrespective of the experience of the cook.
SUMMARY OF THE INVENTION
In accordance with an aspect of the present invention, a data analytics system for efficient
cooking process using a pressure-cooking vessel having a pressure release valve is disclosed.
The system includes a portable device adapted to collect cooking information in real-time
4
pertaining to the cooking process that is being carried out by the pressure cooking vessel using a
heat source. The system also includes a server communicably coupled to the portable device to
receive the collected cooking information and generate recommendations regarding at least an
optimal number of required operations of the pressure release valve of the pressure cooking
vessel, time duration for completion of the cooking process, improvement of performance and
cooking efficiency of the pressure cooking device, replacement cycle of the pressure cooking
device and required heat intensity for the cooking process. The present invention envisages that
the cooking information includes at least one of type of food being cooked in the cooking
process, the time of the day when the cooking process is being performed, type of the heat source
for the cooking process, type of pressure cooking vessel, number of operations of the pressure
release valve happened in the real-time, time interval between the subsequent operations of the
pressure release valve.
In another aspect of the present invention, the cooking information includes geographical
location of the cooking process.
In yet another aspect of the present invention, the server includes an Artificial Intelligence (AI)
model adapted to generate recommendations based on the real-time cooking information
received from the portable device, and an AI training module coupled to the AI model to create
or train the AI model based on training data derived from historical cooking information.
In still another aspect of the present invention, the AI training module incudes a training data
module to receive training data derived from the historical cooking information and perform
processing thereof for training of the AI model, a testing data module to receive testing data
derived from the historical cooking information and evaluate the generated recommendations of
the AI model, and an AI algorithm module including a machine learning algorithm to receive the
training data and the testing data to train and test the AI model to generate recommendations.
In still another aspect of the present invention, the portable device is a mobile phone, a tablet, a
notebook computer and a desktop computer.
5
In still another aspect of the present invention, the machine learning algorithm of the AI
algorithm module could be at least one of decision trees, random forests, support vector
machines (SVM), neural networks (convolutional neural networks, recurrent neural networks),
gradient boosting machines, K-nearest neighbors (KNN), and logic regression.
In still another aspect of the present invention, the server is adapted to selectively switch off the
heat source based on recommendation regarding the required heat intensity for the cooking
process.
BRIEF DESCRIPTION OF DRAWINGS
Fig. 1 illustrates a monitoring system for a pressure cooking vessel as disclosed in the parent
application.
Fig. 2 illustrates a data analytics system for efficient cooking, in accordance with another
embodiment of the present invention..

