Safety belt usage state detection method and vehicle

Abstract

The application provides a safety belt use state detection method and a vehicle, and relates to the technical field of automobile safety. The method comprises the following steps: acquiring a state signal of a safety belt buckle and an acceleration signal in a safety belt pulling process; determining whether the safety belt buckle is in an insertion state according to the state signal; if the safety belt buckle is in the insertion state, obtaining a pulling dynamics characteristic of the pulling process based on the acceleration signal; and determining a use state of the safety belt according to the pulling dynamics characteristic and a pre-stored reference characteristic. The reference characteristic is determined based on the acceleration signal in the pulling process of the safety belt under different use conditions, so that whether the safety belt is effectively buckled is inferred by analyzing the dynamics characteristic of the safety belt pulling behavior, the accuracy of safety belt state detection is improved, and the driving safety of the vehicle is improved.

Description

Technical Field

[0001] This application relates to the field of automotive safety technology, and in particular to a method for detecting the usage status of seat belts and a vehicle thereof. Background Technology

[0002] Seat belts are a core component of a vehicle's passive safety system, effectively restraining occupants and reducing the risk of injury or death in a collision. However, in practice, there are various instances where seat belts are not used correctly. For example, occupants may only insert the latch into the buckle but fail to tighten the webbing, or use a separate buckle to avoid vehicle warning signals. These practices leave occupants without effective protection in a collision, posing significant safety hazards.

[0003] In related technologies, the determination of whether a seat belt is used mainly relies on the two states of the latch switch being connected or disconnected, which cannot determine whether the seat belt is actually tightened.

[0004] Therefore, there is a need to provide a method for detecting the usage status of seat belts in order to accurately determine whether the seat belts are actually tightened. Summary of the Invention

[0005] This application provides a method and vehicle for detecting the usage status of a seat belt, so as to accurately identify whether the seat belt is actually tightened.

[0006] In a first aspect, embodiments of this application provide a method for detecting the usage status of a seatbelt, including: Acquire the status signal of the seat belt buckle and the acceleration signal during the seat belt pulling process; Based on the status signal, determine whether the seat belt buckle is in the inserted state; If the seatbelt buckle is in the inserted state, the pulling dynamics characteristics of the pulling process are obtained based on the acceleration signal; The usage state of the seat belt is determined based on the pull-out dynamic characteristics and the pre-stored reference characteristics; wherein, the reference characteristics are determined based on the acceleration signals during the pull-out process corresponding to the seat belt being tightened under different usage conditions.

[0007] Based on the above technical content, the embodiments of this application first determine whether the buckle is in the inserted state according to the status signal of the seat belt buckle, and start the detection of the fastening state after the seat belt buckle is actually inserted, and avoid invalid judgment by setting trigger conditions; when it is determined that the buckle is in the inserted state, the dynamic characteristics of the pull-out process are extracted based on the acceleration signal. The dynamic characteristics can characterize the user's pull-out behavior. The dynamic characteristics are compared with the pre-stored benchmark characteristics. The benchmark characteristics are pre-established based on the pull-out process corresponding to the effective fastening of the seat belt under different usage conditions (such as different body types of occupants, different clothing thicknesses in different seasons, different fastening habits, etc.), which can cover the pull-out behavior characteristics of the effective fastening of the seat belt under diverse usage scenarios. This application's embodiments, by matching dynamic characteristics with reference characteristics, can accurately distinguish between the effectively fastened state of the seat belt and the partially inserted state where the buckle is inserted but not effectively fastened, overcoming the technical limitations of related technologies that rely on the binary judgment of the buckle switch and cannot identify partially inserted states. At the same time, compared with the existing technology's method of identifying the seat belt's usage status based on a single static feature such as the tension value on the seat belt, this application's embodiment, by analyzing the dynamic characteristics of the seat belt's pulling process, can reduce the probability of misjudgment and improve the accuracy of seat belt usage status detection.

[0008] In one possible implementation, the reference feature includes a pull-up dynamics feature reference vector and a pull-up dynamics feature fluctuation range; Before determining the usage state of the seat belt based on the pull-out dynamics characteristics and pre-stored reference characteristics, the method further includes: For each acceleration signal during the pulling process, the corresponding maximum acceleration, acceleration rise time, and tensioning energy are determined based on the acceleration signal; wherein, the acceleration rise time is the time taken for the acceleration signal to change to the maximum acceleration during the pulling process, and the tensioning energy represents the total energy input to the seat belt during the pulling process; Based on the maximum acceleration, acceleration rise time, and tension energy corresponding to each acceleration signal, the corresponding feature vectors are obtained; among them, a feature vector is a vector composed of the maximum acceleration, acceleration rise time, and tension energy during one pull of the seat belt; Cluster analysis is performed on the feature vectors to determine the reference vector of the pull-pull dynamics feature and the fluctuation range of the pull-pull dynamics feature; wherein, the reference vector of the pull-pull dynamics feature is a statistical vector characterizing the central trend of the feature vector, and the fluctuation range of the pull-pull dynamics feature is a statistical matrix characterizing the fluctuation range of the feature vector.

