Method for assessing a vital parameter of a passenger, system and motor vehicle
Patent Information
- Application Number
- EP2023818385
- Authority / Receiving Office
- EP · EP
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-01-20
- Filing Date
- 2023-12-05
- Publication Date
- 2025-11-26
AI Technical Summary
Passengers often engage in activities that do not align with their current mental state, leading to poor well-being due to unrecognized internal conditions such as stress or fatigue, which existing technologies fail to address effectively during vehicle journeys.
A method utilizing EEG devices to record vital parameters like brain frequency and cameras to assess passenger activity, comparing these to determine a matching or mismatching state, and adjusting vehicle functions like lighting, seating, and audio systems to align the passenger's internal state with their activity, supported by artificial intelligence for improved accuracy.
The method effectively supports passengers by aligning their internal state with their activity, enhancing comfort and reducing stress by adjusting vehicle settings based on real-time assessments, thereby improving mental well-being during vehicle journeys.
Smart Images
Figure EP2023084258_25072024_PF_FP_ABST
Abstract
Description
[0001] Method for assessing a vital parameter of a passenger, as well as system and motor vehicle
[0002] DESCRIPTION:
[0003] The invention relates to a method for assessing a vital parameter of a passenger as well as a system and a motor vehicle.
[0004] Often, a person performs an activity but is in a different (mental) state. This can often lead to the person feeling unwell or can cause long-term stress. The scenario described is commonplace. One would like to
[0005] You're reading a book, but you can't concentrate properly. Or you'd like to relax or sleep, but you can't seem to get into the right frame of mind. Often, you're stressed, but you don't realize what state your body or mind is in. If the current activity doesn't match your current state of mind or condition, it often leads to a feeling of poor well-being, often without knowing why.
[0006] From DE 10 2020 208722 A1 a method for assisting a vehicle occupant before, during and after a sleep break during an autonomous journey in a vehicle is known.
[0007] DE 10 2019 201 695 A1 discloses a biometric sensor fusion for classifying the condition of a vehicle occupant.
[0008] The invention is based on the object of improving the adjustment of a vehicle function with respect to a passenger. This object is achieved by the subject matter of the independent patent claims. Advantageous developments of the invention are defined by the dependent patent claims, the following description, and the figures.
[0009] One aspect of the invention relates to a method for assessing a vital parameter of a passenger in a vehicle. At least one vital parameter of the passenger is recorded using a first measuring unit. A vital parameter state class is determined based on the recorded vital parameter. A second measuring unit records an activity of the passenger. The recorded activity is assigned to an activity state class. Subsequently, an assessment result is determined from a comparison of the assigned vital parameter state class with the assigned activity state class. A vehicle function of the vehicle is adjusted based on the assessment result.
[0010] For example, the first measuring unit comprises an electroencephalography (EEG) device. An EEG device records voltage fluctuations on the surface of the head. These voltage fluctuations are caused by physiological processes in individual brain cells, which contribute to the brain's information processing through changes in electrical state. The voltage fluctuations exhibit different frequencies. These can be divided into frequency bands, so-called EEG bands. For example, the frequency bands can be divided into delta waves, theta waves, alpha waves, beta waves, and gamma waves.
[0011] In particular, at least one of the passenger's vital parameters is the frequency of the voltage fluctuations recorded by the EEG device. Depending on the frequency band in which the frequency lies, the recorded vital parameter can be assigned to a vital parameter state class. Possible vital parameter state classes include, for example, "relaxation," "concentration," "sleep," and "stress."
[0012] The second measuring unit for recording the passenger's activity can, for example, operate according to a different functional principle than the first measuring unit. In particular, the second measuring unit comprises a camera or a time-of-flight camera. The camera, which can also be referred to as an interior camera, records the passenger. The passenger performs the activity, such as reading. By evaluating an image signal from the camera, the activity can be recognized, for example, using a computing unit. The activity can then be assigned to the activity state class. There are several activity state classes, for example "relaxation", "concentration", "sleep", and "stress". For example, reading can be assigned to the activity state class "concentration". In particular, there are the same vital parameter state classes as activity state classes.
