How to detect an event or situation such as an attack

Abstract

The present invention relates to a method for detecting an event or situation occurring in the vicinity of at least a user, for example a valuable goods carrier, comprising: -) measuring values ​​of personal parameters associated with the user's body and / or environmental parameters associated with the user's environment; -) analysing the values ​​obtained by the measuring step against predetermined patterns, trends and / or ranges of values ​​over time; and -) determining, depending on the results of the analysis, whether the measured values ​​correspond to predetermined indicators of an event, wherein said indicators include at least first order indicators indicating a high probability of the event occurring and second order indicators indicating a relatively low probability of the event occurring.

Description

[Technical Field]

[0001] [Corresponding application] This patent application claims priority to European Patent Application Publication No. 22210863.1, filed December 1, 2022, by Connextivity Group S.A., the contents of which are incorporated by reference in their entirety into this PCT application.

[0002] The present invention relates to the field of methods for detecting events or situations, such as attacks, and devices suitable for such methods.

[0003] More particularly, the present invention relates particularly, but not exclusively, to the field of valuables and cash transportation and to methods that can be used to protect and assist carriers in the event of an attack. [Background technology]

[0004] Despite the increasing use of electronic payment methods and other technological instruments for this purpose (e.g. credit or debit cards, mobile payments), large amounts of cash are still transported in vehicles, making this cash a target for malicious actors.

[0005] Although certain technological measures have been used to protect banknotes and similar products (e.g., systems that mark stolen banknotes with distinctive ink if the containers carrying them are forced open), cash carriers are one of the weak links in cash transport security, and therefore, fast and reliable detection of theft-intended attacks on cash carriers is a long-felt need in the cash transport industry. Moreover, over 95% of attacks occur when carriers are outside their vehicles in collection / delivery areas. However, attacks can also be carried out against moving vehicles, forcing them to stop or take a route that deviates from the planned one.

[0006] During an actual attack, cash carriers experience extreme panic or fear, which triggers a physical reaction commonly known as the stress response, which increases the carrier's ability to avoid the attack, fight, or flee; in such cases, the carriers typically forget to follow established rules due to stress and / or may be unable to act appropriately or may be incapacitated or unable to take further action, for example, due to a direct threat from the robber or the need to take other urgent action (e.g., flee in life-threatening situations, respond to a firearm from the robber). Such a physical stress response reaction is hereinafter referred to as high acute stress.

[0007] Attacks also occur while the vehicle is in motion, and primarily in rural areas, which leads to abnormal driving situations when the vehicle is being followed or forced to stop or is trying to escape an attack. All of these reactions are deviations from the normal progression and expected situation or movement of the carrier.

[0008] It has also been found that in many cases, robbery attacks are made possible due to the presence of an "insider," for example, because the carrier is an accomplice or has advance knowledge that a robbery will be carried out. In fact, the route or path and / or timing to be taken by a carrier in a certain vehicle is typically not known until the last moment in order to avoid the preparation of a robbery on a given route at a given moment. Thus, when an attack occurs, it is often because someone has provided the attacker with information about the transport route and times, and this person can only be an "insider," since such plans are kept secret and communicated only at the last minute.

[0009] Such insiders are expected to exhibit (for example) feelings of fear, foreboding, tension, and guilt prior to an attack, i.e., minutes, hours, or days before the event occurs. Thus, changes in a user's daily physical stress response patterns can be detected through a combination of continuous measurement / analysis over days and weeks to identify complicit actors in a situation. Such physical stress responses over time are hereinafter referred to as a user's stress trend over time.

[0010] Angelica Reyes-Munoz et al., "Integration of Body Sensor Networks and Vehicular Ad-hoc Networks for Traffic Safety," SENSORS, vol. 16, no. 1, January 15, 2016 (2016-01-15), p. 107, XP055394143, DOI: 10.3390 / S16010107, discloses a body sensor network for monitoring a person's vital signs, which is used to detect four behavioral states: drowsiness, intoxication, driving under emotional disturbance, and distracted driving. This prior art refers to increased activation of the parasympathetic nervous system and loss of activation of the sympathetic nervous system, which manifests as a decrease in coordination and safe driving ability. In contrast, in the present invention, at the time when a carrier is considered to be driving, the intended detection refers to a state of sympathetic nervous system activation to enhance the carrier's ability to avoid robbery, i.e., a fight-or-flight response: in times of danger, the body prepares itself and becomes more aware of its surroundings. Therefore, the intended detection of the driver's state is a conflicting behavioral state.

[0011] Similar to the above publication, US Pat. No. 10,912,509 discloses a portable intelligent driver health monitoring system for road safety.

