Claims:1. A computer implemented method for recommending one or more practices of a farming activity to an individual working in a field, the method comprising the steps of :
receiving an information of a plurality of agricultural activities of the individual working in the field and a plurality of spatio-temporal parameters on an electronic device using a plurality of sensors;
filtering the received information of the plurality of agricultural activities using a filtration module;
recognizing a plurality of gesture sequences from the received information of agricultural activity using a state machine model;
determining one or more spatio-temporal parameters with respect to the recognized plurality of gesture sequences of the agricultural activity of the field;
analyzing at least one of the determined one or more spatio-temporal parameters and the recognized plurality of gesture sequences using a recommendation module; and
recommending a set of ideal practices of the agricultural activity in real time to the individual working in the field using recommendation module.

2. The method claimed in claim 1, wherein the plurality of gestures sequences are recognized when a predefined set of conditions are satisfied.
3. The method claimed in claim 1, wherein the spatio-temporal parameters comprises of temperature, soil moisture, air pressure or humidity.
4. The method claimed in claim 1, wherein the plurality of sensors comprises of on-body sensors and on-field sensors.
5. The method claimed in claim 4, wherein the plurality of sensors comprises of an accelerometer, a gyroscope, a magnetometer, or GPS.
6. The method claimed in claim 1, wherein the recommendation of the set of ideal practices of the agricultural activity is based on at least one of analyzed plurality of spatio-temporal parameters and the plurality of gesture sequences using the state machine model defined for a plurality of agriculture activity.
7. The method claimed in claim 1, wherein the electronic device comprises of a handheld device and remotely place server.
8. The method claimed in claim 7, wherein the hand held device includes mobile phone, i-pad, Google Glass, smart watch, wearable sensor device.
9. A system for recommending one or more practices of a farming activity to an individual working in a field, the system comprising:
a plurality of sensors to detect a one or more spatio-temporal parameters of the field;
a memory; and
a processor communicatively coupled with the memory, wherein the memory comprising:
an activity detection module to receive an information of plurality of agricultural activities of the individual working in the field,
a filtration module to filter the received information of the plurality of agricultural activities,
a state machine model to recognize a plurality of permissible gesture sequences of the filtered plurality of agricultural activities, and
a recommendation module to analyze at least one of the recognized plurality of gesture sequence of the agricultural activity and the plurality of spatio-temporal parameters to recommend a set of ideal practices of the agricultural activity to the individual working in the field.

10. The system claimed in claim 9, wherein the plurality of sensors comprises of an accelerometer, a gyroscope, a magnetometer, or a GPS.
11. The system claimed in claim 9, wherein the spatio-temporal parameters comprises of temperature, soil moisture, air pressure or humidity.
12. The system claimed in claim 9, wherein the plurality of sensors comprises of on-body sensors and on-field sensors.
, Description:
FORM 2

THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENT RULES, 2003

COMPLETE SPECIFICATION
(See Section 10 and Rule 13)

Title of invention:
A COMPLEX ACTIVITY RECOGNITION AND RECOMMENDER SYSTEM FOR PRECISION FARMING WITH TEMPORALLY CORRELATED GESTURES

Applicant:
Tata Consultancy Services Limited
A company Incorporated in India under the Companies Act, 1956
Having address:
Nirmal Building, 9th floor,
Nariman point, Mumbai 400021,
Maharashtra, India

The following specification particularly describes the invention and the manner in which it is to be performed.
FIELD OF THE INVENTION
[001] The present invention relates generally to an activity recommender system, more particularly a system and method for recommending best farming practices of an agricultural activity in a real time, based on spatio-temporal parameters and a plurality of permissible gesture sequences of an agriculture activity of an individual working in the field.

BACKGROUND OF THE INVENTION
[002] In most parts of world, individuals are still using traditional method for agriculture. Nevertheless, these means are unable to keep pace up with the needs of growing world population. To meet the end of the growing world needs, individuals and growers have to learn new techniques of farming which in turn help the individuals by improvement in yield, reduction in farming cost, reduction in destruction to the environment and increase in the quality of produce.

[003] In the current scenario the farmer may learn a technique from peers or though workshops but ensuring that best practices of farming are followed cannot be ensured. Best farming practices ensures precision agriculture and directly impacts the quality and quantity of the agricultural output. Farming practices identification and informing best practices with respect to spatio-temporal parameters of an identified area in the real time, where a farmer is performing his activities is difficult.

[004] In an agricultural activity, which is a combination of multiple repeated gestures of the farmer, there are more than one permissible gesture sequence to ensure that correct way of farming or precision farming technique is followed.