[0013] The vital parameter state class is compared with the activity state class. The assessment result of this comparison indicates, for example, whether the assigned vital parameter state class matches the assigned activity state class. For example, if the passenger's recorded vital parameter was assigned to the "sleep" vital parameter state class, and the passenger's recorded activity was assigned to the "concentration" activity state class, then the vital parameter state class and the activity state class do not match. From this, it can be determined, for example, that the passenger is in an internal state in which they could sleep. The recorded activity of reading in this example requires concentration and is therefore assigned to the "concentration" activity state class.Thus, in this example, the assigned vital parameter state class and the assigned activity state class do not match. It is possible that the passenger feels stressed and / or uncomfortable as a result. The vehicle function to be adjusted could be, for example, the brightness of a light in the vehicle, a massage setting for a vehicle seat, a seat heating setting for the vehicle seat, and / or a setting for an audio system in the vehicle. It is possible that one or more vehicle functions of the vehicle will be adjusted as needed depending on the assessment result.
[0014] It is possible for the passenger to be supported according to their inner, mental state, which is described by the vital parameter state class. In the example mentioned, the brightness of the light can be dimmed so that the passenger can sleep. When the passenger is asleep, the vital parameter state class corresponds to the assigned
[0015] Activity state class. This makes it possible for the passenger's mental state to be improved because a discrepancy between the passenger's internal state and the passenger's activity has been eliminated.
[0016] However, it is also possible for the passenger to be supported in their activity. The vehicle's functions can be adjusted to adapt the passenger's inner state to the activity. In the example already mentioned, the brightness of the vehicle's lights can be increased. This can also eliminate the discrepancy between the passenger's inner state and their activity. This also improves the passenger's mental state, making them feel comfortable rather than stressed.
[0017] In one embodiment, a degree of state expression of the assigned vital parameter state class is determined depending on a measured value of the recorded vital parameter. The assessment result is determined based on this. In particular, the degree of state expression can be referred to as a confidence value. For example, if the frequency of the voltage fluctuations measured by the EEG device lies in a frequency range that lies in a borderline area between two different frequency bands, then the degree of state expression is lower than for frequencies that do not lie in such a borderline area. For example, delta waves have a frequency between 0.1 and < 4 Hz. Delta waves are particularly typical of a deep sleep phase. Theta waves are in the frequency range between 4 and 8 Hz. Theta waves occur particularly frequently when one is drowsy.For example, if the recorded frequency is 4 Hz, the confidence value for theta waves can be set low. The confidence value can range from 0 to 100 percent.
[0018] This allows the vehicle function to be adjusted as needed, as the assessment result is determined based on the degree of the condition. For example, if the determined frequency is 4 Hz, and the passenger is to be assisted with reading, which corresponds to the activity state class "Concentration," it is particularly advantageous in this example if the brightness of the light in the vehicle is set higher than at a determined frequency that lies in a frequency range between 7 and 8 Hz.
[0019] In one embodiment, at least one additional vital parameter is determined. The vital parameter status class is determined based on the additional vital parameter. This can improve the determination of the passenger's internal status. The additional vital parameter can be used, for example, to verify the measured value of the first recorded vital parameter.
[0020] For example, the additional vital parameter could be the conductivity of the passenger's skin, which can be used to detect sweat, a passenger's pulse, or pupil dilation. If necessary, the additional vital parameter is recorded using a separate measuring unit.
[0021] It is possible for the first recorded vital parameter to be assigned to a vital parameter status class based on its measured value. At least one additional vital parameter can be determined simultaneously, at least temporarily, and also assigned to a vital parameter status class. If appropriate, the respective assigned vital parameter status classes may match. In this case, a particularly high degree of status severity can be determined.
[0022] It is possible to use artificial intelligence (AI), particularly a neural network, to improve the classification of the recorded vital parameter measurements. For this purpose, the artificial intelligence can be trained, in particular, using data from a large number of vehicles and measurements from their measurement units. This can ensure that the vital parameter state class is determined that corresponds to the passenger's internal state.
[0023] In one embodiment, sensor data is generated using the second measuring unit to record the activity. The generated sensor data is evaluated using artificial intelligence and assigned to an activity. The activity, in turn, is assigned to the activity state class.