[0009] Based on the above technical content, in this embodiment of the application, the reference features are defined as the pull-pull dynamic feature reference vector and the pull-pull dynamic feature fluctuation range. The reference features are obtained by first extracting the maximum acceleration, acceleration rise time, and tensioning energy from the acceleration signal during the pull-pull process to form a feature vector, and then determining the pull-pull dynamic feature reference vector and the pull-pull dynamic feature fluctuation range through cluster analysis. Since the pull-pull dynamic feature reference vector can characterize the central trend of the feature vector, and the pull-pull dynamic feature fluctuation range can characterize the fluctuation range of the feature vector, the two together constitute a complete description of the statistical distribution of pull-pull behavior under normal tensioning mode, providing a standardized statistical reference for subsequent matching judgment. This makes the comparison between dynamic features and reference features have a quantifiable mathematical basis, avoiding the uncertainty caused by relying on subjective experience to set judgment thresholds, and improving the consistency and repeatability of the judgment.

[0010] In one possible implementation, the pull-out dynamics features include maximum acceleration, acceleration rise time, and tension energy; determining the usage status of the seatbelt based on the pull-out dynamics features and pre-stored reference features includes: Based on the maximum acceleration, acceleration rise time, and tensioning energy in the aforementioned pull-out dynamics characteristics, the feature vector to be detected is obtained; The usage status of the seat belt is determined based on the degree of matching between the feature vector to be detected and the reference vector of the pull-out dynamics feature and the fluctuation range of the pull-out dynamics feature.

[0011] Based on the above technical content, in this embodiment of the application, the pulling dynamics feature is specifically defined as maximum acceleration, acceleration rise time, and tension energy. Based on these three features, a feature vector to be detected is obtained. Then, based on the degree of matching between this feature vector and the reference vector of the pulling dynamics feature and the fluctuation range of the pulling dynamics feature, the usage status of the seat belt is determined. Thus, the essential characteristics of the pulling behavior are comprehensively described from three dimensions: pulling force, urgency, and total input. Compared with a single-dimensional detection method, this can more comprehensively reflect the user's pulling behavior and improve the accuracy and reliability of seat belt usage status identification.

[0012] In one possible implementation, the matching degree includes a Mahalanobis distance determined based on the feature vector to be detected, the reference vector of the pull-up dynamics feature, and the range of fluctuation of the pull-up dynamics feature, and a cosine similarity determined based on the feature vector to be detected and the reference vector of the pull-up dynamics feature; The determination of the seatbelt's usage status based on the matching degree between the detected feature vector and the pull-out dynamic feature reference vector and the pull-out dynamic feature fluctuation range includes: If the Mahalanobis distance is less than or equal to a preset distance threshold, and the cosine similarity is greater than or equal to a preset similarity threshold, then the seat belt is determined to be in a fastened state. If the Mahalanobis distance is greater than the preset distance threshold, or the cosine similarity is less than the preset similarity threshold, then the seat belt is determined to be in a virtual insertion state.

[0013] Based on the above technical content, in this embodiment of the application, Mahalanobis distance and cosine similarity are used to comprehensively judge the degree of matching. The two methods are used to judge the degree of matching between the feature vector to be detected and the benchmark feature from different dimensions. Furthermore, through cross-validation, the accuracy of determining the tight state can be improved.

[0014] In one possible implementation, after determining whether the seatbelt buckle is in the inserted state based on the status signal, the method further includes: If the seatbelt buckle is in the inserted state, the maximum acceleration and tension energy are obtained based on the acceleration signal; The usage status of the seat belt is determined based on the maximum acceleration and the tension energy, as well as the pre-stored maximum acceleration reference value and tension energy reference value; wherein, the maximum acceleration reference value and tension energy reference value are determined based on the acceleration signal during the pulling process corresponding to the tightening of the seat belt in different usage conditions.