Description:This patent describes the subject matter for patenting with specificity to meet statutory requirements. However, the description itself is not intended to limit the scope of this patent. The principles described herein may be embodied in many different forms.
Illustrative embodiments of the invention now will be described more fully hereinafter with reference to the accompanying drawings, in which some, but not all embodiments of the invention are shown. Indeed, the invention may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will satisfy applicable legal requirements. Like numbers refer to like elements throughout.
The present invention envisages a data analytics system that enables efficient cooking process without any dependence on the experience of the cooks. The system is adapted to provide guidance to the cooks in respect of making the cooking process faster, fuel efficient and cost-effective. The data analytics system will be explained in relation to Fig. 2. However, before that, the description seeks to incorporate by reference, the monitoring system defined in the parent application and which is being explained in conjunction with Fig. 1. The monitoring system 100 monitors the cooking process being carried out through the pressure cooking vessel 105 that releases internal pressure of the vessel 105 during cooking operation. The monitoring system 100 includes an input device 110 adapted to receive an input from a user or a cook. Further, the system 100 also includes an audio feedback device 115 disposed preferably in vicinity of the pressure cooking vessel 105 and adapted to keep track in real-time of the number of times the pressure release valve actually operates to release pressure inside the vessel. Thus, each time the pressure cooking vessel 105 generates a whistle due to operation of the pressure release valve to release internal pressure of the pressure cooking vessel 105, the audio feedback device 115 detects the sound of the whistle. Each whistle is counted using an operation counter 120a Once the count reaches a prefixed count value, an indication is provided to a communicator module 125, which generates an alert for the user to be apprised that the desired number of whistles have been generated and thus the food has been cooked as desired. The indication may be provided on a portable device of the cook/user as an option. An audible alert is also generated with the help of an alarm or buzzer circuit. In an alternate embodiment, a controller unit 130 having a receiver 130a communicably coupled to a transceiver 125a of the communicator module 125 and a relay unit 130b having at least one relay to control the operation of a heat source 135 to the pressure cooking vessel 105 is also provided. In use, the relay of the relay unit 130b may be operated by the communicator module 125 to switch off the heat source 135. In an embodiment of the present invention, if the heat source is a gas stove, the relay unit 130b may include a gas valve that blocks or allows gas supply to reach the gas stove. In another embodiment of the present inventio, if the hear source is an induction heater, the relay unit 130b could be an electrical relay that blocks or enables electric supply to the induction heater. The gas valve and the electrical relay are any conventional valve and relay, respectively, and a detailed explanation of the same is being avoided for sake of brevity as it will be apparent to a skilled person.
The present invention envisages to collect useful data from such numerous monitoring system and analyze the same to create an Artificial Intelligence module that could provide suggestions to the cooks related to their cooking operations to enable them to perform the operations with efficiency while also helping them save fuel and cost. In an embodiment of the present invention, the recommendations may include suggestions regarding the number of whistles required to cook the particular food being cooked, improving the performance and cooking efficiency of the pressure cooking device, if the device needs a replacement or the replacement cycle for the device, and suggestion regarding the approximate time period after which the heat source should be switched off. In an embodiment of the present invention, the heat source 135 could be remotely switched off if there’s a need. Fig. 2 illustrates the data analytics system 500 that is coupled to a plurality of monitoring systems 100a-n, each of which are monitoring cooking process being carried out through pressure cooking vessels 105a-n. All the monitoring systems 100a-n collect cooking information regarding the cooking processes being monitored by them. In particular, the monitoring systems 100a-n collect at least the cooking information about the type of food being cooked, the time of the day when the cooking is being performed, the type and size of the cooking vessel, whether the heat source is gas based or electricity based, the number of whistles that were required to cook the food, the time interval between the subsequent whistles, and the time taken for the cooking process to be completed. The location where the cooking process is being carried out may be optionally provided as well. The details about the type of food being cooked, the time of the day, details of the cooking device, details of heat source and, optionally, the location where the cooking process is happening may be provided through the input device 110. In an embodiment of the present invention, the input device 110 may be communicably coupled to a portable communication device, such as mobile phone, tablet, laptop and the like, of the cook/user for providing the afore-said details. Further, each of the monitoring systems 100a-n are communicably coupled to a server 600, either directly or through the portable communication device of the cook, which is communicably coupled to their monitoring system 100 a-n, for transmitting the cooking information thereto. The server will be explained in conjunction with Fig. 3.

