Anticipating solutions to potential stored energy threats

Abstract

A method, system, and computer program product for simulating potential impacts and possible solutions of releasing stored energy using augmented reality. The method may include aggregating IoT feeds from devices in a surrounding area. The method may also include calculating an amount of stored energy in the surrounding area based on the IoT feeds. The method may also include predicting background conditions that may result from releasing stored energy in the surrounding area. The method may also include determining one or more impacts for each of the background conditions. The method may also include calculating a severity of the one or more impacts for each background condition. The method may also include determining one or more proposed solutions based on the severity. The method may also include transmitting a recommendation of at least one proposed solution for implementation.

Description

[Technical field]

[0001] The present disclosure relates to augmented reality, and more particularly, to using augmented reality to simulate potential impacts of releasing stored energy and possible solutions. [Background technology]

[0002] Stored energy is energy that is held or possessed by an object. There can be different forms of stored energy, including gravitational potential energy (e.g., energy stored in an object as a result of the object's position or height), mechanical energy (e.g., energy stored in an object as a result of the application of a force), electrical energy (e.g., energy stored in an object as a result of the movement of electrons through or to the object), energy stored in pressurized gases and / or liquids, etc. Stored energy can be anywhere, including in areas where it may not be expected. For example, stored energy can be found throughout various work environments, including areas with tensioned cables or wireline reels, torqued drill strings, compressed springs, pressured wells / tanks / pipelines, objects being carried / lifted / raised above the ground, etc. Summary of the Invention

[0003] The present disclosure provides a computer-implemented method, system, and computer program product for simulating potential impacts and possible solutions due to the release of stored energy using augmented reality. The method can include aggregating IoT feeds from one or more devices in a surrounding area. The method can also include calculating an amount of stored energy in the surrounding area based on the IoT feeds. The method can also include predicting one or more contextual situations that may result from the release of stored energy in the surrounding area. The method can also include determining one or more impacts for each of the one or more contextual situations, where the one or more impacts are caused by the one or more contextual situations. The method can also include calculating a severity of the one or more impacts for each of the one or more contextual situations. The method can also include determining one or more proposed solutions based on the severity. The method can also include transmitting a recommendation of at least one proposed solution from the one or more proposed solutions for implementation.

[0004] The above summary is not intended to describe each illustrated embodiment or every implementation of the present disclosure.

[0005] The drawings included in this application are incorporated in and form a part of this specification. The drawings illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure. The drawings are merely illustrative of particular embodiments and are not intended to limit the disclosure. [Brief description of the drawings]

[0006] [Figure 1] 1 is a flowchart of a set of operations for predicting potential solutions to the effects of energy release, according to some embodiments. [Diagram 2]1 is a schematic diagram of an example augmented reality environment, according to some embodiments. [Diagram 3] 1 is a block diagram of a first example computer system according to some embodiments. [Figure 4] 1 is a schematic diagram of a second example computer system, according to some embodiments. [Diagram 5] 1 is a block diagram of a sample computer system according to some embodiments. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0007] While the invention is susceptible to various modifications and alternative forms, specifics thereof have been shown by way of example in the drawings and will be described in detail. It should be understood, however, that the intention is not to limit the invention to the particular embodiments described. On the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the scope of the invention.

[0008] The present disclosure relates to augmented reality, and more particularly to using augmented reality to simulate potential effects of releasing stored energy and possible solutions. The present disclosure is not necessarily limited to such applications, although various aspects of the present disclosure may be appreciated through the discussion of various examples using this context.

[0009] Stored energy can build up, and as the energy builds up, it becomes increasingly likely that it will suddenly be released, causing potentially serious hazards or impacts. For example, as a spring becomes increasingly compressed or stretched, the stored energy continues to build and accumulate. Finally, the stored energy can build up to the point where the spring suddenly unfolds, releasing the stored energy with a large force. In another example, rock masses (especially rock masses that are part of a fault plane) can continue to accumulate energy as the fault plane continues to move and create frictional resistance. The friction can continue to cause the accumulation of stored energy until finally the stored energy is suddenly released, causing an earthquake. The hazards caused by the sudden release of stored energy can include damage to property as well as threats to humans, such as serious injury or possibly death.

[0010] Traditionally, various technologies such as the Internet of Things (IoT) may be used to track and / or calculate stored energy in an environment. IoT technologies may allow information to be transferred to various computing devices without any human interaction. Thus, IoT devices, and potentially image scanning technologies, may be used to determine how much stored energy is in an area. However, once it is determined how much stored energy is accumulated, it may be up to humans to decide how to address the problem. If this problem is not addressed, a sudden release of stored energy may cause accidents and / or damage in the area where the energy is suddenly released.

[0011] The present disclosure provides a computer-implemented method, system, and computer program product for simulating potential impacts and possible solutions from the release of stored energy using augmented reality. Through the use of augmented reality (AR) along with IoT and artificial intelligence (AI), not only can the amount of stored energy in the surroundings be determined, but the stored energy can be analyzed to automatically predict potential impacts and possible solutions from the release of stored energy to prevent the impact from occurring (or at least reduce the severity of the impact). Using a combination of AR, IoT, and AI can improve the accuracy of the determination and analysis of the amount of stored energy in the surrounding area (because a more accurate and complete visual representation of the surrounding area can be achieved (helping to get a better data read of the surrounding area) and continuous learning and training can be used to constantly improve the algorithms and calculations), and can also automatically allow potential impacts and possible solutions to be accurately predicted without the need for human intervention.

[0012] The surrounding area, as referred to herein, can include an area or environment from which various IoT devices and AR devices can gather data. In some cases, the surrounding area is an area visible to an AR device. Augmented reality (AR) can include a synthetic view of a computer-generated image to a view of the surrounding area (e.g., a real-world environment). Although this specification discusses AR, in some embodiments, virtual reality (VR) technology may also be used.

[0013] In some embodiments discussed further herein, AR (leveraging AI and IoT) may be used to derive a simulation of the effects of a release of stored energy (e.g., a sudden release) in the surroundings that may result in an accident or impact due to the release of energy by running one or more background solutions (e.g., test cases) via augmented reality. The stored energy may be calculated by aggregating data feeds from various IoT sensors in the surrounding area. In some instances, possible solutions to prevent the impacts shown in various background situations may be determined and communicated by the user. By predicting the impact of the release of energy (using the background solutions) and generating possible solutions, the impact of the release of stored energy may be minimized or possibly even eliminated, potentially preventing a great deal of damage in the surrounding area and potential threats to individuals.