[0015] Based on the above technical content, this application provides another feasible method for determining the usage status of seat belts, namely, judging the usage status of seat belts based on maximum acceleration and tension energy, as well as pre-stored maximum acceleration reference values ​​and tension energy reference values. Compared with the feature vector matching judgment method, the above-mentioned single feature threshold judgment method reduces the computational load and can improve the judgment speed with limited resources. In addition, combining the feature vector matching judgment method and the single feature threshold judgment method can improve the flexibility and applicability of the seat belt usage status detection method.

[0016] In one possible implementation, determining the usage status of the seatbelt based on the maximum acceleration and the tension energy, as well as pre-stored maximum acceleration reference values ​​and tension energy reference values, includes: If the maximum acceleration is less than a first preset multiple of the maximum acceleration reference value, or if the tensioning energy is less than a second preset multiple of the tensioning energy reference value, then the seat belt is determined to be in a loose insertion state. The first preset multiple is determined based on the minimum acceleration required for the seat belt to be tightened under different usage conditions, and the second preset multiple is determined based on the minimum tension energy required for the seat belt to be tightened under different usage conditions.

[0017] In this embodiment, the minimum acceleration and minimum tension energy required for the seatbelt to be fastened represent a basic lower limit of pulling force and energy input needed for effective fastening. Below this lower limit, effective fastening is highly unlikely. Therefore, this embodiment uses the minimum acceleration and minimum tension energy required for the seatbelt to be fastened as thresholds, which are compared with the maximum acceleration and tension energy during the pulling process to determine whether the seatbelt's usage status is a false insertion. This intuitive determination method based on physical thresholds is simple to calculate and has a fast response, which helps improve the detection efficiency of the seatbelt's usage status.

[0018] In one possible implementation, the method further includes: If the seatbelt buckle is in the inserted state, the acceleration rise time is obtained based on the acceleration signal; If the maximum acceleration is greater than a third preset multiple of the maximum acceleration reference value, and the acceleration rise time is less than a fourth preset multiple of the acceleration rise time reference value, then the seat belt is determined to be in an abnormally rapid pull-out state. The acceleration rise time reference value is determined based on the acceleration signal during the pulling process corresponding to the tightening of the seat belt in different usage situations. The third preset multiple is determined based on the maximum acceleration required for the seat belt to be tightened in different usage situations. The fourth preset multiple is determined based on the minimum acceleration rise time required for the seat belt to be tightened in different usage situations.

[0019] Based on the above technical content, this application provides another possible seat belt usage state, namely, the abnormally rapid pull-out state, which may occur in vehicle collision scenarios. Here, the maximum acceleration and minimum acceleration rise time required for the seat belt to be fastened represent the upper limit of the effective fastening pull-out behavior. When the maximum acceleration exceeds a certain threshold and the acceleration rise time is less than a certain threshold, it indicates that the occupant is pulling the seat belt with extremely high speed and force, significantly different from normal fastening behavior, and likely indicates an emergency or system malfunction. Based on this, this embodiment uses the maximum acceleration and minimum acceleration rise time required for the seat belt to be fastened as thresholds to determine whether the seat belt usage state is an abnormally rapid pull-out state. The above-mentioned abnormal behavior judgment method based on physical thresholds has the characteristics of simple calculation and fast response, and can promptly identify the occupant's abnormally forceful pulling of the seat belt, enriching the detection dimensions of seat belt usage state.

[0020] In one possible implementation, after determining the usage state of the seatbelt based on the pull-out dynamics characteristics and pre-stored reference characteristics, the method further includes: If the seat belt is in a loose insertion state, the initial alarm priority is determined, and the seat pressure of the seat corresponding to the seat belt within a preset time period is obtained. If the seat pressure remains within the preset seat pressure range for the preset duration, the initial alarm priority is adjusted to increase the alarm priority.

[0021] Based on the above technical content, this application embodiment, after determining a false insertion state, further introduces a seat pressure signal to determine whether there is continuous pressure on the seat, and determines whether the seat pressure is caused by an occupant based on a preset seat pressure range. If there is indeed an occupant on the seat, the false insertion behavior poses a safety risk, and the alarm priority is increased. Correspondingly, if there is no pressure on the seat or the pressure is unstable, it may be due to accidental contact by an object, and there is no need to increase the alarm priority. The above-mentioned alarm priority correction mechanism based on seat pressure can effectively distinguish between a real occupant's false insertion and a false insertion state caused by accidental pressure from an object, avoiding false alarms caused by accidental pressure from an object, and helping to improve the accuracy of alarms and user experience.