OBJECTIVE OF THE INVENTION
[005] In accordance with the present invention, the primary objective is to provide a system and method for recognizing a plurality of permissible gesture sequences of a complex agriculture activity.

[006] Another objective of the invention is to provide a system and method for identifying complex agricultural activities with higher accuracy.

[007] Another objective of the invention is to provide a system and method for recommending a set of agricultural activities based on n-dimensional space analysis of at least one of the plurality of permissible gesture sequences of an agricultural activity and spatio-temporal parameters.

SUMMARY OF THE INVENTION
[008] The following presents a simplified summary of some embodiments of the disclosure in order to provide a basic understanding of the embodiments. This summary is not an extensive overview of the embodiments. It is not intended to identify key/critical elements of the embodiments or to delineate the scope of the embodiments. Its sole purpose is to present some embodiments in a simplified form as a prelude to the more detailed description that is presented below.

[009] In the view of the forgoing, an embodiment herein provides a system and method for recognizing a plurality of permissible gesture sequences of a complex agriculture activity and recommending a set of ideal practices of farming in the real time to an individual working in the field. The plurality of permissible gesture sequences are recognized by using a state machine specific to the agricultural activity. The set of ideal practices are based on analysis of at least one of a plurality of spatio-temporal parameters of the field and the plurality of recognized gesture sequences of an individual working in a field. The system collects raw sensor data using a plurality of sensors, while individual working in the field.

[0010] In one aspect, a method for recognizing the plurality of permissible gesture sequences of a complex agriculture activity and recommending a set of ideal practices of farming in the real time to an individual working in the field. The plurality of permissible gesture sequences are recognized by using a state machine specific to the agricultural activity. The set of ideal practices are based on analysis of at least one of a plurality of spatio-temporal parameters of the field and a plurality of gesture sequences of an individual working in a field. The method comprising the steps of: receiving an information of a plurality of agricultural activities of the individual working in the field and a plurality of spatio-temporal parameters on an electronic device using a plurality of sensors; filtering the received information of a plurality of agricultural activities using a filtration module; recognizing a plurality of gesture sequences of a complex agriculture activity from the received information using state machine model; determining one or more spatio-temporal parameters of the plurality of spatio-temporal parameters with respect to the recognized plurality of gesture sequences of the complex agriculture activity; analyzing at least one of the determined one or more spatio-temporal parameters and the recognized plurality of gesture sequence using recommendation module; and recommending a set of ideal practices of the agricultural activity in the real time to the individual working in the field.

[0011] In another aspect, a system for recognizing a plurality of permissible gesture sequences of a complex agriculture activity and recommending a set of ideal practices of farming in the real time to an individual working in the field. The plurality of permissible gesture sequences are recognized by using a state machine specific to the agricultural activity. The set of ideal practices are based on analysis of at least one of a plurality of spatio-temporal parameters of the field and a plurality of gesture sequences of an individual working in a field. In one aspect, the system comprises of a user interface, a memory, a processor communicatively coupled with the memory, a plurality of sensors to detect one or more spatio-temporal parameters of the field. Further the system comprises of an activity detection module to receive an information of plurality of agricultural activities and a filtration module to filter the received information of the plurality of agricultural activities of the individual working in the field. Furthermore the system comprises of a state machine model to recognize a plurality of gesture sequences of the filtered plurality of agricultural activities of an individual. A recommendation module of the system to analyze at least one of the plurality of gesture sequences and the plurality of spatio-temporal parameters to recommend a set of ideal practices of the agricultural activity.

[0012] It should be appreciated by those skilled in the art that any block diagram herein represent conceptual views of illustrative systems embodying the principles of the present subject matter. Similarly, it will be appreciated that any flow charts, flow diagrams, state transition diagrams, pseudo code, and the like represent various processes which may be substantially represented in computer readable medium and so executed by a computing device or processor, whether or not such computing device or processor is explicitly shown.

BRIEF DESCRIPTION OF THE FIGURES
[0013] The embodiments herein will be better understood from the following detailed description with reference to the drawings, in which:
[0014] Figure 1 is a block diagram showing a system for recommending one or more practices of a farming activity to an individual working in a field;
[0015] Figure 2 is a block diagram showing a system for receiving information of agricultural activities at the electronic device using a plurality of sensors;
[0016] Figure 3 is a block diagram showing a system for recognizing a plurality of permissible gesture sequences of a complex agriculture activity using a state machine model; and
[0017] Figure 4 illustrates a flow diagram showing a method for recommending one or more practices of a farming activity to an individual working in a field.

