US-20260127238-A1 - CONFIDENTIALITY PRESERVING INTRAORGANIZATIONAL EXPERT SEARCH

US20260127238A1US 20260127238 A1US20260127238 A1US 20260127238A1US-20260127238-A1

Abstract

A processing system including at least one processor may obtain at least one search term and an identity of a searcher, identify individuals who are each either a one-step or two-step association of the searcher, identify first documents associated with the individuals and associated with the search term(s), calculate, for each individual, a score based upon citations of second documents to documents associated with the individual from among the first documents, generate an invitation to at least one individual to appear in a search result, and obtain a consent from the at least one individual. The processing system may then present the search result as an ordered list of at least a portion of the individuals, where the ordered list is ordered by the score for each individual, and where the at least the portion of the plurality of individuals includes the at least one individual.

Inventors

Yaron Kanza
Divesh Srivastava
Caroline Stone
David Wood

Assignees

AT&T INTELLECTUAL PROPERTY I, L.P.

Dates

Publication Date: 20260507
Application Date: 20260105

Claims (20)

1 . A method comprising: obtaining, by a processing system including at least one processor, at least one search term and an identity of a searcher; identifying, by the processing system, a plurality of individuals who are associations of the searcher, wherein the plurality of individuals includes individuals who are one-step associations of the searcher and individuals who are two-step associations of the searcher; identifying, by the processing system, from at least one document database a first plurality of documents associated with the plurality of individuals and also associated with the at least one search term; calculating, by the processing system for each individual of the plurality of individuals, a score for the individual that is based upon a number of citations of a second plurality of documents from the at least one document database to documents associated with the individual from among the first plurality of documents, wherein the score for the individual comprises a topical influence index, and wherein the second plurality of documents is also associated with the at least one search term; and presenting, by the processing system, a search result comprising an ordered list of at least a portion of the plurality of individuals, wherein the ordered list is ordered by the score for each individual of the at least the portion of the plurality of individuals, and wherein the at least the portion of the plurality of individuals includes at least one individual who has provided a preapproval to appear in the search result.
2 . The method of claim 1 , wherein the one-step associations comprise at least one of: a colleague in an organizational unit of the searcher; a co-author of at least one document in which the searcher is an author; or a co-inventor identified in at least one patent document in which the searcher is an inventor.
3 . The method of claim 2 , wherein the two-step associations comprise at least one of: a colleague in an organizational unit of at least one one-step association of the searcher; a co-author of at least one document in which at least one one-step association of the searcher is an author; or a co-inventor identified in at least one patent document in which at least one one-step association of the searcher is an inventor.
4 . The method of claim 1 , wherein the score for each individual comprises a global impact topical influence index.
5 . The method of claim 1 , wherein the second plurality of documents excludes documents that are not associated with the at least one search term.
6 . The method of claim 1 , wherein the score for each individual comprises a strict topical influence index.
7 . The method of claim 1 , further comprising: identifying the second plurality of documents as being associated with the at least one search term.
8 . The method of claim 1 , wherein each document of the first plurality of documents is determined to be associated with at least one individual of the plurality of individuals when the at least one individual is at least one of: an author of the document; an editor of the document; or for a document comprising a patent document, an inventor indicated for the document.
9 . The method of claim 1 , further comprising: obtaining a selection of the at least one document database from among a plurality of available document databases.
10 . The method of claim 1 , wherein the at least one document database comprises an internal database of an organization of the searcher.
11 . The method of claim 1 , further comprising, for each individual of the at least the portion of the plurality of individuals: generating a word cloud based upon frequencies of words contained in the documents associated with the individual from among the first plurality of documents.
12 . The method of claim 11 , wherein the presenting of the search result comprises presenting the word cloud for each individual of the at least the portion of the plurality of individuals.
13 . The method of claim 11 , wherein relative sizes of words in the word cloud are proportional to the respective frequencies of the words.
14 . The method of claim 1 , wherein the score for the individual is based upon a composition of document scores for the documents associated with the individual from among the first plurality of documents.
15 . The method of claim 14 , wherein a document score for a document associated with the individual comprises a weighted combination of an information retrieval metric of the document for the at least one search term and information retrieval metrics for each document from the second plurality of documents citing to the document associated with the individual.
16 . A non-transitory computer-readable medium storing instructions which, when executed by a processing system including at least one processor, cause the processing system to perform operations, the operations comprising: obtaining at least one search term and an identity of a searcher; identifying a plurality of individuals who are associations of the searcher, wherein the plurality of individuals includes individuals who are one-step associations of the searcher and individuals who are two-step associations of the searcher; identifying from at least one document database a first plurality of documents associated with the plurality of individuals and also associated with the at least one search term; calculating, for each individual of the plurality of individuals, a score for the individual that is based upon a number of citations of a second plurality of documents from the at least one document database to documents associated with the individual from among the first plurality of documents, wherein the score for the individual comprises a topical influence index, and wherein the second plurality of documents is also associated with the at least one search term; and presenting a search result comprising an ordered list of at least a portion of the plurality of individuals, wherein the ordered list is ordered by the score for each individual of the at least the portion of the plurality of individuals, and wherein the at least the portion of the plurality of individuals includes at least one individual who has provided a preapproval to appear in the search result.
17 . A device comprising: a processing system including at least one processor; and a computer-readable medium storing instructions which, when executed by the processing system, cause the processing system to perform operations, the operations comprising: obtaining at least one search term and an identity of a searcher; identifying a plurality of individuals who are associations of the searcher, wherein the plurality of individuals includes individuals who are one-step associations of the searcher and individuals who are two-step associations of the searcher; identifying from at least one document database a first plurality of documents associated with the plurality of individuals and also associated with the at least one search term; calculating, for each individual of the plurality of individuals, a score for the individual that is based upon a number of citations of a second plurality of documents from the at least one document database to documents associated with the individual from among the first plurality of documents, wherein the score for the individual comprises a topical influence index, and wherein the second plurality of documents is also associated with the at least one search term; and presenting a search result comprising an ordered list of at least a portion of the plurality of individuals, wherein the ordered list is ordered by the score for each individual of the at least the portion of the plurality of individuals, and wherein the at least the portion of the plurality of individuals includes at least one individual who has provided a preapproval to appear in the search result.
18 . The device of claim 17 , wherein the one-step associations comprise at least one of: a colleague in an organizational unit of the searcher; a co-author of at least one document in which the searcher is an author; or a co-inventor identified in at least one patent document in which the searcher is an inventor.
19 . The device of claim 18 , wherein the two-step associations comprise at least one of: a colleague in an organizational unit of at least one one-step association of the searcher; a co-author of at least one document in which at least one one-step association of the searcher is an author, or a co-inventor identified in at least one patent document in which at least one one-step association of the searcher is an inventor.
20 . The device of claim 18 , wherein the score for each individual comprises a global impact topical influence index.

