Determining a heatwave counter and severity index

Abstract

Methods and systems for determining the AccuWeather HeatWave Counter and Severity Index are discussed. The AccuWeather HeatWave Counter and Severity Index is intended to be used to understand, present, and predict the severity of HeatWaves, issue public safety announcements, and support policy decisions related to climate change. In particular, the methods and systems of the invention are effective for monitoring periods of excessive heat and generating warnings and recommendations during the HeatWaves to reduce temperature-related health risks to people and domestic animals and impacts on temperature-sensitive products.

Description

DETERMINING A HEATWAVE COUNTER AND SEVERITY INDEXBACKGROUND

[0001] HeatWaves are periods of abnormally hot temperatures lasting several days or longer. They are dangerous because they can cause heat-related illnesses, such as heat exhaustion and heatstroke, which can be life-threatening. People can experience harm from HeatWaves because their bodies are not used to extreme temperatures. HeatWaves can cause other medical problems, such as dehydration, heart attack, and stroke.

[0002] HeatWaves are dangerous for children, older adults, and anyone with chronic medical conditions such as heart disease, asthma, and diabetes. These groups are more vulnerable to the effects of heat because their bodies may not be able to regulate their temperatures in the same way as younger individuals. HeatWaves can also negatively impact the health of domestic animals and perishable items such as food, wine, and pharmaceuticals.

[0003] The risk of heat-related illnesses also increases in urban areas due to the urban heat island effect. This situation occurs when asphalt and concrete in cities absorb and retain heat, making temperatures in cities even higher than those in rural areas. Other factors, such as air pollution or lack of access to air conditioning, can also increase the risk of heat-related illnesses.

[0004] HeatWaves can also cause crop failure due to drought and other extreme weather events. These extreme temperature events can lead to food shortages and higher food prices, which can majorly impact people’s food security.

[0005] People may reduce or eliminate a Heatwave’s adverse health risks and other impacts by knowing beforehand that it has been forecasted to occur and its relative scale or strength.SUMMARY

[0006] Methods and systems are described herein for calculating a Heatwave Counter and Severity Index that models the intensity, duration, and frequency of HeatWaves.

[0007] However, technical hurdles must be overcome to implement such a system. First, there must be a standardized method to evaluate every location for a HeatWave, regardless of the location’s unique climatology, topography, proximity to large bodies of water, and land use patterns, among other characteristics.

[0008] Additionally, the system must be simple to calculate, implement, and comprehend, allowing for widescale use and adoption.

[0009] AccuWeather’s HeatWave Counter and Severity Index can be determined for any location based on the location’s predetermined HeatWave temperature threshold.

[0010] AccuWeather has determined the HeatWave temperature threshold for every location in the United States as being one of seven values. These values are 90 degrees Fahrenheit (°F), 95° F, 100° F. 105° F, 110° F, 115° F. and 120° F. Although these HeatWave temperature thresholds are in increments of five degrees Fahrenheit, the methodologies contemplated herein would allow for reducing the increment to less than five degrees Fahrenheit to provide greater specificity in the application.AccuWeather’s industry -leading, historical weather database spanning more than 70 years, from 1950 to the current, was utilized to create the HeatWave temperature thresholds.A location’s climatology, topography, elevation, proximity to the ocean or freshwater, and land-use patterns influence the HeatWave temperature threshold.

[0012] The HeatWave temperature thresholds for twenty-six selected locations in the UnitedStates are listed as follows:1. Albuquerque, NM 100 14. Citrus View, C A 1102. Atlanta. GA 90 15. Dayton, OH 903. Atlanta, GA 90 16. Death Valley, C A 1204. Austin, TX 100 17. Huntsville, AL 955. Bakersfield, CA 105 18. Little Rock, AR 956. Bangor. ME 90 19. Madison, WI 907. Birmingham, AL 90 20. Minot, ND 908. Boise, ID 100 21. New Orleans, LA 959. Burlington, VT 90 22. Phoenix, AZ 11510. Carlsbad, C A 110 23. Raleigh, NC 9511. Charlotte, NC 95 24. Savannah, GA 9512. Cheyenne, WY 90 25. Wichita, KS 9513. Chicago, IL 90 26. Wilmington, NC 90

[0013] For this application, a HeatWave is declared when locations experience or are forecasted to experience three (3) or more consecutive days with daily high temperatures above their HeatWave temperature thresholds.For example, a HeatWave is declared when the city of Atlanta, Georgia, has a daily high-temperature forecast of greater than 90° F for three or more consecutive days. Similarly, a HeatWave is declared in Carlsbad, California, when a daily high temperature exceeds 110° F over three (3) or more consecutive days.

[0015] AccuWeather has created its HeatWave Counter and Severity Index to compare and contrast Heatwaves for specific or different locations.

[0016] The AccuWeather HeatWave Counter and Severity Index is calculated by summing the scoring values for various temperature ranges associated with the location’s daily high temperature values above the location’s HeatWave temperature threshold. This process is completed each day of the HeatWave or forecasted HeatWave. The higher the daily temperature above the location’s HeatWave temperature threshold, the higher the AccuWeather HeatWave Counter and Severity Index value. The scoring values for the HeatWave temperature thresholds are presented as follows:Degrees F: 90 - 93 Scoring Value, Add 1 Degrees F: 95 - 98 Scoring Value, Add 193 - 95 Scoring Value, Add 2 98 - 100 Scoring Value, Add 2 95 - 97 Scoring Value, Add 3 100 - 102 Scoring Value, Add 3 97 - 99 Scoring Value, Add 4 102 - 104 Scoring Value, Add 4 99 - 101 Scoring Value, Add 5 104 - 106 Scoring Value. Add 5101 or Higher Scoring Value, Add 6 106 or Higher Scoring Value, Add 6Degrees F: 100 - 103 Scoring Value, Add 1 Degrees F: 105 - 108 Scoring Value, Add 1103 - 105 Scoring Value, Add 2 108 - 110 Scoring Value, Add 2105 - 107 Scoring Value, Add 3 110 - 112 Scoring Value, Add 3107 - 109 Scoring Value, Add 4 112 - 114 Scoring Value, Add 4109 - 111 Scoring Value, Add 5 114 - 116 Scoring Value, Add 5111 or Higher Scoring Value, Add 6 116 or Higher Scoring Value, Add 6Degrees F: 110 - 113 Scoring Value, Add 1 Degrees F: 115 - 118 Scoring Value, Add 1113 - 115 Scoring Value, Add 2 118 - 120 Scoring Value, Add 2115 - 117 Scoring Value, Add 3 120 - 122 Scoring Value, Add 3117 - 119 Scoring Value, Add 4 122 - 124 Scoring Value, Add 4119 - 121 Scoring Value, Add 5 124 - 126 Scoring Value. Add 5121 or Higher Scoring Value, Add 6 126 or Higher Scoring Value, Add 6Degrees E: 120 - 123 Scoring Value, Add 1123 - 125 Scoring Value, Add 2125 - 127 Scoring Value, Add 3127 - 129 Scoring Value, Add 4129 - 131 Scoring Value, Add 5131 or Higher Scoring Value, Add 6

[0017] Several examples are presented below to illustrate the application of the AccuWeatherHealWave Counter and Severity Index.Example No. 1Location: Oklahoma City,OklahomaHeatWave Temperature Threshold: 100° FHeatWave Counter andSeverity Index Scoring ValuesDaily High -Temperature Forecast, Day #1, 99° F: n / a (< TemperatureThreshold)Daily High-Temperature Forecast, Dav #2, 101° F: 1 (HeatWave Day#1)Daily High-Temperature Forecast, Day #3, 102° F: 1 (HeatWave Day#2)Daily High -Temperature Forecast, Day #4, 104° F: 2 (HeatWave Day#3)Daily High -Temperature Forecast, Day #5, 98° F: n / a (< TemperatureThreshold)AccuWeather HeatWave Counter and Severity Index: 4(Sum of HeatWave Counter and Severity Index scoring values)Example No. 2.Example Location: Chicago, IllinoisHeatWave Temperature Threshold: 90° FHeatWave Counter andSeverity' IndexScoring ValuesDaily High -Temperature Forecast, Day #1, 88° F: n / a (< TemperatureThreshold)Daily High -Temperature Forecast. Dav #2, 91° F: 1 (HeatWave Day#1) ’Daily High-Temperature Forecast, Dav #3, 94° F: 2 (Heatwave Day#2)Daily High-Temperature Forecast, Day #4, 98° F: 4 (Heatwave Day#3)Daily High -Temperature Forecast, Day #5, 94° F: 2 (Heatwave Day#4)Daily High -Temperature Forecast, Day #6, 89° F: n / a (< TemperatureThreshold)AccuWeather HeatWave Counter and Severity Index: 9(Sum of HeatWave Counter and Severity Index scoring values)Example No. 3.Example Location: Phoenix, ArizonaHeatWave Temperature Threshold: 115° FHeatWave Counter andSeverity Index _ Scoring Values _Daily High-Temperature Forecast, Day #1, 113° F: n / a (< TemperatureThreshold)Dailv High -Temperature Forecast, Dav #2. 116° F: 1 (HeatWave Dav#1) 'Daily High-Temperature Forecast, Dav #3, 119° F: 2 (Heatwave Day#2)Daily High-Temperature Forecast, Day #4, 121° F: 3 (HeatWave Day#3)Daily High-Temperature Forecast, Day #5, 117° F: 1 (HeatWave Day#4)Daily High-Temperature Forecast, Day #6, 110° F: n / a (< TemperatureThreshold)AccuWeather HeatWave Counter and Severity Index: 7(Sum of HeatWave Counter and Severity Index scoring values)

[0018] The AccuWeather HeatWave Counter and Severity Indices are significant in the examples above. However, the HeatWave Counter and Severity Index of 9 in the Chicago, Illinois, example indicates its HeatWave to be the most severe of the three.

