Description:Non-Provisional Patent Specification
Title: PROCESS FOR IDENTIFYING SUSPECT ENTITIES VIA NETWORK DEPTH USING DOCUMENT ANALYTICS
BACKGROUND
Field of Invention
[001] The present invention generally relates to detection process, and more particularly, to a process for identifying suspect entities via network depth using document analytics.
Description of Related Art
[002] Identifying suspicious entities and potential threats is crucial for law enforcement and intelligence agencies, who track activities of various suspects digitally. Users of well-known public and private computer networks utilize gadgets like desktop computers, laptop computers, tablets, smart phones, browsers, etc. to communicate with one another through connected computers and servers. For many years, such communication is tracked to identify new threats.
[003] Interconnected network devices transmit digital data over the network, often in the form of data packets. Unfortunately, criminal activity discussions may happen over private networks that are not accessible. Malicious actions may occur as results of these discussions.
[004] There are several innovations in the field of mapping networks between entities, to identify relationship of different unknown entities with known suspects. Most of these network mapping innovations aim to establish connections between organizations or individuals based on their digital footprints. In the framework of suspect and threat profile of an entity, no invention is specifically focused on papers, particularly outdated documents, consisting of records of activities of various existing suspects and mention of their footprints digitally as well as offline, that need to be digitally converted and may not already exist in a readable state.
SUMMARY
[005] According to an embodiment of the present invention provide a process for identifying suspect entities via network depth using document analytics. The process comprising categorizing text from a plurality of documents into entities belong to any one of the predetermined category sets. The process includes finding depth of relationship of a given suspect entity with other entities belonging to the mentioned category sets of entities. The process also includes identifying a root and a subject dependency by Text Analytics based on relationship and dependency between words. The process further comprising identifying pronouns and prepositions to identify the root and the subject dependency. The process also comprises using libraries of documents that is relevant for suspect relationship identification. The process including identifying relevancy and performing data cleaning activities.
[006] According to an embodiment of the present invention provide an identification of depth of relationships between different entities based on documents and articles mentioning the entities, is critical for the purpose of understanding any entity to its fullest.
[007] Such an understanding leads to better profiling of an entity, thus helping establish contextual threat levels of the entity, and enhancing the suspect list in the context of any threat. For example, without such understanding, one may not be able to unveil how a particular terrorist organization is connect to an individual that promotes the ideologies based on which the organization has been created.
[008] Failure of such unveiling may mean failure of identifying threats in advance. Typically, such understanding is hidden inside billions of pages of information, and experts need to spend a lot of time combing through these pages, with the fear of bias and fatigue acting as impediment. It is critical that such information is captured through use of artificial intelligence driven identification, made possible through this invention.
[009] According to an embodiment of the present invention the present invention is relevant for law enforcement, intelligence, and other related agencies. Further, the present invention provides the required knowledge in taking informed decisions, based on billions of pages of documents and in-depth understanding of a suspect’s relationship with other entities isn’t possible without manual intervention.
[0010] These and other advantages will be apparent from the present application of the embodiments described herein.
[0011] The preceding is a simplified summary to provide an understanding of some embodiments of the present invention. This summary is neither an extensive nor exhaustive overview of the present invention and its various embodiments. The summary presents selected concepts of the embodiments of the present invention in a simplified form as an introduction to the more detailed description presented below. As will be appreciated, other embodiments of the present invention are possible utilizing, alone or in combination, one or more of the features set forth above or described in detail below.
BRIEF DESCRIPTION OF THE DRAWINGS
[0012] The above and still further features and advantages of embodiments of the present invention will become apparent upon consideration of the following detailed description of embodiments thereof, especially when taken in conjunction with the accompanying drawings, and wherein:
[0013] FIG. 1 illustrates a flowchart of a process for identifying suspect entities via network depth using document analytics, according to embodiments of the present invention.
[0014] The headings used herein are for organizational purposes only and are not meant to be used to limit the scope of the description or the claims. As used throughout this application, the word "may" is used in a permissive sense (i.e., meaning having the potential to), rather than the mandatory sense (i.e., meaning must). Similarly, the words “include”, “including”, and “includes” mean including but not limited to. To facilitate understanding, like reference numerals have been used, where possible, to designate like elements common to the figures. Optional portions of the figures may be illustrated using dashed or dotted lines, unless the context of usage indicates otherwise.
DETAILED DESCRIPTION
[0015] The following description includes the preferred best mode of one embodiment of the present invention. It will be clear from this description of the invention that the invention is not limited to these illustrated embodiments, but the invention also includes a variety of modifications and embodiments thereto. Therefore, the present description should be seen as illustrative and not limiting. While the invention is susceptible to various modifications and alternative constructions, it should be understood, that there is no intention to limit the invention to the specific form disclosed, but, on the contrary, the invention is to cover all modifications, alternative constructions, and equivalents falling within the spirit and scope of the invention as defined in the claims.
[0016] In any embodiment described herein, the open-ended terms “comprising,” “comprises,” and the like (which are synonymous with “including,” “having” and “characterized by”) may be replaced by the respective partially closed phrases “consisting essentially of,” consists essentially of,” and the like or the respective closed phrases “consisting of,” “consists of, the like.
[0017] As used herein, the singular forms “a”, “an”, and “the” designate both the singular and the plural, unless expressly stated to designate the singular only.
[0018] One implementation of the invention allows for the identification of numerous questionable entities through document analytics and network depth. A text may be divided into entities that belong to any one of the specified category groups by being divided into a variety of documents. It is possible to ascertain the extent of a suspect entity's connections to other entities that fall into the aforementioned category groupings of entities. According to embodiments of the present invention, the aforementioned category sets may comprise organizations, events, individuals, and so forth.