[0014] Referring now to FIG. 1, a flow chart illustrating a method 100 for predicting potential solutions to the effects of energy release is depicted, according to some embodiments. In some embodiments, the method 100 is performed by a server (e.g., computer system / server 502 (FIG. 5)) on or connected to an augmented reality device (e.g., AR device 210 (FIG. 2), AR device 330 (FIG. 3), or AR device 430 (FIG. 4)). In some embodiments, the method 100 is implemented as a computer script or computer program (e.g., computer executable code) to be executed on or connected to a computer system (e.g., system 200 (FIG. 2), system 300 (FIG. 3), or computer system 500 (FIG. 5), or a combination thereof). In some embodiments, the computer system is on or connected to the AR device (and may further be on or connected to an AI system and / or IoT system).

[0015] The method 100 includes an operation 110, which aggregates IoT feeds from one or more devices in the surrounding area. Various devices with IoT capabilities (i.e., IoT devices) may be in the surrounding area and / or nearby. In some cases, the IoT devices may include sensors. For example, a warehouse may have sensors placed throughout (e.g., at the ends of an islet), and these sensors may be IoT devices or may be pre-linked to IoT devices, or both. In another example, various sensors, or devices with sensors, or both may be placed near a fault plane in the environment to gather various data about the fault. In yet another example, the sensors may be components of an augmented reality device (e.g., AR glasses, or any other portable device with AR capabilities), and the sensors may gather data using the capabilities of the AR device (e.g., video capabilities). In some embodiments, one or more IoT feeds are received from an augmented reality device.

[0016] Data collected from one or more sensors and IoT devices may be transmitted or fed into the system. In some embodiments, the sensors and IoT devices are components of the system. In some embodiments, the sensors and IoT devices are on or connected to an augmented reality device, which transmits an IoT feed to the system. Once the system receives one or more IoT feeds from one or more devices, the one or more IoT feeds may be analyzed. In some embodiments, analyzing the one or more IoT feeds includes identifying which data was collected from the IoT devices / sensors and determining which data from the IoT feeds is energy data. In some embodiments, the IoT feeds may be analyzed using video and image analysis techniques.

[0017] The energy data may be any data necessary or possibly useful in determining the stored energy of a surrounding area. For example, geological data, environmental data, population distribution data, infrastructure setup data, etc. may be used in determining the stored energy of a surrounding area. In some cases, the stored energy of a surrounding area may correspond to an object in motion (e.g., a spring being compressed, a swing set swinging, a fault plane moving, etc.). In these cases, data regarding the speed of the object, the height of the object, the proximity of the object to others in the surrounding area, etc. may be used to help determine the stored energy.

[0018] In some embodiments, aggregating IoT feeds further includes collecting energy data from one or more IoT feeds, hi some embodiments, energy data from one IoT feed may be combined or correlated with energy data from other IoT feeds in the one or more IoT feeds to simplify aggregation.

[0019] The method 100 includes an operation 120 of calculating an amount of stored energy in a surrounding area based on the IoT feed. Once the IoT feeds are aggregated and, in some cases, energy data is identified and collected from the IoT feeds, the IoT feed data or the energy data or both may be used to calculate an amount of stored energy in the surrounding area. In some embodiments, calculating the amount of stored energy in the surrounding area may include identifying one or more objects in the surrounding area and calculating an amount of stored energy for each object. The objects may be any material that can be seen, touched (or otherwise sensed).

[0020] In some embodiments, machine learning (e.g., supervised learning) may be used to calculate the amount of stored energy. Supervised learning is a type of machine learning where an input is paired with an output and the mapping of various input-output pairs may be used to determine a function or algorithm. Supervised learning may analyze input-output training data and learn / train an algorithm based on the data. Using machine learning techniques such as supervised learning, an algorithm may be developed (i.e., learned and trained) using various input-output pairs of IoT feed data, such as energy data (as input) and the amount of stored energy (as output). In some embodiments, the IoT feed data (e.g., energy data) used as input may be specific to a particular object in a surrounding area to determine or calculate the amount of stored energy for the particular object.

[0021] In some embodiments, the system includes or is connected to a knowledge corpus, and data collected from the knowledge corpus is used as training data to train the algorithms using machine learning. The knowledge corpus can include historical or past data about objects in the surrounding area and historical amounts of stored energy corresponding to the objects.

[0022] In some embodiments, such as depicted in FIG. 1, method 100 proceeds from operation 120 to operation 130 to determine whether there is a concerning level of stored energy. Determining whether there is a concerning level of stored energy may help increase or improve the efficiency of predicting potential solutions (for the impact of releasing energy) before determining the impact of the release of stored energy. In some cases, not every occurrence of stored energy in the surrounding area may be used when determining the impact of a sudden release of stored energy. In some embodiments, if the stored energy is at a lower or less concerning level, the impact of the release (e.g., a sudden release) may not have many, if any, hazards or impacts resulting from the release, so the impact of the release may not need to be determined.

[0023] Determining whether there is a concerning level of stored energy may include determining a threshold (or, in some cases, a level) of stored energy levels in the surrounding area. In some embodiments, each object in the surrounding area may have a threshold of stored energy levels. In some embodiments, the threshold may be learned through machine learning, such as supervised learning or reinforcement learning or both. Reinforcement learning is another type of machine learning that can analyze data to determine which appropriate action can be taken to maximize rewards / outcomes. Reinforcement learning can focus on finding the best path for a unique situation (e.g., from a large number of "correct" paths) rather than finding one correct answer based on inputs.

[0024] In some embodiments, machine learning may be used to determine how much stored energy (e.g., a level or amount of stored energy) has the potential to cause damage or threat when released. For example, the knowledge corpus can have data on past releases of stored energy of objects in the surrounding area or at least objects very similar to these. For example, there may be data stored in the knowledge corpus about fault planes, releases of stored energy, and earthquakes. This data may be used to determine a threshold amount of stored energy on the fault planes that may cause an earthquake. In another example, objects in the surrounding area may include forklifts in a warehouse and the knowledge corpus may include historical data about the forklifts, the height of the forklifts, objects that have fallen from the forklifts, etc. In this example, machine learning may be used to determine a threshold amount of stored energy that may cause damage (such as an object that will fall from the forklift).

