Conceptual Searching

December 16, 2022

Conceptual Searching

Importance of Conceptual Searching

Relativity offers a wide range of search features designed to simplify and enhance the document review process. Relativity search can be essential in one case, as it is used to reduce the amount of data to review and find the most relevant documents. There are two main methods relativity uses to search for data:

Presence Searching

Occurrence search looks through the data set to find a match for a specific word using Boolean logic, which is a form of algebra where all values are either true or false.

Conceptual Searching

Conceptual Searching uses mathematics to derive possible meanings of a word and tries to understand semantic meaning and context.

What is Conceptual Searching?

You can use conceptual searching to find information without a precisely phrased query by applying a block of text against the database to find documents that have similar conceptual content. This can help in setting priorities or finding important documents. Concept Searching is very distinctive from keyword or metadata search. A concept search performed in Analytics quickly and efficiently reveals conceptual similarities between queries and documents, so you can focus on the concepts you think matter most. The following table illustrates the differences between standard search and concept search. Using conceptual searching, you can submit a query that is anywhere within a sentence the length of an entire document and return documents that contain the concepts that the query expresses. Using a single word for a query is not recommended as the results may be broad and unreliable. The match is not based on a specific term in the query or document. Query and documents may or may not share terms, but they share conceptual meaning. Each term of the conceptual index has a position vector in the conceptual space. Each searchable document also has a vector of concept spaces. These vectors, when close to each other, share a correlation or conceptual relationship. Increased distance indicates a decrease in correlation or shared ideas. Two objects that are shut collectively share conceptuality, regardless of any precise shared terms. During conceptual searching, you generate text that illustrates a single concept (called a concept query) and then submits it to the index for a tentative mapping to the concept space. Conceptual Analysis Indexes use the same mapping logic to map queries into concept spaces as searchable documents.

Importance of conceptual searching

The importance of conceptual searching is as follows:

Many language barriers prevent keyword research from being effective. These problems revolve around word inconsistencies—such as a single word can have many meanings, multiple words can have the same meaning, and some words have special meanings in a particular context or group of people. Concept search is more accurate and avoids these problems because it does not rely on word matches to find relevant documents.
Communication can often be intentionally distorted or ambiguous. However, because concept search can look at a document as a whole, it can still find conceptual meaning in a document with intentional ambiguity.
Conceptual searching forces a focus on conceptual relevance rather than a single word.
Conceptual searching encourages the user to express an idea in the same way that people are used to describing concepts and ideas. Concept search can handle very long queries.
Conceptual searching ultimately works by finding correlations of words within a document and across a document set Therefore, in the context of a data set, conceptual analytics can provide a very accurate word relation list (dynamic synonym list).

The limitations of keyword-based searches are well documented. A syntactic search engine will return results based only on the words and phrases a searcher enters. Synonyms, synonyms, and translations all prove problematic in this situation. This technology, on its own, is not powerful enough to find all the patent and non-patent literature related to your novel idea. Conceptual inquiry, however, considers the meaning of an inquirer's question. It uses this understanding of the search to find the most relevant results, regardless of the wording used by a searcher or publication to communicate the concept. The most powerful search solutions can identify results beyond just common synonyms, using AI to truly understand the concepts being described. When you're pushing a new idea through the innovation pipeline, the stakes are high. R&D resources should be allocated to the most promising projects. Administrative and criminal prices related to patenting should be cautiously considered. Determining whether an innovation is marketable requires a thorough understanding of the technology landscape. This is only possible with a search engine that finds the most relevant patent and non-patent literature, no matter how you describe your technology. With keyword-based search engines, finding relevant results (and confidently eliminating irrelevant results) requires at least some skill in specialized techniques. Conceptual search democratizes patent searches, removes barriers in the innovation lifecycle, and gives searchers across professional disciplines confidence in their search results. The concept-based search considers how important a concept is within a document to rank search results based on relevance.