Description

This application is a continuation of U.S. patent application Ser. No. 18/887,026 filed on Sep. 16, 2024, now U.S. Pat. No. 12,517,969 which is a continuation of U.S. patent application Ser. No. 17/734,400 filed on May 2, 2022, now U.S. Pat. No. 12,093,333, both of which are herein incorporated by reference in their entireties. BACKGROUND The present disclosure relates generally to expert finder systems, and more particularly to methods, computer-readable media, and apparatuses for presenting an ordered list of individuals in accordance with scores based upon a number of citations of a second plurality of documents from at least one document database to documents associated with the individuals from among a first plurality of documents from the at least one document database that are associated with at least one search term. BRIEF DESCRIPTION OF THE DRAWINGS The present disclosure can be readily understood by considering the following detailed description in conjunction with the accompanying drawings, in which: FIG. 1 illustrates one example of a system including a telecommunication network, according to the present disclosure; FIG. 2 illustrates an example search result screen with representative word clouds and an example search result screen that presents a search result in the context of an organization hierarchy; FIG. 3 illustrates a flowchart of an example method for presenting an ordered list of individuals in accordance with scores based upon a number of citations of a second plurality of documents from at least one document database to documents associated with the individuals from among a first plurality of documents from the at least one document database that are associated with at least one search term; and FIG. 4 illustrates a high-level block diagram of a computing device specially programmed to perform the functions described herein. To facilitate understanding, identical reference numerals have been used, where possible, to designate identical elements that are common to the figures. DETAILED DESCRIPTION The present disclosure broadly discloses methods, non-transitory (i.e., tangible or physical) computer-readable media, and apparatuses for presenting an ordered list of individuals in accordance with scores based upon a number of citations of a second plurality of documents from at least one document database to documents associated with the individuals from among a first plurality of documents from the at least one document database that are associated with at least one search term. For instance, in one example, a processing system including at least one processor may obtain at least one search term and an identity of a searcher, identify a plurality of individuals who are each either a one-step association of the searcher or a two-step association of the searcher, and identify from at least one document database a first plurality of documents associated with the plurality of individuals and also associated with the at least one search term. The processing system may next calculate, for each individual of the plurality of individuals, a score for the individual that is based upon a number of citations of a second plurality of documents from the at least one document database to documents associated with the individual from among the first plurality of documents, generate an invitation to at least one individual of the plurality of individuals to appear in a search result, and obtain a consent to appear in the search result from the at least one individual. The processing system may then present the search result comprising an ordered list of at least a portion of the plurality of individuals, where the ordered list is ordered by the score for each individual of the at least the portion of the plurality of individuals, and where the at least the portion of the plurality of individuals includes the at least one individual. Recently there has been a rapid increase in the demand for experts in the areas of artificial intelligence, machine learning, data science, cyber-security, blockchain, natural language processing, distributed systems, cloud computing, and so forth. With the rising demand for experts in these and other fields, the search for experts is becoming a challenge for large organizations, which struggle to use such experts in an effective way. Examples of the present disclosure describe an expert finder system that allows members of an organization to find experts in a way that is fast, effective, and privacy-aware. In expert finding systems, the goal is to find an expert-a specialist with wide knowledge in a specified area or with particular technological abilities. Experts can have different roles in an organization. They can advise on new technologies and systems, review written material, and assist in solving problems that require specialization or unique knowledge. Experts often have a critical role in the development of new products or services, and frequently, their expert a