An artificial intelligence system for emergency safety

Abstract

The present invention discloses an emergency safety artificial intelligence system, which includes: a data acquisition module, a data analysis module, a decision support module, an intelligent smoke exhaust module, an intelligent evacuation sign module, an intelligent water spray module, a remote command module, an intelligent rescue module, and a decision support module, which are arranged at a remote server, and determine multiple optimal evacuation paths and optimal rescue paths according to personnel density, personnel travel speed, personnel current position, flame spread trend, and smoke diffusion range; it can guide firefighters in real time to evacuate the personnel to be rescued to the optimal rescue path of the safe exit, which can effectively reduce casualties and property losses. Through the optimization of personnel rescue path and guidance equipment, the spread of the fire scene detection is added to the rescue model, and the optimized algorithm is combined with the improved rescue indication device to intelligently generate the optimal rescue path, providing a reference route for the rescue path.

Description

Technical Field

[0001] The present invention belongs to the field of computer simulation, and in particular relates to an emergency safety artificial intelligence system. Background Art

[0002] For large buildings, due to the complex structure and multiple safety exits, different fire points directly affect the choice of evacuation routes. The evacuation signs in the building directly affect the evacuees' choice of evacuation routes. However, the evacuation signs in traditional buildings are not intuitive and their expression is mainly two-dimensional. The evacuation method that relies on two-dimensional and single-pointing evacuation signs as an evacuation induction method can no longer meet the safety evacuation needs of today's buildings.

[0003] At the same time, when a fire occurs in a high-rise office building, people will generally feel fear and tension, and the smoke and high temperature during the fire will affect the visual and respiratory systems of the evacuees, which will affect their evacuation decision-making and evacuation capabilities. The chimney effect of high-rise buildings is strong, and they are directly affected by wind speed and direction, which greatly increases the difficulty of evacuation.

[0004] The problem is how to provide evacuation instructions based on the emergency safety system in the early stages of a disaster and provide effective rescue routes for rescue workers. Summary of the invention

[0005] In view of the existing problems, the present invention provides a system, which includes the following modules:

[0006] The data acquisition module is installed on the ceiling of the building and collects information such as the density of people in the building, the speed of people moving, the ambient temperature, the smoke concentration, and the fire scene image through sensors;

[0007] A data analysis module is provided at a remote server, and predicts the flame spreading trend and smoke diffusion range according to the ambient temperature and smoke concentration;

[0008] The decision support module is set up at the remote server and determines multiple optimal evacuation routes and optimal rescue routes based on the density of people, the speed of people moving, the current location of people, the trend of flame spread, and the range of smoke diffusion;

[0009] The intelligent smoke exhaust module detects the smoke concentration in the fire scene and the visibility value reflected by the fire scene image. When the smoke concentration exceeds the first threshold or the visibility value reflected by the fire scene image is less than the second threshold, the smoke exhaust fan is started and the power and wind speed of the smoke exhaust fan are automatically adjusted;

[0010] An intelligent evacuation sign module is arranged at intersections, including T-shaped intersections and cross-shaped intersections, and includes an indicator light, a buzzer, and a power supply. When the smoke concentration exceeds a first threshold, the indicator light is turned on in a strobe mode, and the buzzer is turned on in a long-sounding mode;

[0011] The intelligent water spray module is installed on the top of the ceiling, 1 meter away from the exhaust fan. It adjusts the water spray status according to the smoke concentration and the temperature of the fire scene. When the smoke concentration exceeds the first threshold, the water spray module adopts the atomization mode, which can quickly eliminate smoke with the smoke exhaust fan to improve the visual visibility of personnel.

[0012] Remote command module, which allows command personnel to view fire scene images, understand the fire development and firefighters' location information in real time, and collaborate with firefighters through voice communication;

[0013] The intelligent rescue module is installed in the firefighter's wearable device. When the smoke concentration exceeds the first threshold, the position of the personnel in the image is determined through the image collected by the thermal imager, and the position of the intelligent evacuation sign with the shortest distance is prompted.

