Patent Grant
11748817
Aspects of the disclosure generally relate to sensors and computer hardware and software. In particular, various aspects of the disclosure include a framework for generating an assessment of neighborhood safety parameters using sensors and sensor data.
When an individual is looking to move to an area he or she is not familiar with, he or she may not be aware of problems that may be typically associated with the area, such as the crime rate, an increased risk of flood or fire, or the like. An individual moving to a new area may be interested in information that is current (e.g., in real time), reliable, and from a trusted source. Without accurate information associated with a particular area, insurance providers might not be able to accurately assess neighborhood risk and the impact of such risk, and real estate prices may not accurately reflect the effects of neighborhood safety. There is also a desire for this information to be accessible to users on a user interface having intuitive functionalities. The present disclosure may address one or more of the shortcomings described above.
The following presents a simplified summary in order to provide a basic understanding of some aspects of the disclosure. The summary is not an extensive overview of the disclosure. It is neither intended to identify key or critical elements of the disclosure nor to delineate the scope of the disclosure. The following summary merely presents some concepts of the disclosure in a simplified form as a prelude to the description below.
Aspects of the disclosure relate to systems, methods, apparatuses and computer-readable media for generating parameters for neighborhood safety using sensors and sensor data.
One example method may include: receiving, by a computing device having one or more processors and from a user device, a request for generating a neighborhood safety assessment for a desired geographic area. The request may be based on an assessment of a first neighborhood safety parameter of a plurality of neighborhood safety parameters. The computing device may determine or identify one or more sensors associated with the desired geographic area; and receive, from the one or more sensors, a present value for a characteristic of the first neighborhood safety parameter of the one or more neighborhood safety parameters. The present value may be received by the computing device or measured by the sensors in real time. The computing device may generate, based on the received present value, an assessment of the first neighborhood safety parameter of the one or more neighborhood safety parameters for the desired geographic area. Assessments of other neighborhood safety parameters of the one or more neighborhood safety parameters may also be generated.
The method may further comprise: receiving, by the computing device and via an electronic storage medium, a past value for the characteristic of the first neighborhood safety parameter; and comparing the received past value to the received present value of the characteristic of the first neighborhood safety parameter. The comparison may be used to generate a catastrophe model for the desired geographic area. The assessment of the first neighborhood safety parameter for the desired geographic area may be further based on the comparison of the received past value to the received present value and/or on the catastrophe model.
Neighborhood safety parameters may include, for example, environmental parameters and social parameters. A characteristic of an environmental parameter may include, for example, a pollutant level, a pollen level, a precipitation level, a temperature; an indication of humidity, a wind speed or velocity, an indication of a weather event or upcoming weather event; a seismograph reading, a characteristic of a terrain, or an indication of a microbe or disease presence.
A characteristic of a social parameter may include, for example, a frequency of, a severity of, or a count of a crime or misdemeanor; a frequency, severity, or a count of a civil unrest; a frequency, severity, or a count of a cybercrime; or a count of residents or workers in the desired geographical area with a criminal record.
In accordance with other embodiments of the present disclosure, another example method comprises: receiving, by a computing device having one or more processors and from a user device, a request for generating an neighborhood safety assessment for a desired geographic area, wherein the request is based on an assessment of a first neighborhood safety parameter of a plurality of neighborhood safety parameters; receiving, by the computing device, an electronic file at least one insurance claim associated with the first neighborhood safety parameter for the desired geographic area; recognizing, using the one or more processors of the computing device and from the electronic copy of at least one insurance claim, one or more terms associated with the first neighborhood safety parameter; and generating, based on the recognized one or more terms, a value of a characteristic of the first neighborhood safety parameter; generating an assessment of the first neighborhood safety parameter for the desired geographic area based on the value of the characteristic of the first neighborhood safety parameter.
In accordance with other embodiments of the present disclosure, an example system comprises: one or more processors; and memory storing computer-executable instructions that, when executed by the one or more processors, cause the system to: receive, from a user device, a request for generating an neighborhood safety assessment for a desired geographic area, wherein the request is based on an assessment of a first neighborhood safety parameter of a plurality of neighborhood safety parameters; identify one or more sensors associated with the desired geographic area; receive, in real time and from the one or more sensors, a present value for a characteristic of the first neighborhood safety parameter of the one or more neighborhood safety parameters; and generate, based on the received present value, an assessment of the first neighborhood safety parameter of the one or more neighborhood safety parameters for the desired geographic area.
Other features and advantages of the disclosure will be apparent from the additional description provided herein.
A more complete understanding of the present invention and the advantages thereof may be acquired by referring to the following description in consideration of the accompanying drawings, in which like reference numbers indicate like features, and wherein:
In the following description of the various embodiments, reference is made to the accompanying drawings, which form a part hereof, and in which is shown by way of illustration, various embodiments of the disclosure that may be practiced. It is to be understood that other embodiments may be utilized.
As will be appreciated by one of skill in the art upon reading the following disclosure, various aspects described herein may be embodied as a method, a computer system, or a computer program product. Accordingly, those aspects may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, such aspects may take the form of a computer program product stored by one or more computer-readable storage media having computer-readable program code, or instructions, embodied in or on the storage media. Any suitable computer readable storage media may be utilized, including hard disks, CD-ROMs, optical storage devices, magnetic storage devices, and/or any combination thereof. In addition, various signals representing data or events as described herein may be transferred between a source and a destination in the form of electromagnetic waves traveling through signal-conducting media such as metal wires, optical fibers, and/or wireless transmission media (e.g., air and/or space).
At a high level, systems and methods are disclosed for creating a model and/or safety score(s) using various applicable data (e.g., claims data, catastrophe models (CATs), weather data, crime data, etc.). The models and/or scores could be made available to consumers, through real estate or other property or neighborhood focused websites, who may be interested in purchasing the scores and/or models or through an entity's quote process where it could result in recommendations for additional policies or coverages. When an individual is looking to move to an area he or she is not familiar with, he or she may not be aware of problems that may be typically associated with the area, such as the crime rate, an increased risk of flood or fire, or the like. For example, a prospective buyer may not realize that an area has an increased flood or fire risk. An individual could use the models and/or scores as a way to become more familiar and comfortable with a neighborhood, for example, when moving to or seeking to establish oneself in a new area. Furthermore, the scoring could lead to increased coverage limits, more products bought or changes to the property to reduce risk.
Input/Output (I/O) 109 may include a microphone, keypad, touch screen, and/or stylus through which a user of the computing device 101 may provide input, and may also include one or more of a speaker for providing audio output and a video display device for providing textual, audiovisual and/or graphical output. Software may be stored within memory 115 and/or storage to provide instructions to processor 103 for enabling device 101 to perform various functions. For example, memory 115 may store software used by the device 101, such as an operating system 117, application programs 119, and an associated internal database 121. Further memory 115 may include random access memory (RAM) 105 and read-only memory (ROM) 107. Processor 103 and its associated components may allow the system 101 to execute a series of computer-readable instructions, e.g., to receive requests for generating neighborhood safety parameters for a desired area, establish connections with and send queries to external computing systems, process natural language input, generate a characteristic or value for a neighborhood safety parameter, determine a quantifiable effect of a neighborhood safety parameter on a property value, and/or determine a quantifiable effect of a neighborhood safety parameter on an insurance condition.
The system 101 may operate in a networked environment 100 supporting connections to one or more remote computers, such as terminals 141, 151, 161, and 171. The terminals 141, 151, 161, and 171 may be personal computers, servers (e.g., web servers, database servers), or mobile communication devices (e.g., mobile phones, portable computing devices, and the like), and may include some or all of the elements described above with respect to the sensing or monitoring system 101. The network connections depicted in
It will be appreciated that the network connections shown are illustrative and other means of establishing a communications link between the computers may be used. The existence of any of various network protocols such as TCP/IP, Ethernet, FTP, HTTP and the like, and of various wireless communication technologies such as GSM, CDMA, WiFi, WiMAX, and wireless mesh networks, is presumed, and the various computing devices and system components described herein may be configured to communicate using any of these network protocols or technologies.
Additionally, one or more application programs 119 used by the system 101 may include computer-executable instructions for receiving data of a present or past characteristic for one or more of a plurality of neighborhood safety parameters, and generating a safety assessment of a desired area based on the received data. The data may be received from environmental sensors 181 (e.g., weather stations, seismographs and other geological sensors, pollutant sensors, satellite cameras or sensors, drone cameras or sensors, etc.) Furthermore, one or more application programs 119 used by the sensing system 101 may include computer-readable instructions for comparing the past characteristic to the present characteristic for the one or more neighborhood safety parameters and generating a catastrophe or disaster model for the desired area, e.g., based on the comparison. The application programs 119 may also be used to communicate any sensed or determined data to other users for alerting them to neighborhood safety conditions so that they can take preventive action. The application program 119 may also be used to assist in generating a total assessment of a neighborhood's safety based on assessments of one or more neighborhood safety parameters.
