Voice-Text Based Crop Issue Identification
In India, several thousand tonnes of crop gets destroyed every year due to incorrect usage of pesticides, insecticides, plant growth regulators etc. Whenever there is a disease outbreak in a farmer’s field, the first person whom they usually look forward to is the local vendor from whom they purchase their farming products like seeds, spraying equipments etc. In India, officially you need to have at least a certain relevant degree before you can start your own fertilizer shop. However, these norms are hardly practiced.
These local vendors have their own interest in mind, since they need to sell the products of the companies from whom they purchase the chemicals in bulk. Thus, more often than not, with no practical scientific knowledge, they end up suggesting completely incorrect solutions to the farmer.
One of the major aims of Farmonaut is to help farmers figure out what the problem is with their crop, and also provide government approved solutions for the problems identified by our system. Though the government has released a scientifically approved database, however the database is highly user inaccessible. The government database is in the form of document file of hundreds of pages. It is really unreasonable to expect a farmer to download this large document and scroll through hundreds of pages to identify what the potential problem is with their crop. At Farmonaut, the first thing we did is to sanitize this government approved database, and present it to the farmers in a user-friendly form.
The segregated database is accessible through our android app and contains government approved information about 100+ crops, 300+ problems and 150+ chemicals (pesticides, insecticides, plant growth regulators etc.). The database includes very specific details of chemical usage such as Quantity, Formulation (g/ml)% and Dilution in water (L).
Read the following article to know in-depth about the Farmonaut Database:
At Farmonaut, we jumped one step ahead and added another layer of user friendliness to access our database. We have designed a system which is capable of identifying potential problems with a farmer’s crop by just their voice or text explanation.
The voice-text based crop issue identification system is available on our Android app. A farmer can simply explain what issues he/she is facing with his crop and our system in real-time will identify the potential problem with the crop as well as the government approved solutions attached with the results as well. Given the vastness of India and a large number of languages being spoken in the Indian subcontinent, we can not expect our system to work only in one specific language. Hence, we have created our system to work in more than 50 languages. The farmers can ask their problems in a language of their choice and can still get government approved solutions in real time.
The following section below shows a few examples of how Farmonaut’s voice-text based crop issue identification system works.
The Voice-text based crop issue identification system works as a chat bot, wherein farmers can ask for the solution to their problems just like someone will message another user on a messaging service. The farmer can simply type their query into the text box or can speak about their query by clicking on the speech button. Once the speech of the farmer is finished or if farmer clicks on the send button after his text information about the problem is ready, the system will process their speech/text to identify the crop as well the problem being faced by the farmer. Upon correct identification of the problem, the system will return all the government approved solutions from which the farmer can select one of his choice.
For example, in the case above, the Farmer has asked in hindi the following query:
Asked Query: आम की फसल की उपज बढ़ाने के कुछ उपाय बताइये| अभी एकदम नयी फसल है|
Our system identifies within seconds that the user is looking for ways to enhance yield of their mango crop and hence, provides all the government approved solutions to the user about chemicals measures to be used to enhance the yield of his/her mango produce.
Some other examples of the Voice-text Based Crop Issue Identification queries are listed below.
There may be times when the voice-text based crop issue identification system is not able to identify the problem properly. There are 4 such cases which we want to highlight.
Case 1:
When our system has correctly identified the crop as well as the problem being faced by the crop, the system still gives the farmer an option to post his query on to the discussion forum to further proof check about his problem from the community.
Case 2:
When our system has correctly identified the crop of the query but not problem, the farmer can post this unsuccessful query onto the discussion forum to get remedies from the farming community itself.
Case 3:
When our system has not been able to identify both crop as well as the problem, and if the farmer feels that his/her query was correct, they can post this voice-text crop issue identification query on to the discussion forum to get remedies from the farming community.
A detailed article about the discussion forum and Farmonaut database will be available soon.
The app is available for android on Google PlayStore:
https://play.google.com/store/apps/details?id=com.farmonaut.android
We will keep posting about any such informative information on to our blogs, to help as many people as possible. Farmonaut is built upon a vision to bridge the technological gap between farmers and strives to bring state-of-the-art technologies in the hands of each and every farmer. For any queries/suggestions, please contact us at [email protected].
We have some more interesting articles coming up soon. Stay tuned!
Wait!!