[0022] In one possible implementation, there are multiple benchmark features, with different benchmark features corresponding to different users; Determining the usage status of the seat belt based on the pull-out dynamics characteristics and pre-stored reference characteristics includes: Obtain the user identification identifier on the seat corresponding to the seat belt; Based on the user identity identifier, the target benchmark feature is determined from multiple benchmark features; The usage status of the seat belt is determined based on the pull-out dynamics characteristics and the target reference characteristics.

[0023] Based on the above technical content, this application introduces a personalized baseline feature matching mechanism based on user identity identifiers. This involves pre-storing multiple baseline features corresponding to different users, acquiring the user's identity identifier on the seat during detection, determining the target baseline feature from the multiple baseline features based on this identifier, and then matching the target baseline feature with the pull-out dynamics feature. This enables personalized detection for different occupants, adapting to differences in fastening habits and pull-out characteristics among different users, and further improving the accuracy and personalization of seatbelt status detection.

[0024] Secondly, embodiments of this application provide a seatbelt usage status detection device, comprising: The acquisition module is used to acquire the status signal of the seat belt buckle and the acceleration signal during the seat belt pulling process; The processing module is used to determine whether the seat belt buckle is in the inserted state based on the status signal; The processing module is further configured to, if the seatbelt buckle is in the inserted state, obtain the pulling dynamic characteristics of the pulling process based on the acceleration signal; The processing module is further configured to determine the usage status of the seat belt based on the pull-out dynamic characteristics and pre-stored reference characteristics; wherein the reference characteristics are determined based on the acceleration signals during the pull-out process corresponding to the seat belt being tightened under different usage conditions.

[0025] Thirdly, embodiments of this application provide a vehicle including a memory and a processor. The memory stores a computer program that can run on the processor. When the processor executes the computer program, it implements the seat belt usage status detection method as described in any of the first aspects.

[0026] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the seatbelt usage status detection method as described in any of the first aspects.

[0027] It is understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here.

[0028] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this specification. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 This is a schematic diagram of an application scenario provided by an embodiment of this application; Figure 2 This is a schematic flowchart of a seat belt usage status detection method provided in an embodiment of this application; Figure 3 This is a schematic flowchart of a seat belt usage status detection method provided in another embodiment of this application; Figure 4 This is a schematic flowchart of a seat belt usage status detection method provided in another embodiment of this application; Figure 5 This is a schematic diagram of the structure of a seat belt usage status detection device provided in an embodiment of this application; Figure 6This is a schematic diagram of the structure of a vehicle provided in one embodiment of this application. Detailed Implementation

[0031] The present application will be described more clearly below with reference to specific embodiments. These embodiments will help those skilled in the art to further understand the function of the present application, but do not limit the present application in any way. It should be noted that those skilled in the art can make several modifications and improvements without departing from the concept of the present application. These all fall within the protection scope of the present application.

[0032] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0033] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0034] In the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0035] References to "one embodiment" or "some embodiments" in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized. Furthermore, "a plurality" mentioned in the embodiments of this application should be interpreted as two or more.

[0036] Seat belts are a core component of a vehicle's passive safety system, effectively restraining occupants and reducing the risk of injury or death in a collision. However, in practice, there are various instances where seat belts are not used correctly. For example, occupants may only insert the latch into the buckle but fail to tighten the webbing, or use a separate buckle to avoid vehicle warning signals. These practices leave occupants without effective protection in a collision, posing significant safety hazards.

[0037] Some related technologies rely primarily on the on / off state of the buckle switch to determine whether the seatbelt is in use, but cannot determine whether the seatbelt is actually tightened. Other related technologies, after the seatbelt buckle is engaged, determine whether the seatbelt is tightened by detecting whether the tension on the seatbelt exceeds a preset tension threshold or whether the extended length of the seatbelt exceeds a preset length threshold.

[0038] However, the above criteria rely on the static characteristics of the seatbelt after it has been pulled out, ignoring the dynamic signals during the pulling process. Furthermore, the judgment conditions based on set tension or length thresholds are too simplistic to accommodate individual differences in usage scenarios, such as different body types, seasonal clothing thickness, and fastening habits, easily leading to misjudgments or missed judgments. Therefore, a seatbelt usage status detection method is needed to accurately determine whether the seatbelt has been substantially tightened.

[0039] In practice, the applicant has discovered that the effective tightening of a seatbelt involves pulling out identifiable dynamic characteristics. This process is not a simple uniform motion, but a complex dynamic process involving multiple stages, including initiation, acceleration, wrapping around the body, deceleration, and locking. The acceleration waveform generated by this process contains dynamic information characterizing the occupant's pulling behavior. Based on this, in the embodiments of this application, the applicant collects the acceleration signal, extracts the pulling dynamic characteristics, and matches them with pre-established benchmark features to determine whether the seatbelt is effectively tightened. The benchmark features are determined based on the acceleration signals during the pulling process corresponding to the seatbelt tightening under different usage conditions, covering the effective tightening pulling behavior characteristics of seatbelts in diverse usage scenarios, thereby improving the accuracy of seatbelt usage status detection.