[0025] In some embodiments, determining whether there is a concerning level of accumulated energy may further include comparing the calculated amount of accumulated energy to a threshold amount of accumulated energy. In some instances, the accumulated energy and the threshold amount of accumulated energy may correspond to an object.

[0026] For example, continuing with the forklift example from above, the forklift may have a box on it that is being lifted by the forklift. In this example, the box may be the object. Potential energy may be calculated to determine the stored energy (using the mass of the box, the acceleration of gravity, and the height of the box, which may have been determined through aggregation of IoT feeds). In this example, the stored energy may correspond to potential energy. As the box is lifted higher, the stored energy of the box may increase. There may be historical data stored in the corpus of knowledge about the potential energy (or stored energy) of the box being lifted by the forklift and the damage caused by the release of the stored energy (e.g., the box breaking, the box falling and posing a threat to other individuals, etc.). In some embodiments, the historical data is specific to the warehouse and may even be the size of the box depending on data that has been collected and stored from previous scenarios. This data may be used with machine learning to determine an approximate amount of potential energy of the box that would not cause damage if it were to fall, or perhaps an approximate amount of potential energy of the box that would likely not fall at all. This approximate amount of potential energy may be the stored energy threshold in this example. The actual stored or potential energy of the box may be calculated to be 1000 kilojoules (kJ). The stored energy threshold may be 10 kJ. Thus, when comparing the stored energy to the stored energy threshold, it may be determined that the stored energy is greater than the threshold and therefore there is a concerning level of stored energy.

[0027] In some embodiments, determining whether there is a concerning amount of stored energy may include determining whether objects in the surrounding area or other nearby objects have any safety measures to help contain or prevent damage, and if so, these may be included as a factor in determining the stored energy threshold.

[0028] For example, a forklift may have appropriate safety measures to prevent a box from falling off the forklift. Specifically, in this example, the forklift may have size limitations on objects being placed on the forklift, and may require the object to be pressed up against the back of the forklift. In this example, when considering the safety measures, it may be determined that a box may have approximately 1500 kJ of stored energy before there is concern that the box will fall or cause other damage (as long as the box meets the size requirements and is placed up against the back of the forklift). In this instance, the actual amount of stored energy of 1000 kJ is less than the 1500 kJ threshold, and therefore the box may not have a level of stored energy of concern.

[0029] If, in operation 130, it is determined that there is no level of stored energy in the surrounding area that is of concern, method 100 may end after operation 130. In some cases, if the amount of stored energy in the surrounding area, or the amount of energy in objects in the surrounding area, or both, is not of concern, there may be minimal to no likelihood of damage / impact even if the stored energy were to be released. Thus, it may not be necessary to predict potential solutions to the impact of the release of energy, and method 100 may end.

[0030] In some instances, method 100 may automatically proceed from operation 120 to operation 140 without determining whether the level of stored energy is of concern or high. In this manner, all stored energy in the surrounding area (e.g., the stored energy of each object in the surrounding area) may be analyzed and potential solutions to the impact of the release of stored energy may be determined for all stored energy in the surrounding area, regardless of how concerning the level of stored energy may be. This may improve the accuracy of the prediction because every amount of stored energy is considered and used in determining the potential impact of the release of stored energy.

[0031] If, at operation 130, it is determined that there is a concerning level of stored energy in the surrounding area, method 100 proceeds to operation 140 to predict one or more background conditions that may result from the release of the stored energy. The background conditions may be specific to the surrounding area, or specific objects in the surrounding area, or both. In some embodiments, the predicted background conditions are determined by simulating the potential effects of the release of the stored energy. In some embodiments, the background conditions are test cases. For example, predicting the one or more background conditions may include running (e.g., via simulation) one or more test cases in which the stored energy is released in the surrounding area. In some embodiments, the test cases may be run using an augmented reality device. In some embodiments, video from the augmented reality device (e.g., achieved via an IoT feed) may be used for the test cases. In some embodiments, machine learning may be used to determine possible outcomes of the release of the stored energy in the test cases. For example, reinforcement learning (a type of machine learning) analyzes the data and possible conclusions of the data. Reinforcement learning can utilize energy data (from IoT feeds) and historical data (e.g., from a knowledge corpus) and use the data to determine possible conclusions.

[0032] In some embodiments, predicting one or more background conditions (e.g., when using machine learning) includes collecting historical data from a knowledge corpus about damage caused by similar stored energy levels. The historical data may be used to learn and train a machine learning algorithm that predicts the background conditions. Once the historical data is collected, the system can then use the historical data to train a machine learning algorithm, and the machine learning algorithm (and the calculated amount of stored energy (e.g., from act 120)) can be used to determine potential damage from the release of the stored energy.

[0033] In some embodiments, the knowledge corpus includes historical data, such as data about the surrounding area. The knowledge corpus may also include external data about the surrounding area, including at least one of geological data, environmental data, and demographic data.

[0034] Method 100 includes operation 150, determining one or more impacts for each of one or more background conditions. The impacts may include any potential threats caused by the release of stored energy. In some embodiments, for each of the background conditions, one or more impacts for each object in the surrounding area (or, in some cases, each object having a concerning level of stored energy) are determined. In some embodiments, the one or more impacts may be determined using machine learning.

[0035] In some embodiments, determining the one or more impacts includes running a simulation of each of the one or more background conditions. The simulation may simulate steps or events that occur when the stored energy is released. In some embodiments, determining the one or more impacts for each of the one or more background conditions further includes calculating a threat level for each object in the surrounding area (for each of the background conditions). The threat level may indicate a seriousness of a potential impact on the object due to the release of the stored energy. In some instances, the system may determine one or more impacts of the release of the stored energy for each object, and the threat level may indicate a seriousness for each of the one or more impacts. The threat level may be a number, a percentage, a decimal, a number / percentage / decimal range, a category, etc. For example, the threat level may be 8 (i.e., out of 10), 80%, 0.8, etc. In another example, the threat level may be a range that is 70-75% dangerous. In yet another example, the threat level may be a category such as slightly dangerous, moderately dangerous, very dangerous, etc. In some embodiments, the higher the threat level, the more severe (and in some cases, the more likely) the impact will be.