[0024] In other words, an activity can be recognized from the evaluated sensor data. The activity is carried out by the passenger. The recognized activity is assigned the respective activity state class. In other words, the assigned activity state class is a target state of the passenger in which they should be when performing the recognized activity. The use of artificial intelligence improves the recognition of the activity and thus the assigned activity state class. In one embodiment, the assessment result is displayed to the passenger. Depending on the assessment result, at least one suggestion is displayed to the passenger. Depending on whether the suggestion is accepted by the passenger, the vehicle function is adjusted.
[0025] In particular, different cases can be differentiated depending on the assessment result. If, for example, the assessment result contains information that the assigned vital parameter state class does not correspond to the assigned activity state class and, in particular, a high degree of state severity was determined, this can be displayed to the passenger if necessary. For this purpose, the passenger is shown, for example, "You are in a different current state." on an output unit. The display or output to the passenger can be acoustic or visual. The user can be shown a suggestion as to whether a currently determined mental state that corresponds to the vital parameter state class should be promoted, or whether they would like support in changing their mental state and thus adapting it to the current activity.
[0026] In another case, the assigned vital parameter status class may correspond to the activity status class. If the severity of the status is low, the output unit can suggest to the passenger whether they would like to be supported according to their internal state.
[0027] In another case, the vital parameter state class "Stress" is detected. Then, regardless of the assigned activity state class, the passenger is shown the following suggestion, for example: "We have detected a stressful state in you. Should we help you relax?" By distinguishing between the different cases, the vehicle functions can be adjusted as needed depending on the assessment result.
[0028] In one embodiment, the at least one vital parameter is recorded using an electroencephalography device of the first measuring unit. Using an EEG device allows for particularly reliable assignment of the vital parameter to the vital parameter state class.
[0029] In one embodiment, the activity is recorded using a camera of the second measuring unit. The camera captures the passenger and generates sensor data. By analyzing the sensor data, the passenger's activity can be identified. The sensor data can also be used to record additional vital parameters.
[0030] In one embodiment, fleet data is used to assign the vital parameter to the vital parameter state class and / or to assign the recorded activity to the activity state class.
[0031] For example, artificial intelligence can be trained using fleet data. The fleet data contains, for example, information on recorded vital parameters and the respective assigned vital parameter status classes and / or the recorded activities and the respective assigned activity status classes of a large number of vehicles, in particular more than 10 vehicles, in particular more than 100, and in particular more than 1,000 vehicles. Using the fleet data, the vital parameter is reliably assigned to the vital parameter status class and / or the recorded activity is assigned to the activity status class.
[0032] A further aspect of the invention relates to a system. The system comprises a first measuring unit for recording at least one vital parameter of a person. Furthermore, the system comprises a determination unit for determining a vital parameter status class depending on the recorded vital parameter. The system comprises a second measuring unit for recording an activity of the person, an assignment unit for assigning the recorded activity to an activity status class, and a computing unit for determining an assessment result from a comparison of the assigned vital parameter status class with the assigned activity status class and for setting a function depending on the assessment result.
[0033] Another aspect of the invention relates to a motor vehicle. The motor vehicle has a system according to the invention.
[0034] For use cases or application situations that may arise during the method and which are not explicitly described here, it may be provided that, in accordance with the method, an error message and / or a request for input of feedback from the passenger is issued and / or a standard setting and / or a predetermined initial state is set.
[0035] The invention also includes at least one computing unit for the motor vehicle. The at least one computing unit can have a data processing device or a processor device that is configured to carry out an embodiment of the method according to the invention. For this purpose, the processor device can have at least one microprocessor and / or at least one microcontroller and / or at least one FPGA (Field Programmable Gate Array) and / or at least one DSP (Digital Signal Processor). Furthermore, the processor device can have program code that is configured to carry out the embodiment of the method according to the invention when executed by the processor device. The program code can be stored in a data memory of the processor device. A processor circuit of the processor device can, for example, have at least one circuit board and / or at least one SoC (System on Chip).The invention also includes further developments of the motor vehicle according to the invention and the system according to the invention that have features already described in connection with the further developments of the method according to the invention. For this reason, the corresponding further developments of the motor vehicle according to the invention and the system according to the invention are not described again here.
[0036] The motor vehicle according to the invention is preferably designed as a motor vehicle, in particular as a passenger car or truck, or as a passenger bus.