[0040] First refer to Figure 1 , Figure 1 The illustration shows an application scenario diagram provided according to an embodiment of this application, in which the equipment involved includes a seat belt usage status detection device and a seat belt.

[0041] The seatbelt usage status detection device stores a computer program to execute the seatbelt usage status detection method provided in this application embodiment. First, the device pre-stores reference features determined based on acceleration signals during the pulling process corresponding to the seatbelt being tightened under different usage conditions. Next, the device can acquire acceleration signals during the seatbelt pulling process using an accelerometer mounted on the seatbelt retractor shaft, and obtain the seatbelt buckle status signal based on a buckle status detection device.

[0042] Based on the above, when the seat belt buckle is determined to be in the inserted state according to the status signal of the seat belt buckle, the pulling dynamic characteristics of the pulling process are obtained based on the acceleration signal, and combined with the pre-stored reference characteristics, it is determined whether the use state of the seat belt is a effectively fastened state or a loosely inserted state where the buckle is inserted but not effectively fastened.

[0043] The following is combined Figure 1 Application scenarios, refer to Figures 2-4 This application describes a seatbelt usage status detection method according to exemplary embodiments thereof. It should be noted that the above application scenarios are shown only to facilitate understanding of the spirit and principles of this application, and the embodiments of this application are not limited in any way. Rather, the embodiments of this application can be applied to any applicable scenario.

[0044] It should be noted that the embodiments of this application can be applied to vehicles, where the vehicle can be a server or a host computer, meaning the seatbelt usage status detection method provided by the exemplary embodiments of this application can be executed on the server or the host computer of the vehicle. Furthermore, this seatbelt usage status detection method can be executed on the same device or on different devices.

[0045] refer to Figure 2 , Figure 2 This is a schematic flowchart illustrating a seatbelt usage status detection method according to an embodiment of this application. The following description uses a seatbelt usage status detection device as the executing entity. Figure 2 As shown, the method in the embodiments of this application may include: Step 201: Obtain the status signal of the seat belt buckle and the acceleration signal during the seat belt pulling process; Step 202: Determine whether the seat belt buckle is in the inserted state based on the status signal.

[0046] Here, the seatbelt buckle refers to a mechanical locking device installed on the side of the seat, used to form a releasable engagement with the latch or insert at the end of the seatbelt webbing. When the latch is inserted into the buckle, the locking mechanism inside the buckle will lock it and trigger an electronic component such as a microswitch or Hall sensor to output an electrical signal, that is, the status signal of the seatbelt buckle, indicating that the seatbelt has been inserted or connected.

[0047] Optionally, the seatbelt buckle status signal uses a high level to indicate that the latch is engaged and a low level to indicate that the latch is not engaged. Typically, when the latch is detected not being engaged, the vehicle will issue a warning to prompt the occupant to fasten their seatbelt.

[0048] In some real-world driving scenarios, although the seatbelt buckle status signal indicates that the latch has inserted into the buckle, the seatbelt is not actually tightened, failing to provide effective restraint for the occupant. For example, an occupant may use a separate latch instead of the seatbelt latch to insert into the buckle to avoid seatbelt warnings, but the seatbelt is not actually tightened. Therefore, this application embodiment uses the seatbelt's acceleration signal to determine whether the seatbelt has been pulled out and whether it has been effectively tightened when the seatbelt buckle status signal indicates that the latch has inserted into the buckle.

[0049] The acceleration signal during the seatbelt pulling process refers to the acceleration waveform data monitored by an acceleration acquisition device, reflecting the change of the webbing pulling action over time as the occupant pulls the seatbelt webbing out of the retractor. This waveform is a dynamic waveform in a time series and can contain dynamic change information such as acceleration, deceleration, and constant speed.

[0050] Acceleration signals can be acquired by integrating a miniature accelerometer at the retractor shaft or by reusing the diagnostic interface of the seatbelt pretensioner system. This requires the accelerometer to have a high sampling rate and sufficient range to capture the complete acceleration waveform at the start, peak, stop, and locking moments of the latch insertion into the buckle.

[0051] Step 203: If the seat belt buckle is in the inserted state, the pulling dynamics characteristics of the pulling process are obtained based on the acceleration signal.