[0036] In some embodiments, calculating the threat level of each object in the surrounding area includes determining a possible release energy level of each object. The possible release energy level may be the most likely energy level (or range of energy levels) of the object to be released. In other words, the possible release energy level should correspond to the amount of stored energy that would likely be released if the object's stored energy were hypothetically released. In some embodiments, releasing the stored energy may release all of the object's stored energy. In some embodiments, only a portion of the object's stored energy is released. For example, a box that falls off a shelf would likely release all of its stored energy from the box. In some embodiments, objects close to the unique object may also be considered when calculating the threat level, since stored energy released from one object may be transferred to another object. For example, a spring may contract (increasing stored energy) and then stretch (releasing stored energy) back to its original shape. The spring may be connected to, or at least in close proximity to, another object, and when the spring stretches, the stored energy released during the stretching may be transferred to the other object. In some cases, the transfer of energy to a second object may cause impact and / or damage.

[0037] Calculating the threat level of each object may also include estimating the duration of the impact of a possible released energy level. Once it is determined how much energy may be released, it may be estimated how long the impact from the released energy level may last. The duration of the impact may help identify how great an effect the impact will have on the surrounding area, or objects in the surrounding area, or both. For example, a strong force applied over a short period of time (e.g., by impact) may have a high effect, and a strong force applied over a long period of time may have an even higher effect. However, a weaker force applied over a longer period of time may have a lesser effect on the surrounding area, even though the impact duration may be longer. Thus, the possible released energy level may be reviewed along with the duration of the impact when determining the threat level.

[0038] Calculating the threat level of each object can also include estimating potential damage from possible released energy levels. Estimating the potential damage can include analyzing the duration of the impact and the possible released energy levels and determining the potential damage using the analysis. In some embodiments, test cases can be run using the possible released energy levels and the duration of the impact to estimate the potential damage.

[0039] In some embodiments, calculating the threat level of each object includes estimating a recovery time. The recovery time may be the time to recover from potential damage. In some instances, the recovery time from damage may be very quick, even though the potential damage from possible energy release levels may be high. For example, a pipe may become detached from another pipe due to the release of stored energy within the pipe. Even though the pipes may become completely detached, repairing the pipes may simply involve reattaching them and no other repairs / replacements are necessary. Thus, in this example, the recovery time from the release of stored energy may be short. The recovery time may be determined in some instances through running test cases and utilizing machine learning.

[0040] In some embodiments, the threat level is calculated by correlating (and possibly weighting) various factors (i.e., at least the likely energy release level, the duration of the impact, the potential damage, and the recovery time).

[0041] In some embodiments, determining one or more effects on each of the one or more background conditions in response to calculating a threat level for each object in the surrounding area can include determining that one or more objects in the surrounding area breach a threshold threat level. Determining that one or more objects breach a threshold threat level can include determining that the threat level of the objects breaches a threshold threat level. The threshold threat level may be determined using historical data from a knowledge corpus. In some embodiments, the threshold threat level indicates a maximum or near-maximum threat level at which no negligible damage can occur due to the release of stored energy. Thus, in some embodiments, after the threshold threat level is achieved and / or breached, there may be a possibility of negligible damage due to the release of stored energy.

[0042] In some embodiments, a user may determine the threshold threat level. For example, some users may desire a threshold threat level where there is no damage, and therefore damage may be more likely to occur only if the threshold threat level is breached. In another example, a user may desire the threshold threat level to be relatively high, for example when the result of the stored energy being released is an earthquake, and therefore breaching the damage threshold may indicate huge potential damage from the earthquake. Since earthquakes may have the potential to cause a large amount of damage, if the threshold threat level was low, there could be a large amount of potential impacts that breach the threshold threat level, and therefore the most serious potential impacts may be potentially lost within a large amount of other potential impacts.

[0043] In some embodiments, predicting the one or more background conditions includes determining, for each of the one or more background conditions, the result of releasing the stored energy of at least one or more objects in the surrounding area that breach a threshold threat level. In some cases, the determination may be based on the surrounding area and the one or more objects. Once it is determined that the threat level and the corresponding objects may breach the threshold threat level, it may be determined what will happen to each object that breaches the threshold threat level (i.e., what the result will be) when the stored energy is released. For example, returning to the forklift example, a large box lifted by the forklift may have the potential to fall off the forklift (e.g., when the forklift is at a high height), creating a threat that exceeds the threshold threat level (e.g., the contents of the box may be destroyed, the box may fall on another object and destroy the other object, the box may fall on a human and pose a threat to the human, etc.). Even though the box may have an impact far beyond the threshold threat level, the release of stored energy for the box may merely cause the box to move on the forklift, likely resulting in minimal to no damage to either the box or the forklift, or any other nearby objects. In this example, it may be determined that the result of releasing stored energy for one context is the box falling off the forklift. In this instance, the box falling off the forklift may breach the threshold threat level for the box. In other examples, when the context may simply result in the box moving on the forklift, the box may not breach the threshold threat level, and in some instances this context may not be considered when determining the impact for each of the contexts.

[0044] In some embodiments, determining the one or more effects for each of the one or more contextual conditions is performed on an augmented reality device. The augmented reality device can simulate various test cases and predict the effects based on the test cases. In some embodiments, determining the one or more effects is performed utilizing an augmented reality device. For example, data collected from the AR device and IoT feeds may be used when simulating the various contextual conditions and predicting the effects. In some embodiments, machine learning and artificial intelligence techniques are used to train the simulation algorithms and continually improve the predictions and decisions.

[0045] In some embodiments, the method 100 includes determining a probability of occurrence of each of the one or more background conditions. The probability of occurrence may be the probability that the unique background condition may occur. In some embodiments, the probability is expressed as a percentage. In some embodiments, the probability is expressed as a decimal system. In some embodiments, determining the probability of occurrence of each of the one or more background conditions may include determining all possible outcomes of each of the one or more background conditions. Then, in some embodiments, the outcome of the release of stored energy of at least one or more objects in the surrounding area breaching a threshold threat level (discussed above) may be compared to the total amount of possible outcomes of each of the one or more background conditions to determine the probability of occurrence.