[0019] The AccuWeather HeatWave Counter and Severity Index can provide a relative scale ranking that could be used with public safety announcements to warn the public about the health risks of HeatWaves. It can also be used to rank and compare current or forecasted Heatwaves with those in the past. Furthermore, the AccuWeather HeatWave Counter and Severity Index could be used to support policy decisions related to climate change.

[0020] In some embodiments, the AccuWeather HeatWave Counter and Severity Index may be used to determine exposure, including user-specific exposure. In particular, the methods and systems are effective for monitoring and generating recommendations based on long-term exposure. The recommendations may include a user-specific exposure score, wherein the userspecific exposure score indicates health risks corresponding to long-term exposure of the user. For example, each user may have exposure to UV radiation at a different intensity7, time inter;7al, and / or frequency. Each of these factors may thus affect the total exposure of the user over a given time penod (e.g.. a week, month, lifetime, etc.). Moreover, each user may have different biometric characteristics (e.g., a skin type, existing exposure related conditions, age, and / or familial medical history). Each of these factors may also bear on the effect of the cumulative exposure of the user over a given time period. Thus, the methods and systems take these various user-specific factors and characteristics and input them into an exposure model (e.g., a model trained to determine a likelihood of health risk to users based on biometric data for the users and exposure profile s of locations at which the user spent the locations) to determine a user-specific exposure score. This score may be generated for display along with other content such as recommendations for minimizing further exposure.

[0021] However, in order to implement such a system, several technical hurdles need to be overcome. First, each user may have exposure to UV radiation at a different intensity, time interval, and / or frequency. Accordingly, the system may need to independently determine and track each of these factors. For example, in some cases, the intensity of UV radiation at a given location may be provided by a third party (e.g.. via information transmitted from a remote source). However, such information is conventionally expressed in too broad of terms to be useful. For example, even if the location of a user is known (e.g., via global positioning data and / or other location information), the UV radiation that affects that user may depend on additional environmental factors such as whether the user is in direct sunlight, partial sunlight (e.g., in a shaded area) as well as if any location characteristics intensifies the UV radiation.For example, UV radiation at the beach may be intensified by sunlight reflecting off the water and UV radiation in a snowy area may be intensified by sunlight reflecting off the snow. Similarly, a user may not experience a reduced amount of UV radiation, if any, if the user applies sunscreen or is located indoors. Conventional systems have no mechanism for distinguishing and / or accounting for these factors.

[0022] Additionally, users may each exhibit different intervals of exposure. For example, one user may remain in direct sunlight at a location for the entirety of his / her time at a location. However, a different user may only experience the sunlight (or a particular intensity) intermittently (e.g., by moving in and out of an indoor location). Frequency is further an issue as one user may routinely receive exposure over a given time period (e.g., a month), while another user may only receive exposure one time.

[0023] To overcome these technical hurdles, the methods and systems rely on directly detecting and monitoring exposure of UV radiation (e.g., through content capture devices carried with the user). Moreover, as opposed to recording the exposure as a static or given amount, the system may record the exposure as an exposure profile. The exposure profile may measure the intensity of UV radiation at the location during the time interval or intervals as a function of time. By measuring the exposure as a function of time, the system allows for the tracking and accounting for the changes in exposure (e.g., based on a user moving indoors, changes in cloud coverage, changes in environmental factors, etc.).1024] As yet another technical hurdle, different users may experience different effects when subjected to UV radiation with these different factors. Accordingly, the methods and systems need to account for these differences. As mentioned above, these differences may include biometric characteristics (e.g., a skin type, existing exposure-related conditions, age, and / or familial medical history) and / or behavioral characteristics (e.g., sunblock use, use of hats, long- sleeves, etc.). The system may likewise monitor these biometric and / or behavioral characteristics to generate a user profile for a user that indicates this information. The user profile may be expressed as a vectorized feature input that may be processed by the exposure model. By expressing this information in a vectorized feature input, the system may assign probabilities (e.g., likelihood the user is using sunblock of a given SPF) as well as known medical data. While each of the factors may differ and / or in some cases be weighted differently, the exposure model may be trained to recognize and interpret data trends that are otherwise unknown.

[0025] In some aspects, methods and systems are disclosed for determining exposure based on location and time-specific data. For example, the system may retrieve first biometric data fora user from a user profile. The system may monitor a location of the user. The system may determine a first exposure profile for a first location during a first-time interval. The system may determine a second exposure profile for a second location during a second time interval. The system may determine a first composite exposure profile based on the first exposure profile and the second exposure profile, wherein the first composite exposure profile corresponds to a third time interval, and wherein the third time interval includes the first-time interval and the second time interval. The system may generate a first feature input based on the first biometric data and the first composite exposure profile. The system may input the first feature input into an exposure model. The system may receive a first output from the exposure model. The system may generate for display, in a user interface of a user device, a user-specific exposure score based on the first output.

[0026] Various other aspects, features, and advantages of the invention will be apparent through the detailed description of the invention and the drawings attached hereto. It is also to be understood that both the foregoing general description and the following detailed description are examples, and not restrictive of the scope of the invention. As used in the specification and in the claims, the singular forms of “a.” “an,” and “the” include plural referents unless the context clearly dictates otherwise. In addition, as used in the specification and the claims, the term “or” means “and / or” unless the context clearly dictates otherwise. Additionally, as used in the specification “a portion,” refers to a part of, or the entirety of (i. e. , the entire portion), a given item (e.g., data) unless the context clearly dictates otherwise.BRIEF DESCRIPTION OF THE DRAWINGS

[0027] FIG. 1A shows a diagram for HeatWave temperature thresholds, in accordance with one or more embodiments.

[0028] FIG. IB shows a diagram for determining user-specific exposure based on location and time-specific data, in accordance with one or more embodiments.

[0029] FIG. 2 shows illustrative system components for determining user-specific exposure based on location and time-specific data, in accordance with one or more embodiments.

[0030] FIG. 3 shows illustrative model architecture for determining user-specific exposure based on location and time-specific data, in accordance with one or more embodiments.

[0031] FIG. 4A-E shows illustrative pseudocode for determining user-specific exposure based on location and time-specific data, in accordance with one or more embodiments.

[0032] FIG. 5 shows an illustrative chart for detailing user-specific exposure based on location and time-specific data, in accordance with one or more embodiments.

[0033] FIG. 6 shows an illustrative chart for detailing user-specific exposure based on location and time-specific data, in accordance with one or more embodiments.

[0034] FIG. 7 shows an illustrative chart for detailing user-specific exposure based on location and time-specific data, in accordance with one or more embodiments.

[0035] FIG. 8 shows an illustrative chart for detailing user-specific exposure based on location and time-specific data, in accordance with one or more embodiments.

[0036] FIG. 9 shows an illustrative chart for detailing user-specific exposure based on location and time-specific data, in accordance with one or more embodiments.

[0037] FIG. 10 shows an illustrative chart for detailing user-specific exposure based on location and time-specific data, in accordance with one or more embodiments.

[0038] FIG. 11 shows an illustrative chart for detailing user-specific exposure based on location and time-specific data, in accordance with one or more embodiments.

[0039] FIG. 12 shows a flowchart of the steps involved in determining user-specific exposure based on location and time-specific data, in accordance with one or more embodiments.DETAILED DESCRIPTION OF THE DRAWING

[0040] In the following description, for the purposes of explanation, numerous specific details are outlined to provide a thorough understanding of the embodiments of the invention. It will be appreciated, however, by those having skill in the art that the embodiments of the invention may be practiced without these specific details or with an equivalent arrangement.

[0041] FIG. 1 A illustrates the HeatWave temperature thresholds for the United States. The HeatWave temperature thresholds range from 90° F to 120° F in seven increments. The data used to create Figure 1A were taken from AccuWeather’s industry -leading historical weather database that spans more than 70 years, from 1950 to the current time. The database expands every hour of every day by adding observed meteorological and environmental data. The data were curated for every location in the United States and contoured in color bands to create Figure 1. A location’s climatology, topography, elevation, proximity to the ocean or freshwater, and land-use patterns influence the HeatWave temperature threshold.