[0052] Understandably, the pulling process of a seatbelt being effectively fastened is not a simple uniform linear motion, but a complex dynamic process involving multiple stages such as initiation, acceleration, wrapping around the body, deceleration, and locking. The acceleration waveform generated by this process contains dynamic information characterizing the occupant's pulling behavior, such as the pulling force, speed, duration, and smoothness of the action. In contrast, the acceleration waveform of a half-hearted insertion (such as only inserting the latch without pulling out the webbing, or only slightly pulling out a small amount of webbing) differs significantly from that of effective fastening in terms of amplitude, duration, and energy. Therefore, by extracting the dynamic characteristics that characterize these differences, effective fastening and half-hearted insertion can be effectively distinguished.

[0053] In this step, the pull-out dynamics feature refers to the quantitative parameters extracted from the acceleration signal during the seatbelt pull-out process, which characterize the dynamic properties of the occupant's pull-out behavior. Optionally, the pull-out dynamics feature may include one or more feature parameters used to describe the force, speed, duration, and variation of the pull-out action.

[0054] Optionally, the acquired acceleration signals are analyzed and processed to extract feature parameters that reflect the dynamic characteristics of the pulling behavior, thus forming a pulling dynamic feature. This pulling dynamic feature can be one-dimensional or multi-dimensional, and the feature parameters it contains can be selected and combined according to the actual application scenario and detection accuracy requirements. For example, the pulling dynamic feature can be a three-dimensional vector composed of maximum acceleration, acceleration rise time, and tensioning energy.

[0055] Here, maximum acceleration refers to the maximum amplitude of the acceleration signal during a single pull. This characteristic reflects the maximum force with which the occupant pulls the seatbelt. Acceleration rise time refers to the time elapsed from the start of a preset threshold (e.g., zero acceleration) to reaching the maximum acceleration. This characteristic reflects the speed or gradualness of the pull action. Tightening energy refers to the total work done by the occupant on the seatbelt during a single pull; this characteristic comprehensively reflects the force and duration of the pull process.

[0056] It should be noted that the pull-out dynamics characteristics can include the maximum acceleration, acceleration rise time, and tensioning energy mentioned above, and can also include other characteristics extracted from the acceleration signal. For example, the acceleration zero-crossing rate and the acceleration rise slope. The acceleration zero-crossing rate refers to the number of times the acceleration signal crosses zero per unit time, reflecting the smoothness or jitter of the pull-out action; the acceleration rise slope refers to the average rate of change of acceleration from the start of the pull-out to the maximum acceleration, reflecting the rapidity of the pull-out start. In practical applications, these characteristics can be flexibly combined to meet the actual needs of seatbelt status detection.

[0057] Step 204: Determine the usage status of the seat belt based on the pull-out dynamic characteristics and the pre-stored reference characteristics; wherein, the reference characteristics are determined based on the acceleration signals during the pull-out process corresponding to the seat belt being tightened under different usage conditions.

[0058] Here, the benchmark feature is a statistically determined feature of the acceleration signal during the pulling process when the seat belt is effectively tightened under different usage conditions (such as different body types of occupants, different clothing thicknesses in different seasons, different tightening habits, etc.), which serves as a reference standard for judging whether the real-time pulling behavior belongs to effective tightening.

[0059] For example, assuming the pull-pull dynamics feature is a three-dimensional vector composed of maximum acceleration, acceleration rise time, and tension energy, the pull-pull dynamics features corresponding to a large number of effective tightening and pulling processes can be statistically analyzed. The mean vector obtained from the statistics can be used as the baseline feature, which can characterize the central trend of the distribution of pull-pull dynamics features of effective tightening behavior. Furthermore, the baseline feature can also include the covariance matrix calculated based on the mean vector, which can characterize the allowable fluctuation range of pull-pull dynamics features for effective tightening behavior. The distribution range constructed based on the mean vector and covariance matrix can comprehensively characterize the cooperative fluctuation space among multiple feature parameters. Compared with single threshold judgment, this better reflects the natural variation characteristics of actual pulling actions, resulting in a lower misjudgment rate and stronger robustness.

[0060] It should be noted that in this step, "different usage scenarios" refers to various factors that affect the seatbelt pull-out dynamics, including but not limited to differences in occupant body shape, clothing thickness, fastening habits, and seat position. For example, occupants of different heights and weights require different pulling force, range of motion, and duration when fastening their seatbelts; clothing thickness affects the frictional resistance between the seatbelt and the body and the smoothness of the pull-out action depending on the season or clothing; different occupants exhibit individual differences in pulling speed, force, and smoothness of action when fastening their seatbelts; changes in the seat's fore-and-aft and up-and-down position affect the relative distance between the retractor and the buckle, thus affecting the travel and duration of the pull-out action. By collecting sample data covering these various scenarios, the broad adaptability of the baseline characteristics can be improved.