[0037] As a further solution, the invention also encompasses a computer-readable storage medium comprising instructions which, when executed by a computer or computer network, cause the computer or computer network to carry out an embodiment of the method according to the invention. The storage medium can, for example, be designed at least partially as a non-volatile data memory (e.g., as a flash memory and / or as an SSD - solid state drive) and / or at least partially as a volatile data memory (e.g., as a RAM - random access memory). However, the storage medium can also be operated, for example, as a so-called app store server on the Internet. The computer or computer network can provide a processor circuit with at least one microprocessor. The instructions can be provided as binary code or assembler and / or as source code of a programming language (e.g., C).
[0038] The invention also encompasses combinations of the features of the described embodiments. The invention therefore also encompasses implementations that each comprise a combination of the features of several of the described embodiments, unless the embodiments are described as mutually exclusive.
[0039] Exemplary embodiments of the invention are described below. Figure 1 shows an exemplary embodiment of a flowchart of a method according to the invention;
[0040] Fig. 2 is a schematic representation of an embodiment of modules of a system according to the invention;
[0041] Fig. 3 is a schematic representation of an embodiment of a vehicle with a system according to the invention.
[0042] The exemplary embodiments explained below are preferred embodiments of the invention. In the exemplary embodiments, the described components of the embodiments each represent individual features of the invention that can be considered independently of one another, each of which also develops the invention independently of one another. Therefore, the disclosure is intended to encompass combinations of the features of the embodiments other than those shown. Furthermore, the described embodiments can also be supplemented by further features of the invention already described.
[0043] In the figures, the same reference symbols designate elements with the same function.
[0044] Fig. 1 shows an embodiment of a flowchart for a method for assessing a vital parameter of a passenger of a vehicle 15. In particular, the vehicle 15 is fully autonomous.
[0045] In a step S1, at least one vital parameter of the passenger is recorded using a first measuring unit 5 (Fig. 2). For this purpose, an EEG device can be used, for example, as part of the first measuring unit 5. This can, in particular, be installed in a seat of the vehicle 15. In a step S2, a vital parameter state class is determined depending on the recorded vital parameter. For example, there are the vital parameter state classes "relaxation," "concentration," "sleep," and "stress." A measurement signal from the EEG device can, for example, be evaluated by at least one computing unit 9 (Fig. 3), for example by determining a frequency band of the measurement signal. Depending on the determined frequency band, the corresponding vital parameter state class can then be assigned, if necessary. An exemplary assignment of the frequency bands to the vital parameter state classes can, in particular, be the following.Delta waves with a frequency of 0.1 Hz to <4 Hz can be assigned to the vital parameter class "sleep." Theta waves with a frequency of 4 Hz to <8 Hz can be assigned to the vital parameter class "relaxation." Alpha waves with a frequency of 8 Hz to <13 Hz can be assigned to the vital parameter class "concentration." Beta waves with a frequency between 13 Hz and <30 Hz, especially between 21 Hz and 38 Hz, can be assigned to the vital parameter class "stress."
[0046] In step S3, the passenger's activity is recorded using a second measuring unit 7 (Fig. 2). The second measuring unit 7 may, for example, comprise a camera that is directed, in particular, at the passenger. The camera can generate a further measurement signal, in particular camera images.
[0047] In a step S4, the detected activity is assigned to an activity state class. For this purpose, for example, the further measurement signal, for example from the at least one computing unit 9, is evaluated. For example, the passenger's eyes are part of the camera images. The computing unit 9 can, for example, recognize and analyze the eyes, for example, whether they are moving back and forth to read, are closed, or are directed at something outside the vehicle 15. In one embodiment, an artificial intelligence can be trained for this purpose, for example from the camera images, to recognize an activity of the passenger and assign it to an activity state class. For example, the recognized activity can be assigned to an activity state class "relaxation," "concentration," "sleep," or "stress." In particular, the same activity and vital parameter state classes can exist.
[0048] In step S5, an assessment result is determined from a comparison of the assigned vital parameter state class with the assigned activity state class. For this purpose, it can first be checked whether the vital parameter state class corresponds to the activity state class. In one embodiment, a degree of severity of the vital parameter state class can also be determined. Furthermore, it can be checked, if necessary, whether the vital parameter state class "stress" has been assigned to the vital parameter. The assessment result can then contain, for example, information about whether the vital parameter state class corresponds to the activity state class, the degree of severity, and optionally whether the vital parameter state class "stress" has been assigned to the vital parameter.