[0012] US Patent Application Publication No. 2005 / 0195079 discloses an emergency situation detector for subjects such as security guards, pilots, firefighters, etc. It includes a threshold operated detector that uses physiological sensors to detect voice input as well as stress, location sensors, and vehicle sensors to infer the existence of an emergency situation.

[0013] Thus, while prior art publications disclose the use of stress response inputs or vehicle sensors to identify driver behavior that is inappropriate for road safety, the present invention instead aims to identify, among other purposes, individuals who appear to be driving aggressively when the attacker forces the vehicle to stop and deviate from its route.

[0014] The current situation and technical means for protecting against such attacks / robberies and for reacting quickly to said events are insufficient and there is a need in the field under consideration for improved methods and devices that allow for simple, fast and efficient detection of attacks.

[0015] There is also a need to be able to detect dishonest individuals, such as inside informants as defined herein.

[0016] There is a further need to tailor the system to the user and their daily activities so that events such as the occurrence of an attack can be better detected. [Prior art documents] [Patent documents]

[0017] [Patent Document 1] U.S. Patent No. 10,912,509 [Patent Document 2] US Patent Application Publication No. 2005 / 0195079 [Non-patent literature]

[0018] [Non-Patent Document 1] Angelica Reyes-Munoz et al. "Integration of Body Sensor Networks and Vehicular Ad-hoc Networks for Traffic Safety", SENSORS, vol. 16, no. 1, January 15, 2016 (2016-01-15), 107 pages, XP055394143, DOI: 10.3390 / S16010107 Summary of the Invention [Problem to be solved by the invention]

[0019] Accordingly, it is an object of the present invention to improve upon the methods and means known in the art.

[0020] More specifically, it is an object of the present invention to provide methods and means to assist carriers in the event of an attack or other event and to automatically accomplish certain actions, such as sending notifications and data to a control center, without requiring carrier intervention.

[0021] Another object of the present invention is to more accurately detect abnormal events or parameters and to enable certain actions to be taken when such abnormal events or parameters are detected.

[0022] It is a further object of the present invention to improve the detection process by learning and avoiding errors.

[0023] Another purpose is to aid in the detection of "insider informants," as mentioned above, which are dishonest people from the inside who provide information to attackers.

[0024] In an embodiment, the present invention preferably focuses on the detection of specific events, such as attack detection for valuable goods carriers.

[0025] Although the body's physiological stress response is used as one measurement, in embodiments the method is used to detect panic situations during an attack. The method can also use a combination of continuous measurements / analysis of the user (detecting fear / premonition / tension / guilt) before the robbery occurs to identify accomplices in this situation.

[0026] Preferably, in some embodiments, all sensors used in the methods of the present invention are installed by the user (e.g., the carrier). In other embodiments, some of the sensors and detectors may originate from the carrier's environment (from the company's premises, vehicles, customer premises, or roads used, such as from fixed cameras used for traffic control, vehicle license plate reading, or street safety control). All such data from the sensors can be used to improve detection methods and algorithms.

[0027] In some embodiments, the method uses a personalized / general monitoring method to detect the presence of various indicators [events] within a time window. Different events that may occur towards the approach of a burglar can also be monitored.

[0028] For example, in some embodiments, once an event is detected and recognized (or identified), the system may activate an alarm at a remote site and / or trigger some other action at the site (such as sirens, recording the carrier's environment, disabling portions of the vehicle and blocking doors closed, shutting down the engine, marking banknotes or other transported goods with ink, glue, or other security measures, etc.) without requiring any specific action by the carrier that is the victim of the attack.

[0029] One idea of ​​the present invention is to use an algorithm to measure the values ​​of certain parameters and determine whether the time trends of the measurements correspond to a normal pattern, preferably the time trends of various indicators, for example in the last seconds or minutes before an event, or the duration of certain parameters over time and / or once an event is detected and / or after a detected event.

[0030] If a value or values ​​do not correspond to normal values / ranges / trends / patterns, the algorithm will detect (or identify or recognize) some predetermined abnormal situation, which in turn will trigger some predetermined response.

[0031] In some embodiments, the algorithm may be able to learn over time (e.g., adapt to normal values ​​for each user) and more accurately detect trends in abnormal or out-of-range values / parameters for each user, where the values ​​are individual (associated with each user) and not absolute.

[0032] The measured parameters are preferably personal parameters (e.g. physical or physiological) of the user, e.g. the carrier. Movement parameters (e.g. related to movement or lack thereof, unexpected acceleration or the environment, i.e. increased temperature, increased noise, e.g. shouting, explosions, impacts, etc., unplanned routes, etc.) may also be added.

