System and method for determining allergens that pose a risk of respiratory illness to a user of the system

Abstract

A system and method determines allergens that can put a user of the system at risk for a respiratory illness attack. Historical data prior to a respiratory illness attack is statistically analyzed. The data is related to locations where the user has been present and includes environmental factors and optionally also human or animal contact factors. A set of locations where a respiratory illness attack is most likely to have been triggered and the most likely plant types (or animal types, molds or dust mites) that have caused the respiratory illness attack is derived.

Description

Technical Field

[0001] This invention relates to a system and method for identifying allergens that pose a risk to a user. Such allergens may include plant pollen, animal dander, dust, and mold. Background Technology

[0002] The spread of respiratory allergies (allergic rhinitis) is increasing. In the United States, approximately one-third of adults have respiratory allergies, and up to 40% of children are allergic to respiratory allergens. Pollen, dust mites, mold, and pet dander are common sources of respiratory allergies.

[0003] There are many different types of pollen and many different examples of other types of allergens that can cause allergies. Without seeing a doctor, allergy sufferers are unlikely to know which type of airborne allergen they are allergic to. People with allergic rhinitis usually see a doctor for allergen screening. This typically involves a skin prick test or an immunoglobulin E (IgE) blood test. This process is time-consuming and unpleasant, especially for children.

[0004] Even if individuals do know which type of specific allergen they are reacting to, effectively avoiding allergic reactions remains a problem for a variety of reasons.

[0005] First, there are many different types of airborne allergens. Pollen concentrations are only widely reported and predicted. However, pollen predictions (in newspapers, on smartphone apps, or on television) are very general and often fail to provide a specific individual with enough information to know whether pollen will pose a risk to them. For example, a high pollen count does not necessarily mean that any particular individual will be affected, as there are many different types of pollen from different kinds of trees, grasses, and various weeds. A high total pollen count does not necessarily indicate a high concentration of the specific pollen that an individual will react to. Conversely, a low pollen count does not necessarily mean a low concentration of the specific allergen that an individual is concerned about. For airborne allergens other than pollen, no objective data are available.

[0006] Secondly, it is unclear when and where an individual might be exposed to a specific allergen. Individuals have many opportunities to inhale airborne allergens, such as outdoor pollen, contact with dust mites carried by colleagues or classmates, or inhaling indoor mold. However, people rarely know when and where they are at risk of inhaling allergens because visible allergic reactions usually occur sometime within 24 hours of inhaling the allergen.

[0007] Therefore, there is a need for a system and methodology that can better determine when and where people may be exposed to allergens that affect them, and that can identify those allergens. Summary of the Invention

[0008] This invention is defined by the claims.

[0009] According to an example of one aspect of the invention, a system for identifying an allergen that poses a risk of respiratory illness to the user of the system is provided, the system comprising:

[0010] processor;

[0011] The first input to the processor is used to receive an indication that a respiratory attack has occurred; a position indicator; and

[0012] The second input to the processor is used to receive historical data for a period of time prior to the onset of respiratory illness, wherein the historical data is correlated with the user's location during that period, and the historical data includes at least environmental factors, including known plant types present in the vicinity of the location.

[0013] The processor is adapted to process historical data so that:

[0014] By assigning weights to environmental factors, the locations where respiratory disease attacks are most likely to have been triggered can be identified; and

[0015] Based on historical data associated with the identified locations, the set of plant types most likely to cause respiratory disease outbreaks is identified.

[0016] This system identifies potential allergens for users without requiring skin prick tests or expensive IgE blood tests. It uses statistical analysis of conditions that led to previous respiratory illness attacks, specifically a combination of location information and environmental factors at those locations. Some of this information can be manually entered into the system by the user, while others are provided automatically, such as location information (from GPS systems or other location indicators), pollen count information (from external databases), and plant information (from external databases such as crop locations). The various factors are weighted to determine the most likely location leading to the subsequent respiratory illness attack.

[0017] This location information helps identify the most likely plant clusters, which may be the cause of respiratory disease outbreaks at that location.

[0018] The most basic implementation of this system can identify the plant types for which pollen is an allergen. However, the system can also identify animal species that cause allergies, or mold or dust that poses a risk to a specific user.

[0019] Based on the information collected and identified by the system, allergens that may be risk factors for a user can first be identified. Then, it can be indicated when and where a specific user might be exposed to their specific allergen. Therefore, it can be instructed how to avoid contact with those specific allergens.