[0049] In a step S6, a vehicle function of the vehicle 15 is adjusted depending on the assessment result. For example, a massage function of a vehicle seat of the vehicle 15, an audio system, and / or a video system can be adjusted for this purpose. One goal, for example, can be to change the passenger's vital parameter such that the vital parameter, particularly upon re-measurement of the vital parameter, can be assigned to the vital parameter state class that corresponds to the same activity state class. Another goal can be to increase the degree of severity but not change the vital parameter state class. It is also possible, for example, to suggest to the passenger that they change their activity because their current activity is assigned to an activity state class that does not correspond to the vital parameter state class.The vehicle function can also be configured to assist the passenger when changing their activity. As shown in the flowchart in Fig. 1, steps S3 and S4 can be performed simultaneously with steps S1 and S2, at least temporarily. If necessary, step S5 can only be performed after steps S2 and S4 have been completed.
[0050] Fig. 2 shows a schematic representation of an embodiment of modules of a system according to the invention for assessing at least one vital parameter of the passenger.
[0051] The system can comprise the modules “Sensory current condition” 1 , “Improvement of well-being” 2 , “Sensory current activity” 3 and “Vehicle condition control” 4 .
[0052] The "Sensory Current Condition" module 1 can perform steps S1 and S2. For this purpose, the "Sensory Current Condition" module 1 has, for example, the first measuring unit 5 to perform step S1. In particular, the measuring unit 5 can have an EEG device integrated into a headrest of the vehicle seat. The "Sensory Current Condition" module 1 can also have a determination unit 6 to perform step S2. The determination unit 6 can, in particular, have an artificial intelligence module EEG condition classifier, in particular a neural network. In this case, the vital parameter condition class can be determined according to the vital parameter. Furthermore, the degree of severity can, in particular, be determined.
[0053] The "Sensory Current Activity" module 3 can, for example, perform steps S3 and S4. For example, the "Sensory Current Activity" module 3 can have the second measuring unit 7 and the assignment unit 8. The second measuring unit 7 can have the camera for observing the passenger. The assignment unit 8 can have a passenger activity classifier module, in particular a further neural network, for recognizing the activity and assigning the activity to an activity state class.
[0054] The “Improved Well-being” module can, for example, have at least one computing unit 9 for carrying out step S5 and, if appropriate, an output unit 10. The output unit 10 can output information to the passenger visually and / or acoustically. In particular, the output unit 10 can output the assessment result to the passenger, for example by displaying it on a screen in the vehicle 15. In this case, suggestions can be displayed to the passenger depending on the assessment result. In one embodiment, the passenger can then select whether they would like to be supported in what way. The passenger can select the suggestion, for example, by speech or a haptic input, in particular on the screen.
[0055] For example, if the assessment result shows that the vital parameter state class does not correspond to the activity state class and, in particular, the vital parameter state class is not “stress”, then the passenger can choose whether they would like to be supported in changing the vital parameter so that the assigned vital parameter state class corresponds to the activity state class, or whether they would like to change their activity and maintain the current activity state class and be supported in doing so, or whether they do not want any support.
[0056] In another example, if the assessment result indicates that the vital parameter status class corresponds to the activity status class and, where applicable, the degree of severity falls below a predefined threshold, the passenger can select whether or not they wish to be supported according to their vital parameter status class. The threshold can be statically defined, if appropriate, or it can correspond to the average degree of severity of the previously recorded vital parameters. Optionally, especially if the degree of severity exceeds the predefined threshold, no suggestion can be displayed, and steps S1 to S5 are performed again, particularly after a predefined time interval.
[0057] In yet another example, if the assessment result indicates that the vital parameter status class “stress” has been assigned, the passenger can select whether he or she would like to be supported in relaxing.
[0058] The “vehicle state control” module 4 comprises, for example, a controller 11, an actuator 12, a controlled system 13, and a measuring element 14. Depending on the desired vital parameter state class, different controllers 11 can be used, which in particular carry out step S6. The desired vital parameter state class can be determined in particular depending on the passenger's selection. Possible actuators 12 can be a massage function of a vehicle seat of the vehicle 15 or other settings of the vehicle seat, an audio system of the vehicle 15 for playing music, a brightness or color of an interior lighting of the vehicle 15, or a setting for output on the screen of the vehicle 15. The controlled system 13 can be the passenger, in particular their internal state and / or their well-being.The measuring element 14 can have the first measuring unit 5, which in particular comprises the EEG device, and the determination unit 6, which in particular comprises the EEG state classifier module.