[0014] A method comprising the following steps:

[0015] S1. Collect the density of people in the building, the speed of people moving, the ambient temperature, the smoke concentration, and the fire scene image through sensors;

[0016] S2. Predicting the flame spreading trend and smoke diffusion range according to the ambient temperature and smoke concentration;

[0017] S3. Determine multiple optimal evacuation routes and optimal rescue routes based on the density of people, the speed of people moving, the current location of people, the trend of flame spread, and the range of smoke diffusion;

[0018] S4, detecting the smoke density in the fire scene and the visibility value reflected by the fire scene image. When the smoke density exceeds a first threshold or the visibility value reflected by the fire scene image is less than a second threshold, the smoke exhaust fan is started and the power and wind speed of the smoke exhaust fan are automatically adjusted;

[0019] S5. When the smoke concentration exceeds the first threshold, the indicator light in the intelligent evacuation module is turned on in strobe mode and the buzzer is turned on in long-sounding mode; the water spraying state is adjusted according to the smoke concentration and the fire scene temperature. When the smoke concentration exceeds the first threshold, the water spraying module adopts the atomization mode;

[0020] S6. Commanders can view fire scene images in real time based on the data sent back from the fire scene, understand the fire development and the location of firefighters, and collaborate with firefighters through voice communication;

[0021] S7. When the smoke concentration exceeds the first threshold, the firefighters determine the positions of the personnel in the image through the images collected by the thermal imager, and indicate the position of the intelligent evacuation sign with the shortest distance.

[0022] Furthermore, the flame spread trend and smoke diffusion range are predicted based on the ambient temperature and smoke concentration:

[0023] S20, the remote server is connected to the IoT relay;

[0024] S21, reporting the sensor device information to the IoT relay,

[0025] S22, determining at the IoT relay whether the remote server has subscribed to the sensor device information, and if so, sending the sensor device information and the collected information to the remote server;

[0026] S23, the remote server predicts the flame spreading trend and smoke diffusion range according to the ambient temperature and smoke density.

[0027] Furthermore, multiple optimal evacuation routes and optimal rescue routes are determined based on the density of people, the speed of people moving, the current location of people, the trend of flame spread, and the range of smoke diffusion, including:

[0028] S31, obtaining a building plan, and performing rasterization processing on the building plan;

[0029] S32, superimposing the sensor equipment information, the flame spread trend, and the smoke diffusion range onto the building plan to determine the safety grid range;

[0030] S33, calculating the optimal sub-path from the current position to the first safety staircase within the safety grid according to the ant colony model, and calculating the optimal sub-path from the first safety staircase to the safety exit;

[0031] S34. Connect multiple optimal sub-paths to form an optimal path.

[0032] Furthermore, the optimal sub-path from the current position to the first safety staircase within the safety grid is calculated according to the ant colony model, including

[0033] S331. Set the calculation path model:

[0034]

[0035] In the formula, (x, y) is the real-time location of the firefighter, (x i ,y i ) is the location of the person to be rescued, (x j ,y j) represents the first safe staircase; M means that no fire occurred at the i entrance during the rescue process; i is a natural number; t is the current time;

[0036] S332, set the selection probability of the first safety staircase to P,

[0037]

[0038] S333. When several simulated firefighters arrive safely at the first safety staircase, update the pheromone model:

[0039]

[0040] Among them, τ ij (t+1) is the pheromone concentration left by the firefighter in the ij path at time t+1, ε is the volatility factor, and W represents the constant of pheromone concentration; T k It refers to the total length of the path that the firefighters have traveled in this cycle;

[0041] S334, until the maximum number of iterations is reached, the optimal sub-path from the current position to the first safe staircase is output. If there is only one firefighter, there is no need to update the pheromone model.

[0042] Further,

[0043] Calculate the smoke concentration deviation and temperature deviation. When both deviations are higher than the preset values, the current grid is determined to be a dangerous grid and needs to be bypassed.

[0044] Calculate the smoke concentration deviation value and temperature deviation value of the adjacent grids of the dangerous grid until the deviation values ​​are both lower than the preset values, and then determine the range of the dangerous grid;

[0045] Furthermore, the fire spread trend is determined based on the sensor sampling time and the changes in the parameters of the adjacent dangerous grids;

[0046] An electronic device, characterized in that it includes a processor, a memory, a communication interface and a program, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing the steps of an emergency safety processing method.

[0047] A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement an emergency safety processing method.

[0048] The beneficial effects of the present invention are as follows:

[0049] During the rescue process, the present invention applies an improved optimal algorithm to find the specific path from the rescued persons in the building to the nearest safe exit as the basis for planning the rescue path, which can guide firefighters in real time to evacuate the rescued persons to the optimal rescue path for the safe exit, and can effectively reduce casualties and property losses.