[0046] Method 100 includes operation 160, which calculates the severity of an impact of each of one or more background circumstances. A severity (indicating how severe or damaging the impact may be) may be determined for each individual background circumstances. In this manner, unique background circumstances that have the potential for increased impact may be identified and highlighted. In some embodiments, calculating the severity of the impact includes determining the impact that occurs for the unique background circumstances (e.g., via simulation using an algorithm determined / formed through machine learning). In some cases, calculating the severity may include comparing the impact for each unique background circumstances to the impact for other background circumstances, such that the severity may indicate the severity of the impact compared to other impacts (from other background circumstances). In some embodiments, multiple factors (such as the nature of the impact on the background circumstances, the spread of the impact, the duration of the impact, etc.) may be considered (and possibly weighted) when calculating the severity.

[0047] In some cases, the threat level of each object may be used to determine the severity. In some embodiments, determining the severity of the impact on the background situation includes summing each threat level of each object in the background situation. In some cases, the sum of the threat levels may be the severity. In some embodiments, the severity is an average of the threat levels of each object in the background situation. In some embodiments, the severity corresponds to the highest threat level of the background situation.

[0048] Method 100 includes operation 170, determining whether the severity indicates that the potential impact of the release of stored energy in the surrounding area is severe. In some instances, a threshold severity value may be determined (e.g., through machine learning, pre-determined by a user, etc.) and any severity equal to or greater than the severity may be determined to be severe. For example, the severity may be a number from 1 to 10. Specifically, in this example, the severity may be determined to be 6. Since the threshold severity value may be 7, when comparing the severity to the threshold, it may be determined that the potential impact for a particular severity (and particular contextual circumstances) may not be severe. In some embodiments, the severity may be categorical (e.g., mild, moderate, severe, very severe, etc.) and any severity with a severe or very severe category may indicate that the potential impact is severe.

[0049] In some embodiments, operation 170 is repeated for each context and its corresponding severity. There may be numerous objects with stored energy in the surrounding area, and numerous contexts with each object and that could potentially occur if the stored energy were released. The severity of each context may need to be considered to determine which context is most important to prevent. In some embodiments, the threshold severity value is the same for each context. For example, the threshold severity value may be 7 (or a category of serious, for example) for every context. In some embodiments, the threshold severity value may be unique for each context. In some embodiments, the threshold severity value may not be unique for every context, but may be unique for each object. For example, if a box were to fall from a forklift, the box would come into contact with the floor. Both the box and the floor would be considered objects, but the box may have a lower threshold severity value than the floor, since the box may be much more susceptible to damage than the floor.

[0050] If the severity of the background condition is determined to be not serious at operation 170, method 100 may review the severity of other background conditions at operation 175 and then return to operation 170 to determine whether the severity of the other background conditions is serious. As described above, operation 170 may be repeated for each background condition. If the severity of the background condition is not serious, the severity of the other background conditions may be reviewed to check whether any of the other background conditions, and their corresponding severity, are serious.

[0051] In some embodiments, if none of the severities are determined to be severe, method 100 may end after operations 170 and 175 (not depicted).

[0052] Returning to operation 170, if the severity of at least one background situation is determined to be severe, method 100 proceeds to operation 180 to determine one or more proposed solutions based on the severity. In some embodiments, machine learning techniques (such as reinforcement learning) may be used to determine or predict one or more proposed solutions. Reinforcement learning may determine actions to be taken in the environment to maximize rewards (in this case, to reduce or remove the impacts that cause higher severity). Reinforcement learning may be a goal-focused algorithm that focuses on the goal of minimizing impacts and learning the best possible actions (i.e., proposed solutions) to achieve said goal. In some embodiments, determining one or more proposed solutions is also based on the probability of occurrence.

[0053] In some embodiments, determining the one or more proposed solutions may include running a simulation (e.g., an AR-based simulation) and then, based on the simulation, identifying a safety factor of release of stored energy such that an impact or at least a severe impact cannot occur. The proposed solution may include a guide on how to achieve the safety factor of release of stored energy. In some embodiments, determining the one or more proposed solutions may include simulating a future effect if the selected solution is applied as a preventative measure. The future effect may be a new value of the stored energy level, a rate of change of the energy level over time, etc. In some embodiments, determining the one or more proposed solutions may include personalizing the recommendation through dynamic user profile synthesis. In some instances, a user (e.g., a user of an augmented reality device) may set up a user profile prior to using the device. The user profile may include user preferences for threshold amounts of severity, threat, etc. Additionally, the user profile may include historical data (including energy data) collected from previous usage of the device by the user.

[0054] Method 100 includes operation 190, transmitting a recommendation of at least one proposed solution (from the one or more proposed solutions) for implementation. In some embodiments, all proposed solutions determined in operation 180 may be transmitted as recommendations. In some embodiments, only the best proposed solution (e.g., the proposed solution that produces the least impact) may be transmitted as a recommendation for implementation. In some embodiments, transmitting the recommendation may include simulating (on an AR device) a background situation along with the proposed solution. In some cases, there may be a separate simulation for each transmitted recommendation. In some embodiments, transmitting the recommendation may include depicting a predicted future effect if at least one proposed solution is applied. The predicted future effect may be depicted through an augmented reality device, and in some cases, the future effect may be depicted as a simulation. The simulation may include showing a future effect if the recommended solution is implemented.

[0055] 2, a schematic diagram of an example augmented reality environment 200 is depicted, according to some embodiments. The augmented reality environment 200 includes an AR device 210. In this instance, the AR device 210 is AR glasses, but the AR device 210 may be any device with AR capabilities. In some embodiments, the AR device 210 is worn by a user (not depicted).

[0056] In some embodiments, the AR device 210 collects data about the surrounding area and transmits the data to a computer system (e.g., system 300 (FIG. 3) or system 400 (FIG. 4) or both). The data may be transmitted as an IoT feed and then aggregated by the computer system (e.g., in operation 110 of FIG. 1). In some embodiments, the computer system may then calculate (e.g., in operation 120 of FIG. 1) an amount of stored energy in the surrounding area based at least on the data collected by the AR device 210. In some embodiments, the computer system may simulate the background conditions using the AR device 210 to predict one or more background conditions (e.g., in operation 140 of FIG. 1).