[0033] At a general level, an attack detection algorithm is based on monitoring certain events (e.g., highly anomalous events called first-order indicators or a combination of secondary anomalous events called second-order indicators) or a set of certain events occurring within a certain time period (e.g., the last moment). Once a detection occurs, the system activates an alert to a remote control center so that action can be initiated immediately and preferably automatically.

[0034] "Indicators of aggression" are calculated to detect anomalous events with a high probability of occurrence before and during an attack and correspond to the values ​​or parameters described above. Such indicators include, for example (non-exclusive list): detection of high acute stress (i.e., extreme reactions of panic or fear) through increased heartbeat interval variability; cardiovascular markers related to pulse wave; skin and core body temperature; respiratory rate; skin conductance response; and sweat levels; aggressive driving; physical activity; and sudden stops classified as suspicious based on historical geolocation (outside of known safe areas) due to user location; vehicles outside of the normal route; noise; impacts; etc. Many other indicators are possible within the scope of the present invention to detect anomalies that exceed normal (or expected) value ranges or trends for the user or their surroundings. The parameters described above for detecting high acute stress may also be used alone as indicators of an attack or another event to be detected, depending on the application in which the method of the present invention is used.

[0035] "Indicators of attack" may also be used to detect when an attack is about to occur. The physiological parameters referred to herein may be different if the subject knows that a robbery is about to occur, and thus may help improve security by generating some specific actions in anticipation of preventing the robbery, i.e., additional plan changes, cancellation of transportation, changes in route or timing, reconnaissance of the planned route with environmental detectors to detect unusual presences or obstacles, etc.

[0036] Features and embodiments of the present invention are set forth in detail in the following description thereof and in the appended claims.

[0037] Although this specification is primarily concerned with detecting attacks on carriers transporting valuable goods, the invention is not limited to this application, and the principles are applicable to other applications in which personal parameters (associated with a person or user) and external parameters (related to the user's environment) are analyzed by algorithms to detect certain events or situations related to the user.

[0038] For example, high acute stress detection: a common field of use is to measure a person's acute stress level and to detect whether there is a risk to the proper performance of a given task, primarily for critical tasks such as: -) First responders (doctors) in situations where lives are often at risk; -) Doctors, for example before surgery or in emergency rooms; -) Police: for example, during investigative activities or pursuits; -) Firefighters, in cases of emergencies involving fire or chemicals, etc.; -) Aircraft pilot (e.g. commercial or military); -) racing drivers (e.g. car racing); -) soldiers (e.g., during training or combat operations); -) Astronauts (e.g., during training or during a real mission); -) Logistics: For example, if you suspect that a worker driving a vehicle carrying goods may become ill or try to steal goods.

[0039] Detection of abnormal driving or behavior: A common application area is to assess any abnormalities in the driving of a given user (too slow, fast, erratic, unusual or incorrect trajectory...) or in the behavior of a person that may affect the success of a mission.

[0040] (High Acute Stress: Abnormal Driving Detection; Unknown Stops and Route Changes) Attack Detection: -) Transporting valuables -) Prisoner transport -) VIP transportation -) Hijacking of a transport (e.g., an airplane).

[0041] All these applications are examples and should not be considered limiting: other equivalent applications are possible within the scope of the invention.

[0042] In an embodiment, the present invention provides a method for detecting an event or situation occurring in the vicinity of at least a user, for example, a valuable goods carrier, comprising: -) measuring values ​​of personal parameters associated with the user's body and / or environmental parameters associated with the user's environment; -) analyzing the values ​​obtained by the measuring step in relation to predetermined or unpredictable patterns, trends and / or ranges of values ​​over time; -) determining, depending on the results of the analysis, whether the measurements correspond to one or more predetermined indicators of the event; A method comprising: The method relates to a method in which the one or more indicators include at least a first order indicator indicating a high probability of an event occurring and / or a second order indicator indicating a relatively low probability of an event occurring.

[0043] In an embodiment, the predetermined first event recognition (or identification) is triggered by the detection of at least one first-order indicator of the event.

[0044] In an embodiment, once at least one first-order indicator is detected by the algorithm, then a predetermined primary event response may be triggered. The response may be of several types, depending, for example, on the application. For example, it may be an alarm.

[0045] In an embodiment, the predetermined second event recognition (or identification) may be triggered by the detection of at least two second-order indicators. The reaction may be of several types, depending on, for example, the application. For example, it may be an alarm.

[0046] In an embodiment, event recognition (or identification) may be triggered by detection of at least first-order and second-order indicators.

[0047] In an embodiment, detection may be performed over a period of time, for example to measure trends.