[0061] In some embodiments, the pull-out dynamic feature vector obtained in step 203 can be compared with a pre-established benchmark feature, and the seat belt can be determined as to whether it has been effectively tightened based on the comparison result. The comparison can be made using distance measurement, similarity measurement, threshold comparison, or other mathematical methods that can measure the difference or similarity between features, and this application embodiment does not limit the specific methods used.

[0062] This embodiment first determines whether the seatbelt buckle is in the inserted state based on the buckle's status signal, ensuring that the tightening state detection is only initiated after the seatbelt is actually inserted, avoiding invalid judgments. When the buckle is determined to be in the inserted state, the dynamic features of the pull-out process are extracted based on the acceleration signal. These dynamic features characterize the user's pull-out behavior. This dynamic feature is compared with pre-stored benchmark features. The benchmark features are pre-established based on the pull-out process corresponding to the effective tightening of the seatbelt under different usage conditions (such as different body types of occupants, different clothing thicknesses in different seasons, different tightening habits, etc.). Therefore, these benchmark features can cover normal tightening patterns under diverse usage scenarios. By judging the matching degree between the dynamic features and the benchmark features, the "false insertion" behavior (insertion of the buckle but not effective tightening) can be accurately identified. The above-mentioned approach of using dynamic feature matching provides a method to infer the tightening state from the pull-out behavior, upgrading the detection of the seatbelt's usage state from merely judging whether it is inserted to judging whether it is effectively tightened. This achieves effective identification of deceptive behaviors such as false insertion, improving the accuracy of seatbelt status detection and its adaptability in diverse usage scenarios.

[0063] exist Figure 2 Based on the embodiments, another embodiment of this application refines the reference features, defining the reference features as the pull-out dynamic feature reference vector and the pull-out dynamic feature fluctuation range, which are used to describe the distribution of the pull-out behavior features when the seat belt is fastened under different usage conditions. Figure 3 This is a schematic flowchart of a seat belt usage status detection method provided in another embodiment of this application.

[0064] like Figure 3 As shown, the method includes: Step 301: Obtain the status signal of the seat belt buckle and the acceleration signal during the seat belt pulling process; Step 302: Determine whether the seat belt buckle is in the inserted state based on the status signal.

[0065] Here, the seatbelt buckle refers to a mechanical locking device installed on the side of the seat, used to form a releasable engagement with the latch or insert at the end of the seatbelt webbing. Optionally, the seatbelt buckle status signal uses a high level to indicate that the latch is inserted into the buckle, and a low level to indicate that the latch is not inserted into the buckle. Typically, when the latch is detected not being inserted into the buckle, the vehicle will issue a warning to prompt the occupant to fasten their seatbelt.

[0066] Considering that there may be situations where the buckle status signal indicates that the latch has been inserted into the buckle, but the seat belt is not actually tightened, this application embodiment, after determining that the safety buckle is in the inserted state, further determines whether the seat belt is effectively fastened based on the acceleration signal of the seat belt, so as to improve the detection accuracy of the seat belt usage status.

[0067] The acceleration signal refers to the acceleration waveform data monitored by the acceleration acquisition device during the process of the occupant pulling the seat belt webbing out of the retractor, which reflects the change of the webbing pulling action over time. This waveform is a dynamic waveform in time series and can contain dynamic change information such as acceleration, deceleration, and constant speed.

[0068] Step 303: If the seat belt buckle is in the inserted state, the pulling dynamic characteristics of the pulling process are obtained based on the acceleration signal.

[0069] In this step, the pull-out dynamics characteristics refer to the quantitative parameters extracted from the acceleration signal during the seatbelt pull-out process, which characterize the dynamic properties of the occupant's pull-out behavior. In this embodiment, the pull-out dynamics characteristics include maximum acceleration, acceleration rise time, and tensioning energy.

[0070] The maximum acceleration refers to the maximum amplitude of the acceleration signal during a single pull. This characteristic reflects the maximum force an occupant exerts when pulling the seatbelt. Effective fastening typically requires overcoming the seatbelt's retraction force and body resistance, resulting in a significant acceleration peak; while half-pulling often involves less force, leading to a significantly lower maximum acceleration.