[0057] 2, the AR device 210 can display an AR simulation 220 of the potential effects if the stored energy is released. In some embodiments, the AR simulation 220 is a simulation of a background.

[0058] In the surrounding area (as depicted in AR simulation 220), two individuals, person 224 and person 226, are swinging on a set of swings 222. In this example surrounding area, the swing being used by person 226 may have a broken string. Using a computer system (e.g., system 300 (FIG. 3) or system 400 (FIG. 4) or both) and method 100 (FIG. 1)), it may be determined that when the swing strings are pulled taut, they store potential energy, and when the strings are slack, the stored potential energy may be released. Based on this determination, the computer system may use AR device 210 to predict, via simulation, a background situation of what may occur if the stored energy is released. In the particular AR simulation 220 (i.e., background situation), if the stored energy is released and the strings snap / break, person 226 may fall off the swing. A person 226 falling off the swing may be an effect on the context of the AR simulation 220 (e.g., as determined in operation 150 of FIG. 1 ). The AR simulation 220 may depict the potential effect by showing a person 226a stationary on the swing, a person 226b in the air after falling off the swing (after the straps come slack), and a person 226c on the ground after falling off the swing.

[0059] In some embodiments, a threat level of the person 226 (objects in the surrounding area) may be determined when determining the impact on the background situation depicted in the AR simulation 220. Falling off the swing may be determined to be likely to injure the person 226, and therefore the person 226 may have a high threat level. Additionally, in some embodiments, the overall severity of the background situation depicted in the AR simulation 220 may be determined by the computer system. The severity may be determined using at least the threat level of the person 226, the threat level of the person 224, and the threat level of both swings as these are all objects in the background situation of the AR simulation 220. In some instances, the severity of the background situation of the AR simulation 220 may be determined to be severe because the person 226 is the only object with a high threat level.

[0060] In some embodiments, there may be other scenarios (not depicted) that may occur if the stored energy is released and the swing cord becomes loose. For example, instead of the person 226 falling in the direction depicted in the AR simulation 220 (going from position 226a to 226b to 226c), the person 226 may fall in the direction of the person 224. In this scenario, both the person 226 and the person 224 may have a high threat level because the swing may come loose and the person 226 may fall off the swing, causing both the person 226 and the person 224 to be injured. For example, the person 226 may fall on the person 224. The overall severity of this scenario (not depicted) may be very serious because both the person 226 and the person 224 may have a high threat level.

[0061] In some embodiments, the AR device 210 may be worn by a user and the AR simulation 220 may be shown to the user. In some embodiments, the AR simulation 220 (not depicted) may also display potential solutions (e.g., determined in act 180 of FIG. 1 and transmitted to the AR device 210 in act 190) for preventing the simulated effects on the background situation shown in the AR simulation 220. For example, if the swing is gradually coming down due to gravitational forces (rather than from the energy exerted by the person 226 as he or she moves their legs up and down while swinging), it may be determined that the accumulated potential energy is slowly converted to kinetic energy to prevent the swing from coming loose. In other words, if the person stops moving their legs up and down and simply allows gravitational forces to determine the action of the swing, the swing will slowly stop and prevent the person 226 from falling. The AR simulation 220 may display this recommendation to the user of the AR device 210.

[0062] Referring to FIG. 3, a block diagram of a first illustrative computer system 300 according to some embodiments is depicted. In some embodiments, the computer system 300 can execute the method 100 (FIG. 1). The computer system 300 includes a sensor 310, an artificial intelligence (AI) system 320, and an augmented reality (AR) device 330. In some embodiments, the sensor 310 includes one or more IoT devices / sensors that collect data about the surrounding area. The sensor 310 can transmit an IoT feed to the AI ​​system 320. In some embodiments, the AI ​​system 320 performs the operations (i.e., 110-190) of the method 100 (FIG. 1). Components of the AI ​​system are discussed further herein and depicted in FIG. 4. The AI ​​system may be an artificial intelligence system, or a system having artificial intelligence (e.g., neural networks and machine learning) capabilities, or both. In some embodiments, the AI ​​system 320 determines the impact of releasing the stored energy and uses machine learning to predict potential solutions to eliminate or at least minimize the potential impact. The effects and / or solutions may be transmitted to and simulated at the AR device 330, which may allow the user to see (through the AR device 330) a simulation of the effects of the release of stored energy, along with, in some cases, a potential solution. Example simulations are discussed herein and depicted in FIG.

[0063] Although the sensor 310, the AI ​​system 320, and the AR device 330 are depicted as separate components of the system 300 in FIG. 3, in some instances, these components may be integrated. For example, the AR device 330 may be part of the AI ​​system 320.

[0064] 4, a schematic diagram of a second example computer system 400 is depicted in accordance with some embodiments. In some embodiments, computer system 400 is capable of performing method 100 (FIG. 1). Computer system 400 includes sensor 405, sensor 410, and sensor 415. Although three sensors are depicted, computer system 400 may include any number of sensors. In some embodiments, sensors 405, 410, and 415 correspond to sensor 210 (FIG. 2).

[0065] Computer system 400 includes AI system 420. In some embodiments, AI system 420 corresponds to AI system 320 (FIG. 3). As depicted in FIG. 4, AI system 420 includes data fusion module 421, machine learning module 423, simulation module 425, and knowledge corpus module 427. Knowledge corpus module 427 can include a knowledge corpus having historical data about stored energy levels, objects in the surrounding area, damage, etc. In some embodiments, data fusion module 421 performs at least operation 110 (FIG. 1). Data fusion module 421 can receive IoT feeds from sensors 405, 410, and 415 and can fuse or aggregate the IoT feeds. In some embodiments, data fusion module 421 sends the IoT feeds, or at least a copy of the IoT feeds, to the knowledge corpus.

[0066] In some embodiments, the machine learning module 423 performs at least operations 120-175 (FIG. 1). In some embodiments, a simulation module 425 (having simulation capabilities) can assist in performing at least some of the operations. The simulation module 423 can receive historical data from the knowledge corpus module 427, and can use the historical data to learn and / or train the machine learning algorithms used in the machine learning module 423. For example, when predicting a background situation due to the release of stored energy (e.g., operation 140 (FIG. 1)), the machine learning module 423 can gather historical data about damage and events caused by similar stored energy levels from the knowledge corpus of the knowledge corpus module 427. The machine learning module 423 can then use the historical data to train the machine learning algorithms, and can use the machine learning algorithms (and the calculated amount of stored energy (e.g., from operation 120 (FIG. 1))) to determine the potential damage due to the release of stored energy.