DETAILED DESCRIPTION OF THE INVENTION
[0018] Some embodiments of this invention, illustrating all its features, will now be discussed in detail. The words "comprising," "having," "containing," and "including," and other forms thereof, are intended to be equivalent in meaning and be open ended in that an item or items following any one of these words is not meant to be an exhaustive listing of such item or items, or meant to be limited to only the listed item or items.

[0019] It must also be noted that as used herein and in the appended claims, the singular forms "a," "an," and "the" include plural references unless the context clearly dictates otherwise. Although any systems and methods similar or equivalent to those described herein can be used in the practice or testing of embodiments of the present invention, the preferred, systems and methods are now described. In the following description for the purpose of explanation and understanding reference has been made to numerous embodiments for which the intent is not to limit the scope of the invention.

[0020] One or more components of the invention are described as module for the understanding of the specification. For example, a module may include self-contained component in a hardware circuit comprising of logical gate, semiconductor device, integrated circuits or any other discrete component. The module may also be a part of any software program executed by any hardware entity for example processor. The implementation of module as a software program may include a set of logical instructions to be executed by a processor or any other hardware entity.

[0021] The disclosed embodiments are merely exemplary of the invention, which may be embodied in various forms.

[0022] The elements illustrated in the Figures interoperate as explained in more detail below. Before setting forth the detailed explanation, however, it is noted that all of the discussion below, regardless of the particular implementation being described, is exemplary in nature, rather than limiting. For example, although selected aspects, features, or components of the implementations are depicted as being stored in memories, all or part of the systems and methods consistent with the attrition warning system and method may be stored on, distributed across, or read from other machine-readable media.

[0023] Method steps of the invention may be performed by one or more computer processors executing a program tangibly embodied on a computer-readable medium to perform functions of the invention by operating on input and generating output. Suitable processors include, by way of example, both general and special purpose microprocessors. Generally, the processor receives (reads) instructions and data from a memory (such as a read-only memory and/or a random access memory) and writes (stores) instructions and data to the memory. Storage devices suitable for tangibly embodying computer program instructions and data include, for example, all forms of non-volatile memory, such as semiconductor memory devices, including EPROM, EEPROM, and flash memory devices; magnetic disks such as internal hard disks and removable disks; magneto-optical disks; and CD-ROMs. Any of the foregoing may be supplemented by, or incorporated in, specially-designed ASICs (application-specific integrated circuits) or FPGAs (Field-Programmable Gate Arrays). A computer can generally also receive (read) programs and data from, and write (store) programs and data to, a non-transitory computer-readable storage medium such as an internal disk (not shown) or a removable disk.

[0024] In view of the foregoing, an embodiment herein provides a system and method for recognizing a plurality of permissible gesture sequences of a complex agriculture activity and recommending a set of ideal practices of farming in the real time to an individual working in the field. The plurality of permissible gesture sequences are recognized by using a state machine model specific to the agricultural activity. The set of ideal practices are based on analysis of at least one of a plurality of spatio-temporal parameters of the field and a plurality of repetitive sequence of gestures of an individual working in a field. The agricultural activity is a sequence of repetitive gestures. The knowledge of the sequence of repetitive gestures and temporal constraints are important in a complex agriculture activity. The system may break the agricultural activity into gestures using signal processing and classification algorithms. The system may accept all permutable gesture sequences in real time using a state machine. Further, the system may determine a plurality of spatio-temporal parameters of the field. The sensor and spatio-temporal parameters are dynamic to every specific crop, different activities based on the specific crop and techniques to be used for the crop. The system may analyze an n-dimensional region of spatio-temporal parameters and the sequence of repetitive gestures, as a region for precision farming. Any data point that may fall outside the region would trigger the recommender module of the system to generate a set of instructions towards ideal practices of the agricultural activity for the farmer working in the field to ensure that he would follow a best and precise agricultural activity.

[0025] According to an embodiment of the invention, a system (100) for recognizing a plurality of gesture sequences of a complex agriculture activity and recommending a set of ideal practices of farming in the real time to an individual working in the field. The plurality of gesture sequences are also referred as the plurality of permissible gesture sequences if a first set of predefined conditions are satisfied, as shown in fig. 1. The first set of predefined conditions are different for each agricultural activity. The set of ideal practices are based on analysis of at least one of a plurality of spatio-temporal parameters of the field and a plurality of gesture sequences of an individual working in a field. In one aspect, the system (100) comprises of a user interface (102), a memory (104), a processor (106) communicatively coupled with the memory (104), a plurality of sensors (108) to detect one or more spatio-temporal parameters of the field. Further the system (100) comprises of an activity recognition module (110) to receive an information of plurality of agricultural activities and a filtration module (112) to filter the received information of the plurality of agricultural activities of the individual working in the field. Furthermore the system (100) comprises a state machine model (114) to recognize a plurality of gesture sequences of an agriculture activity of the filtered plurality of agricultural activities of an individual by using the state machine model (114). A recommendation module (116) of the system (100) to analyze at least one of the plurality of gesture sequences and the plurality of spatio-temporal parameters to recommend a set of ideal practices of the agricultural activity.