Additionally or alternatively, one or more application programs 119 used by the sensing system 101 may include computer-executable instructions for using image, text, and/or natural language processing to generate assessments of various parameters of neighborhood safety using filed insurance claims, crime reports, suspicious activity reports, property damage reports, etc. Neighborhood safety assessments may be used to determine or update various insurance conditions (e.g., rates, adjustments, incentives, and the like) or quantify an effect on property prices in a neighborhood.
The systems described herein may be used by an insurance provider, real estate organization, financial institution or other entity to better assess the safety profile of a neighborhood. The systems and methods described herein may be used by or with other entities or types of entities and/or for other purposes without departing from the invention.
On a high level, the example computing systems may include but are not limited to, a user device 220, one or more systems or servers for receiving requests for and generating assessments and other analytics of neighborhood safety parameters (“neighborhood safety system” 202), one or more systems or servers used by municipal office 151 (e.g., “municipal computing system” 230), one or more systems or servers used by insurance office 161 (e.g., “insurance computing system 254”), and a plurality of devices, systems, or servers used for or facilitating the sensing of environmental data (e.g., “environmental sensors” 240). As shown in
At a high level, a user may inquire to know the safety profile of a geographical area (“desired area”). For example, a prospective mover may want to know how safe a neighborhood is before making a decision to buy a property in the neighborhood. The user, via user device 220, may send a request to the neighborhood safety system 202 to assess the safety of the desired area. The safety of a desired area may be assessed via a plurality of safety parameters, as will be discussed further herein. Each safety parameter may have a characteristic or value. After receiving the request, the neighborhood safety system 202 may query external systems or devices for relevant information to assess the safety of the desired area. The external systems or devices may be based on sensors and/or offices based in the desired area. For example, the external systems or devices may include, but are not limited to, the environmental sensors 240, the municipal computing system 230, the insurance computing system 254, etc. The neighborhood safety system 202 may be remotely located from, or be local to, the neighborhood or the desired area for safety assessment. In some aspects, the neighborhood safety system 202, can be the same as or otherwise associated with the insurance computing system 254.
After receiving a request for an assessment of a safety parameter for a neighborhood or desired area, the neighborhood safety system 202 may use a module, application, software, code, or interface to determine the geographic location of the neighborhood or the desired area. As shown in
The neighborhood safety system 202 may comprise various data or storage engines to create, read, update, and/or delete data from its memory 216. These engines may include, for example, safety parameter assessment engine(s) 205 and a property assessment engine 204. As was described in conjunction with memory 115 in
The assessment of the safety parameter may involve the safety parameter assessment engine 205 determining a quantifiable and/or qualitative characteristic, value, property, and/or description for the safety parameter. For simplicity, the characteristic, value, property, and/or quality may be referred to as “characteristic and/or value,” “parameter characteristic and/or value,” and/or “safety parameter characteristic and/or value.” Thus, a characteristic and/or value for geological events, environmental, and/or weather related safety parameters may include, but is not limited to, a pollutant level, an indication of a weather event or upcoming weather event (e.g., temperature, barometer reading, humidity level, etc.), a seismograph reading, etc. A characteristic and/or value of a safety parameter related to disease may include an indication of a microbe or disease presence (e.g., cell or antigen count); a concentration or count of doctors, medical facilities, or pharmacies in the desired area; etc. A characteristic and/or a value for a safety parameter related to crime may include, for example, the number or frequency of incidents of a criminal activity (e.g., kidnapping, burglary, robbery, homicide, battery, assault, larceny, bullying, money laundering, cybercrime, etc.). Characteristics and/or values for a safety parameter related to fire may include incidents, frequency, or severity of fires, arson, wildfires, etc. Characteristics and/or values for a safety parameter related to terrain may include a measurement of the relative evenness or flatness of a terrain; a number of incidents of, a frequency of, or a severity of mud slides, sinkholes, avalanches, or other terrain-related events; etc.
The safety parameter assessment engine 205 may utilize various machine learning based tools 206 to generate an assessment of a safety parameter, based on received information of the characteristics and/or values of the safety parameter. For example, if a user were to request an assessment of weather related events (a safety parameter) for a specific neighborhood, the neighborhood safety system 202 may receive current temperature, precipitation, air pressure, and humidity data from weather sensors 252, but also stored temperature, precipitation, air pressure, and humidity data from the past. The safety parameter assessment engine 205 may input the data into a trained machine learning algorithm to forecast weather trends in the future, and assess the safety based on the forecasted weather trends. The trained machine-learning algorithm may be stored as an ML tool 206 and/or within memory 216. Furthermore, the safety parameter assessment engine 205 may use characteristics and/or values for a safety parameter to predict or model a disaster or catastrophe. In some aspects, a module, plug-in, software, and/or code (e.g., “disaster modeler” 210) may enable the safety parameter assessment engine 205 to model or predict the development of, onset of, severity of, and/or damage caused by the disaster or catastrophe. The disaster modeler 210 may also use various machine learning based tools 211 to predict or model a disaster or catastrophe based on training data or trained machine-learning algorithms that use characteristics and/or values of a safety parameter.
In fulfilling requests to generate assessments for a safety parameter, the neighborhood safety system 202 may establish connections with external systems, such as municipal computing system 230 and insurance computing system 254, e.g., via network interfaces 214, 236, and 260. From such systems, the neighborhood safety system 202 may receive information that involves natural language entries. For example, in order to assess the crime of a neighborhood, the neighborhood safety system 202 may receive crime reports of crimes that have occurred in the neighborhood over a preselected duration of time. The crime reports may be received digitally from the municipal computing system 230, e.g., from a crime reports database 234. However, the digitized crime reports may nevertheless be in the form of a natural language input (e.g., “On Sep. 1, 2010, Neighborhood Grocery was robbed, resulting in $10,000 loss in business.”), and the characteristics and/or values of a safety parameter (e.g., crime) may not be as apparent to the neighborhood safety system 202.
In another example, in order to assess safety parameters, the neighborhood safety system 202 may receive insurance claims filed over a preselected duration of time. The insurance claims may be submitted or filed by property owners or renters, business owners or renters, vehicle owners or renters, and the like, who reside, do business in, or otherwise have an interest in the neighborhood or desired area. The insurance claims may have been submitted and/or filed at an insurance provider office or agency. The insurance computing system 254 associated with the insurance provider office or agency may have verified the insurance claims, e.g., via a verification module 258, and stored the verified insurance claims, e.g., in an insurance claims database 256. The neighborhood safety system 202 may electronically receive the insurance claims from the insurance computing system 254. However, the electronically received insurance claims may nevertheless be in the form of a natural language input (e.g., “On Sep. 1, 2010, Neighborhood Grocery owner Bob requests compensation of a loss suffered in the amount of $10,000 as a result of a robbery”). Consequently, the characteristics and/or values of a safety parameter (e.g., crime) may not be as apparent to the neighborhood safety system 202. In some aspects, and to overcome the above-described issues, the neighborhood safety system 202 may include a natural language processor (e.g., “NLP” 208) to process the received natural language input.
The NLP 208 may be a subsystem, software, plug-in, application, or code that may include various processors (e.g., pre-processors, post-processors, etc.), libraries, and/or AI-based systems (e.g., machine learning (ML) tools 209) to analyze and convert natural language to one that could result in a computing system 202 to perform substantive functions. The substantive functions may include identifying, creating, replacing, updating, and/or deleting a characteristic and/or value for a safety parameter. A library and AI-based tools (e.g., ML tool 209) may guide the NLP 208 for various uses in natural language processing, including the undergoing of supervised and unsupervised learning from language data. The library may be a repository, look-up table, and/or database and may be located within memory 216. Together with the library, the ML tool 209 may support common NLP tasks, such as tokenization, sentence segmentation, part-of-speech tagging, named entity extraction, chunking, parsing, and coreference resolution. These tasks may be needed to build more advanced text processing services. The ML tool 209 may also include maximum entropy and perceptron based machine-learning tools.
In some aspects, the neighborhood safety system may use an assessment of a safety parameter to determine its quantitative effect on other aspects of the neighborhood or desired area. For example, a user seeking to sell a property in the neighborhood may desire to know what effect the safety profile of the neighborhood would have on the property value of the property that the user is seeking to sell. Various algorithms for and/or computer executable instructions for property valuation, may be stored in memory 216. Furthermore, the neighborhood safety system 202 may receive property information (e.g., existing property values, property details, etc.) from the municipal computing system 230, which may store property information of properties in the neighborhood or desired area, e.g., in property database 232. The property assessment engine 204 may use an assessment of a safety parameter, stored computer executable instructions and algorithms related to property valuation, and received property information to quantify the effect of a safety parameter on a property value.