[0048] In an embodiment, the predetermined event recognition (or identification) may be the occurrence of an attack.

[0049] In an embodiment, first-order indicators may include high acute stress, sustained high acute stress, high driving speed, hard braking, aggressive driving, abnormal stopping, irregular routes, specific sounds, man down, and bullet impact.

[0050] In an embodiment, second level indicators may include sustained acute stress, unknown stops, abnormal driving conditions, abnormal speed conditions, and unusual physical movements.

[0051] In an embodiment, the user is preferably a carrier.

[0052] In an embodiment, the value is measured by a sensor as disclosed in this application.

[0053] In an embodiment, the method includes a learning phase during which the user's personal parameters are monitored over time, thus allowing the method to adapt to each user and their daily activity patterns.

[0054] In embodiments, the learning phase may be performed continuously or at regular or irregular intervals, as described below.

[0055] In an embodiment, the method measures and analyzes parameters to detect anomalous behavior by a user, e.g., an "insider." In such a case, some parameters may be anomalous before an attack because the insider user knows that an attack is about to occur. Therefore, a user who knows that a robbery is about to occur will react differently to the event than a user who does not know that a robbery is about to occur.

[0056] In embodiments, a combination of continuous measurements / analysis over days and weeks can detect changes in a user's patterns and identify accomplices.

[0057] In an embodiment, measurements of personal parameter values ​​may be used to predict the occurrence of an event / situation or for forensic analysis, for example after an attack has occurred, to determine whether an insider was present or to learn from an actual situation.

[0058] In an embodiment, a predetermined reaction may be triggered depending on the outcome of the algorithmic analysis, such as an attack alarm or another event notification. [Brief explanation of the drawings]

[0059] [Figure 1] 1 illustrates a general configuration of an embodiment of the method according to the present invention. [Figure 2A] 1 is a functional embodiment of the method according to the present invention; [Figure 2B] 1 is a functional embodiment of the method according to the present invention; [Figure 2C] 1 is a functional embodiment of the method according to the present invention; [Figure 2D] 1 is a functional embodiment of the method according to the present invention; [Figure 2E] 1 is a functional embodiment of the method according to the present invention; [Figure 2F] 1 is a functional embodiment of the method according to the present invention; [Figure 2G] 1 is a functional embodiment of the method according to the present invention; [Figure 2H] 1 is a functional embodiment of the method according to the present invention; DETAILED DESCRIPTION OF THE INVENTION

[0060] [Detailed explanation] In some embodiments, the method of the present invention is an attack detection countermeasure having the following characteristics:

[0061] It includes and uses sensors to detect specific parameters, including but not limited to the following list: -) Accelerometer, gyroscope, magnetometer (for detecting human activity levels and abnormal driving events); -) ECG / PPG (heart rate variability detection); -) Skin temperature sensor; -) Core body temperature sensor; -) Skin conductance sensor (for detecting body sympathetic nerve activation and sweat level); -) Respiration sensor (respiration rate detection); -) GPS sensor (location, route detection, speed); -) Speed ​​sensor; -) Acoustic sensor; -) Shock sensor; -) Human activity type recognition sensor, such as moving, running, jumping, etc.; -) Human physical activity level sensor, for example, moving fast, running fast, etc.; -) Sensors capable of detecting information about the user's surrounding environment (vehicle sensors, indoor location, sound, temperature, street and / or security cameras, weather information); -) Cameras, for example for instant video recognition of murder weapons; -) Radiation sensor; -) Gas composition.

[0062] Preferably, the method of the present invention uses sensors primarily located on the user's body as the primary source of information, although in some embodiments sensors are located in the user's environment as well.

[0063] Sensors generate data and have a timestamp. Sensors include, but are not limited to, sensor devices that directly detect parameters and methods / detectors that directly process measured data of a parameter to determine an indirectly detected parameter. Sensor devices may include a battery and communication means (wired or wireless).

[0064] These are just examples of possible sensors and measured parameters, and many other sensors / parameters can be used to provide useful information for embodiments of the present invention, depending, for example, on the application.

[0065] Methods according to embodiments of the present invention are described in more detail below.

[0066] In an embodiment, for the purpose of assessing whether an attack event has occurred, an embodiment of the method according to the invention may take into account two types of parameters, namely: "Indicators of attack" (referred to as "first-class indicators" in the following discussion) are strong indicators of an abnormal event. and "abnormal conditions," so-called "second-order indicators," that are less indicative of an abnormal event (such as an attack) and therefore define a lower probability of an attack occurring. However, in some cases, such abnormal conditions may be indicative of an attack, for example, if they persist for a certain amount of time, or if certain abnormal conditions occur simultaneously or in close proximity to each other, or in a certain sequence. Thus, a combination of second-order indicators may also indicate the presence of an attack.