[0026] In the preferred embodiment of the invention, the system (100) receives the plurality of agricultural activities using a plurality of sensors (108) while an individual is working in the field as shown in fig. 2. It would be appreciated that the plurality of sensors (108) comprises of on-body sensors and on-field sensors. The on-body sensors are the sensors that can be carried by the individuals in the farms configured to sense the activities performed by the individuals. The on-body sensors may include but is not limited to global positioning system (GPS), accelerometer, camera, microphone, magnetometer, and gyroscope and proximity sensor. The GPS determines the location of the individual performing an agricultural activity. The accelerometer determines the acceleration which further deduces the attributes related to the gesture of the individual working in the field. The proximity sensor detects the presence of nearby objects with respect to the individual. In an embodiment inbuilt sensors of handheld electronic devices (smart phones, tabs, iPad etc.) can be used to detect activity performed by individuals in the field.

[0027] The on-field sensors are the sensors that are typically, installed at the site or in the farms for sensing the environmental data with respect to agricultural parameters. The agricultural parameters may include but is not limited to water availability deployment, weather forecast, soil moisture, temperature, humidity, leaf wetness, sunlight availability, gaseous content in the soil, fertilizer content in the soil, growth of crop, pesticide content on the crop, and agricultural activities performed by the individuals in their farms. The on-field sensors may include but is not limited to temperature sensor, humidity sensor, soil moisture sensor, leaf wetness sensor, gas sensors, actinometer, dew warning sensor and ceilometer. The set of sensors (108) are communicatively coupled with the electronic device (118) through the network (202).

[0028] In the preferred embodiment of the invention, an activity detection module (110) of the system (100) receives information of the plurality of agricultural activities of the individual. A filtration module (112) of the system (100) is using signal processing to filter the received information of the plurality of agricultural activities. An agricultural activity is a sequence of repetitive gestures. The agriculture activities may include, but not limited to, land preparation, planting, transplanting, manual weeding, spraying of chemicals, irrigating, ploughing, supervision, surveillance, tilling, growing and harvesting. The system (100) breaks the agricultural activity into the sequence of gestures using complex agriculture activity recognition, wherein the complex agriculture activity recognition includes an activity classification engine to classify the received complex agriculture activity data based on classification algorithms. Further, it includes a sequence detection engine for recognizing a permissible set of gesture sequence using the state machine model of the agriculture activity as shown in the fig. 3. The knowledge of the sequence of repetitive gestures and temporal constraints are important in the agriculture activity. A state machine model (114) of the agriculture activity of the system (100) is configured to identify more than one permissible ways of doing the agricultural activity. The state machine model (114) may have n-states for n-gestures in the agricultural activity. The state machine model (114) defines a plurality of permissible gesture sequences that are required to perform the complex agricultural activity correctly according to a set of predefined condition for each agriculture activity. The repetitive sequence of gestures in the permissible domain associates every individual gesture with one or more pre-defined constraints. The electronic device (118) of the system (100) comprises of a handheld device and remotely placed server. Further, the handled device may include mobile phone, iOS device, Google Glass, smart watch and wearable sensors device. Furthermore, the remotely placed servers is having a plurality of pre-defined agricultural activity and a crop protocol data.

[0029] It would be appreciated that the one or more pre-defined constraints are spatio-temporal parameters. The spatio-temporal parameters are influential parameters, play a major role in identifying a set of ideal practices of the agricultural activity.

[0030] In the preferred embodiment of the invention, the recommendation module (116) to analyze at least one of the plurality of permissible gesture sequences and the plurality of spatio-temporal parameters to recommend a set of ideal practices of the agriculture activity to the individual working in the field. The recommendation module (116) passes the agriculture activity data, in the permissible domain associates every individual gesture with one or more pre-defined constraints, and the plurality of spatio-temporal parameters to a recommender engine to identify an activity specific model and an ideal set of pre-defined constraints from the plurality of spatio- temporal parameters from the memory (104) of the system (100). Further, the recommendation module (116) may analyze the plurality of permissible gesture sequences and the plurality of spatio-temporal parameters and generates a set of ideal practices of the agriculture activity. It would be appreciated that the recommendation module (116) may generate a set of ideal practices based on analysis of at least one of the plurality of permissible gesture sequences and the plurality of spatio-temporal parameters. It may not necessary that the recommendation module (116) should analyze the plurality of permissible gesture sequences and the plurality of spatio-temporal parameters together to generate the set of ideal practices. The recommendation module (116) may analyze any one of them and generate the set of ideal practices.

