Systems and methods for generating search results based on optical character recognition techniques and machine-encoded text
Disclosed are systems and methods for generating search result data based on machine-encoded text generated by computer vision optical character recognition machine learning techniques performed on digital media. The disclosed systems and methods provide a novel framework for performing machine learning visual search or machine learning text extraction techniques on digital media in order to extract and analyze the data therein and further conduct search queries based on the extracted and analyzed data. The disclosed framework may leverage the aforementioned computer vision machine learning techniques in order to provide a user with relevant search results regarding objects and text detect in digital media captured on a user device.
1. A computer-implemented method for generating search result data based on machine-encoded text data, the method comprising:
transmitting an image from a device search engine module to a device OCR machine learning module of a user device;
receiving, at the device search engine module, machine-encoded text from the device OCR machine learning module;
rendering a geometrical bounding element comprising the machine-encoded text, wherein the geometrical bounding element is overlaid onto the image;
receiving a selection via a graphical user interface of at least a portion of the machine-encoded text corresponding to the geometrical bounding element;
transmitting from the user device a search request comprising one or more of: a device identifier, a location of the user device, and a query comprising the portion of the machine-encoded-text, to a search application system;
authenticating the received search request at the search application system via an API gateway and upon authenticating the search request, transmitting the search request to a server search engine module;
searching for and identifying media and text data corresponding to the selected portion of the machine-encoded text; and
receiving at the user device search results corresponding to the search request.
2. The computer-implemented method of claim 1 , further comprising:
automatically determining the location of the user device based on GPS coordinates or identifying the name of the location from object data or text data in the digital image.
3. The computer-implemented method of claim 1 , wherein rendering a geometrical bounding element comprising the machine-encoded text, further comprises:
analyzing text in the digital image by conducting natural language processing techniques on the analyzed text.
4. The computer-implemented method of claim 2 , wherein rendering a geometrical bounding element comprising the machine-encoded text, further comprises:
generating an enhanced location profile based on the determined location and search results corresponding to the search request.
5. The computer-implemented method of claim 1 , further comprising:
determining whether the geometrical boundary element is rendered visible or transparent based on a determination of the amount of text in the digital image.
6. The computer-implemented method of claim 1 , wherein authenticating the received search request at the search application system via an API gateway further comprises:
determining whether the search request comprises an authentication token.
7. The computer-implemented method of claim 1 , wherein receiving at the user device search results corresponding to the search request further comprises:
displaying search results comprising content ranked according to relevance associated with the subject matter or text corresponding to the selected portion of the machine-encoded text.
8. A system for generating search result data based on machine-encoded text data, the system comprising:
a memory storage device storing instructions for generating search result data based on machine-encoded text data; and
one or more processors configured to execute the instructions for generating search result data based on machine-encoded text data by performing the steps of:
transmitting an image from a device search engine module to a device OCR machine learning module of a user device;
receiving at the device search engine module machine-encoded text from the device OCR machine learning module;
rendering a geometrical bounding element comprising the machine-encoded text, wherein the geometrical bounding element is overlaid onto the image;
receiving a selection via a graphical user interface of at least a portion of the machine-encoded text corresponding to the geometrical bounding element;
transmitting from the user device a search request comprising one or more of: a device identifier, a location of the user device, and a query comprising the portion of the machine-encoded-text, to a search application system;
authenticating the received search request at the search application system via an API gateway and upon authenticating the search request, transmitting the search request to a server search engine module;
searching for and identifying media and text data corresponding to the selected portion of the machine-encoded text; and
receiving at the user device search results corresponding to the search request.
9. The system of claim 8 , wherein the processor is further configured to execute the instructions to perform one more additional steps comprising:
automatically determining the location of the user device based on GPS coordinates or identifying the name of the location from object data or text data in the digital image.
10. The system of claim 8 , wherein rendering a geometrical bounding element comprising the machine-encoded text, further comprises:
analyzing text in the digital image by conducting natural language processing techniques on the analyzed text.
11. The system of claim 9 , wherein rendering a geometrical bounding element comprising the machine-encoded text, further comprises:
generating an enhanced location profile based on the determined location and search results corresponding to the search request.
12. The system of claim 8 , wherein the processor is further configured to execute the instructions to perform one more additional steps comprising:
determining whether the geometrical boundary element is rendered visible or transparent based on a determination of the amount of text in the digital image.
13. The system of claim 8 , wherein authenticating the received search request at the search application system via an API gateway further comprises:
determining whether the search request comprises an authentication token.
14. The system of claim 8 , wherein receiving at the user device search results corresponding to the search request further comprises:
displaying search results comprising content ranked according to relevance associated with the subject matter or text corresponding to the selected portion of the machine-encoded text.
15. A non-transitory computer-readable medium for generating search result data based on machine-encoded text data, the method comprising:
at least one storage medium with instructions thereon for generating search result data based on machine-encoded text data; and
at least one processor that executes the instructions to perform a method comprising:
transmitting an image from a device search engine module to a device OCR machine learning module of a user device;
receiving at the device search engine module machine-encoded text from the device OCR machine learning module;
rendering a geometrical bounding element comprising the machine-encoded text, wherein the geometrical bounding element is overlaid onto the image;
receiving a selection via a graphical user interface of at least a portion of the machine-encoded text corresponding to the geometrical bounding element;
transmitting from the user device a search request comprising one or more of: a device identifier, a location of the user device, and a query comprising the portion of the machine-encoded-text, to a search application system;
authenticating the received search request at the search application system via an API gateway and upon authenticating the search request, transmitting the search request to a server search engine module;
searching for and identifying media and text data corresponding to the selected portion of the machine-encoded text; and
receiving at the user device search results corresponding to the search request.
16. The non-transitory computer-readable medium of claim 15 , further comprising:
automatically determining the location of the user device based on GPS coordinates or identifying the name of the location from object data or text data in the digital image.
17. The non-transitory computer-readable medium of claim 15 , wherein rendering a geometrical bounding element comprising the machine-encoded text, further comprises:
analyzing text in the digital image by conducting natural language processing techniques on the analyzed text.
18. The non-transitory computer-readable medium of claim 16 , wherein rendering a geometrical bounding element comprising the machine-encoded text, further comprises:
generating an enhanced location profile based on the determined location and search results corresponding to the search request.
19. The non-transitory computer-readable medium of claim 15 , further comprising:
determining whether the geometrical boundary element is rendered visible or transparent based on a determination of the amount of text in the digital image.
20. The non-transitory computer-readable medium of claim 15 , wherein authenticating the received search request at the search application system via an API gateway further comprises:
determining whether the search request comprises an authentication token.