[0050] By optimizing the rescue path for personnel and the guidance equipment, the spread of the fire detected at the scene is added to the rescue model. The optimized algorithm is combined with the improved rescue indication device to intelligently generate the optimal rescue path and provide a reference route for the rescue path.

[0051] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above description and other purposes, features and advantages of the present invention more obvious and easy to understand, the preferred embodiments are specifically cited and described in detail as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0053] Figure 1 Structure diagram of emergency safety artificial intelligence system DETAILED DESCRIPTION

[0054] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0055] In the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be connected, detachably connected, or integrated; it can be mechanically connected or electrically connected; it can be directly connected or indirectly connected through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0056] Example 1

[0057] A system comprising the following modules:

[0058] The data acquisition module is installed on the ceiling of the building and collects information such as the density of people in the building, the speed of people moving, the ambient temperature, the smoke concentration, and the fire scene image through sensors;

[0059] A data analysis module is provided at a remote server, and predicts the flame spreading trend and smoke diffusion range according to the ambient temperature and smoke concentration;

[0060] The decision support module is set up at the remote server and determines multiple optimal evacuation routes and optimal rescue routes based on the density of people, the speed of people moving, the current location of people, the trend of flame spread, and the range of smoke diffusion;

[0061] The intelligent smoke exhaust module detects the smoke concentration in the fire scene and the visibility value reflected by the fire scene image. When the smoke concentration exceeds the first threshold or the visibility value reflected by the fire scene image is less than the second threshold, the smoke exhaust fan is started and the power and wind speed of the smoke exhaust fan are automatically adjusted;

[0062] An intelligent evacuation sign module is arranged at intersections, including T-shaped intersections and cross-shaped intersections, and includes an indicator light, a buzzer, and a power supply. When the smoke concentration exceeds a first threshold, the indicator light strobe mode and the buzzer long sound mode are turned on;

[0063] The intelligent water spray module is installed on the top of the ceiling, 1 meter away from the exhaust fan. It adjusts the water spray status according to the smoke concentration and the fire temperature. When the smoke concentration exceeds the first threshold, the water spray module adopts the atomization mode, which can quickly eliminate the smoke with the smoke exhaust fan to improve the visual visibility of personnel.

[0064] Remote command module, which allows command personnel to view fire scene images, understand the fire development and firefighters' location information in real time, and collaborate with firefighters through voice communication;

[0065] The intelligent rescue module is installed in the firefighter's wearable device. When the smoke concentration exceeds the first threshold, the position of the personnel in the image is determined by the image captured by the thermal imager, and the position of the intelligent evacuation sign with the shortest distance is prompted.

[0066] Example 2

[0067] An emergency safety processing method, applied to safety processing equipment, comprises the following steps:

[0068] S1. Collect the density of people in the building, the speed of people moving, the ambient temperature, the smoke concentration, and the fire scene image through sensors;

[0069] S2. Predicting the flame spreading trend and smoke diffusion range according to the ambient temperature and smoke concentration;

[0070] S3. Determine multiple optimal evacuation routes and optimal rescue routes based on the density of people, the speed of people moving, the current location of people, the trend of flame spread, and the range of smoke diffusion;

[0071] S4, detecting the smoke density in the fire scene and the visibility value reflected by the fire scene image. When the smoke density exceeds a first threshold or the visibility value reflected by the fire scene image is less than a second threshold, the smoke exhaust fan is started and the power and wind speed of the smoke exhaust fan are automatically adjusted;

[0072] S5. When the smoke concentration exceeds the first threshold, the indicator light in the intelligent evacuation module is turned on in strobe mode and the buzzer is turned on in long-sound mode; the water spraying state is adjusted according to the smoke concentration and the fire scene temperature. When the smoke concentration exceeds the first threshold, the water spraying module adopts the atomization mode;

[0073] S6. Commanders can view fire scene images in real time based on the data sent back from the fire scene, understand the fire development and the location of firefighters, and collaborate with firefighters through voice communication;

[0074] S7. When the smoke concentration exceeds the first threshold, the firefighters determine the positions of the personnel in the image through the images collected by the thermal imager, and indicate the position of the intelligent evacuation sign with the shortest distance.