[0020] Environmental factors are related to weather conditions at the location visited by the individual. Environmental factors may further include weather conditions and pollen count information at the location, and optionally also include indoor conditions, including indoor humidity and / or room ventilation rate and / or indoor temperature. Therefore, both indoor and outdoor environments at the location visited by the individual are monitored.

[0021] The environmental factors of weather conditions include one or more of the following:

[0022] Outdoor humidity;

[0023] Wind speed;

[0024] wind direction;

[0025] temperature.

[0026] This weather information allows for the assessment of the risk of allergen exposure at a specific location.

[0027] Historical data can further include contact factors, which include animals known to be present at the location, and optionally, people known to be present at the location. Weights are then assigned to the contact factors to determine the location. For example, different weights can be assigned to different people based on the pets they own or other information about those individuals (such as the plants they have in their gardens). This information is typically provided to the system manually by the user. The system can then also identify the types of animals that cause allergic reactions. Therefore, the system can handle animals and plants in the same way.

[0028] For example, the processor is adapted to identify the set of most probable plant types by applying a weight to each plant type that is at least related to the amount of plant types present at the identified location. Thus, once a location is identified, the most probable plant type is determined based on information about that particular location, if the plant is the likely cause (e.g., not a pet).

[0029] In this way, there is a two-stage process for identifying the source of allergens. First, the most likely location is derived from historical information about all locations visited by system users, and then statistical analysis is performed on the possible plant types for specific locations.

[0030] For example, the weights for each plant type are related to environmental factors (pollen count, pollution level, wind information) and the generally known allergenicity level of that plant type.

[0031] Therefore, for a single respiratory illness episode, the set of most probable causes is identified. The processor is preferably adapted to identify a more accurate set of most probable plant types by combining sets of the most probable plant types from multiple previous respiratory illness episodes. In this way, additional information can be used to narrow down the possible causes of the illness episode.

[0032] For example, the maximum suitable duration for monitoring is 48 hours, and monitoring can be performed within a timeframe of 6 to 36 hours (leading to an onset of illness) or 12 to 36 hours. Shorter durations will reduce data storage requirements, while longer durations will improve accuracy but require more data storage. 24 hours is the typical maximum timeframe that may pass before a respiratory illness onset after allergen exposure becomes apparent.

[0033] In addition to identifying potential allergens for users, the processor can also be adapted to provide users with location-specific suggestions to avoid respiratory illnesses.

[0034] An example of another aspect of the invention provides a method for determining an allergen that poses a risk level for a respiratory illness attack to a user of the system, the method comprising:

[0035] Tracking user location;

[0036] Receive input indicating an onset of respiratory illness;

[0037] Receive historical data for a period prior to the onset of respiratory illness, wherein the historical data is correlated with the user's location during that period, and the historical data includes at least environmental factors, such as known plant types present at that location; and

[0038] Process historical data so that:

[0039] By assigning weights to environmental factors, the locations where respiratory disease attacks are most likely to have been triggered can be identified; and

[0040] Based on historical data associated with the identified locations, the set of plant types most likely to have caused respiratory disease outbreaks was identified.

[0041] Environmental factors may further include weather conditions at the location and pollen count information at the location, and optionally also include indoor conditions, including indoor humidity and / or room ventilation rate and / or indoor temperature, and the weather conditions of the environmental factors include one or more of outdoor humidity, wind speed, wind direction and temperature.

[0042] The method may include identifying the set of most likely plant types by applying a weight to each plant type that is at least related to the amount of plant types present at the determined location.

[0043] The method may include identifying the set of most likely plant types by combining the set of most likely plant types from multiple previous respiratory disease episodes.

[0044] This method can also be used to provide users with location and activity suggestions to avoid respiratory illness attacks.

[0045] Historical data may further include contact factors, which include animals known to be present at the location, and optionally also people known to be present at the location.

[0046] The present invention can be implemented at least in part by software, and thus provides a computer program including computer program code means that, when the program is run on a computer, the computer program code means is adapted to implement the methods defined above. Attached Figure Description

[0047] Examples of the invention will now be described in detail with reference to the accompanying drawings, in which:

[0048] Figure 1 A system for identifying allergens that pose a risk to a user is shown;

[0049] Figure 2 A method for identifying allergens that pose a risk to a user is shown; and

[0050] Figure 3 The diagram illustrates the implementation. Figure 1 An example of a computer's processor system. Detailed Implementation

[0051] This invention provides a system and method for identifying allergens that pose a risk of respiratory illness attacks to system users. Statistical analysis is performed on historical data prior to the respiratory illness attack. This data is correlated with the user's existing location and includes environmental factors, and optionally also human or animal exposure factors. A set of locations where respiratory illness attacks were most likely triggered and a set of the most likely plant types (or animal types, molds, or dust mites) that have caused the respiratory illness attacks are derived.