As shown in Fig. 3, the server 600 includes an Artificial Intelligence (AI) model 605 that is adapted to receive real-time data cooking information from the one or more monitoring systems 100a-n and are adapted to provide recommendations related to the cooking process to the said one or more monitoring systems 100 a-n. The cooking recommendations may include, but are not limited to, enhancing fuel efficiency, reducing cooking time, optimized usage of ingredients, the health condition of the heat source or pressure cooking vessel, the heat intensity that needs to be maintained for the cooking process, such as slow, medium, high or no heat, and the like. Additionally, the AI model 605 is adapted to predict that an undesirable condition may occur during the cooking process and generate alert signals for the cooks using the one or more monitoring systems 100a-n to pre-alert the cooks about the likelihood of an undesirable event and prevent the same. The model might also directly send a signal to the communicator module 125 to cutoff the heat source by operating the relay unit 130b if it is determined that there is a likelihood of an undesirable event, such as overcooking or overheating. Both the recommendations and the alert signals enable a cooking process that is efficient, saves fuel and is cost effective as well. To create the AI model 605, the server 600 also includes an AI training module 610 that is primarily responsible for creating and refining the AI model 605 and a memory 615 that is adapted to store the historical cooking information that was received from the one or more cooking monitoring systems 100 a-n in the past. The AI training module 610 is adapted to receive a training data, which is derived from the stored historical cooking information in the memory 615 and devise a training methodology to train the AI model 605, using methodologies such as reinforced learning, to be able to generate alerts and recommendations. Further, the AI training module 610 includes a training data module 620 that gathers the historical cooking information from the memory 615 and/or the one or more monitoring systems 100 a-n. The training data module 620 cleans the collected data, preprocesses it and formats the same to make it compatible with the type of AI algorithm used by the AI training module 610 . This is termed as the training data. Further, the AI training module 610 also includes a testing data module 625 that gathers a portion of the historical data, similar to that of the training data module 620, in the memory 615 and uses the same for evaluation of the performance of the model that is being trained by the AI training module 610 in terms of the accuracy of the predictions made by the AI module 605. The data at the testing data module 625 is referred to as testing data. The AI training module 610 also includes an AI algorithm module 630 that may use any of the available machine learning algorithms selected from, but not limited to, decision trees, random forests, support vector machines (SVM), neural networks (convolutional neural networks, recurrent neural networks), gradient boosting machines (e.g. XGBoost, LightGBM), K-nearest neighbors (KNN), logic regression and the like. The training data module 620 feeds the training data into the chosen algorithm and train a specific version of an AI model 605 to recognize patterns and make predictions. Further, before the AI training module can generate the final AI model 605 which could be deployed for prediction, the AI model 605 needs to be tested for accuracy and preciseness of its predictions and for this, the AI training module 610 uses the testing data from the testing data module 625 and evaluates the AI model 605. The AI training module 610 runs the AI model 605 through the testing data comparing each predicted recommendation with the correct historical event that occurred. This is done for a multitude of scenarios and is repeated for each recommendation. Based on its correctness of predicted recommendation, the AI training module 610 evaluates the AI model 605 for its prediction accuracy, robustness and generalization capabilities by consideration of key performance metrices like accuracy, precision, recall and F1 score. Particularly, the AI model 605 is tested for specific use cases. With specific reference to the present invention, the AI model 605 may be tested to check, in an embodiment, the accuracy in providing the recommendations Based on the test results, the AI model 605 could be refined to achieve the desired performance level. The AI model is deployed in the server 600 once it conforms to the desired performance related metrices.

In use, when one or more cooks start a cooking process on a pressure cooking vessel, the respective monitoring systems 100a-n thereof provide the real-time cooking information to the server 600. Particularly the server 600 may receive information at least regarding at least the type of food being cooked, the time of the day when the cooking is being performed, the type of pressure cooking vessel, whether the heat source is gas based or electricity based, the number of whistles that have happened, the time interval between the subsequent whistles. The “type of food” herein refers to the food item that is being cooked in the cooking vessel and may include, but not limited to, lentils, rice (white/brown), different vegetables, beans and any such food items that could be cooked using a pressure cooking vessel. The present invention recognizes that different types of food will require cooking process running for different durations. Also, the present invention envisages that the ambient heat may affect the duration of the cooking process and thus, it may be essential to know the time of the day (early morning, noon, after noon, evening or night) when the cooking process is being performed. Also, by determining the time duration between two whistles, the AI model 605 will be able to determine if the cooking process is progressing as per the prediction and if not, the AI model 605 may rectify its prediction if the cooking process is going faster/slower than the predicted cooking process. The server 600 may also receive the information about the geographical location of the place where the cooking process is being carried out. This information could be gathered from the location parameters of the portable device of the cook. All this cooking information is provided to the AI model 605, which in turn generates recommendations as well as timely alerts for pre-warning the cook about any adverse event related to the cooking activity being performed by him/her. In another embodiment, the AI model 605 could directly communicate with the communicator module 125 to operate the relay unit 130b and cut off the heat source to stop the cooking process. The recommendations are provided by way of assigning different weights to the different parameters of the cooking information and providing the same to the AI model 605, which runs the parameters through the machine learning algorithm used in the AI model 605 and generates a weighted score based on which recommendations related to the number of whistles that may be required, the remaining cooking time or number of whistles, the heating intensity (such as slow, medium, high or no heat), and the like may be generated. The present invention envisages that the weights assigned to the different parameter of the cooking information will be dynamically adjusted as the AI model 605 experientially learns from the various cooking processes monitored by it and analyzing the cooking information of the said processes continually. For easier understanding, in an exemplary use, the AI model 605 may receive information from the portable device of the cook that he is cooking lentils in a hilly area around noon. The cook also enters information about the type of heat source, i.e. gas based, that is being used. Based on the received information, the AI model 605 will provide a recommendation that the cooking needs to be carried out for 20 minutes at low heat intensity and the number of whistles that should be released must be 6. The AI model 605 also receives the number of whistles happening in real-time to generate alerts when the predicted number of whistles is about to be achieved.