Based on the requests received from the user device 220, the neighborhood safety system 202 may apply assessments of neighborhood safety parameters in other aspects. For example, the neighborhood safety system 202 may quantify the effect of an assessment on an insurance condition (e.g., rates, adjustments, incentives, and the like). In some aspects, an assessment of a safety parameter may be used to update an insurance policy of a user. For example, if the user were to reside in, work in, or otherwise be associated with the neighborhood or desired area for which the neighborhood safety system 202 has generated a safety assessment, the neighborhood safety system may be used to update the user's insurance policy. This aspect may occur, for example, where the neighborhood safety system 202 is utilized by the user's insurance provider or is an extension of the insurance computing system 254.
The neighborhood safety system 202, e.g., via its safety parameter assessment engine 205, may aggregate and/or holistically evaluate assessments of individual safety parameters of a neighborhood or desired area to determine an overall or comprehensive safety assessment. For example, the overall or comprehensive safety assessment may be an amalgamation of assessments of individual safety parameters. Also or alternatively, where assessments of individual safety parameters involve a quantitative score, the overall or comprehensive safety assessment may be a total score or a weighted average (e.g., mean, median, etc.) of individual scores.
User device 220 may comprise, for example, a cell phone, smartphone, tablet (e.g., with cellular transceivers), laptop (e.g., communicatively coupled to cellular transceivers), desktop, wearable devices (e.g., smart watches, electronic eye-glasses, etc.), or other types of computing devices configured to communicate with the neighborhood safety system e.g., over a network via network interface 224. The user device 220 may be associated with a user who desires to know the safety of a neighborhood or desired area. The user device 220 may directly or indirectly transmit or receive information to the neighborhood safety system 202. For example, the user device may run an application, program, or software (e.g., 226), or display a website. The application, program, software or website may be managed, created, or hosted by the neighborhood safety system 202, e.g., via application interface. Furthermore, the user device 220 may comprise a user interface 228 to allow the user to view displayed contents of the application 226, or enter input, e.g., via a keyboard, keypad, touch screen, mouse, etc. For example, a user may enter a request to generate an assessment of a safety parameter via the user interface 228, and this request may be sent to the neighborhood safety system 202. Furthermore as described above, the user device 220 may have an internal geographical tracking device (e.g., a global positioning system (GPS) 222). The GPS 222 may be used to automatically determine a neighborhood or a desired area for a request for an assessment of a safety parameter, if the neighborhood or the desired area is at the user device's present location. The user device 220 may be configured in a similar manner as terminal 171 and/or system 101 of
The municipal computing system 230 may be comprised of a property database 232, a crime reports database 234, and a network interface 236. In some aspects, in addition to or as an alternative to the municipal computing system 230, there may be a plurality of computing systems that collectively store relevant information pertaining to individuals or property of a municipality, and which could be used to assess the safety of a neighborhood or a desired area. For example, a computing system of a police station may store crime reports, e.g., in a crime reports database 234, and a computing system of a local tax collections office may store information pertaining to a plurality of properties of a neighborhood or desired area, e.g., in a property database 232.
The plurality of environmental sensors 240 may include, but are not limited to sensors that measure a pollutant (e.g., pollutant sensors 246), sensors placed on a satellite or drone (e.g., satellite sensors 248), geological sensors 250 (e.g., seismographs), and weather sensors 252 (e.g., thermometer, barometer, wind vanes, anemometer, optical sensors, humidity sensors, etc.). The individual environmental sensors need not be located at the same place. For example, while the neighborhood or desired area may have a weather sensor 252, the nearest pollutant sensor 246 or geological sensor 250 may be at the center of the metropolitan area of the neighborhood or of the desired area.
The insurance computing system 254 may be comprised of an insurance claims database 256, a verification module 258, and a network interface 260. As discussed above, the insurance computing system 254 may be a computing system or systems that store filed and/or verified insurance claims of users, workers, or property owners located in the neighborhood and/or desired area of the requested safety assessment. The computing system or systems may be of an insurance office, insurance agency, insurance provider, etc. In some aspects, the insurance claims database 256 may categorize filed and unverified insurance claims, verified insurance claims, and/or compensated insurance claims. The verification process may be performed by a module, program, software, or algorithm for assessing an insurance claim and confirming that there is no fraudulent information, e.g., by the verification module 258. The insurance claims may be based on a claim for compensation for a damage or loss incurred. The damage or loss may indicate an aspect of a safety parameter. For example, a user may file an insurance claim for loss caused by a robbery, which may indicate a prevalence of crime in a neighborhood. In another example, a user may file an insurance claim for damage caused by a hurricane, which may indicate a prevalence of catastrophic weather events in a neighborhood.
At step 302 the neighborhood safety system 202 may receive a request to assess neighborhood safety based on a plurality of safety parameters (e.g., a request for a “neighborhood safety assessment”) for a desired area or neighborhood. The request may be sent by the user via user device by inputting the request, via clicking icons or other functionalities on the user interface, natural language input via text and/or audio, or the like. An application associated with the neighborhood safety system 202, and running on the user device may enable the user to send the request. The request may be specify, a geographic area for which a safety assessment is requested (e.g., “desired area”). The desired area may be a vicinity based on a point on a visual map; a vicinity based on an address; an enclosed area on a map; an identifier of a neighborhood, town, village, city, zip code, etc. The vicinity may be inputted based on a desired radius span or proximity from a selected location. In some aspects, e.g., where the user has not explicitly indicated in the request, the desired area may be deemed to be in a vicinity (e.g., radius span) of the user device 220, and located, e.g., using a GPS 222 of the user device 220. The request may further include a list of safety parameters on which to base the requested neighborhood safety assessment. In at least one aspect, safety parameters may be broadly categorized into environmental safety parameters (“environmental parameters”) and social safety parameters (“social parameters”).
Thus, based on the received request, the neighborhood safety system 202 may locate the desired area or neighborhood (e.g., as in step 304), and identify or determine the list of safety parameters on which the assessment is based (e.g., as in step 306). Environmental parameters may include, but are not limited to safety parameters of weather factors or events (e.g., rain, ice, flood, snow, storms, blizzards, hurricane, tornado, avalanche, gust, heat wave, polar vortex, wind chills, freezes, humidity, etc.), geological factors or events (e.g., terrains (e.g., hilliness), mudslides, sinkholes, earthquakes, volcanoes, etc.), and pollution factors or events (e.g., particulates, carbon monoxide, pollen, hay, dust, air pollutants, water pollutants, haze, chemical spill, etc.). Social parameters may include, but are not limited to, crime, unrest, disease (e.g., presence of, levels of, etc.), or the like. In some aspects, environmental parameters may be assessed based on data obtained from environmental sensors that may indicate characteristics and/or values for the environmental parameter.
If the list of parameters include social parameters (e.g., step 308=Y), the neighborhood safety system 202 may request current and/or past social parameter data from the municipal computing system 230 (e.g., as in step 310). The data may indicate characteristics and/or values of the social parameter. For example, the neighborhood safety system 202 may request current and/or past crime data from the local police computing systems, for crimes committed in the desired area. The past data may be based on a predefined duration of time in the past. In some aspects, the neighborhood safety system 202 may use the current and/or past data to generate a forecast of the social parameter for the desired area. For example, the neighborhood safety system may generate a crime forecast for the desired area (e.g., as in step 312). The forecasting may be performed using ML tools 206. The forecast may be presented to the user via user device, e.g., based on demand or accompanied with the neighborhood safety assessment. As used herein, crimes may include, for example, any unlawful human activity that may affect the safety of others, e.g., assault, battery, kidnapping, robbery, homicide, rape, larceny, cybercrime. In some aspects, a safety parameter and an assessment of the safety parameter may refer to one or more of these crimes.
At step 314, the neighborhood safety system 202 may determine a characteristic and/or a value for each of the listed social parameters. For example, if the request for a neighborhood safety assessment was based on crime, the characteristics and/or values may include, e.g., a number of incidences of the crime, a severity of the crime, a severity of each incidence, a frequency of the incidence of the crime, a damage caused by each incidence of the crime, a loss suffered from each incidence of the crime, etc. The characteristics and/or values may be quantified or otherwise digitized and stored into memory 216. For example, an indication of severity may be quantified (e.g., 1=least severe, 10=most severe).
Subsequently, or if the list of parameters does not include social parameters, the neighborhood safety system 202 may determine whether the list of parameters includes environmental parameters (e.g., as in step 316). In some aspects, the determining of whether the list of parameters includes environmental parameters may be prior to, simultaneously with, or subsequent to the determining of whether the list of parameters includes social parameters.