[0031] In an example of a tea plucking activity, wherein the tea plucking activity is an agricultural activity comprises of three gestures such as:
1. Plucking a plurality of leaves and a bud at once (g1);
2. Holding the plurality of leaves and the bud in hand (g2); and
3. Transferring the plurality of collected leaves to the basket (g3).
The tea plucking activity information is received by the activity detection module and the information is filtered out by the filtration module of the system. The filtration of the information is based on signal processing methods of the filtration module. A plurality of repetitive gestures (g1), (g2) and (g3) of the tea plucking activity are identified by a state machine model. The state machine model defines a plurality of permissible repetitive sequence of abovementioned three gestures. The repetitive sequence of gestures in the permissible domain associates every individual gesture with its constraints. In the tea plucking activity the constraints can be time duration for any individual activity. It is well known that the plucked leaves should not be kept long in hand before transferring them to the basket as it deteriorates the quality of tea leaf. Therefore, in the tea plucking activity, it is considered that the tea leaf plucking and holding repetitions with respect to time is a pre-defined constraint or ideal practice to be followed. Hence, the recommendation module of the system identifies an ideal parameter for tea plucking activity is time, and analyze them to generate a set of ideal practices of the tea plucking activity.

[0032] Referring to fig. 4 illustrates a method (300) for recognizing a plurality of permissible gesture sequences of a complex agriculture activity and recommending a set of ideal practices of farming activity in the real time to an individual working in the field. The plurality of permissible gesture sequences are recognized by using a state machine specific to the agricultural activity. The set of ideal practices are based on analysis of at least one of a plurality of spatio-temporal parameters of the field and a plurality of permissible gesture sequences of an individual working in a field.

[0033] At step (302), a plurality of sensors receives information of a plurality of agricultural activities of the individual working in the field and a plurality of spatio-temporal parameters at the electronic device (118) of the system (100). The plurality of sensors (108) comprises on-body sensors and on-field sensors. The on-body sensors are the sensors that may be carried by the individuals in the farms configured to sense the activities performed by the individuals. The on-field sensors are the sensors that are typically, installed at the site or in the farms for sensing the spatio-temporal parameters with respect to agricultural parameters. The agricultural parameters may include but is not limited to water availability deployment, weather forecast, soil moisture, temperature, humidity, leaf wetness, sunlight availability, gaseous content in the soil, fertilizer content in the soil, growth of crop, pesticide content on the crop, and agricultural activities performed by the individuals in their farms.

[0034] At step (304), the filtration module (112) of the system filtered out the received information of the plurality of agricultural activities of the individual working in the field and a plurality of spatio-temporal parameters. The filtration module (112) of the system using signal processing technique to filter the received information of the plurality of agricultural activities.

[0035] At step (306), a state machine model (114) of the agriculture activity is configured to recognize more than one permissible ways of doing the agricultural activity. The state machine model (114) may have n-states for n-gestures in the agricultural activity. The state machine model (114) defines a plurality of permissible sequence of gestures that are required to perform the complex agricultural activities correctly.

[0036] At step (308), the recommendation module (116) passes the repetitive sequence of gestures, in the permissible domain associates every individual gesture with one or more pre-defined constraints, and the plurality of spatio-temporal parameters to a recommender engine to select an activity specific model and an ideal set of pre-defined constraints from the plurality of spatio- temporal parameters from the memory (104) of the system (100).

[0037] At step (310), the recommendation module (116) may analyze the plurality of permissible gesture sequences and the plurality of spatio-temporal parameters. The knowledge of the sequence of repetitive gestures and temporal constraints are important in the agriculture activity. These parameters help to define a region in the n-dimensional space which corresponds to the precision farming. The parameters and gestures falling in this region of the model ensures that ideal and precision farming practices are being followed, while data outside that region facilitates the model to generate recommendations to the individual to perform better.

[0038] At step (312), the recommendation module (116) recommends a set of ideal practices of the agricultural activity in the real time to the individual working in the field. The recommendation is based on at least one of analyzed plurality of spatio-temporal parameters and the plurality of permissible gesture sequences.

[0039] The foregoing is only preferred embodiments of the present invention, it is not intended to limit the present invention, any modifications within the spirit and principles of the present invention made, equivalent replacement and improvement, etc., should be included in this within the scope of the invention.