[0067] In some embodiments, the knowledge corpus module 427 includes historical data, such as data about the surrounding area. The knowledge corpus module 427 may also include external data about the surrounding area, including at least one of geological data, environmental data, and demographic data. The historical data may be used by the machine learning module 423.

[0068] In some embodiments, the machine learning module 423 communicates the results of the machine learning to the simulation module 425. In some embodiments, the simulation module 425 can perform at least operations 180 and 190 (FIG. 1). The simulation module 425 can have simulation capabilities and can simulate various test cases and background situations. In some embodiments, the machine learning module 423 and the simulation module 425 are in constant communication and the simulation module 425 can frequently simulate various potential effects, etc., as determined by the machine learning module 423.

[0069] The computer system 400 further includes an AR device 430. In some embodiments, the AR device 430 may be AR glasses, as depicted in FIG. 4. In some embodiments, the AR device may be a tablet, or any other type of mobile / portable device, or both. In some embodiments, the simulation module 425 may transmit the simulation to the AR device 430, which allows a user to view the simulation in augmented reality. FIG. 2 depicts an example AR simulation.

[0070] 5, computer system 500 is a computer system / server 502 shown in the form of a general purpose computing device according to some embodiments. In some embodiments, computer system / server 502 is located on a linking device. In some embodiments, computer system 502 is connected to a linking device. Components of computer system / server 502 may include, but are not limited to, one or more processors or processing units 510, a system memory 560, and a bus 515 that couples various system components, including system memory 560, to processor 510.

[0071] Bus 515 may represent any one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures, including, by way of example and not limitation, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MCA) bus, an Enhanced ISA (EISA) bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0072] Computer system / server 502 typically includes a variety of computer system readable media. Such media may be any available media that can be accessed by computer system / server 502, and includes both volatile and nonvolatile media, removable and non-removable media.

[0073] The system memory 560 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 562 and / or cache memory 564. The computer system / server 502 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, a storage system 565 may be provided for reading and writing non-removable non-volatile magnetic media (not shown, but typically referred to as a "hard drive"). Although not shown, a magnetic disk drive may be provided for reading and writing removable non-volatile magnetic disks (e.g., "floppy disks"), and an optical disk drive may be provided for reading and writing removable non-volatile optical disks, such as CD-ROMs, DVD-ROMs, or other optical media. In such instances, each may be connected to the bus 515 by one or more data media interfaces. As further depicted and described below, the memory 560 may include at least one program product having a set (e.g., at least one) of program modules configured to perform functions of embodiments of the present disclosure.

[0074] The programs / utilities 568 have a set (at least one) of program modules 569, which may be stored in the memory 560, as well as, by way of example and not limitation, an operating system, one or more application programs, other program modules, and program data. Each of the operating system, one or more application programs, other program modules, and program data, or some combination thereof, may include an implementation of a networking environment. The program modules 569 generally perform the functions and / or methods of embodiments of the present invention as described herein.

[0075] The computer system / server 502 may also communicate with one or more external devices 540, such as a keyboard, pointing device, display 530, one or more devices that allow a user to interact with the computer system / server 502, or any device that allows the computer system / server 502 to communicate with one or more other computing devices (e.g., network card, modem, etc.), or a combination thereof. Such communication may occur via an input / output (I / O) interface 520. Additionally, the computer system / server 502 may communicate with one or more networks, such as a local area network (LAN), a general wide area network (WAN), or a public network (e.g., the Internet), or a combination thereof, via a network adapter 550. As depicted, the network adapter 550 communicates with other components of the computer system / server 502 via a bus 515. It is understood that other hardware and / or software components, not shown, may be used with the computer system / server 502. Examples include, but are not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archive storage systems.

[0076] The present invention may be a system, method, or computer program product, or combination thereof, at any possible level of technical detail of integration. The computer program product may include a computer-readable storage medium (or media) having computer-readable program instructions for causing a processor to carry out aspects of the present invention.

[0077] A computer readable storage medium can be a tangible device capable of holding and storing instructions for use by an instruction execution device. A computer readable storage medium can be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of computer readable storage media includes the following: portable computer diskettes, hard disks, random access memory (RAM), static random access memory (SRAM), portable compact disk read only memory (CD-ROM), digital versatile disks (DVD), memory sticks, floppy disks, mechanically encoded devices such as punch cards or ridge-in-groove structures having instructions recorded thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein should not be interpreted as signals that are transitory in nature, such as electric waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., light pulses passing through a fiber optic cable), or electronic signals transmitted through wires.

[0078] The computer readable program instructions described herein can be downloaded from a computer readable storage medium to each computing / processing device or to an external computer or storage device over a network, such as the Internet, a local area network, a wide area network, or a wireless network, or a combination thereof. The network can comprise copper transmission cables, optical transmission fiber, wireless transmission, routers, firewalls, switches, gateway computers, or edge servers, or a combination thereof. A network adapter card or network interface in each computing / processing device receives the computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium in the respective computing / processing device.

[0079] The computer readable program instructions for carrying out the operations of the present invention may be source or object code written in any combination of one or more programming languages, including assembler instructions, instruction set architecture (ISA) instructions, machine language instructions, machine dependent instructions, microcode, firmware instructions, state setting data, configuration data for integrated circuit devices, or object oriented programming languages ​​such as Smalltalk®, C++, or the like, and procedural programming languages ​​such as the “C” programming language or similar. The computer readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (e.g., through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, a programmable logic device, a field programmable gate array (FPGA), or a programmable logic array (PLA) can execute computer readable program instructions by utilizing state information of the computer readable program instructions to individualize the electronic circuitry to perform aspects of the present invention.

[0080] Aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer readable program instructions.