If the list of parameters includes environmental parameters (e.g., step 316=Y), the neighborhood safety system 202 may request current and/or past environmental parameter data from the relevant environmental sensor(s) 240 and/or from their respective or collective storage 242 (e.g., as in step 318). The data may indicate characteristics and/or values of the environmental parameter on which the neighborhood safety assessment is requested to be based. For example, the neighborhood safety system 202 may request current and/or past weather data from the local weather sensors 252, for weather related measurements in the desired area. The past data may be based on a predefined duration of time in the past (e.g., last five years). In some aspects, the neighborhood safety system 202 may use the current and/or past data to generate a forecast of environmental parameter data for the desired area (e.g., as in step 320). For example, the neighborhood safety system 202 may generate a weather forecast for the desired area, and predict weather events or disasters that may affect neighborhood safety. The weather forecasting and/or disaster modeling may be performed using safety parameter assessment engine 205, disaster modeler 210 or their respective ML tools 206 and 211.
At step 322, the neighborhood safety system 202 may determine a characteristic and/or a value for each of the listed environmental parameters. For example, if the request for a neighborhood safety assessment was based on weather, the characteristics and/or values may include, e.g., a temperature, a barometer reading, a humidity level, a flood depth, a wind speed, a description of the weather (e.g., cloudy, sunny, windy, etc.) etc. The characteristics and/or values may be quantified or otherwise digitized and stored into memory 216. For example, a description of the weather may be quantified based on cloud cover (e.g., 1=sunny/clear, 10=most cloudy), or digitized based on binary true statements (e.g., precipitation=1 and no precipitation=0).
In some aspects, the characteristics and/or values of safety parameters other than environmental parameters and social parameters may be determined, e.g., by establishing connections with and receiving data from the appropriate relevant systems. It is contemplated that the list of parameters on which the neighborhood safety assessment is based need not be limited to one or both of environmental parameters or social parameters, and may be entirely comprised of parameters other than environmental parameters or social parameters. Furthermore, the request for the neighborhood safety assessment need not indicate a list of safety parameters on which to base the neighborhood safety assessment. In some examples, the request may be based on a predetermined default set of safety parameters or may be based on a comprehensive list of safety parameters, and/or may be based on a holistic safety parameter.
Furthermore, the neighborhood safety system 202 may utilize insurance based information to determine or update further characteristics and/or values of safety parameters for the neighborhood safety assessment. Thus, at step 324, the neighborhood safety system 202 may receive insurance claims for losses incurred by properties or individuals in the desired area. The insurance claims may be received from the insurance computing system 254. The insurance claims may be verified or otherwise vetted to confirm they are not fraudulent or frivolous, e.g., by verification module 258, and/or by the neighborhood safety system 202 upon receipt. The insurance computing system may be located and a request may be sent to it, based on a determination of the insurance office or provider that services properties and/or individuals in the desired area. For example, customer data for the insurance offices or providers, property data for the insurance offices or providers, or information pertaining to the geographic regions of insurance offices or providers may be stored in memory 216. Based on the desired area, the neighborhood safety system 202 may send requests for insurance claims from the relevant insurance computing system 254. Also or alternatively, the insurance computing system 254 may be a centralized computing system that stores records of insurance claims from various insurance providers, and maps the insurance claims to various geographic points, including those in the desired area.
The insurance claims, however, may not necessarily be in a format that a computing system may use to identify, determine, or update characteristics and/or values for various safety parameters. The insurance claims may be in a natural language format. For example, an insurance claim may read: “On Sep. 1, 2010, Neighborhood Grocery owner Bob requests compensation of a loss suffered in the amount of $10,000 as a result of a robbery”. Consequently, the characteristics and/or values of a safety parameter (e.g., crime) may not be as apparent to the neighborhood safety system 202. Thus, at step 326, the neighborhood safety system 202 may process the insurance claims to identify relevant terms associated with one or more parameters of the list of parameters. A natural language processor (e.g., “NLP” 208) of the neighborhood safety system 202 may process the received natural language input to identify, create, replace, update, and/or delete a characteristic and/or value for a safety parameter of the listed safety parameters. Furthermore, AI-based tools (e.g., ML tool 209) and any libraries for the AI-based tools stored in memory 216 may guide the NLP 208 in the natural language processing, including the undergoing of supervised and unsupervised learning from language data to determine relevant terms associated with one or more safety parameters. It is possible that the received insurance claims and their processing may result in new safety parameters or new characteristics and/or values for existing or new safety parameters. Depending on user preferences laid out in the request for neighborhood safety assessment or system settings, the new safety parameters and/or new characteristics and/or values may be considered in the neighborhood safety assessment. Thus, new safety parameters could be added to the list of safety parameters determined in step 306. Also or alternatively, at step 328, using the processed insurance claims, the neighborhood safety system 202 may determine or update the characteristics and/or values of one or more parameters from the list of parameters identified in step 306.
Depending on the user request or preferences with respect to the neighborhood safety assessment, and/or depending on system settings, the determined or updated characteristics and/or values for the list of safety parameters can be utilized in various ways. An individual score or assessment for each safety parameter may be determined and presented to the user, via an application 226 and/or a user interface 228 of the user device 220. Also or alternatively, the individual scores or assessments can be aggregated, summed up, and/or summarized. For example, as shown in step 330B, the neighborhood safety system 202 may determine a neighborhood safety score of the desired area based on the list of safety parameters and their characteristics and/or values. The neighborhood safety score may be a total score or assessment based on the individual scores or assessments, and may be presented to the user, via an application 226 and/or a user interface 228 of the user device 220. As will be discussed below,
In some aspects, the neighborhood safety system 202 may determine the effect of the neighborhood safety parameters on a property value of the desired area (e.g., as in step 330A). For example, an individual assessment or score for the neighborhood safety parameter of crime could be used to determine a quantitative effect on a property in the desired area (e.g., an amount r percent drop in home value). Based on the located desired area (e.g., from step 304), the neighborhood safety system 202 may determine (e.g., via requesting data from municipal computing systems 230 or by retrieving from memory 216) property data of properties known to be within the desired area. The property data may include property values for a given (e.g., current) year. The neighborhood safety system 202 may utilize external market data that show drops in property values due to increases in crime and other safety parameters to learn relationships between safety parameters and property values. The learning may be applied to the properties of the desired area and the safety parameter data of the desired area to determine the corresponding drop in value.
Furthermore, the neighborhood safety system 202 may determine an effect of the neighborhood safety parameters on an insurance condition for an individual or property associated with the desired area. The individual may own property, rent, and/or work in the desired area, and the property (e.g., car, home, commercial establishment, business, etc.) may be located in or be used in the desired area. For example, an individual seeking to purchase a new home in the desired area, who requests a neighborhood safety assessment may also need home or auto insurance. The neighborhood safety assessment, which may be unfavorable due to safety parameters of weather or crime, could be used to automatically update and/or determine the conditions of the individual's home or auto insurance. The insurance conditions for example, an insurance premium, an insurance rate, an insurance term, a deductible, etc.
The method depicted in
Thus, step 402 may include acquiring, for each of a plurality of parameters involving weather, geological, and/or pollution, a training data set for the machine learning algorithm to be trained. The training data set may include, but is not limited to: past environmental data received within a predetermined period of time; (2) temporal and geographic information for each of the received past environmental data and (3) current environmental data received from the environmental sensor(s). The past environmental data and current environmental data may be received from environmental sensors in the neighborhood or desired area for which a forecasting of future environmental data is requested.
In some implementations, the environmental data may be obtained by establishing a connection with the appropriate environmental sensors 240 (e.g., pollutant sensors 246, geological sensors 250, weather sensors 252, etc.). The nearest environmental sensors may be located based on the desired area or neighborhood that is requested to be assessed. Furthermore, geographical and temporal data may be received from the environmental sensors 240, e.g., via a timestamp of when the environmental data was gathered by the environmental sensor, and the location of the environmental sensor (e.g., longitude and latitude, distance from user, distance from the desired area or neighborhood, etc.). For example, the temporal information may involve the date and time at which the environmental data was obtained (e.g., sensed), and the geographic information may refer to a point or location within the desired area or the neighborhood in which a request for a safety assessment has been made. For past environmental data, the neighborhood safety system 202 may access stored data (e.g., database 242 of environmental sensors 240).