[0067] For other indices and / or conditions, other classes of indices (such as third class) can be defined depending on the field of application of the method according to the invention.

[0068] In an embodiment of the present invention, these indicators and abnormal conditions allow for determining and / or assessing the level of abnormality for a particular concept for a particular time frame and identifying the probability of occurrence of a predetermined event. Then, as a result of this, the system / method selects a notification of an appropriate predetermined event to be performed after said determination / assessment of the situation.

[0069] In an embodiment of the present invention, attack indicators include (but are not limited to): Personal / user physiologically relevant "High acute stress" indicator: This uses, for example, information from the last 90 seconds (or less) of heart rate variability and physical activity level data. The detection time window may be less than or more than 90 seconds, this value is non-limiting and merely an example. The time window may be different lengths, for example, for different people. Other physiological sensors can also be used for more accurate stress detection. "Sustained Acute Stress" indicator: This is activated, for example, 50 seconds or more after an activated acute stress event, using information from the last 90 seconds of heart rate variability and physical activity level data. Again, the time values ​​are examples and other values ​​may be used in some embodiments. These may be adapted to the person / user.

[0070] Typically, indicators associated with a person / user (e.g., a carrier) may be standardized at the same value or range (e.g., average heart rate or a specific range, similarly for skin temperature or skin conductance, applicable to all indicators measured on one person's body), or may be individualized to take into account the physical and physiological characteristics of one person: that is, one user may have, for example, a lower heart rate than another user, and therefore parameters must be adapted to be relevant to each user and to be able to detect indicators or abnormal conditions based on measurements.

[0071] In some embodiments, a learning phase can be performed, allowing the system to measure desired values / parameters and trends of the user and all information sources and store these values ​​for future use when the user is actually working, for example, as a courier transporting cash, valuables, and / or banknotes. The learning phase can be performed once at the start of employment or periodically (e.g., at predetermined intervals) to take into account changes in the user's physical condition, such as aging, improvements in physical condition due to intensive sports training, or, conversely, deterioration due to illness, smoking, lack of sleep, etc. The learning phase can also be performed permanently, allowing the system to take into account a person's current physical condition and their physical fitness (or lack of physical fitness). Such a system can be used, for example, in sports (e.g., marathon running), where training for a set goal is adapted to the user daily by taking into account the user's current condition and physical fitness (e.g., overtraining leads to rest instructions, while undertraining leads to increased training instructions specific to the determined end goal the user is to achieve). Thus, immediate adaptation of the system is achieved, thereby improving the efficiency of the method in all application fields.

[0072] The learning phase can also be improved by subjecting the user (e.g., a trucker) to exercises, such as attack simulations, intensive driving training sessions, and other specific exercises related to the field of application while wearing the sensor, where the measured values ​​can also be used to improve the systems and methods and adapt them to the user.

[0073] The principles of these learning steps are of course applicable to other possible applications of the method according to the invention and can be adapted to take into account the specific application envisaged and the parameters, indicators and data relevant to this specific application.

[0074] Related to the user's movements (or related to the environment) "High speed driving": For example, 80% of the speed values ​​(derived from the GPS sensor) are greater than 140 km / h in the last 10 seconds or based on the speed limit in the area (e.g. exceeding said speed limit). Again, these are exemplary values ​​and may be adapted depending on the case, the route selected, etc. For example, it seems that just detecting that the vehicle is exceeding a certain speed limit may be enough to set off an alarm. "Harsh Braking": For this parameter, acceleration data measurements from the user can be used to detect unusual braking behavior. "Aggressive driving": For this parameter, acceleration, gyroscope and speed data can be used, which can be caused by more than three abnormal driving events occurring at the last moment, such as abrupt steering, sudden acceleration and high speed. All values ​​are examples and should not be considered as limiting the range and may be adapted to the vehicle's route: i.e., driving on mountain roads (with many curves and braking) should not be considered as aggressive driving, while an alarm should be activated if this occurs on a normal straight and flat road. All sensors are worn by the user, and therefore a learning phase is required to adjust the detection method to the user's body movements in combination with the vehicle type. "Environmental": sounds of vehicle explosions, impacts, etc. may also be detected and used to trigger alarms. Street cameras may be used to detect vehicles passing on the wrong road, in the wrong direction, or at abnormal speeds.

[0075] These are merely exemplary embodiments, and other parameters and / or indicators and data may be detected and used in the method of the present invention, and a learning phase is required, for example, to remove user behavior from vehicle behavior (truck, car, airplane) depending on the vehicle used by the user.