[0075] Furthermore, the flame spread trend and smoke diffusion range are predicted based on the ambient temperature and smoke concentration:

[0076] S20, the remote server is connected to the IoT relay;

[0077] S21, reporting the sensor device information to the IoT relay,

[0078] S22, determining at the IoT relay whether the remote server has subscribed to the sensor device information, and if so, sending the sensor device information and the collected information to the remote server;

[0079] S23, the remote server predicts the flame spreading trend and smoke diffusion range according to the ambient temperature and smoke density.

[0080] Furthermore, multiple optimal evacuation routes and optimal rescue routes are determined based on the density of people, the speed of people moving, the current location of people, the trend of flame spread, and the range of smoke diffusion, including:

[0081] S31, obtaining a building plan, and performing rasterization processing on the building plan;

[0082] S32, superimposing the sensor equipment information, the flame spread trend, and the smoke diffusion range onto the building plan to determine the safety grid range;

[0083] S33, calculating the optimal sub-path from the current position to the first safety staircase within the safety grid according to the ant colony model, and calculating the optimal sub-path from the first safety staircase to the safety exit;

[0084] S34. Connect multiple optimal sub-paths to form an optimal path.

[0085] Furthermore, the optimal sub-path from the current position to the first safety staircase within the safety grid is calculated according to the ant colony model, including

[0086] S331. Set the calculation path model:

[0087]

[0088] In the formula, (x, y) is the real-time location of the firefighter, (x i ,y i ) is the location of the person to be rescued, (x j ,y j ) represents the first safe staircase; M means that no fire occurred at the i entrance during the rescue process; i is a natural number; t is the current time;

[0089] S332, set the selection probability of the first safety staircase to P,

[0090]

[0091] S333. When several simulated firefighters arrive safely at the first safety staircase, update the pheromone model:

[0092]

[0093] Among them, τ ij (t+1) is the pheromone concentration left by the firefighter in the ij path at time t+1, ε is the volatility factor, and W represents the constant of pheromone concentration; T k It refers to the total length of the path that the firefighters have traveled in this cycle;

[0094] S334, until the maximum number of iterations is reached, the optimal sub-path from the current position to the first safe staircase is output. If there is only one firefighter, there is no need to update the pheromone model.

[0095] Further,

[0096] Calculate the smoke concentration deviation and temperature deviation. When both deviations are higher than the preset values, the current grid is determined to be a dangerous grid and needs to be bypassed.

[0097] Calculate the smoke concentration deviation value and temperature deviation value of the adjacent grids of the dangerous grid until the deviation values ​​are both lower than the preset values, and then determine the range of the dangerous grid;

[0098] Furthermore, the fire spread trend is determined based on the sensor sampling time and the changes in the parameters of the adjacent dangerous grids.

[0099] The advantages of the present invention are as follows:

[0100] The present invention can guide firefighters in real time to evacuate the people to be rescued to the optimal rescue path for the safe exit, which can effectively reduce casualties and property losses. By optimizing the rescue path for personnel and the guidance equipment, the spread of the fire scene detection is added to the rescue model, and the optimized algorithm is combined with the improved rescue indication device to intelligently generate the optimal rescue path and provide a reference route for the rescue path.

[0101] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the device or unit can be electrical or other forms.

[0102] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0103] Each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software program modules.

[0104] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0105] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.