[0052] Figure 1 A system 10 according to an example of the present invention is shown. The system shown is associated with (and carried by) a specific user.

[0053] System 10 is used to identify allergens that may pose a risk of respiratory illness to the user of the system. It includes a processor 12 and a location indicator 14 for identifying or tracking the user's location. The location indicator is, for example, a location sensor, such as a GPS sensor. However, other methods of identifying location can be used, such as imaging information, for example, images from Google Glass. These images can also enable location tracking within a time period of interest.

[0054] The memory 13 is used to store data over a moving time window so that historical data is available when needed.

[0055] The processor and location indicator may be part of a mobile phone or tablet computer 16. Therefore, the invention can be implemented by loading suitable software onto a mobile phone, which may already include all the hardware required to implement the system of the invention.

[0056] The processor has a first input 18 for receiving an indication that a respiratory illness attack (“RA”) has occurred and a second input 20 for receiving historical data (“Hist”) from a period of time prior to the respiratory illness attack. This data is received from memory 13. When a user has a respiratory illness attack, such as an asthma attack, the user can press a simple emergency button. This enables the system to capture historical data.

[0057] Processor 12 determines the location from historical data where a respiratory illness attack is most likely to have occurred. For the determined location, it then derives the most probable allergen or a set of possible allergens.

[0058] Historical data 20 is received from a memory, which in turn obtains data from a database 22, for example, via an internet connection. The historical data 20 is essentially information about the probability of exposure to allergens based on location.

[0059] Historical data specifically includes environmental factor 24, and optionally also includes contact factor 26.

[0060] Environmental factors, for example, are part of the data in the database and include plant types known to exist near the location. Therefore, the database stores maps of plant crop varieties and their locations. Environmental factors also include weather conditions and pollen counts at the location. Particle concentration levels can also be monitored.

[0061] Weather conditions include one or more of outdoor humidity, wind speed, wind direction, and temperature. These may all be obtained from database 22, but some or all may also be obtained from local sensors that form part of the system, such as temperature sensors, relative humidity sensors, and particulate concentration sensors. These are outdoor weather conditions, but environmental factors may further include indoor conditions, such as indoor humidity and / or room ventilation rate and indoor particulate concentration. This information may be obtained from local sensors or, for example, through communication with a building management system.

[0062] Therefore, monitoring indoor and outdoor environments at locations visited by individuals over time allows for the assessment of the risk of allergen exposure at specific locations.

[0063] Historical data also preferably includes contact factor 26, for example, related to pet interactions that occurred at that location. However, it may include interactions with people, for example, when the pets of those other people are identified as risk factors associated with those people.

[0064] This contact information is more individualized and therefore less likely to be obtained from the shared database 22. Instead, the processor has a third input 28 for receiving information (“Info”) from the user, which provides a higher degree of system customization for a specific user. For this reason, contact factor 26 is shown as part of device 16 rather than database 22.

[0065] The processor first determines the most likely location of allergen exposure based on historical information.

[0066] Therefore, weights are assigned to environmental factors and optional contact factors, and the time spent visiting the location is also taken into account. Weights exist for each factor considered.

[0067] Convert each factor into a weight, for example, from 1 to 5 (other scales can be used, such as 1, 3, 5, 7, so the highest weight has a greater influence).

[0068] For example, wind speeds below 5 km / h might have a weight of 1, and wind speeds above 50 km / h might have a weight of 5, with intermediate wind speeds divided into residual zones 2 to 4. Particulate concentrations (such as PM2.5 or PM10) can be treated in the same way. For example, below 5 μg / m³... 3 The PM2.5 concentration may correspond to weight 1 and be higher than 50 μg / m³. 3 The PM2.5 concentration may correspond to a weight of 5.

[0069] All other factors that are measured as digital scales can be handled in the same way, such as temperature, humidity, room ventilation rate, and pollen count.

[0070] For example, humidity is a key indicator of allergen release. High humidity may cause allergens to be released from pollen and cause pollen to attach to other small particles. Allergens on these small particles are more likely to be inhaled.