Step 404 may involve creating feature vectors for each of the plurality of parameters. In some aspects, there may be a feature vector created for each location point in the desired area or neighborhood at which the environmental data was measured. The feature vector may include, for example: (1) the past environmental data received within the predetermined period of time, and (2) the temporal and geographical information for each of the received past environmental data. Each of these features may be quantified and/or may be expressed as mathematical functions. At step 406, the feature vectors may be associated with the current environmental data, for each of the plurality of parameters. As discussed above, there may be a feature vector for every point or location in the desired area or neighborhood where there is a past environmental data and a corresponding current environmental data.
Step 408 may include training a machine learning algorithm using the associated feature vectors. The resulting machine learning algorithm would be one that can forecast environmental data (e.g., current environmental data based on past environmental data) for a plurality of parameters based on (a) environmental data received within a predetermined period of time, and (b) a temporal and geographical information for the environmental data. Thus, the training in the above described aspect involves learning the relationship between past environmental data (e.g., environmental data received within a predetermined period of time) in a geographic area and the environmental data at a designated time (e.g., current time) in a geographic area. However, the designated time need not be at the current time. For example, as will be discussed in the application phase 400B, the trained machine-learning algorithm may be used to predict environmental data for a designated time in the future, based on inputted environmental data comprising of past environmental data and current environmental data. Furthermore, the geographic area and the points of location within it need not be the neighborhood or desired area for which there is the request for the safety assessment.
The training of the machine-learning algorithm may involve supervised learning between a domain (e.g., the feature vectors) and a range (e.g., the current environmental data). Examples of machine learning algorithms may include, but are not limited to multi-layer perceptron, neural networks, support vector machines, linear regression, logistic regression, decision tree learning, or a combination thereof.
The training method 400A may then save the results of the machine learning algorithm, including feature weights, in a memory of the neighborhood safety system 202, e.g., memory 216. Alternatively or additionally, an external computing system or server (e.g., a research lab) may save the trained machine-learning algorithm, which can be retrieved to be used by the neighborhood safety system 202 for production method 400B. The stored feature weights may define the extent to which a geographical or temporal factor or a specific type of environmental data affects the current environmental data at a given location and a given time (e.g., current time).
Referring to production method 400B, step 410 may include receiving a request to predict a weather, geological, and/or pollution event for a desired area. The request may be inputted by the user into the user device 220 via application 226 and/or user interface 228. For example, as explained in conjunction with
At step 412, the neighborhood safety system 202 (e.g., at the ML tool at the safety parameter assessment engine 205 and/or at the disaster modeler 210) may receive (a) past and current environmental data received within a predetermined period of time, and from environmental sensor(s) within the desired area; and (b) temporal and geographic information for each of the received environmental data. As discussed above, the temporal information may involve the date and/or time at which the environmental data was obtained (e.g., sensed), and the geographic information may refer to a point or a location within the desired area or the neighborhood in which a request for a safety assessment has been made. Step 414 may include creating a feature vector comprising of (a) the received environmental data (e.g., the past and current environmental data received within a predetermined period of time, and from environmental sensor(s) within the desired area); and (b) temporal and geographic information for each of the received environmental data.
At step 416, the neighborhood safety system 202 may identify a trained machine learning algorithm for the requested weather, geological, and/or pollution event to be forecasted and the desired area or neighborhood. For example, the neighborhood safety system 202 may search for and retrieve (e.g., from memory 216 and/or ML tools 206 or 211) a trained machine learning algorithm for predicting the event that is requested by the user (e.g., weather, geological, and/or pollution event). For example, some trained machine learning algorithms may have used a training data set comprising mostly of pollutant emissions data, and would be better at forecasting a possible pollution related haze event of a neighborhood. Some trained machine learning algorithms may have relied on a training data comprising weather related measurements (e.g., precipitation levels, temperatures, etc.), and may be better equipped at predicting a weather event. In some implementations, the neighborhood safety system 202 may identify a trained machine-learning algorithm from external computing systems and/or servers. After identification and retrieval, the neighborhood safety system 202 may input the created feature vector into the identified trained machine-learning algorithm (e.g. as in step 418). Based on the training in method 400A, the trained machine-learning algorithm may output the future environmental data, in accordance with the request. The date and/or time in the future for the future environmental data may be based on any temporal constraints applied in the request.
From the future environmental data, the neighborhood safety system 202 may forecast the weather, geological, and/or pollution event (e.g., as in step 420). For example, if future environmental data shows severe precipitation and wind speed of 160 miles per hour, the neighborhood safety system 202 may identify such future environmental data as the weather event of a category 5 hurricane. In some implementations, the training method 400A and/or the production method 400B may be performed by the safety parameter assessment engine 205 or disaster modeler 210 of the neighborhood safety system 202.
A user may select to view the neighborhood safety assessment of at least one safety parameter in further detail. As shown in
The systems, apparatuses, computer-readable media and methods described above may further provide for increased accuracy in identifying risk associated with a home, user, etc. Accordingly, one or more insurance rates, premiums, and the like, may be adjusted based on this more accurate risk.