[0106] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. An emergency safety processing method, characterized in that: The method comprises the following steps: S1. Collect the density of people in the building, the speed of people moving, the ambient temperature, the smoke concentration, and the fire scene image through sensors; S2. Predicting the flame spreading trend and smoke diffusion range according to the ambient temperature and smoke concentration; S3. Determine multiple optimal evacuation routes and optimal rescue routes based on the density of people, the speed of people moving, the current location of people, the trend of flame spread, and the range of smoke diffusion; S4, detecting the smoke density in the fire scene and the visibility value reflected by the fire scene image. When the smoke density exceeds a first threshold or the visibility value reflected by the fire scene image is less than a second threshold, the smoke exhaust fan is started and the power and wind speed of the smoke exhaust fan are automatically adjusted; S5. When the smoke concentration exceeds the first threshold, the indicator light in the intelligent evacuation module is turned on in strobe mode and the buzzer is turned on in long-sound mode; the water spraying state is adjusted according to the smoke concentration and the fire scene temperature. When the smoke concentration exceeds the first threshold, the water spraying module adopts the atomization mode; S6. Commanders can view fire scene images in real time based on the data sent back from the fire scene, understand the fire development and the location of firefighters, and collaborate with firefighters through voice communication; S7. When the smoke concentration exceeds the first threshold, the firefighters determine the position of the personnel in the image through the image collected by the thermal imager, and prompt the position of the intelligent evacuation sign with the shortest distance; Among them, multiple optimal evacuation routes and optimal rescue routes are determined based on the density of people, the speed of people moving, the current location of people, the trend of flame spread, and the range of smoke diffusion, including: S31, obtaining a building plan, and performing rasterization processing on the building plan; S32, superimposing the sensor equipment information, the flame spread trend, and the smoke diffusion range onto the building plan to determine the safety grid range; S33, calculating the optimal sub-path from the current position to the first safety staircase within the safety grid according to the ant colony model, and calculating the optimal sub-path from the first safety staircase to the safety exit; S34, connecting multiple optimal sub-paths to form an optimal path; Among them, the optimal sub-path from the current position to the first safe staircase within the safety grid is calculated according to the ant colony model, including S331. Set the calculation path model: In the formula, (x, y) is the real-time location of the firefighter, (x i ,y i ) is the location of the person to be rescued, (x j ,y j ) represents the first safe staircase; M means that no fire occurred at the i entrance during the rescue process; i is a natural number; t is the current time; S332, set the selection probability of the first safety staircase to P, ; S333. When several simulated firefighters arrive safely at the first safety staircase, update the pheromone model: in, is the pheromone concentration left by the firefighter in the ij path at time t+1, is the volatility factor, W represents the constant of pheromone concentration; T k It refers to the total length of the path that the firefighters have traveled in this cycle; S334, until the maximum number of iterations is reached, the optimal sub-path from the current position to the first safe staircase is output. If there is only one firefighter, there is no need to update the pheromone model.

2. An emergency safety handling method according to claim 1, characterized in that: According to the ambient temperature and smoke concentration, the flame spread trend and smoke diffusion range are predicted: S20, the remote server is connected to the IoT relay; S21, reporting the sensor device information to the IoT relay, S22, determining at the IoT relay whether the remote server has subscribed to the sensor device information, and if so, sending the sensor device information and the collected information to the remote server; S23, the remote server predicts the flame spreading trend and smoke diffusion range according to the ambient temperature and smoke density.

3. An emergency safety artificial intelligence system, running the emergency safety processing method as claimed in claim 1, characterized in that: The system includes: The data acquisition module is installed on the ceiling of the building and collects information such as the density of people in the building, the speed of people moving, the ambient temperature, the smoke concentration, and the fire scene image through sensors; A data analysis module is provided at a remote server, and predicts the flame spreading trend and smoke diffusion range according to the ambient temperature and smoke concentration; The decision support module is set up at the remote server and determines multiple optimal evacuation routes and optimal rescue routes based on the density of people, the speed of people moving, the current location of people, the trend of flame spread, and the range of smoke diffusion; The intelligent smoke exhaust module detects the smoke concentration in the fire scene and the visibility value reflected by the fire scene image. When the smoke concentration exceeds the first threshold or the visibility value reflected by the fire scene image is less than the second threshold, the smoke exhaust fan is started and the power and wind speed of the smoke exhaust fan are automatically adjusted; An intelligent evacuation sign module is arranged at intersections, including T-shaped intersections and cross-shaped intersections, and includes an indicator light, a buzzer, and a power supply. When the smoke concentration exceeds a first threshold, the indicator light strobe mode and the buzzer long sound mode are turned on; The intelligent water spray module is installed on the top of the ceiling, 1 meter away from the exhaust fan. It adjusts the water spray status according to the smoke concentration and the fire temperature. When the smoke concentration exceeds the first threshold, the water spray module adopts the atomization mode, which can quickly eliminate the smoke with the smoke exhaust fan to improve the visual visibility of personnel. Remote command module, which allows command personnel to view fire scene images, understand the fire development and firefighters' location information in real time, and collaborate with firefighters through voice communication; The intelligent rescue module is installed in the firefighter's wearable device. When the smoke concentration exceeds the first threshold, the position of the personnel in the image is determined by the image captured by the thermal imager, and the position of the intelligent evacuation sign with the shortest distance is prompted.

4. An electronic device, characterized in that: The method comprises a processor, a memory, a communication interface and a program, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program comprises instructions for executing the steps in any one of the methods of claims 1-2.

5. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method according to any one of claims 1 to 2.

Images