[0071] It is important to note that some factors may not have a full range of possible values ​​from 1 to 5, and furthermore, only a few values ​​of interest may exist. For example, temperature may be considered to have a relatively small impact on the risk of allergen attachment (e.g., it may be related to mold spores), so only a narrow temperature range (e.g., 22 to 35°C) might be relevant, and even then, only a weight of 3 might be appropriate.

[0072] Other factors may be more binary in nature, and therefore have weights of only 1 or 5 (or other values), such as pet interaction. Different animals may receive different weights. Furthermore, being in a location where a pet lives will receive a higher weight than contact with people who have pets at home (i.e., only indirect contact with their pets).

[0073] Plants located near a crop's nearest occupied location may have weights based on the distance to that location. Therefore, the weight of a nearby plant can be a function of the distance to the plant's known location. The weights may also differ between different plants based on their known general allergies.

[0074] The weights can all be multiplied together (which is why the lowest score is 1 in the example above) to provide the total score.

[0075] This total score is applied to a specific location when those specific conditions are present. Examples of locations are indoors at home, outdoors at home, commuting to work, and indoors at work. Different locations have different contact factors, such as immediate family members at home, pets at home, and colleagues at work (indirect contact with their associated pets).

[0076] The time a user spends at each location is also considered, and this is used as a multiplier. Therefore, for a specific location, the total score is multiplied by the time during which that total score applies. The total score may increase over the duration the user is present at that location. The final score for that location is then the combination of the individual time periods. In other words, a total composite score over the time period is obtained.

[0077] The time period can be as simple as the actual duration (scaled proportionally so that multiplying by time is appropriate, i.e., the nominal time period has a value of 1). However, time periods can also be defined using weighted values, especially if the weights are not calculated every second or minute. For example, a time period in the range of 0 to 30 minutes might have a weight of 1; 30 minutes to 1 hour might have a weight of 3, and over 1 hour might have a weight of 5. The applied weights, compared to other weight values, will ensure that the impact of the duration is correctly accounted for.

[0078] The allergen risk level A (i.e., the final score) for this location becomes:

[0079] A = ∑ i W i xt i

[0080] W i In the time period t i The total score (i.e., risk level) during the period is calculated, and the products are summed to provide the final score for the entire time period when the location exists.

[0081] Based on the allergen risk levels of different locations visited by users before the onset of respiratory illness, the most likely locations that led to the onset of the illness are identified in this way.

[0082] It's important to note that the above method is merely an example. Essentially, this method involves considering multiple risk factors that can be assessed for a specific location and deriving the risk level for that location. The risk levels at different locations can then be compared. The way factors affect risk levels can be determined based on data analysis from multiple system users or through experimental work. Default weight settings can be used initially and can then be developed as more data is collected.

[0083] For each identified location, based on historical data associated with that location, a set of the most likely plant (or even animal) types that have caused the respiratory disease outbreak is determined. It's important to note that more than one location can be identified. For example, in addition to seeking the location with the highest risk score, multiple locations with risk scores exceeding a threshold can be analyzed in the following steps of the method.

[0084] For example, the single location most likely to be the cause can be identified as commuting work (where “location” is used broadly and can include a journey or scenario, i.e., a set of locations in chronological order).

[0085] The processor then identifies the set of most likely plant types that are allergens associated with the commuting trip (there may be no animals associated with the trip).

[0086] This involves using plant information along the commuting route and the associated allergens for each plant, including its quantity, pollen count, pollen allergenicity level, and local environmental factors (such as wind and air pollution levels, humidity, and distance from the plant).

[0087] This essentially involves breaking down the overall risk factor A of commuting into factors of different plants experienced at that location (i.e., the journey).

[0088] By assigning weights to these factors in the manner explained above, probability values ​​can be assigned to different plant types that were once near the user.

[0089] Then, based on probability, determine the most probable set of possible allergen sources, for example, the set of 5 most probable allergen sources.

[0090] Each plant type may have different weights for the amount of plant present, wind speed, allergenicity level, pollen count, and particulate air pollution level, because these factors may have different correlations with the allergen risk of different plants. For example, wind speed will have different effects on pollen from different plants.

[0091] Then, each plant type may have its own allergen risk score, which is the product of these weighted factors. Again, with a minimum weight of 1, the corresponding factor will not affect the risk score.

