CA-3035539-C - SYSTEMS AND METHODS FOR MEASURING COLLECTED CONTENT SIGNIFICANCE

CA3035539CCA 3035539 CCA3035539 CCA 3035539CCA-3035539-C

Abstract

Systems and methods are provided for identifying meta-events. A plurality of event items are received over a given period of time. The plurality of event items are analyzed to determine one or more areas of interests. One or more characteristics of the plurality of events items is measured. The measured number of event items within the particular area of interest within the given time period are compared against a measured number of even items within the particular area of interest within a previous time period. It is determined that a meta-event has occurred when the difference between the measured number of event items within the particular area of interest compared to the measured number of items within the particular area of interest within a previous time period exceeds a threshold measure of event items.

Inventors

Gregory Bala
Sebastian Brinkmann
Hendrik Bartel
James P. Hawley
Phil Kim
Yang Ruan
Mark Strehlow
Faithlyn Tulloch

Assignees

TruValue Labs, Inc.

Dates

Publication Date: 20260505
Application Date: 20170829
Priority Date: 20160829

Claims (13)

CLAIMS 1. A method of identifying meta-events, the method comprising: receiving event items over a given time period, wherein each event item: is keyed to a point in time within the given time period; includes a content; and is associated with a sentiment rating; analyzing the event items to determine one or more predetermined areas of interests; measuring 1) a number of event items within a particular area of interest within the given time period, 2) a precision of the event items within the particular area of interest within the given time period, wherein the precision is a first positive function of a numerical proximity of the sentiment rating of each event item within the particular area of interest, 3) an accuracy of the event items within the particular area of interest within the given time period, wherein the accuracy is a second positive function of a numerical measure of a textual similarity of the content of each event item within the particular area of interest, and 4) a magnitude of the event items outside the particular area of interest within the given time period, wherein: the magnitude is a derivative of a change in a particular characteristic of the event items outside of the particular area of interest; and the magnitude is computed as: M(ci, ... en) = f M ( max(s(t(c1)), ... , s(t(cn))) - min(s(t(c1)), ... , s(t(cn)))) where t(ca is a time stamp of ith content event within a time sampling window, s(t)is a content assessment score at time t, and f M is a positively directed function; calculating a first significance score for the particular area of interest within the given time period based on the number of event items within the particular area of interest within the given time period, the precision of the event items, the accuracy of the event items, and the magnitude of the event items; wherein the first significance score is calculated according to at least one of the following formulas: 1 = the first significance score in the particular area of interest Date Re9ue/Date Received 2024-01-15 = wMM(c1, ... cn) + w1V(c1, ... cn) + WpP(c1, ... c11) + w AA(c1, ... cn) I or 1 = the first significance score in the particular area of interest = [ w MM ( c1 , ... cn)] [w 1 V( c1, ... cn)l [ w pP( c1 , ... cn)] [ w AA( c1 , ... cn)] where, in the above: M(c1, .. ,cn) = the magnitude of the event items; V(c1, ... cn) = the number of event items·, P(c1,···cn) = the precision of the event items; and A(c1, ... cn) = the accuracy of the event items; calculating a historical significance score for the particular area of interest over an entire duration for which event items are present; calculating a historical significance signal by aggregating the historical significance score over the entire duration for which event items are present; comparing the first significance score and the historical significance score; determining that a meta-event has occurred when the first significance score exceeds the historical significance score by a threshold measure, wherein the threshold measure is determined based on a statistical value of the historical significance signal; and providing a notification or alert to a user of a client device that the meta-event has occurred.
2. The method of claim 1, wherein plurality of event items include at least one of a news item, publication, and social media content.
3. The method of claim 1, wherein said analyzing the event items is further used to determine one or more newly generated areas of interest.
4. The method of claim 1, further comprising: generating a signal based on the first significance score and the historical significance score by aggregating the first significance score or the historical significance score; Date Re9ue/Date Received 2024-01-15 displaying the signal as a function of time on a graphical user interface; annotating the signal to illustrate meta-event peaks that exceed a threshold, wherein said meta-event peaks are modified to add a boundary line at a nearest valley or zero crossing at a beginning of each meta-event peak and to add a boundary line at a nearest valley or zero crossing at an end of each meta-event peak; and the threshold is determined based on a statistical value of the signal.
5. The method of claim 4, further comprising: identifying a peak within the signal that is above a particular height, wherein said peak is associated with the meta-event; determining a plurality of events within a time period associated with the identified peak using the threshold; analyzing, using natural language processing methods, the event items to determine which event items are above a threshold of familiarity to each other, thereby identifying a set of event items associated with the meta-event.
6. The method of claim 5, wherein the identified peak is associated with more than one metaevent.
7. The method of claim 5, wherein the set of event items associated with the meta-event is presented as a list.
8. The method of claim 5, wherein the set of event items associated with [[a]] the meta-event is presented as textual excerpts from each event item that is associated with the meta-event.
9. The method of claim 1, further comprising generating boundaries for the meta-event.
10. The method of claim 9, wherein the boundaries are located at nearest flanking dips in the first significance score.
11. The method of claim 9, wherein the boundaries are located at nearest zero crossings in the first significance score. Date Re9ue/Date Received 2024-01-15
12. The method of claim 9, wherein the boundaries are located at a nearest local minimum relative to a peak in the first significance score.
13. The method of claim 9, wherein the boundaries identify bounds in the event items within the particular area of interest within the given time period. Date Re9ue/Date Received 2024-01-15