[0076] In an embodiment of the method, taking into account the above indicators, an attack is detected if: If two or more active indicators of attack are detected, and / or When sustained high acute stress is detected for more than a certain period of time, for example 30 seconds.

[0077] Of course, these are merely examples, and attack detection can be performed by just one indicator, or by the level of the detected indicator, or by the parameters of the indicator: for example, in some situations or applications, some indicators (or their parameters) may be sufficient on their own and may be deemed sufficient to detect an attack or anomalous event alone. Alternatively, the detected value may deviate significantly from a predetermined normal value and / or range, which may also be sufficient to trigger event detection. Thus, for each indicator and / or parameter, a decision can be made about its severity (whether it is acceptable to trigger event detection alone) and about a different level that requires a second indicator to be detected or a detected level that is sufficient to trigger event detection with a single indicator.

[0078] In embodiments of the present invention, abnormal conditions may include: "Sustained acute stress" applied for more than 30 seconds, "Acute Stress Added": Another abnormal state added to low stress, "Abnormal stop": An abnormal stop, "Add stop", a stop with another abnormal condition, "Abnormal driving condition": any abnormal driving event that occurs before the aggressive driving indicator is activated; "Abnormal Speed ​​Condition": An abnormally high driving speed indicator that persists for a period of time before the high driving speed indicator is activated.

[0079] In embodiments of the present invention, any combination of indicators can be used to define a predetermined output of the system, such as event detection (and subsequent reaction, e.g., alarm). Thus, the system may be parameterized as desired by the user. For example, for an abnormal condition to trigger an "attack" event, one of the following conditions must be met: 1) First-class indicators, 2) Multiple second-level indicators, such as two simultaneous abnormal conditions plus high acute stress detection or two abnormal conditions plus a suspicious outage.

[0080] In other embodiments, other conditions or combinations can be defined to trigger "attack" identification (or recognition) and / or action, either locally or at a remote site, for example as illustrated in Figures 2A-2H.

[0081] FIG. 1 illustrates an example of a system and method configuration according to an embodiment of the present invention.

[0082] It includes block 1, which illustrates sensors used in the application (on the user's body or as a situation). As listed above in this specification, the sensors can measure person-related parameters / values ​​(i.e., heart rate, skin temperature) and / or environment-related parameters / values ​​(i.e., GPS, acceleration, movement, noise). Each of these values ​​is input to algorithms (boxes 2-6) that process the values ​​and detect, for example, stress (person-related) and abnormal driving (environment-related) over a period of time. These detected values ​​are then input to algorithms (box 8) that perform analysis to detect an event, which in this embodiment is, for example, an attack. The analysis algorithm can also receive other information, such as traffic information (or road work, speed limits, stopping areas, train crossings, box 7), that can be used to confirm or notify abnormal driving detection.

[0083] The algorithm then sends the results of the analysis to a dashboard or screen 9 together with a predetermined reaction, such as an alarm and / or a location that can be shown on the dashboard. The alarm can be an acoustic and / or visual alarm at the control center. The alarm can be different depending on the situation and / or the detected event. The alarm can also be forwarded to other people, such as rescue services (e.g., police). This forwarding can be direct or after evaluation at the control center (e.g., to confirm an attack). Of course, depending on the field of application (medical personnel, firefighters, pilots, etc.), the alarm can be sent to other people / services predetermined in said field of application. The dashboard can show any predetermined information, such as the user's location, real-time video and audio of the environment in which the user is located (from a camera installed in the vehicle or worn by the user), that is useful for the control center to assess the situation and take appropriate and / or predetermined measures in response to the alarm.

[0084] As will be readily appreciated, the system and method of the present invention can be adapted to the field of application, with the necessary parameters, algorithms, information data, and results displayed on a dashboard. The algorithms may be running on the user's body (a dedicated device, a smart device, e.g., a smartphone or smartwatch), and / or in a specific device (e.g., a computer) located locally in a physical control center or in the cloud. Some algorithms (or parts thereof) may run locally (see, e.g., Boxes 2-6), while other algorithms may reside in the system's central processing unit (see Box 8), which could be hosted in the cloud or in a physical control center.

[0085] To communicate, the different parts of the system can use wired connections or wireless techniques involving antennas, optical means, acoustic means (recording and generating sounds), etc.

[0086] 2A-2H illustrate examples of the functioning of methods according to embodiments of the present invention.

[0087] For example, in Figure 2A, stress is measured (see sensor 1 and box 3 in Figure 1), which may be a high acute stress level or acute stress, as illustrated in Figure 2A. The corresponding signal is input into an aggression detection algorithm (box 8), which generates a high stress indicator, e.g., a first order indicator.