[0092] Therefore, the first step provides the general risk level of the location (or route), while the second step provides the specific risk level associated with each plant.

[0093] The system ultimately outputs a list of possible allergens (shown as output 30, "All"). It can also indicate locations to avoid, shown as output 31 ("Loc"), or it can actually generate routes (e.g., as part of a navigation system) that avoid locations where identified allergens are known to be present.

[0094] To maintain consistent accuracy, the model can be improved through data learning (i.e., database content and weight scores). Furthermore, the processor-operated algorithm can be updated (e.g., by inputting 28) through an exclusion function, allowing it to exclude allergens and allergen sources known not to be triggers for the user. This will provide a personalized allergen estimation model.

[0095] First, data learning is used to define the weights of each factor, as explained above for a specific user. Second, the exclusion function is used to narrow down potential allergens during long-term monitoring.

[0096] The information for the exclusion function can be entered by the user, as mentioned above, but it can also be determined based on the analysis of the dates of the allergy reaction set.

[0097] For a single respiratory illness episode, the set of most probable causes is identified. The processor can identify the set of most probable plant (or animal) types or locations of exposure to dust mites by combining the set of most probable plant (or animal) types from multiple previous respiratory illness episodes with other information. For example, if allergens A through G are likely present, and the top five are identified in each respiratory illness episode, the actual causes should overlap. If an allergen type rarely appears in the list, it can be discarded and identified as a type that the user does not react to. Of course, this analysis can be based on more rigorous statistical analysis. By excluding allergens from the analysis, computational load and time can be reduced.

[0098] In this way, the system can identify potential allergens for its users without requiring skin prick tests or expensive IgE blood tests. It uses statistical analysis of conditions that led to previous respiratory illnesses, particularly location information and combinations of environmental and optional exposure factors at those locations. The system can also indicate when and where a particular user might be exposed to their specific allergen. Therefore, it can instruct on how to avoid contact with those specific allergens.

[0099] As mentioned above, the core aspect of this system is to improve the identification of specific pollen allergies in addition to common pollen allergies. Furthermore, the system can identify allergies to mold, dust, mites, or other allergens.

[0100] For example, key indicators of dust and mold can be obtained from PM10 concentration and indoor humidity. Therefore, indoor humidity and PM10 concentration can be incorporated into historical data, making it possible to identify these risk factors as well.

[0101] The weighting rule for relative humidity is that higher humidity corresponds to a larger weight value, and higher PM10 concentration corresponds to a larger weight value.

[0102] Cleaning frequency indicators can also be used. Frequent cleaning corresponds to lower weighting. Indoor cleaning information can be obtained automatically via wireless communication with floor care devices, or it can be obtained based on fluctuations in detected PM10 data.

[0103] If the indoor humidity in that location is consistently above 80% and cleaning is infrequent, the likelihood of mold growth increases.

[0104] All these various factors can be monitored. At a minimum, the system has the ability to identify different pollen types. However, in an extended implementation, it can identify allergies to any of the various types mentioned above.

[0105] For example, this period can last between 6 and 36 hours, such as a full 24-hour period. This is a typical timeframe that may pass before the onset of respiratory illness after exposure to an allergen becomes apparent.

[0106] Figure 2 A method for determining allergens that pose a risk level to respiratory illness attacks in system users is shown, the method comprising:

[0107] In step 32, the user's location is tracked;

[0108] In step 33, input indicating a respiratory illness attack (RA) is received;

[0109] In step 34, historical data for the period prior to the onset of respiratory illness is received, wherein the historical data is related to the user's location during that period.

[0110] As explained above, historical data includes environmental factors, such as the types of plants known to be present at the location, the weather conditions at the location, and pollen count information at the location; and optionally, it also includes contact factors, such as animals known to be present at the location.

[0111] In step 36, historical data is processed.

[0112] In step 36a, the location where a respiratory disease attack is most likely to be triggered is determined by assigning weights to environmental factors and exposure factors (if used).

[0113] In step 36b, based on historical data associated with the identified location, a set of the most likely plant types that caused the respiratory disease outbreak is determined.

[0114] In step 36c, suggestions are provided regarding the user's location to avoid respiratory illness attacks.

[0115] This method can identify major risk allergens as plant-based, animal-based, or a combination of both. They are then processed in the same way using corresponding weights.

