1. A system of voice-assisted mobile application for pest diagnosis comprising: a voice input module configured to capture farmer speech in local languages and dialects; an automatic speech recognition (ASR) engine operable offline and online to extract crop symptoms from voice input; an optional image capture and classification module configured to analyze crop photographs; a hybrid fusion engine combining voice-derived symptoms, image analysis, and geo-temporal data to generate pest diagnosis; a decision engine configured to provide pest identification and management recommendations; and an output module comprising text-to-speech functionality to deliver recommendations in the farmer’s preferred language.

2. The system as claimed in claim 1, wherein the ASR engine is dialect-aware and optimized for regional language variations and accent differences.

3. The system as claimed in claim 1, wherein the image classification module operates on-device when offline and synchronizes with cloud-based models when online.

4. The system as claimed in claim 1, wherein the hybrid fusion engine employs confidence-based model fusion to combine voice, image, and location data for improved accuracy.

5. The system as claimed in claim 1, wherein the decision engine accesses an offline advice database with periodic version updates to provide recommendations in low-connectivity areas.

6. The system as claimed in claim 1, wherein the output module provides explainable recommendations by indicating whether the diagnosis is based on voice input, image analysis, or both.

7. The system as claimed in claim 1, wherein the system supports multiple regional languages and dialects beyond major national languages.

8. The system as claimed in claim 1, wherein the application synchronizes collected data to a cloud server for centralized analytics, reporting, and model improvement.

9. The system as claimed in claim 1, wherein the recommendations include environmentally safe pest management practices tailored to local crop conditions.

10. The system as claimed in claim 1, wherein the user interface comprises simple icons and voice instructions to overcome literacy barriers among farmers.