[0042] In the following description, for the purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the invention. It will be appreciated, however, by those having skill in the art, that the embodiments of the invention may be practiced without these specific details, or with an equivalent arrangement. In other cases, well-known structures and devices are shown in block diagram form in order to avoid unnecessarily obscuring the embodiments of the invention.

[0043] FIG. IB shows a diagram for determining user-specific exposure based on location and time-specific data, in accordance with one or more embodiments. For example, system 100, as shown in FIG. IB, may retrieve first biometric data for a user from a user profile. System 100 may monitor a location of the user. System 100 may determine a first exposure profile for a first location during a first-time interval. System 100 may determine a second exposure profile for a second location during a second time interval. System 100 may determine a first composite exposure profile based on the first exposure profile and the second exposure profile, wherein the first composite exposure profile corresponds to a third time interval, and wherein the third time interval includes the first-time interval and the second time interval. System 100 may generate a first feature input based on the first biometric data and the first composite exposure profile. The system may input the first feature input into an exposure model. System 100 may receive a first output from the exposure model. System 100 may generate for display, in a user interface of a user device, a user-specific exposure score based on the first output.

[0044] In some embodiments, user device 104 may display a variety7of media assets and / or content. For example, user device 104 may be carried by user 102 as shown in FIG. IB. For example, the media asset and / or content may relate to user-specific exposure score. Users of mobile devices often store a plethora of content on their mobile devices and / or have mobile devices that may generate a plethora of different types of content based on exposure. Additionally, webpages, applications, and other mobile device accessible data that may be accessed from mobile devices also needs protection from exposure. By capturing movement data in reference to geographic locations during times the user is at these geographic locations, the mobile device may generate an exposure profile (e.g., based on exposure) to detect whether a UV activity the user is within typical / normal bounds for the health of the user.

[0045] For example, users may perform activities on a daily, weekly, monthly, or yearly basis. These activities may help assist with determining exposure of users due to the user activities that may be performed in reference to movement data captured with respect to geographic locations at predetermined time intervals. For instance, a user may run every day of the week at Central Park, NY between 8:00 a m. and 9:00 a.m. As another example, another user may have a meeting at their work office between 2:00 p.m. and 2:30 p.m. every Monday of the year. As a user goes on about their daily, weekly, monthly, or yearly routine, the user’ s mobile device may capture exposure profile s (which may be based on numerous factors as discussed herein that are specific to the user) at these locations at predetermined time intervals (e.g., the times at which the user is at these locations) and may store such data to generate a composite exposure profile for the user. For example, in the case the user runs every day of the week between 8:00a.m. and 9:00 a.m. at Central Park, NY, movement data captured by the user’s mobile device may be consistent with that of a running movement (e.g., moving up, down, left to right with a change of location) located at Central Park, NY during the hours of 8:00 a.m. and 9:00 a.m. System 100 may also detect (e.g., via photosensitive circuitry) that user 102 is in direct sunlight during this time. As another example, when the user has a meeting at their w ork office between 2:00 p.m. and 2:30 p.m. every Monday of the year, the movement data captured by the user’s mobile device may be consistent with that of a working movement (e.g.. brief movements up and down for checking their mobile device while staying in a constant location) located at their office between the hours of 2:00 p.m. and 2:30 p.m. In such cases, the system may detect no UV radiation (or an amount below a threshold level). The movement, location, and time data may be used to determine if a user’s current movement, location, and time data indicate that exposure is within ’‘normal bounds” for the user (e.g., based on known health and / or biometric data).

[0046] The system may then generate an exposure score, which may comprise a quantitative or qualitative assessment of the user’s exposure to UV radiation. The system may also generate additional content or media assets such as instructions, warnings, and / or other information. As referred to herein, “media asset” and “content” may include any electronically consumable user asset, such as television programming (including pay-per-view programs, on-demand programs (as in video-on-demand (VOD) systems)), Internet content (e.g., streaming content, downloadable content, Webcasts, etc.), video clips, audio, content information, pictures, rotating images, documents, playlists, websites, articles, books, electronic books, blogs, advertisements, chat sessions, social media, applications, games, and / or any other media or multimedia and / or combination of the same.

[0047] In some embodiments, the media asset and / or content may relate to weather data. For example, in system 100, weather data (e.g., data on current weather conditions) is generated by a plurality of weather sensors, referred to collectively as sensor network 110. Sensor netw ork 110 may include a plurality of w eather sensors and / or a plurality of ty pes of weather sensors, each of which may be owned or controlled by a government, the public, and / or a private entity. As shown in FIG. 1. sensor network 110 may comprise a user device (e.g., a mobile device). The types of w eather sensors in sensor netw ork 110 may include weather sensors that monitor for weather and / or climate conditions such as atmospheric pressure, humidity', solar radiation, temperature, precipitation, etc. The weather sensors may be found in one of more weather stations, which may include private, public, and / or government facilities.

[0048] The weather sensors may collect and / or generate weather data automatically and at predetermined times (e.g., a synoptic weather station) or the weather sensors may collect and / or generate weather data in response to user requests. In some embodiments, weather data may be user-generated and / or user-observed weather data, such as weather data for a geographic area generated and / or collected by a user physically located in the geographic area and directly generating and / or collecting the weather data. For example, such user-generated and / or userobserved weather data may include weather data generated and / or collected by a user using an electronic device (e.g., a smart phone). In some embodiments, user-generated and / or userobserved weather data may be generated and / or collected automatically and passively (e.g., without any interaction from a user).

[0049] In some embodiments, weather sensors may include weather data received from Internet of Things (“loT”) connections, satellite networks, and / or other communication networks. loT connections may include interrelated computing devices, mechanical and digital machines, objects, animals or people that are provided with unique identifiers (“UIDs’') and the ability to transfer data over a network without requiring human-to-human or human-to- computer interaction. It should be noted that loT connections, satellite networks, and / or other communication networks may also be used to transfer user profile data, media asset data, and / or any other data discussed herein.

[0050] Sensor network 110 may also receive and / or detect a location of a user based on global positioning data and / or motion data. As used herein, motion data may represent data that describes or relates to the action or process of moving or being moved. In some embodiments, motion data may represent data that describes or relates to the process of moving a mobile device. In some embodiments, motion data may represent data that is collected by one or more motion sensors (e.g., proximity’ sensors, accelerometers, gyroscopes gravity sensors, photosensors, rotational vector sensors, location sensors, GPS receivers, Bluetooth transceivers, Cellular signal transceivers, etc.) and clocks (e.g., a timekeeping device) which in some embodiments may be collected by a mobile device. In some embodiments, motion data may represent data that describes or relates to a change in position relative to time. In some embodiments, motion data may represent data that describes or relates to lengths of time at a given location. In some embodiments, motion data may represent data that describes or relates movement with respect to a reference point. In some embodiments, motion data may represent current mobile device movement data (e.g., acceleration, orientation, velocity’, tilt, shake, rotation, swing, or the alike), historical device movement data (e.g., historical acceleration, orientation, historical velocity, historical tilt, historical shake, historical rotation,historical swing, or the alike), location data (e.g., current location data, historical location data), and time / date data (e.g., timestamp, date stamp, current time, historical time, current date, historical date, etc.).

[0051] As used herein, movement data may represent data that describes or relates to an act of changing a location or position in space. In some embodiments, movement data may represent data that describes or relates to the physical movement of a mobile device. In some embodiments, movement data may represent data collected by one or more motion sensors on a mobile device (e.g., accelerometers, gyroscopes, gravity sensors, photosensors, rotational vector sensors, location sensors, and the alike). In some embodiments, movement data may only represent the data collected by such motion sensors without respect for a location reference point and / or a time reference point. In some embodiments, movement data may represent data that describes or relates to the movement of a mobile device (e.g., up and down, left and right, side to side, tilt, orientation, shake, swing, bouncing, etc.). In some embodiments, movement data may represent the physical movement of a mobile device and / or motions a user acts upon the mobile device.

[0052] FIG. 2 shows illustrative system components for determining user-specific exposure based on location and time-specific data, in accordance with one or more embodiments. As shown in FIG. 2, system 200 may include user device 222, user device 224, and / or other components. Each user device may include any type of mobile terminal, fixed terminal, or other device. Each of these devices may receive content and data via input / output (hereinafter “I / O”) paths and may also include processors and / or control circuitry to send and receive commands, requests, and other suitable data using the I / O paths. The control circuitry may be comprised of any suitable processing circuitry. Each of these devices may also include a user input interface and / or display for use in receiving and displaying data (e.g., on user device 104 (FIG. 1)). By way of example, user device 222 and user device 224 may include a desktop computer, a server, or other client device. Users may, for instance, utilize one or more of the user devices to interact with one another, one or more servers, or other components of system 200. It should be noted that, while one or more operations are described herein as being performed by particular components of system 200. those operations may, in some embodiments, be performed by other components of system 200. As an example, while one or more operations are described herein as being performed by components of user device 222, those operations may, in some embodiments, be performed by components of user device 224. System 200 also includes user device 222 (e.g., a server), which may be implemented on user device 222 and user device 224, or accessible by communication paths 228 and 230,respectively. It should be noted that, although some embodiments are described herein with respect to machine learning models, other prediction models (e.g.. statistical models or other analytics models) may be used in lieu of, or in addition to, machine learning models in other embodiments (e.g., a statistical model replacing a machine learning model and a non-statistical model replacing a non-machine learning model in one or more embodiments).