[0081] These computer-readable program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, produce means for performing the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams. These computer-readable program instructions may also be stored on a computer-readable storage medium, such that the instructions direct the computer, programmable data processing apparatus, and / or other device to function in a particular manner, such that the computer-readable storage medium having the instructions stored thereon comprises an article of manufacture including instructions that perform aspects of the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams. The computer-readable program instructions may also be loaded into the computer, other programmable data processing apparatus, or other device, such that the instructions, which execute on the computer, other programmable apparatus, or other device, perform a series of operational steps on the computer, other programmable apparatus, or other device to produce a computer-implemented process, such that the instructions, which execute on the computer, other programmable apparatus, or other device, perform the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams.

[0082] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to some embodiments of the present invention. In this regard, each block in the flowcharts or block diagrams may represent a module, segment, or portion of instructions, which includes one or more executable instructions for performing a specified logical function. In some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may in fact be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order depending on the functionality involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or acts or executes a combination of dedicated hardware and computer instructions.

[0083] The description of various embodiments of the present disclosure has been presented for illustrative purposes, but is not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope of the described embodiments. The terms used in this specification have been selected to best explain the principles of the embodiments, practical applications, or technical improvements to the technology found in the market, or to allow those skilled in the art to understand the embodiments disclosed herein.

Claims

1. 1. A computer-implemented method comprising: aggregating IoT feeds from one or more devices in a surrounding area; Calculating an amount of stored energy in the surrounding area based on the IoT feed; and predicting one or more contextual conditions that may result from a release of the stored energy by simulating potential impacts of the release of the stored energy in the surrounding area using augmented reality; determining one or more effects for each of the predicted one or more context conditions, the one or more effects being caused by the predicted one or more context conditions; calculating a severity of the one or more effects for each of the one or more background conditions; determining one or more proposed solutions based on said severity; For implementation, transmitting a recommendation of at least one proposed solution from the one or more proposed solutions, wherein the one or more proposed solutions are displayed through virtual reality. Including, Determining the one or more effects on each of the one or more predicted background conditions, performing a simulation of each of the predicted one or more background conditions; calculating a threat level for each object in the surrounding area for each of the predicted one or more background conditions, the threat level indicating the severity of a potential impact of the object from the release of the stored energy; Including, Computer-implemented method.

2. predicting the one or more background conditions that may result from the release of the stored energy; collecting historical data from a knowledge corpus about at least the events and damage caused by similar stored energy levels; training a machine learning algorithm using the historical data; and using the machine learning algorithm and the calculated amount of stored energy to determine potential events caused by a release of the stored energy; The method of claim 1 , comprising:

3. The method of claim 2 , wherein the historical data includes data regarding the surrounding area.

4. The method of claim 3 , wherein the historical data further comprises external data including at least one of geological data, environmental data, and demographic data.

5. Determining the one or more effects on each of the one or more background conditions determining, in response to said calculating, that one or more objects in said surrounding area breach a threshold threat level; determining, for each of the one or more background conditions, a consequence of the release of the stored energy of at least the one or more objects in the surrounding area breaching the threshold threat level; The method of claim 1 further comprising:

6. calculating the threat level of each object in the surrounding area; determining the possible release energy level of each object; estimating the duration of impact of said possible released energy level; and estimating potential damage from said possible energy release levels; and estimating a recovery time, the recovery time being a time to recover from the potential damage; The method of claim 5 , comprising:

7. The method of claim 1 , wherein the determining of the one or more effects on each of the one or more background conditions is performed in an augmented reality device.

8. aggregating IoT feeds from the one or more devices in the surrounding area; receiving one or more IoT feeds from the one or more devices; analyzing the one or more IoT feeds; collecting energy data from the one or more IoT feeds; The method of claim 1 , comprising:

9. the one or more IoT feeds are received from an augmented reality device; The one or more IoT feeds are analyzed using video and image analysis techniques. The method according to claim 8.

10. Transmitting at least one proposed solution recommendation; Depicting the expected future effects of applying said at least one proposed solution; The method of claim 1 , comprising:

11. The method of claim 10 , wherein the predicted future effects are depicted through an augmented reality device.

12. 1. A system having one or more computer processors, comprising: aggregating IoT feeds from one or more devices in a surrounding area; Calculating an amount of stored energy in the surrounding area based on the IoT feed; and predicting one or more contextual conditions that may result from a release of the stored energy by simulating potential impacts of the release of the stored energy in the surrounding area using augmented reality; determining one or more effects for each of the predicted one or more context conditions, the one or more effects being caused by the predicted one or more context conditions; calculating a severity of the one or more effects for each of the one or more background conditions; determining one or more proposed solutions based on said severity; For implementation, transmitting a recommendation of at least one proposed solution from the one or more proposed solutions, wherein the one or more proposed solutions are displayed through virtual reality. The device is configured to: Determining the one or more effects on each of the one or more background conditions performing a simulation of each of the predicted one or more background conditions; calculating a threat level for each object in the surrounding area for each of the predicted one or more background conditions, the threat level indicating the severity of a potential impact of the object from the release of the stored energy; Including, system.

13. predicting the one or more background conditions that may result from the release of the stored energy; collecting historical data from a knowledge corpus about at least the events and damage caused by similar stored energy levels; training a machine learning algorithm using the historical data; and using the machine learning algorithm and the calculated amount of stored energy to determine potential events caused by a release of the stored energy; The system of claim 12 , comprising:

14. Determining the one or more effects on each of the one or more background conditions determining, in response to said calculating, that one or more objects in said surrounding area breach a threshold threat level; determining, for each of the one or more background conditions, a consequence of the release of the stored energy of at least the one or more objects in the surrounding area breaching the threshold threat level; The system of claim 12 , comprising:

15. calculating the threat level of each object in the surrounding area; determining the possible release energy level of each object; estimating the duration of impact of said possible released energy level; and estimating potential damage from said possible energy release levels; and estimating a recovery time, the recovery time being a time to recover from the potential damage; The system of claim 14 , comprising:

16. aggregating IoT feeds from the one or more devices in the surrounding area; receiving one or more IoT feeds from the one or more devices; analyzing the one or more IoT feeds; collecting energy data from the one or more IoT feeds; The system of claim 12 , comprising:

17. A computer program causing one or more processors to carry out the method according to any one of claims 1 to 11.

18. A computer-readable recording medium having recorded thereon a computer program for executing the method according to any one of claims 1 to 11.

Images