Description:FIELD OF THE INVENTION
This invention relates to a voice-assisted mobile application for farmers-friendly pest diagnosis.
BACKGROUND OF THE INVENTION
Farmers in rural areas often face significant challenges in accurately identifying crop pests and selecting appropriate management practices. Current mobile applications lack effective voice interaction and multilingual support, making pest identification and management recommendation systems inaccessible to a large segment of the farming community. Furthermore, existing solutions are not optimized for real-time field conditions such as poor internet connectivity, regional language variations, and accent differences. This leads to delays in pest detection, misdiagnosis, and inappropriate pesticide use, resulting in reduced crop productivity and economic losses.
SUMMARY OF THE INVENTION
This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the invention.
This summary is neither intended to identify key or essential inventive concepts of the invention and nor is it intended for determining the scope of the invention.
This innovation enables farmers to identify pests and receive management recommendations using voice commands in their local language, eliminating literacy and digital barriers. Combining AI-based diagnosis with optional image support, the app provides real-time, location-specific and environmentally safe guidance, works offline in low-connectivity areas, and delivers recommendations through clear voice instructions, making pest management faster, accurate and accessible for smallholder farmers.
To further clarify advantages and features of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which is illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail with the accompanying drawings.
BRIEF DESCRIPTION OF THE DRAWINGS
The illustrated embodiments of the subject matter will be understood by reference to the drawings, wherein like parts are designated by like numerals throughout. The following description is intended only by way of example, and simply illustrates certain selected embodiments of devices, systems, and methods that are consistent with the subject matter as claimed herein, wherein:
FIGURE 1: FLOW CHART
The figures depict embodiments of the present subject matter for the purposes of illustration only. A person skilled in the art will easily recognize from the following description that alternative embodiments of the structures and methods illustrated herein may be employed without departing from the principles of the disclosure described herein.
DETAILED DESCRIPTION OF THE INVENTION
The detailed description of various exemplary embodiments of the disclosure is described herein with reference to the accompanying drawings. It should be noted that the embodiments are described herein in such details as to clearly communicate the disclosure. However, the amount of details provided herein is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the scope of the present disclosure as defined by the appended claims.
It is also to be understood that various arrangements may be devised that, although not explicitly described or shown herein, embody the principles of the present disclosure. Moreover, all statements herein reciting principles, aspects, and embodiments of the present disclosure, as well as specific examples, are intended to encompass equivalents thereof.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a",” “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes” and/or “including,” when used herein, specify the presence of stated features, integers, steps, operations, elements and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and/or groups thereof.
It should also be noted that in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed concurrently or may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
In addition, the descriptions of "first", "second", “third”, and the like in the present invention are used for the purpose of description only, and are not to be construed as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Thus, features defining "first" and "second" may include at least one of the features, either explicitly or implicitly.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which example embodiments belong. It will be further understood that terms, e.g., those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The present invention discloses a voice-assisted mobile application specifically designed to support farmers in diagnosing crop pests and receiving appropriate management recommendations. The application addresses the limitations of existing mobile solutions by enabling voice-based interaction in multiple regional languages and dialects, thereby overcoming literacy barriers and accent variations common in rural communities.
The system architecture comprises a voice input module that captures farmer speech in real time. An automatic speech recognition (ASR) engine processes the audio input, functioning both offline and online. In offline mode, a lightweight dialect-aware ASR model interprets local language commands, while in online mode, a cloud-based ASR engine provides enhanced accuracy. The ASR engine extracts crop symptoms and relevant keywords from the farmer’s speech, forming the basis for pest diagnosis.
An optional image capture module allows farmers to upload or capture photographs of affected crops. These images are processed by an on-device classifier when offline, or by a cloud-based deep learning model when internet connectivity is available. The hybrid fusion engine combines voice-derived symptoms, image analysis, and geo-temporal data such as location and time of report to generate a context-specific pest diagnosis.
The decision engine integrates this fused data with a knowledge base of pest symptoms, crop-specific vulnerabilities, and management practices. It provides real-time diagnosis and generates treatment recommendations that emphasize environmentally safe and locally relevant solutions. The recommendations are delivered through a text-to-speech (TTS) output module, which communicates the guidance in the farmer’s preferred language. Simple icons and visual cues may also be displayed to assist farmers with limited literacy.
The application is designed to function effectively in low-connectivity environments. An offline advice database is stored locally on the device, with periodic updates provided through small patches. This ensures that farmers in remote areas can access pest management recommendations without requiring continuous internet access. Data collected during offline usage is synchronized with the cloud once connectivity is restored, enabling centralized analytics and model improvement.
AI-enabled analytics enhance the accuracy and reliability of the system. Confidence-based model fusion ensures that outputs from voice, image, and location data are weighted appropriately to minimize misdiagnosis. The system also provides explainable outputs, indicating whether the diagnosis was based on voice input, image analysis, or a combination of both.