[0053] User device 222 may include an input component. The input component may include one or more inputs for interacting with user device 224 such as buttons, touch screens, joy sticks, keypads, keyboards, USB ports, SD card reader ports, floppy-disk ports, CD drives, DVD drives, card readers, card scanners, Near Field Communication (NFC) readers, magnetometers, mobile device sensors, and the like. In some embodiments, the input component may include voice detection functionalities, retinal scanning, facial recognition, fingerprint scanning functionality, or other biometric identification mechanisms. In some embodiments, the input component may detect the presence of other electronic devices proximate to a mobile device and may authorize access to one or more functionalities of a mobile device based on data communicated from / to the detected electronic devices. In some embodiments, user device 222 may include a content-capture device such as an accelerometer, gyroscope, gravity sensor, camera, photosensor, etc. For example, the content-capture device may capture any content and / or data.

[0054] User device 222 may include an accelerometer, which may include one or more types of accelerometers for detecting movement experienced by user device 222 such as piezoelectric accelerometers, piezoresistive accelerometers, capacitive accelerometers, single-axis accelerometers, multi-axis accelerometers, and the alike. For example, an accelerometer may be configured to measure acceleration experienced by user device 222. In some embodiments, accelerometer measurements may be in the form of analog or digital outputs (e.g., analog voltage signals, digital voltage signals, binary values. Alternating Current (AC) signals, Direct Current (DC) signals, etc.).

[0055] For example, the system may obtain accelerometer information. For example, the system may receive information in the form of accelerometer signals from an accelerometer. The accelerometer signals may be analog or digital signals (e.g.. voltage signals, binary signals, sinusoidal signals, etc.). In some embodiments, the system may receive accelerometer signals and store the accelerometer signals to compare the accelerometer signals to an accelerometer signal threshold level. For example, the system may compare the received accelerometer signals to an accelerometer signal threshold. The accelerometer signal threshold level may be a predetermined level for identifying if the system is experiencing acceleration (e.g., movementor other motion). For example, in the case that the received accelerometer signal is a voltage signal, the system may compare the voltage signal transmitted by the accelerometer and compare it to a voltage signal threshold value. For example, the voltage signal may be 1 mV, and the voltage signal threshold may be 0.5 mV. Based on the voltage signal being greater than or equal to the voltage signal threshold, the system may determine that the system is experiencing motion, movement, a change in orientation, a change in position, acceleration, etc. In some embodiments, when the voltage signal is less than the voltage signal threshold, the system may determine that the system is at rest as opposed to experiencing motion, movement, a change in orientation, a change in position, acceleration, etc. Although 1 mV and 0.5 mV are used in the example above, it should be noted that these values may be different based on the type of accelerometer. For instance, the system may receive a voltage signal from an accelerometer indicating 0.3 mV and the voltage signal threshold may be 0.2 mV. In some embodiments, instead of an absolute voltage (e.g., 0.0 mV, 0.1 mV, 0.2 mV, ... , 1.0 mV, ... , 1.5 mV, and so on), the voltage signal may be a binary value with a “1” or a “0” indicating that the system is experiencing motion, movement, a change in orientation, a change in position, acceleration, and the alike.

[0056] User device 222 may include a gyroscope, which may include one or more types of gyroscopes for detecting movement experienced by user device 222 such as mechanical gyroscopes, gas-bearing gyroscopes, optical gyroscopes, and the alike. For example, the gyroscope may be configured to measure the angular velocity experienced by user device 222 to determine the orientation of user device 222. In some embodiments, the gyroscope measurements may be in the form of analog or digital outputs (e.g., analog voltage signals, digital voltage signals, binary values, Alternating Current ("AC") signals, Direct Current ( ‘DC”) signals, etc.).

[0057] User device 222 may include a gravity sensor, which may include a combination of accelerometers and gyroscopes of user device 222 to determine sudden changes in acceleration and determine the relative force of gravity experienced by the mobile device. For example, the gravity sensor may use data from at least one accelerometer and at least one gyroscope of user device 222 to determine the force of gravity. For instance, measurements collected by an accelerometer and a gyroscope may be combined to isolate the force of gravity experienced by user device 222.

[0058] User device 222 may include a photosensor, which may include one or more types of photosensors (or other photosensitive material) for detecting movement, capturing images, capturing videos, determining orientation of user device 222, determining a current location ofuser device 222, facial recognition applications, biometric applications, determining the presence of visible light, determining the presence of UV radiation, Infrared (“IR”) transmission, etc. In some embodiments, the photosensor may include one or more photosensors such as opposed (through-beam), retro-reflective, proximity sensing (diffused), compact cameras, DSLR cameras, mirrorless cameras, action cameras, medium format cameras, traditional film cameras, and other photosensors of the alike.1059] User device 222 may include a rotational vector sensor, which may be a combination of an accelerometer, magnetometer, and gyroscope of user device 222 to determine the orientation of user device 222 with respect to Earth’s coordinate system. For example, using accelerometer, magnetometer, and gyroscope data captured from user device 222, the rotational vector sensor may determine the orientation of user device 222 as a combination of angle and axis measurements.

[0060] User device 222 may include a location sensor, which may include one or more components configured to determine the location of user device 222. In some embodiments, the location sensor may include one or more location sensors configured to determine the location of user device 222 such as Global Positioning System (“GPS ’) receivers, Inertial Navigation Systems (“INS”), and the alike. In some embodiments, the location sensor may be configured to interact with one or more components / sensors of user device 222 to determine the location of user device 222. For instance, by using triangulation, the location sensor may determine the location of user device 222 by triangulating received and transmitted cellular signals from cellular towers. As another example, by using trilateration, the location sensor may determine the location of user device 222 by interacting with one or more satellites. Furthermore, as another example, the location sensor may determine the location of user device 222 by using Bluetooth functionalities of user device 222 by connecting to one or more Bluetooth beacons and using trilateration.

[0061] As an example, in the case that a first satellite transmits an UV signal conveying first timestamp and first position stamp information to the system, the system may record a second timestamp corresponding to when the first satellite’s UV signal was received. In some embodiments, the second timestamp (e.g.. the time of reception of the first satellite’s signal) is based on a clock (or other time measurement device) that is associated with one or more components of the system. For instance, user device 222 may include an on-device clock and may record the second timestamp with respect to the on-device clock when the first satellite’s UV signal is received. In this way, the system may be configured to compute a difference between the first timestamp (e.g., when the first satellite transmitted its UV signal) and thesecond timestamp (e.g., when the system received the first satellite’s UV signal). The system may then store the first timestamp, first position stamp, second timestamp information, and the difference between the first timestamp and the second timestamp in one or more memory components of the system. This process may be repeated for each satellite that the system is interacting with. In some embodiments, the system may use the difference between each timestamp (e.g., the difference in time recorded from the reception of each UV signal of each satellite and the time of reception to the system) and each satellite’s position stamp to determine the current location of the system. For example, to determine the current location of user device 222, the time difference between when each satellite transmits their respective UV signal and the time of reception of each UV signal with respect to a clock device of user device 222, user device 222 may use trilateration based on the time difference, multiplying the time difference by the speed-of-light) and the position stamp from each respective satellite. For example, by knowing the position (e.g., in space) of each satellite and the time differences as described herein (e.g., the respective position stamps), the system may use trilateration to determine the current location of user device 222.

[0062] Each of these devices may also include memory in the form of electronic storage. The electronic storage may include non-transitory storage media that electronically stores information. The electronic storage of media may include (i) system storage that is provided integrally (e.g., substantially non-removable) with servers or client devices and / or (ii) removable storage that is removably connectable to the servers or client devices via. for example, a port (e.g., a USB port, a firewire port, etc.) or a drive (e g., a disk drive, etc.). The electronic storages may include optically readable storage media (e.g., optical disks, etc.), magnetically readable storage media (e.g., magnetic tape, magnetic hard drive, floppy drive, etc.), electrical charge-based storage media (e.g.. EEPROM. RAM, etc.), solid-state storage media (e.g., flash drive, etc.), and / or other electronically readable storage media. The electronic storages may include virtual storage resources (e.g., cloud storage, a virtual private network, and / or other virtual storage resources). The electronic storage may store software algorithms, information determined by the processors, information obtained from servers, information obtained from client devices, or other information that enables the functionality as described herein.

