User interface for use with a search engine for searching financial related documents
A method for rendering context based information on a user interface includes receiving a user request to extract the context based information from a database. The database includes a plurality of documents and the request includes at least one search criteria required to determine a context of the user request. The method includes generating a list of documents corresponding to the context of the user request and rendering on a viewing portion of the user interface the list of documents corresponding to the context of the user request.
1 . A system for searching a plurality of documents and rendering information from the plurality of documents on a user interface of a remote computer, the system comprising:
a memory storing instructions to be executed by one or more hardware processors; and
one or more hardware processors configured to execute the instructions stored in the memory, wherein the instructions, when executed by the one or more hardware processors, cause the system to:
receive a plurality of documents associated with one or more publicly traded companies;
pre-process at least some of the plurality of documents, wherein the pre-processing of each respective document comprises:
identifying chunks of text in said respective document;
generating one or more pieces of metadata associated with at least one of the identified chunks of text in said respective document,
wherein the one or more pieces of metadata associated with said at least one of the identified chunks of text represents at least one topic that is determined using a machine-learning model;
receive a user query from the remote computer to search for information from the pre-processed plurality of documents,
wherein the user query is based on input from a user at the remote computer;
identify a topic of interest associated with the user query;
execute a search of the pre-processed plurality of documents based on the user query, wherein the search uses the generated metadata to identify one or more relevant documents from within the pre-processed plurality of documents;
generate search results comprising the one or more relevant documents from within the pre-processed plurality of documents in response to executing the search,
wherein a relevant document is determined to be relevant when said document contains at least one chunk of text that is associated with generated metadata that represents at least one topic that is similar to the topic of interest associated with the user query, wherein similarity between said at least one topic and the topic of interest is based on the generated metadata;
receive a selection from the user identifying a selected document from the search results; and
cause at least a portion of the selected document from the search results to be rendered on the user interface of the remote computer.
2 . The system of claim 1 , wherein the pre-processing of each respective document further comprises converting sentences of said respective document into a numerical representation.
3 . The system of claim 1 , wherein the instructions, when executed by the one or more hardware processors, further cause the system to use the machine-learning model to determine at least one keyword associated with the user query.
4 . The system of claim 3 , wherein the at least one topic that is similar to the topic of interest associated with the user query is related to the at least one keyword.
5 . The system of claim 3 , wherein a relevant document is determined to be relevant when said document contains at least one chunk of text that contains multiple keywords from the at least one keyword appearing in the same sentence within said chunk of text.
6 . The system of claim 3 , wherein a relevant document is determined to be relevant when said document contains at least one chunk of text that contains multiple keywords from the at least one keyword appearing in the same paragraph within said chunk of text.
7 . The system of claim 3 , wherein a relevant document is determined to be relevant when said document contains at least one chunk of text that contains multiple keywords from the at least one keyword appearing in proximity to one another within said chunk of text.
8 . The system of claim 1 , wherein the instructions, when executed by the one or more hardware processors, further cause the system to render, in addition to the rendered portion of the selected document, content that is generated based on the portion of the first chunk of text.
9 . The system of claim 1 , wherein:
the rendered portion of the selected document includes a second chunk of text from the selected document, and
the second chunk of text is associated with a second topic that is similar to the topic of interest associated with the user query.
10 . The system of claim 1 , wherein the user query includes information identifying a publicly traded company of the one or more publicly traded companies.
11 . The system of claim 10 , wherein the search results include only documents from within the pre-processed plurality of documents that are associated with the publicly traded company identified by the information identifying the publicly traded company from the user query.
12 . The system of claim 1 , wherein:
the rendered portion of the selected document includes at least a portion of a first chunk of text from the selected document that is associated with a first topic that is similar to the topic of interest associated with the user query, and
at least some text from the portion of the first chunk of text is displayed differently in the rendered portion of the selected document.
13 . A computer-implemented method for searching a plurality of documents and rendering information from the plurality of documents on a user interface of a remote computer, the computer-implemented method comprising:
receiving a plurality of documents associated with one or more publicly traded companies;
pre-processing at least some of the plurality of documents, wherein the pre-processing of each respective document comprises:
identifying chunks of text in said respective document;
generating one or more pieces of metadata associated with at least one of the identified chunks of text in said respective document,
wherein the one or more pieces of metadata associated with said at least one of the identified chunks of text represents at least one topic that is determined using a machine-learning model;
receiving a user query from the remote computer to search for information from the pre-processed plurality of documents,
wherein the user query is based on input from a user at the remote computer;
identifying a topic of interest associated with the user query;
executing a search of the pre-processed plurality of documents based on the user query, wherein the search uses the generated metadata to identify one or more relevant documents from within the pre-processed plurality of documents;
generating search results comprising the one or more relevant documents from within the pre-processed plurality of documents in response to executing the search,
wherein a relevant document is determined to be relevant when said document contains at least one chunk of text that is associated with generated metadata that represents at least one topic that is similar to the topic of interest associated with the user query, wherein similarity between said at least one topic and the topic of interest is based on the generated metadata;
receiving a selection from the user identifying a selected document from the search results; and
causing at least a portion of the selected document from the search results to be rendered on the user interface of the remote computer.
14 . The computer-implemented method of claim 13 , wherein the pre-processing of each respective document further comprises converting sentences of said respective document into a numerical representation.
15 . The computer-implemented method of claim 13 , wherein the instructions, when executed by the one or more hardware processors, further cause the system to use the machine-learning model to determine at least one keyword associated with the user query.
16 . The computer-implemented method of claim 15 , wherein the at least one topic that is similar to the topic of interest associated with the user query is related to the at least one keyword.
17 . The computer-implemented method of claim 15 , wherein a relevant document is determined to be relevant when said document contains at least one chunk of text that contains multiple keywords from the at least one keyword appearing in the same sentence within said chunk of text.
18 . The computer-implemented method of claim 15 , wherein a relevant document is determined to be relevant when said document contains at least one chunk of text that contains multiple keywords from the at least one keyword appearing in the same paragraph within said chunk of text.
19 . The computer-implemented method of claim 15 , wherein a relevant document is determined to be relevant when said document contains at least one chunk of text that contains multiple keywords from the at least one keyword appearing in proximity to one another within said chunk of text.
20 . The computer-implemented method of claim 13 , wherein the instructions, when executed by the one or more hardware processors, further cause the system to render, in addition to the rendered portion of the selected document, content that is generated based on the portion of the first chunk of text.
21 . The computer-implemented method of claim 13 , wherein:
the rendered portion of the selected document includes a second chunk of text from the selected document, and
the second chunk of text is associated with a second topic that is similar to the topic of interest associated with the user query.
22 . The computer-implemented method of claim 13 , wherein the user query includes information identifying a publicly traded company of the one or more publicly traded companies.
23 . The computer-implemented method of claim 22 , wherein the search results include only documents from within the pre-processed plurality of documents that are associated with the publicly traded company identified by the information identifying the publicly traded company from the user query.
24 . The computer-implemented method of claim 13 , wherein:
the rendered portion of the selected document includes at least a portion of a first chunk of text from the selected document that is associated with a first topic that is similar to the topic of interest associated with the user query, and
at least some text from the portion of the first chunk of text is displayed differently in the rendered portion of the selected document.