[0116] The system can be divided into different parts in different ways. For example, various sensors are used, including location indicators (such as GSM signal processors for triangulation or GPS or other satellite positioning systems or imaging devices that can visually indicate location) and optional other sensors, such as temperature, humidity, and pollution sensors. There may also be other sensors, such as physiological sensors. These sensors may all be part of the system, or some other sensors may be part of other devices (with other primary functions) with which the system communicates.

[0117] The above system uses processor 12 to process data.

[0118] Figure 3 An example of a computer 40 for implementing the aforementioned processor is illustrated.

[0119] Computer 40 includes, but is not limited to, PCs, workstations, laptops, PDAs, handheld devices, servers, storage devices, etc. Typically, in terms of hardware architecture, computer 40 may include one or more processors 41, memory 42, and one or more I / O devices 43 communicatively coupled via a local interface (not shown). As known in the art, the local interface may be, for example, but not limited to, one or more buses or other wired or wireless connections. The local interface may have additional elements, such as controllers, buffers (caches), drivers, repeaters, and receivers, to enable communication. Further, the local interface may include address, control, and / or data connections to enable appropriate communication between the aforementioned components.

[0120] Processor 41 is a hardware device for executing software that can be stored in memory 42. Processor 41 can actually be any custom or commercially available processor, central processing unit (CPU), digital signal processor (DSP), or auxiliary processor among multiple processors associated with computer 40, and processor 41 can be a semiconductor-based microprocessor (in the form of a microchip) or microprocessor.

[0121] Memory 42 may include any or a combination of volatile memory elements (e.g., random access memory (RAM), such as dynamic random access memory (DRAM), static random access memory (SRAM), etc.) and non-volatile memory elements (e.g., ROM, erasable programmable read-only memory (EPROM), electronically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic tape, optical disc read-only memory (CD-ROM), magnetic disk, floppy disk, magnetic tape cassette, cassette tape, etc.). Furthermore, memory 42 may incorporate electronic, magnetic, optical, and / or other types of storage media. It should be noted that memory 42 may have a distributed architecture, in which various components are placed far apart from each other but are accessible by processor 41.

[0122] The software in memory 42 may include one or more individual programs, each including an ordered list of executable instructions for implementing logical functions. According to an exemplary embodiment, the software in memory 42 includes a suitable operating system (O / S) 44, a compiler 45, source code 46, and one or more applications 47.

[0123] Application 47 includes many functional components, such as computing units, logic, functional units, processes, operations, virtual entities and / or modules.

[0124] The operating system controls the execution of computer programs and provides scheduling, input / output control, file and data management, memory management, communication control, and related services.

[0125] Application 47 can be a source program, an executable program (object code), a script, or any other entity that includes a set of instructions to be executed. When it is a source program, the program is typically translated by a compiler (such as compiler 45), assembler, interpreter, etc. (which may or may not be included in memory 42) to operate correctly in conjunction with operating system 44. Furthermore, application 47 can be written in an object-oriented programming language with data and method classes or a programmable programming language with routines, subroutines, and / or functions, such as, but not limited to, C, C++, C#, Pascal, BASIC, API calls, HTML, XHTML, XML, ASP scripts, JavaScript, FORTRAN, COBOL, Perl, Java, ADA, .NET, etc.

[0126] I / O device 43 may include input devices, such as, but not limited to, a mouse, keyboard, scanner, microphone, camera, etc. Furthermore, I / O device 43 may also include output devices, such as, but not limited to, a printer, monitor, etc. Finally, I / O device 43 may further include devices for transmitting both input and output, such as, but not limited to, a network interface controller (NIC) or modulator / demodulator (for accessing remote devices, other files, devices, systems, or networks), radio frequency (RF) or other transceivers, telephone interfaces, bridges, routers, etc. I / O device 43 also includes components for communication over various networks, such as the Internet or intranets.

[0127] When the computer 40 is in operation, the processor 41 is configured to execute software stored in the memory 42 to transfer data to and from the memory 42, and to control the overall operation of the computer 40 according to the software. The processor 41 reads, in whole or in part, the application 47 and the operating system 44, possibly buffered within the processor 41, and then executes them.

[0128] When application 47 is implemented as software, it should be noted that application 47 can actually be stored on any computer-readable medium for use by or in connection with any computer-related system or method. In the context of this document, a computer-readable medium can be an electronic, magnetic, optical, or other physical device or apparatus that may contain or store computer programs for use by or in connection with a computer-related system or method.

[0129] This invention can be used as part of a pollution mask, air purifier system, HVAC system, or dehumidifier.