[0063] FIG. 2 also includes communication paths 228, 230, and 232. Communication paths 228, 230, and 232 may include the Internet, a mobile phone network, a mobile voice or data network (e.g., a 5G or UTE network), a cable network, a public switched telephone network, or other types of communications network or combinations of communications networks.Communication paths 228, 230, and 232 may include one or more communications paths, such as a satellite path, a fiber-optic path, a cable path, a path that supports Internet communications (e.g., IPTV), free-space connections (e.g., for broadcast or other wireless signals), or any other suitable wired or wireless communications path or combination of such paths. The computing devices may include additional communication paths linking a plurality of hardware, software, and / or firmware components operating together. For example, the computing devices may be implemented by a cloud of computing platforms operating together as the computing devices.

[0064] As an example, with respect to FIG. 2, database 202 may take inputs 204 and provide outputs 206. The inputs may include multiple data sets such as a training data set and a test data set. Each of the plurality of data sets (e.g., inputs 204) may include data subsets of exposure profile s. behavioral characteristics, environmental characteristics, biometric data, exposure factors at one or more locations and / or other data related to generating a composite exposure score. Similarly, in some embodiments, outputs 206 may be fed back to database 202 as input to train database 202 (e.g., a model stored on database 202) alone or in conjunction with user indications of the accuracy of outputs 206, labels associated with the inputs, or with other reference feedback information). In another embodiment, database 202 may update its configurations (e g., weights, biases, or other parameters) based on the assessment of its prediction (e.g., outputs 206) and reference feedback information (e.g., user indication of accuracy, reference labels, or other information). In another embodiment, where database 202 is a neural network, connection weights may be adjusted to reconcile differences between the neural network’s prediction and the reference feedback. In a further use case, one or more neurons (or nodes) of the neural network may require that their respective errors are sent backward through the neural network to them to facilitate the update process (e.g., backpropagation of error). Updates to the connection weights may, for example, be reflective of the magnitude of error propagated backward after a forward pass has been completed. In this way, for example, the database 202 (or one or more models stored on database 202) may be trained to generate better predictions.

[0065] In some embodiments, database 202 may include an artificial neural network, machine learning model, and / or other artificial intelligence-based system. In an artificial neural network embodiment, the artificial neural network may include input layer and one or more hidden layers. Each neural unit of the artificial neural network may be connected with many other neural units of the artificial neural network. Such connections can be enforcing or inhibitory in their effect on the activation state of connected neural units. In some embodiments, each individual neural unit may have a summation function which combines the values of all of itsinputs together. In some embodiments, each connection (or the neural unit itself) may have a threshold function that the signal must surpass before it propagates to other neural units. The artificial neural network may be self-learning and trained, rather than explicitly programmed, and can perform significantly better in certain areas of problem solving, as compared to traditional computer programs. During training, an output layer of the artificial neural network may correspond to a classification of the artificial neural network and an input known to correspond to that classification may be input into an input layer of the artificial neural network during training. During testing, an input without a known classification may be input into the input layer, and a determined classification may be output.

[0066] In some embodiments, the artificial neural network may include multiple layers (e.g., where a signal path traverses from front layers to back layers). In some embodiments, back propagation techniques may be utilized by the artificial neural network where forward stimulation is used to reset weights on the “front” neural units. In some embodiments, stimulation and inhibition for the artificial neural network may be more free-flowing, with connections interacting in a more chaotic and complex fashion. During testing, an output layer of the artificial neural network may indicate whether or not a given input corresponds to a classification of database 202 (e g., whether a subset of exposure profile s, behavioral characteristics, environmental characteristics, biometric data, exposure factors at one or more locations and / or other data related to generating a composite exposure score corresponds to a given composite exposure score and / or exposure profile at a location).

[0067] System 200 also includes API layer 250. In some embodiments, API layer 250 may be implemented on user device 222 or user terminal 224. Alternatively, or additionally, API layer 250 may reside on one or more of cloud components. API layer 250 (which may be A REST or Web services API layer) may provide a decoupled interface to data and / or functionality’ of one or more applications. API layer 250 may provide a common, language-agnostic way of interacting w ith an application. Web services APIs offer a w ell-defined contract, called WSDL, that describes the services in terms of its operations and the data types used to exchange information. REST APIs do not typically have this contract; instead, they are documented with client libraries for most common languages including Ruby. Java. PHP. and JavaScript. SOAP Web services have traditionally been adopted in the enterprise for publishing internal services as w ell as for exchanging information with partners in B2B transactions.

[0068] API layer 250 may use various architectural arrangements. For example, system 200 may be partially based on API layer 250, such that there is strong adoption of SOAP and RESTful Web-services, using resources like Service Repository and Developer Portal but withlow governance, standardization, and separation of concerns. Alternatively, system 200 may be fully based on API layer 250, such that separation of concerns between layers like API layer 250, services, and applications are in place.

[0069] In some embodiments, the system architecture may use a microservice approach. Such systems may use two types of layers: Front-End Layer and Back-End Layer where microservices reside, in this kind of architecture, the role of the API layer 250 may provide integration between Front-End and Back-End. In such cases, API layer 250 may use RESTful APIs (exposition to front-end or even communication between microservices). API layer 250 may use AMQP (e.g., Kafka, RabbitMQ, etc.). API layer 250 may use incipient usage of new communications protocols such as gRPC, Thrift, etc.

[0070] In some embodiments, the system architecture may use an open API approach. In such cases, API layer 250 may use commercial or open-source API Platforms and their modules. API layer 250 may use developer portal. API layer 250 may use strong security constraints applying WAF and DDoS protection, and API layer 250 may use RESTful APIs as standard for external integration.

[0071] FIG. 3 shows illustrative model architecture for determining user-specific exposure based on location and time-specific data, in accordance with one or more embodiments. FIG. 3 shows a graphical representations of artificial neural network models for generating composite exposure score based on an input (e.g., as quantified in a vectorized input feature) exposure profile s. behavioral characteristics, environmental characteristics, biometric data, exposure factors at one or more locations and / or other data related to generating a composite exposure score, in accordance with one or more embodiments. Model 300 illustrates an artificial neural network. Model 300 includes input level 302. Input level may receive information based on exposure profile s, behavioral characteristics, environmental characteristics, biometric data, exposure factors at one or more locations and / or other data related to generating a composite exposure score. Model 300 also includes one or more hidden layers (e.g., hidden layer 304 and hidden layer 306). Model 300 may be based on a large collection of neural units (or artificial neurons). Model 300 loosely mimics the manner in which a biological brain works (e.g.. via large clusters of biological neurons connected by axons). Each neural unit of a model 300 may be connected with many other neural units of model 300. Such connections can be enforcing or inhibitory in their effect on the activation state of connected neural units. In some embodiments, each individual neural unit may have a summation function which combines the values of all of its inputs together. In some embodiments, each connection (or the neural unit itself) may have a threshold function suchthat the signal must surpass before it propagates to other neural units. Model 300 may be selflearning and trained, rather than explicitly programmed, and can perform significantly better in certain areas of problem solving, as compared to traditional computer programs. During training, output layer 308 may corresponds to a classification of model 300 (e.g., whether or not an input corresponds to an exposure profile for a location, a composite exposure profile, etc.) and an input known to correspond to that classification may be input into input layer 302. In some embodiments, model 300 may include multiple layers (e.g., where a signal path traverses from front layers to back layers). In some embodiments, back propagation techniques may be utilized by model 300 where forward stimulation is used to reset weights on the “front” neural units. In some embodiments, stimulation and inhibition for model 300 may be more free-flowing, with connections interacting in a more chaotic and complex fashion. Model 300 also includes output layer 308. During testing, output layer 308 may indicate whether or not a given input corresponds to a classification of model 300 (e.g., whether or not an input corresponds to an exposure profile for a location, a composite exposure profile, etc.).

[0072] FIG. 3 also includes model 350, which is a convolutional neural network. The convolutional neural network is an artificial neural network that features one or more convolutional layers. Convolution layers extract features from a feature input (or an image of a location). Convolution preserves the relationship between pixels by learning image features using small squares of input data. For example, the relationship between the individual exposure profile s. behavioral characteristics, environmental characteristics, biometric data, exposure factors at one or more locations and / or other data related to generating a composite exposure score may be preserved. In another example, the relationship between the individual factors at a location (e.g., directness of sunlight, sunblock use, UV radiation detected, environmental factors, skin type, etc.) may be preserved. As shown in model 350, input layer 352 may proceed to convolution blocks 354 and 356 before being output to convolutional output 358. In some embodiments, model 350 may itself serve as an input to model 300.