Description

SYSTEMS AND METHODS FOR MEASURING COLLECTED CONTENT SIGNIFICANCE BACKGROUND OF THE INVENTION [0002] Events, state or status changes, impacts, performance reports, or any observable alteration of an area of interest can appear in a variety of degrees of importance and clarity, heretofore only qualitatively assessed. SUMMARY OF THE INVENTION [0003] The disclosure provided herein relates to methods and systems for the generation of a numerical index, or plurality of indices, characterizing the magnitude of importance and the level of focused definition of an observable attribute of an area of interest, which, in aggregate, characterize the significance of the attribute. Particularly, the methods and systems disclosed herein relate to novel techniques for assimilating quantitative and/or qualitative input from observers of an area of interest, attributed by observable informative event items characterizing said area of interest. Event items may include, but may not be limited to, news sources, publications, and social media content. Additionally, the input may be transformed into a numerical index, or plurality of indices, reflecting the clarity and importance of events communicated by those informative items. [0004] The methods and systems disclosed herein may be applicable in areas of interest such as evaluating the characteristics of corporate behavior and performance as traditionally and conventionally only characterized heretofore by standardized financial data and metrics. Furthermore, the methods and systems disclosed herein may be applicable in areas of interest that can be attributed by news articles consumable by an observant public, and/or where members of that public have varying degrees of expertise. [0005] It is the object of the methods and systems disclosed herein to quantify the import degree of observable alterations within an area of interest as the alterations occur over time. It is also the object of the methods and systems disclosed herein to additionally provide a method and a system for quantifying the degree of clarity for characterizing observable alterations within an Date rei,me/Date received 2023-03-27 WO 2018/044955 PCT/0S2017/049221 area of interest. It is a further object of the methods and systems disclosed herein to combine the import degree with degree of clarity to produce a degree of significance. [0006] The methods and the systems as disclosed herein may center around the innovative concept of processing, as input, measurements of content attributes from informative entities, such as news articles, reports, and expert opinions over a continuum of time, resulting in derivative measurements of importance, clarity, and their combinations indicating significance. [0007] The methods discussed herein may be particularly suited for, although not limited to, areas of interest comprising corporations with publicly observed qualitative behavior. In some embodiments, methods discussed herein may be particularly suited for one or more asset classes including bonds, mutual funds, exchange traded funds (ETF' s ), sovereign bonds, and real estate. Methods discussed herein may work on areas of interest where there's a content-driven characteristic measurement available over a given period of time. For example, other areas where methods discussed herein may be used may include sports predictions, sports analysis, electoral politics analysis, and/or election prediction. [0008] In a first aspect, a method of identifying meta-events is provided. The method comprises receiving a plurality of event items over a given period of time. Each event item may be keyed to a point in time within the given period of time. Additionally, the method comprises analyzing the plurality of event items to determine one or more areas of interest. The method also comprises measuring at least one of 1) a number of event items within a particular area of interest within a given time period, 2) precision of a number of event items within a particular area of interest within a given time period, 3) accuracy of event items within a particular area of interest within the given time period, and 4) magnitude of the items within a particular area of interest within a given time period. Additionally, the method comprises comparing the measured event items within the particular area of interest within the given time period against a measured number of event items within the particular area of interest within a previous time period. Further, the method comprises determining that a meta-event has occurred when the difference between the measured number of event items within the particular area of interested compared to the measured number of items within the particular area of interest within a previous time period exceeds a threshold measure of the events. [0009] In another aspect, a method of generating a signal that illustrates occurrence of metaevents associated with a particular area of interest is provided. The method com