[0059] For example, the desired vital parameter state class may be "relaxation." In this case, a relaxing massage and / or dimmed interior lighting and / or relaxing music can be set. If necessary, the screen can also be turned off. In another example, the desired vital parameter state class may be "concentration." In this case, for example, an activating massage and / or bright interior lighting and / or activating music can be set. If necessary, sights of a current surrounding of the vehicle 15 can be displayed on the screen. In yet another example, the desired vital parameter state class may be "sleep." In this case, for example, dimmed interior lighting and / or a reclining position of the vehicle seat can be set. If necessary, the screen can be turned off.
[0060] If the current vital parameter state class determined by the measuring element 14 corresponds to the desired vital parameter state class, the "Vehicle State Control" module 4 is terminated. Steps S1 to S6 can then be performed again, for example, after a predefined time interval, e.g., 15 minutes.
[0061] Fig. 3 shows a schematic representation of a vehicle 15 having the system for assessing the vital parameters of the passenger of the vehicle 15. The system can, for example, comprise the first measuring unit 5, the second measuring unit 7, the determination unit 6, the allocation unit 8, and at least one computing unit 9. The allocation unit 8 and the determination unit 6 can, in particular, be part of the computing unit 9.
[0062] Step S1 can be carried out by means of the first measuring unit 5, which can in particular comprise an EEG device. Step S2 can be carried out by means of the determination unit 6, which can be designed as a Kl-module EEG state classifier. Step S3 can be carried out by means of the second measuring unit 7, which can comprise the camera. Step S4 can be carried out by means of the allocation unit 8, which can be designed as a Kl-module passenger activity classifier. Steps S5 and S6 can be carried out by means of the computing unit 9. Overall, the examples show in particular how the well-being of the passenger in autonomous ferry operation can be improved through artificial intelligence-based EEG state control.
Claims
PATENT CLAIMS: 1 . A method for assessing a vital parameter of a passenger of a vehicle (15), comprising the following steps: - detecting (S1) at least one vital parameter of the passenger by means of a first measuring unit (5); - Determining (S2) a vital parameter state class depending on the recorded vital parameter; - detecting (S3) an activity of the passenger by means of a second measuring unit (7); - Assigning (S4) the recorded activity to an activity status class; - determining (S5) an assessment result from a comparison of the assigned vital parameter state class with the assigned activity state class; and - Setting (S6) a vehicle function of the vehicle (15) depending on the assessment result.
2. Method according to claim 1, wherein a degree of a state of the assigned vital state class is determined depending on a measured value of the recorded vital parameter and the assessment result is determined depending thereon.
3. Method according to one of the preceding claims, wherein at least one further vital parameter is determined and the vital parameter state class is determined depending on the further vital parameter.
4. Method according to one of the preceding claims, wherein, in order to record the activity, sensor data are generated by means of the second measuring unit (7), which are evaluated by means of artificial intelligence and assigned to an activity which is assigned to the activity state class.
5. Method according to one of the preceding claims, wherein the assessment result is output to the passenger and at least one suggestion is output to the passenger depending on the assessment result and the vehicle function is adjusted depending on the passenger accepting the suggestion.
6. Method according to one of the preceding claims, wherein the at least one vital parameter is recorded by means of an electroencephalography device of the first measuring unit (5).
7. Method according to one of the preceding claims, wherein the activity is recorded by means of a camera of the second measuring unit (7).
8. Method according to one of the preceding claims, wherein fleet data are used to assign the vital parameter to the vital parameter state class and / or to assign the recorded activity to the activity state class.
9. System comprising: - a first measuring unit (5) for detecting at least one vital parameter of a person; - Determination unit (6) for determining a vital parameter state class depending on the recorded vital parameter; - a second measuring unit (7) for recording an activity of the person; - an assignment unit (8) for assigning the recorded activity to an activity status class; and - at least one computing unit (9) for determining an assessment result from a comparison of the associated Vital parameter state class with the associated activity state class and for setting a function depending on the assessment result.
10. Motor vehicle (15) comprising a system according to claim 9.