[0073] In some embodiments, model 350 may implement an inverted residual structure where the input and output of a residual block (e.g., block 354) are thin bottleneck layers. A residual layer may feed into the next layer and directly into layers that are one or more layers downstream. A bottleneck layer (e.g., block 358) is a layer that contains few neural units compared to the previous layers. Model 350 may use a bottleneck layer to obtain a representation of the input with reduced dimensionality. An example of this is the use of autoencoders with bottleneck layers for nonlinear dimensionality reduction. Additionally, model 350 may remove non-linearities in a narrow layer (e.g., block 358) in order to maintainrepresentational power. In some embodiments, the design of model 350 may also be guided by the metric of computation complexity (e.g., the number of floating point operations). In some embodiments, model 350 may increase the feature map dimension at all units to involve as many locations as possible instead of sharply increasing the feature map dimensions at neural units that perform downsampling. In some embodiments, model 350 may decrease the depth and increase width of residual layers in the downstream direction.

[0074] FIG. 4A-E shows illustrative pseudocode for determining user-specific exposure based on location and time-specific data, in accordance with one or more embodiments. For example, FIG. 4A-E includes pseudocode 400. Pseudocode 400 provides an exemplary' manner in which the system may determine user-specific exposure based on location and time-specific data. In particular, pseudocode 400 provides of a codification of data for exposure profile s. behavioral characteristics, environmental characteristics, biometric data, exposure factors at one or more locations and / or other data related to generating a composite exposure score. It should be noted that the embodiments describe herein may be applied to any software for tracking changes in any set of files, usually used for coordinating work among programmers collaboratively developing source code during software development.

[0075] Pseudocode 400 includes lines 402 for determining local conditions (e.g., environmental factors) at a location such as cloud cover, precipitation, elevation, etc. Lines 404 may include various conversion performed on one or more inputs. Lines 406 may include various conversions and functions for determining exposure profile s and / or amounts of exposure. Lines 408 may include various adjustments based on environmental factors. Lines 410 may include various thresholds for use in generating exposure scores and / or other content.

[0076] In some embodiments, the system may use source code (e.g., Python) that is an interpreted, high-level and general-purpose programming language. The system may use a code with readability' (e.g., in order to provide human-readable commitments, results, and / or other information). For example, the system may use a source code language using significant indentation in order to enhance readability. The system may also select a source code language that has language constructs and an object-oriented approach in order to allow contributors to write clear, logical code for small and large-scale projects.

[0077] The system may use a source code that is dynamically -typed, garbage-collected, and / or has a comprehensive standard library'. For example, a dynamically -typed language is a class of high-level programming languages, which at runtime execute many common programming behaviors that static programming languages perform during compilation. These behaviors may include an extension of the program, by adding new code, by extending objects anddefinitions, or by modifying the type system. A garbage-collected source code language is one that uses automatic memory management. The garbage collector, or just collector, attempts to reclaim garbage, or memory occupied by objects that are no longer in use by the program.

[0078] The system may also select a language that supports multiple programming paradigms, including structured (particularly, procedural), object-oriented and functional programming. For example, the first source code string may be written in Python and indicate whether the first results should be stored on a local device or a remote device. The system may also select a language that may store, based on a storage identifier, the results (e.g., of a logged experiment) in the software development version control system based on instructions in the source code commitment. For example, the system may retrieve a library comprising a common interface (e.g., Pythonic) with an application programming interface that is uniform across Secure Shell network protocols, Hadoop distributed file system protocols, and Simple Storage Sendee protocols. The system may then determine, based on the library', a storage location for the results based on the storage identifier. The system may then transmit a storage instruction to store first results at the storage location (e.g., a hierarchical file structure).

[0079] FIG. 5 shows an illustrative chart for detailing user-specific exposure based on location and time-specific data, in accordance with one or more embodiments. For example, chart 500 illustrates UV indices for a given location (e.g., Oklahoma City, Oklahoma) during the course of the year. In some embodiments, the system may determine a UV index based on location and time as well a user’s behavior for tracking the user’s personal exposure as a function of time. Based on the exposure values, the system may generate appropriate instructions and recommendations to the user when the user approaches and becomes over-exposed to UV radiation. As shown in FIG. 5, the system may generate different user exposure levels based on the location and exposure profile at that location. The system may also qualify the amount of exposure, at a given time and / or cumulatively over a time period, according to the exposure risk. For example, as shown in FIG. 5, the system may qualify' given exposure risk as “Low'” to “Very High”. In some embodiments, the system may modify' the thresholds for risk based on user-specific data (e.g., biometric data) as well as updated information about risk and / or health conditions. In some embodiments, the system may also use machine learning (e.g., as discussed above) to identify trends that indicate potentials risks. For example, the system may receive information about diagnosed conditions for one or more users (or user groups) as w'ell as trends in user-specific information about those users (or user groups) to look for trends and / or patterns that suggest potential health risks even for unknown or undiagnosed conditions.

[0080] FIG. 6 shows an illustrative chart for detailing user-specific exposure based on location and time-specific data, in accordance with one or more embodiments. For example, FIG. 6 shows chart 600, which indicates a user’s exposure as a function of time. For example, the user may have been exposed to UV radiation in Oklahoma City, Oklahoma on July 15th. During that day, the system may determine that the user was exposed to UV radiation from 9:30 - 10:30 AM (e.g., 1.0 hour) and noon - 2:30 PM (e.g.. 2.5 hours). Because the system tracks exposure as a function of time (as opposed to a static average for a given interval), the system may determine exposure as the rate of UV radiation changes over the course of the increments. For example, the exposure may be determined based on determining the area under the curve of the UV index according to:.L" f(x)dxFor example, the system may determine the area under a curve between two points by doing a definite integral between the two points. For example, to find the area under the curve y = f(x) between x = a and x = b, the system may integrate y = f(x) between the limits of a and b.FIG. 7 shows an illustrative chart for detailing user-specific exposure based on location and time-specific data, in accordance with one or more embodiments. For example, as shown in chart 700. the system may determine various intervals for use in generating a composite exposure profile. For example, as shown in FIG. 7, the system may determine a composite exposure profile (or an exposure score) based on the exposure during 20-minute increments. The system may determine the length of these increments based on a comparison of the average exposure during the interval and the actual (e.g., area under the curve) in order to meet a threshold accuracy.

[0082] For example, in some embodiments, the system may take an average of the exposure as shown in FIG. 7 such that:9:30 - 10:30 AM: AVG. (6.3+6.9+7.5 ) x 1.5 = 10.Noon - 2:30 PM: AVG. (8.5+8.3+8.0+7.5+7. 1) x 2.5 = 19.70 exposure Score = 30.05

[0083] FIG. 8 shows an illustrative chart for detailing user-specific exposure based on location and time-specific data, in accordance with one or more embodiments. For example, chart 800 may indicate a health risk associated with a determined exposure score. For example, as shown in chart 800, a determined exposure score may equal 30.05, putting a user in a very high risk level. Accordingly, the system may generate various warnings as guidelines to the user. For example, the system may determine that for a score of less than 10 (e.g., 3 hrs. @ a UV Index < 3; 2 hrs. @ a UV Index < 4; 1 hrs. @ a UV Index < 6), no warning or instruction needs to begenerated. However, the system may determine that for a score of 10 - 15, a warning or instruction to use sunscreen on exposed skin and / or wear protective clothes is required. The system may determine that for a score greater than 15, a warning or instruction to use sunscreen on exposed skin, wear protective clothes, and / or wear eye protection is required. The system may determine that for a score greater than 20, a warning or instruction to use sunscreen on exposed skin, wear protective clothes, wear eye protection, and / or limit exposure time is required. The system may also use discrete scaling for user-specific data such as biometric data (e.g., skin types, medical conditions, etc.), environmental factors at the location, and / or behavior characteristics.

[0084] FIG. 9 shows an illustrative chart for detailing user-specific exposure based on location and time-specific data, in accordance with one or more embodiments. For example, as shown in chart 900, the system may track the frequency of exposure as well as a given exposure profile of that exposure in order to generate a cumulative exposure profile. For example, the system may generate exposure scores for various days in a week. The system may then generate adjustments to warnings and recommendations based on biometric data (e.g.. skin types), frequency (e.g., days of consecutive exposure), environmental factors (e.g., compounding weather impacts and unique location characteristics.

[0085] FIG. 10 shows an illustrative chart for detailing user-specific exposure based on location and time-specific data, in accordance with one or more embodiments. For example, chart 1000 shows the tracking of an exposure profile s across different time intervals for use in generating a cumulative exposure profile and / or an exposure score based on the cumulative exposure profile. For example, the system may retrieve first biometric data for a user from a user profile (e.g., a user as shown in FIG. 1). The system may monitor a location of the user across multiple days, in which each day comprises a time interval. The system may determine a first exposure profile for a first location during a first-time interval (e.g., based on biometric data a UV index, environmental factors, and / or behavior characteristics). The system may determine a second exposure profile for a second location during a second time interval (e.g.. based on biometric data a UV index, environmental factors, and / or behavior characteristics). The system may determine a first composite exposure profile based on the first exposure profile and the second exposure profile, wherein the first composite exposure profile corresponds to a third time interval, and wherein the third time interval includes the first-time interval and the second time interval. For example, as shown in FIG. 10, the system may determine an exposure profile for each day of the week. The system may generate a first feature input based on the first biometric data and the first compositeexposure profile. The system may input the first feature input into an exposure model. The system may receive a first output from the exposure model. The system may generate for display, in a user interface of a user device, a user-specific exposure score based on the first output. For example, the system may generate an exposure score of ‘’159.7.”