It may be noted that the various modules described in the system may be implemented in hardware, including but not limited to a processor and a memory, or a combination of such hardware and software like applications and drivers used for carrying out the methodology of the present invention. The hardware system may also include various system data buses for enabling transmission of data between the modules. The hardware may additionally include communication means, such as LAN adapters, WIFI adapters and any other types of RF adapters for enabling the system to communicate with other communication devices. Further, the communicable coupling between the different modules/apparatus could be enabled by electrical wires and/or system buses, or wirelessly using WIFI or RF waves.
Since other modifications and changes varied to fit particular operating requirements and environments are apparent to those skilled in the art, the invention is not considered limited to the example chosen for purposes of disclosure, and covers all changes and modifications which do not constitute departures from the true spirit and scope of this invention.
Although the invention has been explained in relation to its preferred embodiment, it is to be understood that many other possible modifications and variations can be made without departing from the spirit and scope of the invention as herein described. As one of ordinary skill in the art may appreciate, the example system and method described herein can be modified. For example, certain steps can be omitted, certain steps can be carried out concurrently, and other steps can be added. Although particular embodiments of the invention have been described in detail, it is understood that the invention is not limited correspondingly in scope, but includes all changes, modifications and equivalents coming within the spirit and terms of the invention as described herein. This written description uses examples to disclose the invention, including the best mode, and also to enable any person skilled in the art to practice the invention, including making and using any devices or systems and performing any incorporated methods.
, Claims:1. A data analytics system for efficient cooking process using a pressure-cooking vessel (105) having a pressure release valve, the data analytics system comprising:

a portable device adapted to collect cooking information in real-time pertaining to the cooking process being carried out by the pressure cooking vessel (105) using a heat source (135); and

a server (600) communicably coupled to the portable device to receive the collected cooking information and generate recommendations regarding at least an optimal number of required operations of the pressure release valve of the pressure cooking vessel (105), time duration for completion of the cooking process, improvement of performance and cooking efficiency of the pressure cooking device, replacement cycle of the pressure cooking device and required heat intensity for the cooking process,
wherein the cooking information comprises at least one of type of food being cooked in the cooking process, the time of the day when the cooking process is being performed, type of the heat source (135) for the cooking process, type of pressure cooking vessel, number of operations of the pressure release valve happened in the real-time, time interval between the subsequent operations of the pressure release valve.

2. The data analytics system as claimed in claim 1, wherein the cooking information comprises geographical location of the cooking process.

3. The data analytics system as claimed in claim 1, wherein the server (600) comprises:

an Artificial Intelligence (AI) model (605) adapted to generate recommendations based on the real-time cooking information received from the portable device; and
an AI training module (610) coupled to the AI model (605) to create or train the AI model (605) based on training data derived from historical cooking information.

4. The data analytics system as claimed in claim 3, wherein the AI training module (610) comprises
a training data module (620) to receive training data derived from the historical cooking information and perform processing thereof for training of the AI model (605);
a testing data module (625) to receive testing data derived from the historical cooking information and evaluate the generated recommendations of the AI model (605);
an AI algorithm module (630) comprising a machine learning algorithm to receive the training data and the testing data to train and test the AI model (605) to generate recommendations.

5. The data analytics system as claimed in claim 1, wherein the portable device is a mobile phone, a tablet, a notebook computer and a desktop computer.

6. The data analytics system as claimed in claim 4, wherein the machine learning algorithm of the AI algorithm module (630) comprises at least one of decision trees, random forests, support vector machines (SVM), neural networks (convolutional neural networks, recurrent neural networks), gradient boosting machines, K-nearest neighbors (KNN), and logic regression.

7. The data analytics system as claimed in claim 1, wherein the server (600) is adapted to selectively switch off the heat source (135) based on recommendation regarding the required heat intensity for the cooking process.