While the aspects described herein have been discussed with respect to specific examples including various modes of carrying out aspects of the disclosure, those skilled in the art will appreciate that there are numerous variations and permutations of the above described systems and techniques that fall within the spirit and scope of the invention. For example, one of ordinary skill in the art will appreciate that the steps illustrated in the illustrative figures may be performed in other than the recited order, and that one or more steps illustrated may be optional in accordance with aspects of the disclosure. Further, one of ordinary skill in the art will appreciate that various aspects described with respect to a particular figure may be combined with one or more other aspects, in various combinations, without departing from the invention.
This application claims priority to U.S. provisional application No. 62/648,691, filed on Mar. 27, 2018, and which is hereby incorporated by reference herein.
| Number | Name | Date | Kind |
|---|---|---|---|
| 6006333 | Nielsen | Dec 1999 | A |
| D426206 | Richter | Jun 2000 | S |
| D434419 | Bomze et al. | Nov 2000 | S |
| 6233563 | Jefferson et al. | May 2001 | B1 |
| 6298229 | Tomlinson, Jr. et al. | Oct 2001 | B1 |
| D453767 | Istvan et al. | Feb 2002 | S |
| 6415226 | Kozak | Jul 2002 | B1 |
| 6430542 | Moran | Aug 2002 | B1 |
| D464660 | Weng et al. | Oct 2002 | S |
| 6493629 | Van Bosch | Dec 2002 | B1 |
| 6522265 | Hillman et al. | Feb 2003 | B1 |
| D474479 | Tambata | May 2003 | S |
| D474780 | Tambata | May 2003 | S |
| D475719 | Horie | Jun 2003 | S |
| 6677854 | Dix | Jan 2004 | B2 |
| 6726107 | Ruth | Apr 2004 | B1 |
| 6745153 | White et al. | Jun 2004 | B2 |
| D495338 | Peter et al. | Aug 2004 | S |
| 6771742 | McCalmont et al. | Aug 2004 | B2 |
| 6847825 | Duvall et al. | Jan 2005 | B1 |
| D517087 | Sands | Mar 2006 | S |
| 7012993 | Alton | Mar 2006 | B2 |
| 7024205 | Hose | Apr 2006 | B1 |
| 7027808 | Wesby | Apr 2006 | B2 |
| D522015 | Cummins et al. | May 2006 | S |
| D523442 | Hiramatsu | Jun 2006 | S |
| 7068994 | Van Camp | Jun 2006 | B2 |
| 7091903 | Kim | Aug 2006 | B2 |
| 7092695 | Boling et al. | Aug 2006 | B1 |
| 7099835 | Williams, III | Aug 2006 | B2 |
| D529507 | Cummins | Oct 2006 | S |
| D529510 | Cummins et al. | Oct 2006 | S |
| 7119669 | Lundsgaard et al. | Oct 2006 | B2 |
| 7130406 | Pines et al. | Oct 2006 | B2 |
| 7142959 | Oesterling et al. | Nov 2006 | B2 |
| 7155335 | Rennels | Dec 2006 | B2 |
| 7167796 | Taylor et al. | Jan 2007 | B2 |
| 7174243 | Lightner et al. | Feb 2007 | B1 |
| 7215965 | Fournier et al. | May 2007 | B2 |
| D544871 | Lim et al. | Jun 2007 | S |
| 7236576 | Schnarel et al. | Jun 2007 | B2 |
| 7242966 | Averkamp | Jul 2007 | B1 |
| D550689 | Vigesaa | Sep 2007 | S |
| 7266435 | Wang et al. | Sep 2007 | B2 |
| D553146 | Byeon et al. | Oct 2007 | S |
| 7289786 | Krasner | Oct 2007 | B2 |
| D556770 | O'Donnell et al. | Dec 2007 | S |
| D560226 | Jung et al. | Jan 2008 | S |
| 7323973 | Ceglia et al. | Jan 2008 | B1 |
| D561191 | Haning et al. | Feb 2008 | S |
| 7336172 | Govindaraj | Feb 2008 | B2 |
| D563975 | Vigesaa | Mar 2008 | S |
| D564541 | Lettau et al. | Mar 2008 | S |
| 7343565 | Ying et al. | Mar 2008 | B2 |
| D565581 | Gunn et al. | Apr 2008 | S |
| 7389244 | Kaplan | Jun 2008 | B2 |
| 7405537 | Hoffman et al. | Jul 2008 | B2 |
| D574842 | Kwag et al. | Aug 2008 | S |
| D575302 | Millar et al. | Aug 2008 | S |
| 7421321 | Breed et al. | Sep 2008 | B2 |
| D578134 | Jasinski | Oct 2008 | S |
| D579946 | Lee et al. | Nov 2008 | S |
| 7457693 | Olsen et al. | Nov 2008 | B2 |
| 7460019 | Henderson | Dec 2008 | B2 |
| 7463951 | Ampunan et al. | Dec 2008 | B2 |
| 7480546 | Kamdar et al. | Jan 2009 | B2 |
| D586355 | Mori et al. | Feb 2009 | S |
| 7487111 | Shoen et al. | Feb 2009 | B2 |
| 7499714 | Ki | Mar 2009 | B2 |
| D592223 | Neuhaus | May 2009 | S |
| D593110 | Danton | May 2009 | S |
| D593111 | Danton | May 2009 | S |
| D594465 | Hong et al. | Jun 2009 | S |
| D594468 | Bamford et al. | Jun 2009 | S |
| 7593855 | Craig | Sep 2009 | B1 |
| 7602388 | Plut | Oct 2009 | B2 |
| D605657 | Danton | Dec 2009 | S |
| D607464 | Tang et al. | Jan 2010 | S |
| D608366 | Matas | Jan 2010 | S |
| D611056 | Langlois et al. | Mar 2010 | S |
| D618249 | Ahn et al. | Jun 2010 | S |
| D618696 | Woods et al. | Jun 2010 | S |
| D618700 | Song | Jun 2010 | S |
| D618702 | Lee | Jun 2010 | S |
| D621849 | Anzures et al. | Aug 2010 | S |
| 7777648 | Smith et al. | Aug 2010 | B2 |
| D623555 | Reithlingshoefer et al. | Sep 2010 | S |
| D624556 | Chaudhri | Sep 2010 | S |
| D624589 | Robbins | Sep 2010 | S |
| 7802722 | Papierniak et al. | Sep 2010 | B1 |
| D625312 | Jewitt et al. | Oct 2010 | S |
| 7813980 | Crockett | Oct 2010 | B2 |
| D631889 | Vance et al. | Feb 2011 | S |
| D642194 | Kozlowski et al. | Jul 2011 | S |
| D645051 | Kozlowski et al. | Sep 2011 | S |
| 8140358 | Ling et al. | Mar 2012 | B1 |
| 8166026 | Sadler | Apr 2012 | B1 |
| 8285571 | Demirdjian et al. | Oct 2012 | B2 |
| 8289171 | Morley | Oct 2012 | B2 |
| 8315792 | Speier et al. | Nov 2012 | B2 |
| 8375032 | Birdwell et al. | Feb 2013 | B2 |
| 8606512 | Bogovich et al. | Dec 2013 | B1 |
| 8645014 | Kozlowski et al. | Feb 2014 | B1 |
| 8738422 | Lerner et al. | May 2014 | B2 |
| 8750902 | Xiao et al. | Jun 2014 | B2 |
| 8781657 | Pebbles | Jul 2014 | B2 |
| 8799034 | Brandmaier et al. | Aug 2014 | B1 |
| 8805603 | Cavallaro Kozlowski et al. | Aug 2014 | B1 |
| 8805707 | Schumann, Jr. et al. | Aug 2014 | B2 |
| 8959156 | Polis et al. | Feb 2015 | B2 |
| 9297723 | Hofmann et al. | Mar 2016 | B1 |
| 9384491 | Briggs et al. | Jul 2016 | B1 |
| 9406228 | Kozlowski et al. | Aug 2016 | B1 |
| 9411982 | Dippenaar et al. | Aug 2016 | B1 |
| 9412130 | Wasserman et al. | Aug 2016 | B2 |
| 9497585 | Cooley | Nov 2016 | B1 |
| 9659301 | Briggs et al. | May 2017 | B1 |
| 9674156 | Stiglic et al. | Jun 2017 | B2 |
| 9684924 | Wasserman et al. | Jun 2017 | B2 |
| 9692815 | Caldwell | Jun 2017 | B2 |
| 9697525 | Kozlowski et al. | Jul 2017 | B1 |
| 9881268 | Briggs et al. | Jan 2018 | B1 |
| 10186134 | Moon | Jan 2019 | B1 |
| 20020055861 | King et al. | May 2002 | A1 |
| 20020065703 | Garg | May 2002 | A1 |
| 20020073012 | Lowell et al. | Jun 2002 | A1 |
| 20020096561 | Sullivan | Jul 2002 | A1 |
| 20020184653 | Pierce et al. | Dec 2002 | A1 |
| 20030088347 | Ames | May 2003 | A1 |
| 20040024711 | Camping et al. | Feb 2004 | A1 |
| 20040100363 | Lane et al. | May 2004 | A1 |
| 20040100479 | Nakano et al. | May 2004 | A1 |
| 20040111195 | Vries et al. | Jun 2004 | A1 |
| 20040192336 | Walby | Sep 2004 | A1 |
| 20040203850 | Oesterling | Oct 2004 | A1 |
| 20040221239 | Hachigian et al. | Nov 2004 | A1 |
| 20050027438 | Rockett et al. | Feb 2005 | A1 |
| 20050071052 | Coletrane et al. | Mar 2005 | A1 |
| 20050091272 | Smith et al. | Apr 2005 | A1 |
| 20050144114 | Ruggieri et al. | Jun 2005 | A1 |
| 20050187833 | Royer et al. | Aug 2005 | A1 |
| 20050197771 | Seick et al. | Sep 2005 | A1 |
| 20050261986 | Haynes et al. | Nov 2005 | A1 |
| 20060022846 | Tummala | Feb 2006 | A1 |
| 20060123360 | Anwar et al. | Jun 2006 | A1 |
| 20060245570 | Pfleging et al. | Nov 2006 | A1 |
| 20060247852 | Kortge et al. | Nov 2006 | A1 |
| 20060291633 | Glaza et al. | Dec 2006 | A1 |
| 20070011278 | Nou | Jan 2007 | A1 |
| 20070033540 | Bridges et al. | Feb 2007 | A1 |