[0086] FIG. 11 shows an illustrative chart for detailing user-specific exposure based on location and time-specific data, in accordance with one or more embodiments. For example, chart 1100 may comprise a long-term analysis of a user's exposure over a given time period. In some embodiments, the system may base the long-term exposure on one or more cumulative exposure scores (e.g., a cumulative exposure score corresponding to each month).

[0087] FIG. 12 shows a flowchart of the steps involved in determining user-specific exposure based on location and time-specific data. For example, the system may use process 1300 (e.g., as implemented on one or more system components) in order to determine user-specific exposure based on location and time-specific data.

[0088] At step 1202, process 1200 (e.g., using one or more components described in system 200 (FIG. 2)) receives biometric data. For example, the system may retrieve first biometric data for a user from a user profile. In some embodiments, the first biometric data indicates a skin type, age, and familial cancer history for the user.

[0089] At step 1204, process 1200 (e.g., using one or more components described in system 200 (FIG. 2)) monitors a user location. For example, the system may monitor a location of the user. For example, the system may monitor a location of a user based on motion and / or GPS data.

[0090] At step 1206, process 1200 (e.g., using one or more components described in system 200 (FIG. 2)) determines a first exposure profile. For example, the system may determine a first exposure profile for a first location during a first-time interval. In some embodiments, the system may determine the first exposure profile for the first location during the first time interval based on third party data. For example, the system may determine the first location of the user during the first time interval based on global positioning data received by the user device. The system may transmit a request to a remote server for an exposure profile specific to the first location. The system may receive the first exposure profile for the first location in response to the request.

[0091] In some embodiments, the system may also determine environmental factors that may affect an exposure profile. Environmental factors may include factors that augment an amount or intensity of UV radiation. For example, a location at a beach may include water, which is reflective; thus, increasing an intensity of the UV radiation at the location. For example, thesystem may determine an intensity of UV radiation at the first location during the first time interval as a function of time. The system may then determine an environmental factor for the first location, wherein the environmental factor indicates an amount of the UV radiation reflected by the location.

[0092] In some embodiments, the system may determine the first exposure profile for the first location during the first time interval based on data received by a content-capture device (e.g., a camera). For example, the system may detect, using a content-capture device, UV radiation at the first location. The system may then determine an intensity of the UV radiation at the first location, wherein the first exposure profile for the first location is based on the intensity.

[0093] At step 1208, process 1200 (e.g., using one or more components described in system 200 (FIG. 2)) determines a second exposure profile. For example, the system may determine a second exposure profile for a second location during a second time interval. For example, the system may monitor for the arrival of a user at one location and then the exit of the user from another location. For example, the system may determine an arrival of the user at the first location based on global positioning data received by the user device. The system may assign a start time to the first-time interval based on the arrival. The system may determine a rate of change in an intensity of UV radiation at the first location. The system may compare the rate of change to a threshold rate of change. The system may assign an end time to the first-time interval in response to determining that the rate of change corresponds to the threshold rate of change.

[0094] At step 1210, process 1200 (e.g., using one or more components described in system 200 (FIG. 2)) determines a composite exposure profile based on the first exposure profile and the second exposure profile. For example, the system may determine a first composite exposure profile based on the first exposure profile and the second exposure profile, wherein the first composite exposure profile corresponds to a third time interval, and wherein the third time interval includes the first-time interval and the second time interval. For example, the composite exposure profile may comprise a profile of exposure as a function of time over a given interval. In some embodiments, the given interval may be a long-term interval (e.g., a week, month, season, life-time, etc.).

[0095] For example, in some embodiments determining the first composite exposure profile based on the first exposure profile and the second exposure profile may comprise determining that what time interval should be included (or not included). For example, the system may determine a third exposure profile for a third location during a third time interval, wherein the third time interval is between the first-time interval and the second time interval. The systemmay determine a length of the third time interval. The system may compare the length of the third time interval to a threshold length. In response to determining that the length of the third time interval corresponds to the threshold length, the system may determine to include the second exposure profile in the first composite exposure profile.

[0096] Additionally, or alternatively, the sy stem may determine a fourth exposure profile for a fourth location during a fourth time interval, wherein the fourth time interval is after the second time interval. The system may determine a length of the fourth time interval. The system may compare the length of the fourth time interval to a threshold length. The system may determine to exclude the fourth exposure profile from the first composite exposure profile in response to determining that the length of the fourth time interval does not correspond to the threshold length. The system may determine a second composite exposure profile based on the fourth exposure profile in response to determining to exclude the fourth exposure profile from the first composite exposure profile.

[0097] At step 1212, process 1200 (e.g., using one or more components described in system 200 (FIG. 2)) generates for display a user-specific exposure score based on processing the biometric data and composite exposure profile in an exposure model. For example, the system may generate a first feature input based on the first biometric data and the first composite exposure profile. The system may input the first feature input into an exposure model. The system may receive a first output from the exposure model. The system may generate for display, in a user interface of a user device, a user-specific exposure score based on the first output.

[0098] For example, the exposure model may comprise an artificial intelligence-based model that is trained to determine a likelihood of health risk to users based on biometric data for the users and exposure profile s of locations at which the user spent the locations. The model may process a feature input, which may comprise a vectorized input of biometric, exposure profile, and / or environmental data. For example, the system may determine a length of the first composite exposure profile. The system may compare the length to a threshold length. The system may then determine to generate the first feature input in response to determining that the length corresponds to the threshold length.

[0099] It is contemplated that the steps or descriptions of FIG. 12 may be used with any other embodiment of this disclosure. In addition, the steps and descriptions described in relation to FIG. 12 may be done in alternative orders or in parallel to further the purposes of this disclosure. For example, each of these steps may be performed in any order, in parallel, or simultaneously to reduce lag or increase the speed of the system or method. Furthermore, itshould be noted that any of the devices or equipment discussed in relation to FIGS. 1-11 could be used to perform one or more of the steps in FIG. 12.

[0100] The above-described embodiments of the present disclosure are presented for purposes of illustration and not of limitation, and the present disclosure is limited only by the claims which follow. Furthermore, it should be noted that the features and limitations described in any one embodiment may be applied to any embodiment herein, and flowcharts or examples relating to one embodiment may be combined with any other embodiment in a suitable manner, done in different orders, or done in parallel. In addition, the systems and methods described herein may be performed in real time. It should also be noted that the systems and / or methods described above may be applied to, or used in accordance with, other systems and / or methods.

[0101] The present techniques will be better understood with reference to the following enumerated embodiments:1. A method of determining exposure based on location and time-specific data, the method comprising: retrieving first biometric data for a user from a user profile; monitoring a location of the user; determining a first exposure profile for a first location during a first time interval; determining a second exposure profile for a second location during a second time interval; determining a first composite exposure profile based on the first exposure profile and the second exposure profile, wherein the first composite exposure profile corresponds to a third time interval, and wherein the third time interval includes the first time interval and the second time interval; generating a first feature input based on the first biometric data and the first composite exposure profile; input the first feature input into an exposure model; receiving a first output from the exposure model; generating for display, in a user interface of a user device, a user-specific exposure score based on the first output.2. The embodiment of any one of the preceding claims, wherein determining the first exposure profile for the first location during the first time interval comprises: determining the first location of the user during the first time interval based on global positioning data received by the user device; transmitting a request to a remote server for an exposure profile specific to the first location; and receiving the first exposure profile for the first location in response to the request.3. The embodiment of any one of the preceding claims, wherein determining the first exposure profile for the first location during the first time interv al comprises: detecting, using a content-capture device, UV radiation at the first location; and determining an intensity' of the UV radiation at the first location, wherein the first exposure profile for the first location is based on the intensity.4. The embodiment of any one of the preceding claims, wherein determining the first composite exposure profile based on the first exposure profile and the second exposure profile, further comprises: determining a third exposure profile for a third location during a third time interval, wherein the third time interval is between the first time interval and the second time interv al; determining a length of the third time interval; comparing the length of the third time interv al to a threshold length; and in response to determining that the length of the third time interv al corresponds to the threshold length, determining to include the second exposure profile in the first composite exposure profile.5. The embodiment of any one of the preceding claims, wherein determining the first composite exposure profile based on the first exposure profile and the second exposure profile, further comprises: determining a fourth exposure profile for a fourth location during a fourth time interval, wherein the fourth time interval is after the second time interval; determining a length of the fourth time interval; comparing the length of the fourth time interval to a threshold length; and in response to determining that the length of the fourth time interval does not correspond to the threshold length, determining to exclude the fourth exposure profile from the first composite exposure profile; and in response to determining to exclude the fourth exposure profile from the first composite exposure profile, determining a second composite exposure profile based on the fourth exposure profile.6. The embodiment of any one of the preceding claims, wherein determining the first exposure profile for the first location comprises: determining an intensity of UV radiation at the first location during the first time interval as a function of time; and determining an environmental factor for the first location, wherein the environmental factor indicates an amount of the UV radiation reflected by the location.7. The embodiment of any one of the preceding claims, wherein the exposure model is trained to determine a likelihood of health risk to users based on biometric data for the users and exposure profile s of locations at which the user spent the locations.8. The embodiment of any one of the preceding claims, further comprising: determining an arrival of the user at the first location based on global positioning data received by the user device; assigning a start time to the first time interval based on the arrival; determining a rate of change in an intensity of UV radiation at the first location; comparing the rate of change to a threshold rate of change; and in response to determining that the rate of change corresponds to the threshold rate of change, assigning an end time to the first time interval.9. The embodiment of any one of the preceding claims, wherein the first biometric data indicates a skin type, age, and familial cancer history for the user.10. The embodiment of any one of the preceding claims, further comprising: determining a length of the first composite exposure profile; comparing the length to a threshold length; and in response to determining that the length corresponds to the threshold length, determining to generate the first feature input.11. A tangible, non-transitory, machine-readable medium storing instructions that, when executed by a data processing apparatus, cause the data processing apparatus to perform operations comprising those of any of embodiments 1-10.12. A system comprising: one or more processors; and memory storing instructions that, when executed by the processors, cause the processors to effectuate operations comprising those of any of embodiments 1-10.13. A system comprising means for performing any of embodiments 1-10.