[0088] Attack detection analyzes whether this indicator persists for a certain time (e.g., 30 seconds as illustrated), after which the attack detection algorithm (Box 8) issues an event identification (also called event recognition) signal (e.g., "attack"). While the high stress indicator is being generated, the algorithm also checks whether other indicators are active (e.g., second-order indicators). If so, an event identification signal (e.g., "attack") is issued by the attack detection algorithm. If not, a further test is performed to check whether an abnormal condition has been detected (e.g., a second-order indicator, or a subsequent condition indicator), and if so, an event identification signal (e.g., "attack") is issued by the attack detection algorithm.

[0089] In the other branch ("Acute Stress"), if acute stress detection is maintained for this time (e.g., 50 seconds), a "Sustained Acute Stress Indicator" is generated. If another indicator is (or was) detected, an event identification signal (e.g., "Attack") is issued by the attack detection algorithm.

[0090] 2B illustrates an embodiment of the method (e.g., Box 4) when an indicator of a stall situation is determined. An algorithm controls whether this is an abnormal stall indicator and, if so, whether other predetermined indicators are active. If so, an event identification signal (e.g., "attack") is issued by an attack detection algorithm. In parallel, another algorithm controls whether a stall situation has occurred outside a known area; if this situation persists after a certain time (e.g., 5 minutes), and if another indicator is active, an event identification signal (e.g., "attack") is issued by an attack detection algorithm (Box 8).

[0091] 2C illustrates another embodiment of the invention in the case of an abnormal driving indicator. A procedure (box 4) sends an abnormal driving signal if this indicator does not change after a certain time (e.g., 20 seconds). Once a signal corresponding to this indicator is received, the attack detection procedure (box 8) controls whether other indicators are active (e.g., for 60 seconds) and, if the test is positive, issues an event identification signal (e.g., "attack").

[0092] The algorithm controls whether an out-of-known-area indicator exists and issues an alert if it does not. If this indicator persists for a period of time (e.g., 2 minutes), an event identification signal (e.g., "attack") is issued by the attack detection algorithm.

[0093] 2D illustrates an embodiment of the invention with a sudden stop indicator (Box 2). In this case, the attack detection algorithm considers the road the truck is traveling on, and if it is a highway, the algorithm considers external information data (Box 7), in this case the presence or absence of traffic problems (e.g., traffic congestion) that may be the reason for the sudden stop. If there is no traffic congestion (or another reason for stopping on the highway), the attack detection algorithm (Box 8) issues an event identification signal (e.g., "attack").

[0094] 2E illustrates another embodiment of the invention involving a speed limit indicator. A procedure (Box 4) sends a high speed signal if an over-speed limit indicator is detected, and if this indicator remains unchanged after a certain time (e.g., 10 seconds), a sustained high speed abnormal condition is triggered. Also, an attack detection procedure (Box 8), once receiving a signal corresponding to this indicator, controls whether other indicators are active (e.g., for 60 seconds) and issues an event identification signal (e.g., "attack") if the test is positive.

[0095] The algorithm also controls whether a known out-of-area indicator is present, and if not, issues an event identification, in this case a predetermined second-class event. If this indicator persists for a certain period of time (e.g., two minutes), an event identification signal (e.g., "attack") is issued by the attack detection algorithm.

[0096] 2F illustrates another embodiment of the present invention involving a known out-of-area indicator. If a known out-of-area indicator is detected (box 2), the attack detection algorithm (box 8), once it receives a signal corresponding to this abnormal condition, analyzes whether this abnormal condition persists over time (e.g., 10 minutes) and controls whether other indicators, such as a stress indicator, are active (e.g., 60 seconds). If a stress indicator is present, the attack detection algorithm issues an event identification signal (e.g., "attack"). In parallel, the attack detection algorithm controls the known out-of-area indicator, and if an abnormal condition is present, the attack detection algorithm directly issues an event identification signal (e.g., "attack").

[0097] 2G illustrates another embodiment of the invention with a man down / fall indicator (Box 5). If this indicator is detected, the attack detection algorithm issues a "man down alarm" as a distinguished second-order event. The attack detection algorithm also controls whether another alarm (e.g., another indicator) is activated. If so, it issues an event identification signal (e.g., "attack").

[0098] 2H illustrates another embodiment of the present invention with an SOS button indicator. If this indicator is detected, the attack detection algorithm issues an SOS alarm as an identified secondary event. The attack detection algorithm also controls whether another alarm (e.g., another indicator) is active. If active, the attack detection algorithm (Box 8) issues an event identification signal (e.g., "attack").