[0130] By studying the accompanying drawings, the disclosure, and the appended claims, those skilled in the art can understand and implement other variations of the disclosed embodiments in practicing the claimed invention. In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite articles "a" or "an" do not exclude a plurality. The fact that certain measures are described in mutually different dependent claims does not indicate that a combination of these measures cannot be used advantageously. Any reference numerals in the claims should not be construed as limiting the scope.

Claims

1. A system for determining allergens that may pose a risk of respiratory illness to a user of the system, the system comprising: Processor (12); a first input (18) to the processor for receiving an indication that a respiratory episode has occurred; Position indicator (14); as well as a second input (20) to the processor for receiving historical data for a time period prior to the onset of the respiratory disease, wherein the historical data relates to the location of the user during the time period, the historical data comprising at least environmental factors (24), the environmental factors (24) comprising at least types of vegetation known to be present in the vicinity of the location, The processor (12) is adapted to process the historical data so as to: determining said location where a respiratory illness episode is most likely to have been triggered by assigning weights to said environmental factors; identifying, based on the historical data associated with the determined location, a set of vegetation types, the set of vegetation types comprising candidates that have caused an onset of the respiratory disease; as well as The set of plant types is output as plant types that may pose a risk of respiratory illness onset to the user of the system.

2. A system according to claim 1, wherein the historical data also includes a contact factor (26), the contact factor (26) including animals known to be present at the location, and optionally also including people known to be present at the location, and wherein weights are also assigned to the contact factors.

3. A system according to claim 1 or 2, wherein the environmental factors (24) also include weather conditions at the location and pollen count information at the location, and optionally also include indoor conditions, the indoor conditions including indoor humidity and / or room ventilation rate and / or temperature.

4. The system according to claim 3, wherein the weather conditions of the environmental factors include one or more of the following: Outdoor humidity; Wind speed; wind direction; temperature.

5. A system according to any one of the preceding claims 1-2, 4, wherein the processor (12) is adapted to identify a set of most likely plant types by applying to each plant type a weight at least related to the amount of the plant type present at the determined location.

6. The system of claim 5, wherein the weight for each plant type is further related to the environmental factors and pollen allergenicity level.

7. The system according to any of the preceding claims 1-2, 4, wherein the processor (12) is adapted to identify a set of most likely vegetation types by combining sets of most likely vegetation types from a plurality of previous respiratory disease episodes.

8. The system according to any of the preceding claims 1-2, 4, wherein the duration of the time period is between 6 hours and 36 hours.

9. The system according to any of the preceding claims 1-2, 4, wherein the processor (12) is adapted to provide the user with location-specific recommendations (31) to avoid respiratory episodes.

10. A method for determining an allergen that could present a level of risk of respiratory illness to a user of a system for determining allergens, the method comprising: (32) tracking the location of the user; (33) receiving input indicating an onset of a respiratory disorder; (34) receiving historical data for a time period prior to the onset of a respiratory illness, wherein the historical data is associated with a location of the user during the time period, the historical data comprising at least environmental factors, the environmental factors comprising types of vegetation known to be present at the location; (36) Processing the historical data to: (36a) determining the location where a respiratory illness episode is most likely to have been triggered by assigning weights to the environmental factors; as well as (36b) based on the historical data associated with the determined location, identifying a collection of plant types as candidates for having caused an onset of said respiratory disease; as well as The set of plant types is output as plant types that may pose a risk of respiratory illness onset to the user of the system.

11. The method according to claim 10, wherein the environmental factors further include weather conditions at the location and pollen count information at the location, and optionally further include indoor conditions, wherein the indoor conditions include indoor humidity and / or room ventilation rate and / or indoor temperature, and the weather conditions of the environmental factors include one or more of outdoor humidity, wind speed, wind direction and temperature.

12. The method according to claim 10 or 11, comprising: A set of most likely vegetation types is identified by applying to each vegetation type a weight related to at least an amount of the vegetation type present at the determined location.

13. The method according to any one of claims 10 to 11, comprising: A set of most likely vegetation types is identified by combining the sets of most likely vegetation types from multiple previous respiratory illness episodes.

14. A method according to any one of claims 10 to 11, wherein the historical data further comprises contact factors including animals known to be present at the location, and optionally also humans known to be present at the location.

15. A computer program comprising computer program code means adapted to implement the method according to any one of claims 10 to 14 when said program is run on a computer.

Images