| 20070043770 | Goodrich | Feb 2007 | A1 |
| 20070066276 | Kuz et al. | Mar 2007 | A1 |
| 20070072625 | Fournier et al. | Mar 2007 | A1 |
| 20070088473 | Moon et al. | Apr 2007 | A1 |
| 20070122026 | Ersue et al. | May 2007 | A1 |
| 20070135990 | Seymour et al. | Jun 2007 | A1 |
| 20070139182 | O'Connor et al. | Jun 2007 | A1 |
| 20070142026 | Kuz et al. | Jun 2007 | A1 |
| 20070167147 | Krasner et al. | Jul 2007 | A1 |
| 20070185728 | Schwarz et al. | Aug 2007 | A1 |
| 20070226783 | Mimlitsch | Sep 2007 | A1 |
| 20070240079 | Flynt et al. | Oct 2007 | A1 |
| 20070244628 | Rockett et al. | Oct 2007 | A1 |
| 20070252689 | Rothschild | Nov 2007 | A1 |
| 20070298765 | Dickinson et al. | Dec 2007 | A1 |
| 20080004790 | Ames | Jan 2008 | A1 |
| 20080014908 | Vasant | Jan 2008 | A1 |
| 20080054072 | Katragadda et al. | Mar 2008 | A1 |
| 20080119203 | Shalmon et al. | May 2008 | A1 |
| 20080140287 | Yang et al. | Jun 2008 | A1 |
| 20080167937 | Coughlin et al. | Jul 2008 | A1 |
| 20080177653 | Famolari et al. | Jul 2008 | A1 |
| 20080215240 | Howard et al. | Sep 2008 | A1 |
| 20080261554 | Keller et al. | Oct 2008 | A1 |
| 20080306982 | Moudy | Dec 2008 | A1 |
| 20080319665 | Berkobin et al. | Dec 2008 | A1 |
| 20090002145 | Berry et al. | Jan 2009 | A1 |
| 20090072995 | Thomas et al. | Mar 2009 | A1 |
| 20090088967 | Lerner | Apr 2009 | A1 |
| 20090093236 | Balan et al. | Apr 2009 | A1 |
| 20090125178 | Wilson | May 2009 | A1 |
| 20090210142 | Couckuyt et al. | Aug 2009 | A1 |
| 20090216600 | Hill | Aug 2009 | A1 |
| 20090233572 | Basir | Sep 2009 | A1 |
| 20090287527 | Kolb et al. | Nov 2009 | A1 |
| 20100070487 | Fetsch | Mar 2010 | A1 |
| 20100138242 | Ferrick et al. | Jun 2010 | A1 |
| 20100161382 | Cole | Jun 2010 | A1 |
| 20100207787 | Catten et al. | Aug 2010 | A1 |
| 20100332133 | Harris et al. | Dec 2010 | A1 |
| 20110082816 | Moffett | Apr 2011 | A1 |
| 20110213628 | Peak | Sep 2011 | A1 |
| 20110238999 | Lee et al. | Sep 2011 | A1 |
| 20120136743 | McQuade et al. | May 2012 | A1 |
| 20120179363 | Pierfelice | Jul 2012 | A1 |
| 20130183924 | Saigh | Jul 2013 | A1 |
| 20140222618 | Stamp et al. | Aug 2014 | A1 |
| 20140358943 | Raymond | Dec 2014 | A1 |
| 20150012303 | Ghosh | Jan 2015 | A1 |
| 20150026088 | Alber | Jan 2015 | A1 |
| 20150161867 | Bell | Jun 2015 | A1 |
| 20150207786 | Pitroda | Jul 2015 | A1 |
| 20150242814 | Saad | Aug 2015 | A1 |
| 20150326548 | Marson et al. | Nov 2015 | A1 |
| 20160048934 | Gross | Feb 2016 | A1 |
| 20160086082 | Babinowich | Mar 2016 | A1 |
| 20160140299 | Al Harbi | May 2016 | A1 |
| 20160155201 | Bell | Jun 2016 | A9 |
| 20160232598 | Wasserman et al. | Aug 2016 | A1 |
| 20160337394 | Crowley et al. | Nov 2016 | A1 |
| 20170011465 | Anastassov | Jan 2017 | A1 |
| 20170249702 | Wasserman et al. | Aug 2017 | A1 |
| 20170301048 | Turek et al. | Oct 2017 | A1 |
| 20180053110 | Kang | Feb 2018 | A1 |
| 20180073879 | Hakeem | Mar 2018 | A1 |
| 20180189147 | Banasik | Jul 2018 | A1 |
| 20180189913 | Knopp | Jul 2018 | A1 |
| 20180218446 | Ries et al. | Aug 2018 | A1 |
| 20190156655 | Cordes | May 2019 | A1 |
| Number | Date | Country |
|---|---|---|
| 101252627 | Aug 2008 | CN |
| 107239967 | Oct 2017 | CN |
| 1320004 | Jun 2003 | EP |
| Entry |
|---|
| Evelyn L. Kent, “Cognitive computing The human benefit of natural language processing” dated May 31, 2016, KMWorld https://www.kmworld.com/Articles/News/News-Analysis/Cognitive-computing--The-human-benefit-of-natural-language-processing-111268.aspx#:\ (Year: 2016). |
| Definition Cognitive Computing by TechTarget, dated Jul. 2018 https://searchenterpriseai.techtarget.com/definition/cognitive-computing#:˜: (Year: 2018). |
| “Deep Learning 3 things you need to know,” MathWorks, dated Jul. 18, 2017 https://www.mathworks.com/discovery/deep-learning.html (Year: 2017). |
| Jun. 14, 2019—(WO) International Search Report & Written Opinion—PCT/US 19/024272. |
| Allstate Motor Club Launches Roadside Assistance Mobile App for iPhone and BlackBerry Users, Oct. 27, 2009; http://money.cnn.com/news/newsfeeds/articles/prnewswire/2009102711, 2 pages. |
| TMC News, ATX Launches Enhanced Automatic Collision Notification for BMW, Jan. 11, 2009, http://tmcnet.com/usubmit/2009/01/11/3905139.htm, 4 pages. |
| Automotive Fleet, Aug. 2009, vol. 48, No. 9, Charging for Preventable Accidents: What's the Payoff?, Grace Lauron, 4 pages. |
| Automotive Fleet, May 2009, Bright Ideas Energize Fleet Management, Cindy Brauer and Thi Dao, 5 pages. |
| Automotive Fleet, Sep. 2009 Vol. 48 No. 10, DWT Proven to Increase Accidents, Grace Lauron, 5 pages. |
| Motorola DemonsliaLes New Communications System Available in BMW's Global 2005 Model Year Vehicle Line, http://www.virtualizationconference.com/49572/print, 2 pages, retrieved on Feb. 6, 2009. |
| BMW Assist, Safety & Convenience Services © 2006 BMW of North America, LLC, 16 pages. |
| Automotive Fleet, Emkay Partners With Networkcar to Launch New Networkfleet Telematics Solution, Apr. 29, 2008, © 2009 Automotive Fleet, 1 page. |
| Geotab Management by Measurement, Geotab for Insurance Companies © 2008, 1 page. |
| CIO, High-tech Cars: The Coolest Automotive Technologies, Denise Dubie, Network World, Oct. 5, 2008, http://www.cio.com/article/print/452913, retrieved on Feb. 6, 2009, 2 pages. |
| Inrix News, INRIX Real-Time Traffic Now Available on Over 75 Navigation and Mobile Devices, Jul. 30, 2007, http://www.inrix.com/news_75Devices_30July2007.asp, retrieved Feb. 6, 2009, 1 page. |
| ABIresearch, Wireless Connectivity to the Automobile Is Hindered by Lack of Standards and Interoperability, Jul. 31, 2007, http://www.abiresearch.com/abiprdisplay.jsp?pressid=894, retrieved on Feb. 6, 2009, 1 page. |
| When Accidents Happen, Nationwide Mobile App for IPhone is on Your Side, Melanie Broemsen, May 10, 2009, http://www articlesbase.com/print/909297, retrieved on Jun. 23, 2009, 1 page. |
| Diagnostic Trouble Codes (DTCs) Powertrain Codes for OBD II (OBD-2) equipped GM vehicles, compiled by Anthony W. Haukap; http://myweb.accessus.net/˜090/dtocbd2p.html; retrieved on Jul. 20, 2009, 20 pages. |
| Automotive Fleet, OnStar Receives Honors at Telematics Update Awards © 2009 Automotive Fleet, http://www.automotive-fleet.com/News/Print/Story/2008/05/OnStar Receives, retrieved on Feb. 6, 2009, 1 page. |
| Real time traffic broadcast to debut in Australia, http://www.gpsbusinessnews.com, retrieved Feb. 6, 2009 1 page. |
| ABIresearch, In-Vehicle Infotainment Storage and Networking, Hard Disks, Flash Memory, USB, SD, Bluetooth, UWB, iPod Kits and Other Technologies, http://www.abiresearch.com/producs/market_research/In-Vehicle_Infotainment, retrieved on Feb. 6, 2009, 2 pages. |
| Techworld, Pimp your ride: Cool car technology, Denise Dubie (Network World) Jul. 10, 2008; http://www.techworld.com/au/article/262977/pimp_your_ride_cool_car, retrieved on Feb. 6, 2009, 3 pages. |
| Maya Software Technologies, White Paper, Automotive Telematics—Market Overview and Security Considerations © 2001, 12 pages. |
| Intomobile, Volkswagen Launches iPhone Optimized Website Featuring Access to Emergency Roadside Assistance, http://www.intomobile.com/2009/03/30/volkswagen-launches-iPhone-optimized-website-featuring-access, retrieved on Jun. 23, 2009, 3 pages. |
| RepairPal for iPhone, http://repairpal.com/mobile, retrieved Feb. 2, 2009, 13 pages. |
