Enterprise Search

[ultimate_heading main_heading=”PRODUCT” spacer=”line_only” spacer_position=”bottom” line_height=”1″ main_heading_font_size=”desktop:36px;” main_heading_line_height=”desktop:46px;”][/ultimate_heading]
[ult_tab_element tab_style=”Style_4″ tab_animation=”None” tab_background_color=”#eaeaea” tab_hover_background_color=”#c9060d” acttab_background=”#c9060d” tabs_border_radius=”0″ disp_icon=”Disables” resp_style=”Title”][single_tab title=”Explanation” tab_id=”1562610615228-4-6″]

Enterprise Search (ES) project is a domain-independent scalable semantic search platform. It is an entity based system that enables searches via entities in order to provide more relevant search results. The platform makes use of cutting edge technologies such as deep learning and semantic web to make document retrieval more efficient when compared with traditional search systems. An enterprise search engine enables semantic search in both English and Turkish. Other systems are able to use the platform and integrate the solutions as a service. It aims to serve thousands of users concurrently by using big data technologies.

[/single_tab][single_tab title=”Unique Advantages” tab_id=”1562610767710-3-6″]

• Supports several search options; entity based semantic search, keyword-based semantic search, and traditional keyword search.
• More relevant search results when compared with traditional search systems.
• Users will save time when searching for content.
• Domain independent system that can integrate any knowledge graph.
• Makes use of cutting edge technologies.
• The system is scalable and built on top of distributed systems architecture.
• Easy to use, a responsive user interface that provides system monitoring, configuration management.
• All the services are provided as REST APIs.
• Supports both English and Turkish.

[/single_tab][single_tab title=”Application Scenarios” tab_id=”1561669169545-3-9″]

Semantic Search:
A customer wants to search for information about a specific internal project within a specified department and retrieve related documents for that project using our system. Based on the problem, documents that need to be retrieved about the project from a specific department may occur also multiple times in documents from different departments. This is simply because the project’s name is ambiguous and there are projects with similar names in other departments. Semantic search can be utilized in this case given there is sufficient information and data in the domain-specific knowledge graph.
In our use case, a user searches for a project with a keyword related to a project from a specific department which is ambiguous when compared with projects from other departments.

Solution Overview:

Preface:
Enterprise Search (ES) provides a feasible solution using a knowledge graph for ambiguous search terms. This system’s goal is not to compete for search engines like Google or Yahoo which are used in a common manner. Its goal is to return relevant documents with correct entities in a specific domain according to the business expert’s search query with solving ambiguity using the companies’ own knowledge graph. Knowledge info box about the entities and related documents will be listed back to the user on the result page.
• The user knows related keywords for a project and the department.
• The user chooses a search algorithm in our system.
• If the user chooses a keyword-based semantic search the user makes a search in our system with the keywords and other selected parameters from UI.
• The user controls the returned knowledge info box in order to understand if found entity is the correct one for the given user query.
• If the box shows the entity that the expert is not looking for, an expert can add more keywords that may relate to the desired project such as; department name, country, year, key members to project, etc.
More keyword given by expert will result in better disambiguation and will most likely give correct entity information box, generated from the knowledge graph, as well as related documents from the internal document index.
• If the user chooses an entity based semantic search
The user starts typing the project name and our system will try to find the entity from the knowledge base and make suggestions to the user.
• Users will choose the entity from the list of suggestions. This process can be repeated as many times the users want.
• Users will click the search button and a query will be generated in the background and the documents about the chosen entity will be retrieved from the index.

[/single_tab][/ult_tab_element]
[ultimate_heading main_heading=”PRODUCT VISUALS” spacer=”line_only” spacer_position=”bottom” line_height=”1″ main_heading_font_size=”desktop:36px;” main_heading_line_height=”desktop:46px;”][/ultimate_heading]
[ultimate_heading main_heading=”RESOURCES” spacer=”line_only” spacer_position=”bottom” line_height=”1″ main_heading_font_size=”desktop:36px;” main_heading_line_height=”desktop:46px;”][/ultimate_heading]
[icon_counter flip_box_style=”advanced” box_border_style=”solid” box_border_size=”2″ icon=”Defaults-play-circle-o” icon_size=”40″ icon_color=”#c9060d” block_title_front=”Global Link” block_desc_color=”#000000″ block_front_color=”#ffffff” box_border_color=”#a4a4a4″ block_title_back=”Global Link” block_back_text_color=”#ffffff” block_back_desc_color=”#ffffff” block_back_color=”#c9060d” box_border_color_back=”#a4a4a4″ custom_link=”1″ button_link=”||target:%20_blank|” button_text=”Go to Page” button_txt=”#ffffff”]