Claims

WHAT IS CLAIMED;1. A system for determining a HeatWave Counter and Severity Index for one or more locations by utilizing daily high temperature observations or daily high temperature forecasts for a time in the future for the locations, the system comprising: retrieving historical daily high temperature data for specific locations; determining HeatWave temperature thresholds for the locations from the historical data; determining the delta between the daily high temperatures and the HeatWave temperature thresholds for each day of the observed or forecasted HeatWave; summing the values of the deltas between the daily high temperature observations or daily high temperature forecasts to determine the AccuWeather HeatWave Counter and Severity Index for the HeatWave or forecasted HeatWave.

2. A method of determining exposure based on location and time-specific data, the method comprising: retrieving first biometric data for a user from a user profile; monitoring a location of the user; determining a first exposure profile for a first location during a first time interval; determining a second exposure profile for a second location during a second time interval; determining a first composite exposure profile based on the first exposure profile and the second exposure profile, wherein the first composite exposure profile corresponds to a third time interval, and wherein the third time interval includes the first time interval and the second time interval; generating a first feature input based on the first biometric data and the first composite exposure profile; input the first feature input into an exposure model; receiving a first output from the exposure model; generating for display, in a user interface of a user device, a user-specific exposure score based on the first output.

3. The method of claim 2, wherein determining the first exposure profile for the first location during the first time interval comprises:determining the first location of the user during the first time interval based on global positioning data received by the user device; transmitting a request to a remote server for an exposure profile specific to the first location; and receiving the first exposure profile for the first location in response to the request.

4. The method of claim 2, wherein determining the first exposure profile for the first location during the first time interval comprises: detecting, using a content-capture device, UV radiation at the first location; and determining an intensity of the UV radiation at the first location, wherein the first exposure profile for the first location is based on the intensity.

5. The method of claim 2, wherein determining the first composite exposure profile based on the first exposure profile and the second exposure profile, further comprises: determining a third exposure profile for a third location during a third time interval, wherein the third time interval is between the first-time interval and the second time interval; determining a length of the third time interval; comparing the length of the third time interval to a threshold length; and in response to determining that the length of the third time interval corresponds to the threshold length, determining to include the second exposure profile in the first composite exposure profile.

6. The method of claim 2, wherein determining the first composite exposure profile based on the first exposure profile and the second exposure profile, further comprises: determining a fourth exposure profile for a fourth location during a fourth time interval, wherein the fourth time interval is after the second time interval; determining a length of the fourth time interval; comparing the length of the fourth time interval to a threshold length; and in response to determining that the length of the fourth time interval does not correspond to the threshold length, determining to exclude the fourth exposure profile from the first composite exposure profile; and in response to determining to exclude the fourth exposure profile from the first composite exposure profile, determining a second composite exposure profile based on the fourth exposure profile.

7. The method of claim 2, wherein determining the first exposure profile for the first location comprises: determining an intensity of UV radiation at the first location during the first time interval as a function of time; and determining an environmental factor for the first location, wherein the environmental factor indicates an amount of the UV radiation reflected by the location.

8. The method of claim 2, wherein the exposure model is trained to determine a likelihood of health risk to users based on biometric data for the users and exposure profile s of locations at which the user spent the locations.

9. The method of claim 2, further comprising: determining an arrival of the user at the first location based on global positioning data received by the user device; assigning a start time to the first-time interval based on the arrival; determining a rate of change in an intensity of UV radiation at the first location; comparing the rate of change to a threshold rate of change; and in response to determining that the rate of change corresponds to the threshold rate of change, assigning an end time to the first-time interval.

10. The method of claim 2, wherein the first biometric data indicates a skin type, age, and familial cancer history for the user.

11. The method of claim 2, further comprising: determining a length of the first composite exposure profile; comparing the length to a threshold length; and in response to determining that the length corresponds to the threshold length, determining to generate the first feature input.

12. A non-transitory computer-readable medium for determining exposure based on location and time-specific data comprising instructions that when executed by one or more processors causes operations comprising: retrieving first biometric data for a user from a user profile;monitoring a location of the user; determining a first exposure profile for a first location during a first time interval; determining a second exposure profile for a second location during a second time interval; determining a first composite exposure profile based on the first exposure profile and the second exposure profile, wherein the first composite exposure profile corresponds to a third time interval, and wherein the third time interval includes the first-time interval and the second time interval; generating a first feature input based on the first biometric data and the first composite exposure profile; input the first feature input into an exposure model; receiving a first output from the exposure model; generating for display, in a user interface of a user device, a user-specific exposure score based on the first output.

13. The non-transitory computer-readable medium of claim 12. wherein determining the first exposure profile for the first location during the first time interval comprises: determining the first location of the user during the first time interval based on global positioning data received by the user device; transmitting a request to a remote server for an exposure profile specific to the first location; and receiving the first exposure profile for the first location in response to the request.

14. The non-transitory computer-readable medium of claim 12, wherein determining the first exposure profile for the first location during the first time interval comprises: detecting, using a content-capture device, UV radiation at the first location; and determining an intensity7of the UV radiation at the first location, wherein the first exposure profile for the first location is based on the intensity.

15. The non-transitory computer-readable medium of claim 12, wherein determining the first composite exposure profile based on the first exposure profile and the second exposure profile, further comprises: determining a third exposure profile for a third location during a third time interval, wherein the third time interval is between the first-time interval and the second time interval;determining a length of the third time interval; comparing the length of the third time interval to a threshold length; and in response to determining that the length of the third time interval corresponds to the threshold length, determining to include the second exposure profde in the first composite exposure profile.

16. The non-transitory computer-readable medium of claim 12, wherein determining the first composite exposure profile based on the first exposure profile and the second exposure profile, further comprises: determining a fourth exposure profile for a fourth location during a fourth time interval, wherein the fourth time interval is after the second time interval; determining a length of the fourth time interval; comparing the length of the fourth time interval to a threshold length; and in response to determining that the length of the fourth time interval does not correspond to the threshold length, determining to exclude the fourth exposure profile from the first composite exposure profile; and in response to determining to exclude the fourth exposure profile from the first composite exposure profile, determining a second composite exposure profile based on the fourth exposure profile.

17. The non-transitory computer-readable medium of claim 12, wherein determining the first exposure profile for the first location comprises: determining an intensity of UV radiation at the first location during the first time interval as a function of time; and determining an environmental factor for the first location, wherein the environmental factor indicates an amount of the UV radiation reflected by the location.

18. The non-transitory computer-readable medium of claim 12, wherein the exposure model is trained to determine a likelihood of health risk to users based on biometric data for the users and exposure profile s of locations at which the user spent the locations.

19. The non-transitory computer-readable medium of claim 12, wherein the instructions further cause operations comprising:determining an arrival of the user at the first location based on global positioning data received by the user device; assigning a start time to the first-time interval based on the arrival; determining a rate of change in an intensity of UV radiation at the first location; comparing the rate of change to a threshold rate of change; and in response to determining that the rate of change corresponds to the threshold rate of change, assigning an end time to the first-time interval.

20. The non-transitory computer-readable medium of claim 12, wherein the instructions further cause operations comprising: determining a length of the first composite exposure profile; comparing the length to a threshold length; and in response to determining that the length corresponds to the threshold length, determining to generate the first feature input.

Images