| Tradevibes, The RepairPal iPhone App is Available! © 2007-2008 Mill River Labs, www.tradevibes.com/news/view/repairpal?article=86228, retrieved on Feb. 2, 2009, 1 page. |
| Übergizm™, RepairPal: Roadside Assistance from the iPhone, posted Jan. 22, 2009, http://www.ubergizmo.com/15/archives/2009/01/repairpal_roadside_assistance, retrieved on Feb. 2, 2009, 1 page. |
| Automotive Fleet, Sep. 2009 Vol. 48 No. 10, 10 Recommendations: What Drivers Should Do After a Fleet Accident, Mike Antich, 4 pages. |
| Automotive Fleet/2009 NAFA Planning Guide, NAFA 2009 Institute & Expo Advanced Planning Guide, 2 pages. |
| U.S. Appl. No. 29/396,366, filed Jun. 29, 2011. |
| U.S. Copyright Registration No. TX 7-150-082, “Mini Road Assist”, registered on Mar. 19, 2010. |
| U.S. Copyright Registration No. TX 7-329-434, “Mini Road Assist”, registered on Mar. 19, 2010. |
| U.S. Copyright Registration No. TX 7-150-080, “Mini Road Assist”, registered Mar. 29, 2010. |
| U.S. Copyright Registration No. TX 7-195-526, “Allstate Motor Club Roadside Assistance”, registered Mar. 30, 2010. |
| U.S. Copyright Registration No. TX 7-229-997, “Allstate Motor Club Roadside Assistance”, registered Mar. 19, 2010. |
| U.S. Copyright Registration No. TX 7-150-076, “Allstate Motor Club Roadside Assistance”, registered Mar. 26, 2010. |
| Jan. 16, 2013—U.S. Non-Final Office Action—U.S. Appl. No. 12/859,634. |
| Jun. 7, 2013—U.S. Notice of Allowance—U.S. Appl. No. 12/859,634. |
| Jul. 25, 2012—U.S. Non-Final Office Action—U.S. Appl. No. 12/859,627. |
| Jan. 15, 2013—U.S. Final Office Action—U.S. Appl. No. 12/859,627. |
| “Roadside Assistance with Emergency Roadside Service”, http://www.geico.com/getaquote/auto/emergency-road-service/, downloaded Feb. 25, 2015, pp. 1-5. |
| BoatUS Towing App—Free for All Boaters—BoatUS, http://www.boatus.com/towing/app.asp, downloaded Feb. 25, 2015, pp. 1-2. |
| Software Engineering for Service-Oriented Overlay Computers, D1.4a: UML for Service-Oriented Systems, Sensoria, Oct. 10, 2007, pp. 1-21. |
| Lapadula, A., COWS Specification of the On Road Assistance Scenario, Dec. 19, 2007, pp. 1-9. |
| Mar. 23, 2015—U.S. Non Final Office Action—U.S. Appl. No. 13/446,192. |
| Mar. 23, 2015—U.S. Non Final Office Action—U.S. Appl. No. 13/446,146. |
| Mar. 13, 2015—U.S. Notice of Allowance—U.S. Appl. No. 12/859,627. |
| May 26, 2015—U.S. Non-Final Office Action—U.S. Appl. No. 13/446,146. |
| Feb. 17, 2016—U.S. Notice of Allowance—U.S. Appl. No. 13/446,192. |
| Mar. 17, 2016—(WO) International Search Report and Written Opinion—App PCT/US16/14044. |
| May 4, 2016—U.S. Notice of Allowance—U.S. Appl. No. 14/444,247. |
| Jun. 27, 2016—U.S. Notice of Allowance—U.S. Appl. No. 14/721,689. |
| Aug. 23, 2016—U.S. Non-Final Office Action—U.S. Appl. No. 13/446,146; KFS does not cite OAs as prior art. |
| Sep. 9, 2016—U.S. Non-Final Office Action—U.S. Appl. No. 14/989,390. |
| Sep. 15, 2016—U.S. Non-Final Office Action—U.S. Appl. No. 14/959,402. |
| Oct. 31, 2016—U.S. Notice of Allowance—U.S. Appl. No. 15/058,371. |
| Oct. 7, 2016—U.S. Office Action—U.S. Appl. No. 15/135,101. |
| Dec. 16, 2016—U.S. Non-Final Office—U.S. Appl. No. 14/959,438. |
| Jan. 20, 2017—U.S. Notice of Allowance—U.S. Appl. No. 14/959,402. |
| Feb. 17, 2017—U.S. Notice of Allowance—U.S. Appl. No. 13/446,146. |
| Mar. 3, 2017—U.S. Final Office Action—U.S. Appl. No. 14/989,390. |
| Mar. 10, 2017—U.S. Notice of Allowance—U.S. Appl. No. 15/135,101. |
| Nov. 20, 2015—U.S. Non-Final Office Action—U.S. Appl. No. 14/611,915. |
| Dec. 9, 2013—U.S. Non-Final Office Action—U.S. Appl. No. 13/961,000. |
| Apr. 6, 2016—U.S. Final Office Action—U.S. Appl. No. 13/446,146. |
| Apr. 4, 2017—U.S. Notice of Allowance—U.S. Appl. No. 14/959,438. |
| Sep. 20, 2017—U.S. Notice of Allowance—U.S. Appl. No. 14/989,390. |
| Nov. 2, 2017—U.S. Non-Final Office Action—U.S. Appl. No. 15/180,416. |
| Nov. 2, 2017—U.S. Non-Final Office Action—U.S. Appl. No. 15/258,312. |
| Nov. 16, 2017—U.S. Non-Final Office Action—U.S. Appl. No. 15/593,529. |
| Mar. 27, 2018—U.S. Notice of Allowance—U.S. Appl. No. 15/593,529. |
| May 18, 2018 U.S. Non-Final Office Action—U.S. Appl. No. 15/180,416. |
| May 31, 2018—U.S. Non-Final Office Action—U.S. Appl. No. 15/463,594. |
| May 31, 2018—U.S. Non-Final Office Action—U.S. Appl. No. 15/598,732. |
| Jun. 15, 2018—U.S. Notice of Allowance—U.S. Appl. No. 15/258,312. |
| Jun. 4, 2018—(CA) Office Action—App 2,975,450. |
| Jun. 25, 2018—U.S. Non-Final Office Action—U.S. Appl. No. 15/482,954. |
| Jun. 22, 2018—(EP) Supplementary European Search Report—EP16746952. |
| Anonymous: “On-Board Diagnostics—Wikipedia”, Jan. 29, 2015, XP055478209. |
| Sep. 6, 2018—U.S. Non-Final Office Action—U.S. Appl. No. 15/398,256. |
| Nov. 13, 2018—U.S. Non-Final Office Action—U.S. Appl. No. 15/819,066. |
| Jan. 31, 2019—U.S. Final Office Action—U.S. Appl. No. 15/482,954. |
| The Sweet Setup, How to use 1Password as a digital will, https://thesweetsetup.com/1password-digital-will, Aug. 15, 2018, 8 pages. |
| Mylennium, Digital Asset Toolbox, https://www.mylennium.com/digital-asset-toolbox, Jan. 21, 2019, 4 pages. |
| Deseat.me, Clean up your online presence, https://www.deseat.me, Jan. 21, 2019, 5 pages. |
| Kiplinger, Protect Digital Assets After Your Death, https://www.kiplinger.com/article/retirement/T021-C000-S004-protect-digital-assets-after-your-death.html, Jan. 21, 2019, 5 pages. |
| AfterVault, The Digital Beyond, http://www.thedigitalbeyond.com/online-services-list/aftervault, Jan. 21, 2019, 3 pages. |
| Yodlee, Account Aggregation Software: What it Is and Howto Choose It, https://www.yodlee.com/trending/content/account-aggregation-software-what-it-and-how-choose-it, Jan. 21, 2019, 8 pages. |
| Ernie Feirer “Strategic Visualization: Evolving How You View Commercial Property Insurance Underwriting” LexisNexis website: https://www.lexisnexis.com/risk/downloads/assets/strategic-visualization-wp.pdf Sep. 2015, pp. 1-6. |
| “Underwriting and Rating Integrity” Verisk Analytics, Inc. website: https://www.verisk.com/insurance/capabilities/underwriting/property/underwriting-and-rating-integrity/ visited Dec. 20, 2018, pp. 1-7. |
| Xinrong Li “Catastrophe Model Suitability Analysis: Quantitative Scoring” Cass Business School City University London website: https://www.scor.com/fr/files/actuarial-award-2014-uk-catastrophe-model-suitability-analysis-quantitative-scoring Aug. 2013, pp. 1-71. |
| “Expand your real estate investment horizons” Location Inc website: https://locationinc.com/industry-solutions/real-estate-data/ website visited Dec. 21, 2018, pp. 1-7. |
| Jennifer Nicole Dowling “Finding Your Best-Fit Neighborhood: A Web GIS Application for Online Residential Property Searches for Anchorage, Alaska” Thesis Presented to the Faculty of the USC Graduate School website: https://spatial.usc.edu/wp-content/uploads/2014/10/DowlingJennifer.pdf Dec. 2014, pp. 1-41. |
| Mar. 15, 2019—U.S. Notice of Allowance—U.S. Appl. No. 15/398,256. |
| Jul. 23, 2019—(WO) International Search Report and Written Opinion—PCT/US19/24202. |
| May 8, 2020—U.S. Non-Final Office Action—U.S. Appl. No. 16/365,290. |
| Number | Date | Country | |
|---|---|---|---|
| 20190304025 A1 | Oct 2019 | US |
| Number | Date | Country | |
|---|---|---|---|
| 62648691 | Mar 2018 | US |