[0019] According to one implementation of the invention, a root and a topic dependence can be found using text analytics based on the relationships and dependencies between words.
[0020] The root and the subject dependency may be determined using pronouns and prepositions. The use of several document libraries that provide information useful for identifying questionable relationships is possible.
[0021] The procedure entails determining relevance and carrying out data cleansing tasks. When adding the relevance of suspect identification and having the ability to determine the degree of the link, that is possible to use text analytics to uncover relationships between entities in huge documents. This is possible to determine the degree of relationships between different people, events, and organizations using document analytics (rather than digital footprint analysis). Relevance from the context of suspect identification may be added in one embodiment of the current invention.
[0022] Furthermore, high-level decisions on the identification of other suspects in the context of a threat may be made. Based on the depth of their connections with various other entities, a specific threat may be recognized.
[0023] The identification of the depth of relationships between various entities based on papers and articles mentioning the entities, according to one embodiment of the present invention, is essential for fully comprehending any entity. A better understanding of an entity results in better profiling, which helps determine its contextual threat levels and improves the suspect list in the context of any threat.
[0024] One might not be able to identify, for instance, how a specific terrorist organization is linked to a person who advances the ideology on which the organization was founded without such awareness. If such an unveiling fails, may be impossible to anticipate attacks.
[0025] Experts may spend a lot of time sifting through billions of pages of information in order to uncover such understanding, which is typically hidden there. The fear of bias and exhaustion are two obstacles to this process. That is essential that this data be recorded using the artificial intelligence-driven identification made available by this invention.
[0026] Using text data cleaning and analytics tools on the documents to combine smart analytics of old documents, network depth identification's power to identify documents can be increased. Natural language processing's foundational methods can be used to create relationships.
[0027] FIG. 1 illustrates a flowchart of a process 100 for identifying suspect entities via network depth using document analytics, according to embodiments of the present invention.
[0028] At 102, categorizing text from a plurality of documents into entities belong to any one of the predetermined category sets. According to embodiments of the present invention, the predetermined category sets may comprise organizations, events, individuals, and so forth.
[0029] At 104, finding depth of relationship of a given suspect entity with other entities belonging to the mentioned category sets of entities.
[0030] At 106, identifying a root and a subject dependency by Text Analytics based on relationship and dependency between words.
[0031] At 108, identifying pronouns and prepositions to identify the root and the subject dependency.
[0032] At 110, using libraries of documents that is relevant for suspect relationship identification.
[0033] At 112, identifying relevancy and performing data cleaning activities.
[0034] In an embodiment of the present invention the process 100 may further comprise finding relationship between entities performance of text analytics on large documents with the purpose to find relationship between entities, when adding the relevancy of suspect identification, with the capability to know the depth of relationship.
[0035] The process 100 may comprise using analytics of documents (and not digital footprint) to identify depth of relationship between various individuals, events, and organization.
[0036] The process 100 may comprise adding relevancy from the context of suspect identification.
[0037] In an embodiment of the present invention, the process 100 may comprise making high end decision with respect to identifying more suspects in the context of a threat.
[0038] The process 100 may comprise identifying a particular threat in a deep manner, based on their depth of relationships with various other entities.
[0039] The process 100 may comprise extending the power of network depth identification to documents, using text data cleaning and analytics tools over the documents to bring together smart analytics of old documents.
[0040] Further, the process 100 may comprise establishing relationships using fundamental techniques of natural language processing.
[0041] While the invention has been described in connection with what is presently considered to be the most practical and various embodiments, it is to be understood that the invention is not to be limited to the disclosed embodiments, but on the contrary, is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.
[0042] This written description uses examples to disclose the invention, including the best mode, and also to enable any person skilled in the art to practice the invention, including making and using any devices or systems and performing any incorporated process. The patentable scope the invention is defined in the claims, and may include other examples that occur to those skilled in the art. Such other examples are intended to be within the scope of the claims if they have structural elements that do not differ from the literal language of the claims, or if they include equivalent structural elements within substantial differences from the literal languages of the claims.
, Claims:I/WE CLAIM:
1) A process for identifying suspect entities via network depth using document analytics, the process comprising:
categorizing text from a plurality of documents into entities belong to any one of the predetermined category sets;
finding depth of relationship of a given suspect entity with other entities belonging to the mentioned category sets of entities;
identifying a root and a subject dependency by Text Analytics based on relationship and dependency between words;
identifying pronouns and prepositions to identify the root and the subject dependency;
using libraries of documents that is relevant for suspect relationship identification; and
identifying relevancy and performing data cleaning activities.
2) The process as claimed in claim 1, wherein the process comprising finding relationship between entities performance of text analytics on large documents with the purpose to find relationship between entities, when adding the relevancy of suspect identification, with the capability to know the depth of relationship.
3) The process as claimed in claim 1, wherein the process comprising using analytics of documents (and not digital footprint) to identify depth of relationship between various individuals, events, and organization.
4) The process as claimed in claim 1, wherein the process comprising adding relevancy from the context of suspect identification.
5) The process as claimed in claim 1, wherein the process comprising making high end decision with respect to identifying more suspects in the context of a threat.
6) The process as claimed in claim 1, wherein the process comprising identifying a particular threat in a deep manner, based on their depth of relationships with various other entities.
7) The process as claimed in claim 1, wherein the predetermined category sets comprises organizations, events, individuals, and so forth.
8) The process as claimed in claim 1, wherein the process comprising extending the power of network depth identification to documents, using text data cleaning and analytics tools over the documents to bring together smart analytics of old documents.
9) The process as claimed in claim 1, wherein the process comprising establishing relationships using fundamental techniques of natural language processing.