[0099] Of course, the event identification signal may be different, for example it may depend on the field of application of the method and system.

[0100] The attack detection scenarios described above are examples of applications and capabilities of the method of the present invention and should not be construed as limiting. Many combinations of such scenarios are possible for other applications as set forth herein above, with other parameters and indicators suitable for the selected application, and the principles of the present invention described herein are applicable to such parameters and indicators.

[0101] This specification is not intended to be, and should not be construed as, representative of the entire scope of the invention. The invention is set forth in various levels of detail herein and in the accompanying drawings and detailed description of the invention, and no limitation on the scope of the invention is intended by either the inclusion or exclusion of elements, components, etc. Additional aspects of the invention will become more readily apparent from the detailed description, particularly when taken in conjunction with the drawings.

[0102] Moreover, exemplary embodiments have been described to provide a thorough understanding of the principles of the structure, function, manufacture, and use of the systems and methods disclosed herein. One or more examples of these embodiments are illustrated in the accompanying drawings. Those skilled in the art will understand that the systems and methods specifically described herein and illustrated in the accompanying drawings are non-limiting exemplary embodiments, and that the scope of the present invention is not defined solely by the claims. Features illustrated or described in connection with exemplary embodiments may be combined with features of other embodiments. Such modifications and variations are intended to be included within the scope of the present invention. Many problems with conventional methods and systems have been pointed out herein, and the methods and systems disclosed herein may address one or more of these problems. By describing these problems, no admission of knowledge thereof in the art is intended. Those skilled in the art will recognize that, while certain methods and systems have been described in connection with embodiments of the present invention, the scope of the invention is not so limited. Moreover, while the present invention has been described in conjunction with numerous embodiments, it is evident that many alternatives, modifications, and variations will be or are apparent to those skilled in the applicable art. Accordingly, it is intended to embrace all such alternatives, modifications, equivalents and variations that fall within the spirit and scope of this invention.

Claims

1. A method for detecting an event or situation occurring in the vicinity of at least a user, for example, a valuable goods carrier, comprising: -) measuring values ​​of personal parameters associated with the user's body and / or environmental parameters associated with the user's environment; -) analyzing the values ​​obtained by the measuring step in relation to patterns, trends and / or ranges of values ​​over time; -) determining, depending on the results of the analysis, whether the measurements correspond to one or more predetermined indicators of the event; A method comprising: A method, wherein the one or more indicators include at least a first order indicator indicating a high probability of an event occurring and / or a second order indicator indicating a relatively low probability of an event occurring.

2. The method of claim 1 , wherein the predetermined first event recognition is triggered by the detection of at least one first-order indicator of the event.

3. The method of claim 1 or 2, wherein the predetermined second event recognition is triggered by the detection of at least two second-order indicators.

4. 4. The method of claim 1, wherein the detection is carried out over a period of time.

5. 5. The method of claim 1, wherein the predetermined event recognition is the occurrence of an attack.

6. 6. The method of claim 1, wherein the first-order indicators include high acute stress, sustained high acute stress, high driving speed, hard braking, aggressive driving, abnormal stopping, irregular routes, specific sounds, man-down detection, and bullet impact.

7. 7. The method of claim 1, wherein the second level indicators include persistent acute stress, unknown stalls, abnormal driving conditions, abnormal speed conditions, and unusual physical movements.

8. The method of any one of claims 1 to 7, wherein the user is a carrier.

9. The value is -) Accelerometer, gyroscope, magnetometer, human activity level detection, and abnormal driving event detection; -) ECG / PPG, -) Skin temperature sensor, -) Deep body temperature sensor, -) Skin conductance sensor, -) breathing sensor, -) GPS sensor, -) Speed ​​sensor, -) Acoustic sensor, -) Impact sensor, -) Human activity type recognition sensor, -) Human physical activity level sensor, -) Sensors that can detect the user's surrounding environment behavior, -) Camera, -) Radiation sensor, -) Gas composition sensor, 9. The method of claim 1, wherein the temperature is measured by a sensor worn by the carrier, the sensor comprising:

10. 10. The method according to any one of claims 1 to 9, wherein the method comprises a learning phase during which personal parameters of the user are monitored over time, thus making it possible to adapt the method to each user and their daily activity patterns.

11. The method of claim 10 , wherein the learning step is performed continuously, periodically, or irregularly.

12. 12. The method according to any one of claims 1 to 11, wherein the measurement of personal parameter values ​​is used to predict the occurrence of an event / situation or for forensic analysis.

13. 13. The method of any one of claims 1 to 12, wherein a predetermined reaction is triggered depending on the result of the analysis by the algorithm.

Images