The novelty of the invention lies in its ability to provide farmers with pest diagnosis through voice commands in local languages, supported by optional image analysis, hybrid AI fusion, and offline functionality. Unlike existing applications, the invention is optimized for rural field conditions, supports multiple dialects, and delivers spoken recommendations directly to the farmer, thereby making pest management faster, more accurate, and accessible.
The mobile application comprises the following technical modules:
1. Voice Input Module: Captures farmer speech in local languages and dialects using the device microphone.
2. Automatic Speech Recognition (ASR) Engine: Operates offline with a lightweight dialect-aware model and online with a cloud-based model to extract crop symptoms.
3. Image Capture and Classification Module: Processes crop photographs using on-device classifiers offline and cloud-based deep learning models online.
4. Hybrid Fusion Engine: Combines voice-derived symptoms, image outputs, and geo-temporal data using confidence-based fusion algorithms.
5. Decision Engine: Matches fused data with a pest knowledge base to generate diagnosis and management recommendations.
6. Output Module: Provides recommendations through local-language text-to-speech and simple icons for accessibility.
7. Offline Advice Database: Stores pest management information locally with periodic updates for use in low-connectivity areas.
8. Cloud Synchronization: Uploads collected data to a central server for analytics, reporting, and continuous model improvement.
9. Explainable AI Layer: Indicates the basis of diagnosis (voice, image, or hybrid) to improve farmer trust and transparency.
10. User Interface: Designed with simplicity, featuring voice prompts, icons, and minimal text to overcome literacy barriers.
Best Method of Working
The best method of working the invention involves deploying the mobile application on smartphones commonly used by farmers in rural areas. The farmer initiates the process by speaking into the device in their local language or dialect. The voice input is captured by the application’s audio module and processed through the automatic speech recognition (ASR) engine. When internet connectivity is available, the ASR engine utilizes cloud-based models for enhanced accuracy; in low-connectivity or offline conditions, a lightweight dialect-aware ASR model interprets the farmer’s speech locally. The ASR engine extracts crop symptoms and relevant keywords, forming the basis for pest diagnosis.
Optionally, the farmer may capture or upload an image of the affected crop using the device camera. The image is processed by an on-device classifier when offline, or by a cloud-based deep learning model when online. The hybrid fusion engine then combines the voice-derived symptoms, image analysis, and geo-temporal data such as location and time of report. This fusion ensures that the diagnosis is context-specific and accurate, even under varying field conditions.
The fused data is processed by the decision engine, which references a pest knowledge base containing symptom descriptions, crop-specific vulnerabilities, and recommended management practices. The decision engine generates a diagnosis and provides treatment recommendations that emphasize environmentally safe and locally relevant solutions. These recommendations are delivered to the farmer through a text-to-speech (TTS) output module in the farmer’s preferred language. For farmers with limited literacy, the application also displays simple icons and visual cues to reinforce the spoken instructions.
In offline mode, the application relies on a locally stored advice database that contains pest management information. This database is periodically updated through small patches when connectivity is available, ensuring that farmers in remote areas can access up-to-date recommendations. Data collected during offline usage is synchronized with the cloud once connectivity is restored, enabling centralized analytics, reporting, and continuous model improvement.
AI-enabled analytics enhance the reliability of the system by applying confidence-based fusion algorithms to weigh inputs from voice, image, and location data. The application also provides explainable outputs, indicating whether the diagnosis was based on voice input, image analysis, or a combination of both. This transparency builds farmer trust and ensures clarity in the decision-making process.
In practice, the best method of working the invention involves the farmer describing crop symptoms verbally, optionally supplementing with an image, and receiving real-time spoken recommendations tailored to their crop and region. The system functions seamlessly in both connected and offline environments, supports multiple regional languages and dialects, and delivers accessible, accurate, and environmentally safe pest management guidance.
, C , Claims:1. A system of voice-assisted mobile application for pest diagnosis comprising:
a voice input module configured to capture farmer speech in local languages and dialects;
an automatic speech recognition (ASR) engine operable offline and online to extract crop symptoms from voice input;
an optional image capture and classification module configured to analyze crop photographs;
a hybrid fusion engine combining voice-derived symptoms, image analysis, and geo-temporal data to generate pest diagnosis;
a decision engine configured to provide pest identification and management recommendations; and
an output module comprising text-to-speech functionality to deliver recommendations in the farmer’s preferred language.
2. The system as claimed in claim 1, wherein the ASR engine is dialect-aware and optimized for regional language variations and accent differences.
3. The system as claimed in claim 1, wherein the image classification module operates on-device when offline and synchronizes with cloud-based models when online.
4. The system as claimed in claim 1, wherein the hybrid fusion engine employs confidence-based model fusion to combine voice, image, and location data for improved accuracy.
5. The system as claimed in claim 1, wherein the decision engine accesses an offline advice database with periodic version updates to provide recommendations in low-connectivity areas.
6. The system as claimed in claim 1, wherein the output module provides explainable recommendations by indicating whether the diagnosis is based on voice input, image analysis, or both.
7. The system as claimed in claim 1, wherein the system supports multiple regional languages and dialects beyond major national languages.
8. The system as claimed in claim 1, wherein the application synchronizes collected data to a cloud server for centralized analytics, reporting, and model improvement.
9. The system as claimed in claim 1, wherein the recommendations include environmentally safe pest management practices tailored to local crop conditions.
10. The system as claimed in claim 1, wherein the user interface comprises simple icons and voice instructions to overcome literacy barriers among farmers.