[0071] Acceleration rise time refers to the time elapsed from the start of the acceleration signal at a preset threshold (e.g., zero acceleration) to reaching the maximum acceleration. This characteristic reflects the speed or smoothness of the pulling action. Under normal fastening conditions, the occupant's pulling action is usually smooth, with a moderate rise time; however, a sudden, forceful pull or abnormal operation may result in an excessively short rise time.

[0072] Tensioning energy refers to the total energy input into the seatbelt during a single pull-out process, which is the total work done by the occupant on the seatbelt. This characteristic comprehensively reflects the force and duration of the pull-out process. Effective tightening requires pulling out a sufficient length of webbing and overcoming resistance, resulting in greater tensioning energy; while haphazard pulling, due to its short pulling length and weak force, results in significantly less tensioning energy.

[0073] Optionally, the tensioning energy can be obtained by integrating the square of the acceleration signal within the effective time window of a single pulling process. Based on Newton's second law, force is proportional to acceleration, and the work done by the occupant on the seatbelt is equal to the product of force, velocity, and time. Since velocity is proportional to acceleration, the work is proportional to the square of the acceleration. Therefore, the value obtained by integrating the square of the acceleration signal within the effective time window can characterize the tensioning energy.

[0074] In one feasible implementation, before determining the usage status of the seat belt based on the pull-out dynamics characteristics and the pre-stored reference characteristics, steps 304 to 306 are included to obtain reference characteristics, which include a pull-out dynamics feature reference vector and a pull-out dynamics feature fluctuation range.

[0075] Step 304: For each acceleration signal during the pulling process, determine the corresponding maximum acceleration, acceleration rise time, and tensioning energy based on the acceleration signal.

[0076] Among them, the acceleration rise time is the time it takes for the acceleration signal to change to the maximum acceleration during the pulling process, and the tension energy represents the total energy input into the seat belt during the pulling process.

[0077] It should be noted that the definitions of maximum acceleration, acceleration rise time, and tensioning energy in step 304 are the same as those of maximum acceleration, acceleration rise time, and tensioning energy constituting the pulling dynamics in step 303, and will not be repeated here.

[0078] Step 305: Based on the maximum acceleration, acceleration rise time, and tension energy corresponding to each acceleration signal, obtain the corresponding feature vector; wherein, a feature vector is a vector composed of the maximum acceleration, acceleration rise time, and tension energy during one pull of the seat belt; Step 306: Perform cluster analysis on the feature vectors to determine the baseline vector and fluctuation range of the pull-pull dynamics feature; wherein, the baseline vector of the pull-pull dynamics feature is a statistical vector characterizing the central trend of the feature vector, and the fluctuation range of the pull-pull dynamics feature is a statistical matrix characterizing the fluctuation range of the feature vector.

[0079] Among them, the reference vector of the pull-up dynamics feature is the mean vector obtained by statistically analyzing a large number of pull-up dynamics feature vectors. This mean vector is a statistical vector that can characterize the central trend of the feature vectors. Correspondingly, the fluctuation range of the pull-up dynamics feature is the covariance matrix further calculated based on the large number of pull-up dynamics feature vectors and the aforementioned mean vector. This covariance matrix is ​​a statistical matrix that can characterize the fluctuation range of the feature vectors.

[0080] As mentioned above, the baseline features are determined based on the acceleration signals during the tightening and pulling process of the seatbelt under different usage conditions. Therefore, when obtaining the baseline features, it is necessary to collect effective tightening sample data under diverse usage scenarios. For example, multiple occupants of different body types (such as thin, standard, and robust) are invited to perform seatbelt tightening and pulling actions according to the standard method under different seasonal conditions. The acceleration signals during each seatbelt tightening and pulling action are collected to obtain a large amount of effective tightening sample data.

[0081] Based on a large amount of effective fastening sample data, the pulling dynamics features of each seatbelt pulling process are extracted. These features are a three-dimensional feature vector composed of maximum acceleration, acceleration rise time, and tension energy. Next, a large number of such three-dimensional feature vectors are statistically analyzed to calculate the mean vector and covariance matrix. Here, the mean vector and covariance matrix together constitute the baseline features used to describe the statistical distribution of the effective fastening behavior of the seatbelt. The mean vector represents the central position of the effective fastening behavior in the feature space. The covariance matrix represents the fluctuation range of the effective fastening behavior. Each covariance within the covariance matrix can also represent the correlation between different feature parameters; for example, maximum acceleration and tension energy are usually positively correlated.

[0082] The following example illustrates how to obtain the mean vector and covariance matrix, using the mean vector as a three-dimensional eigenvector and the covariance matrix as a 3×3 symmetric matrix.

[0083] The mean vector is obtained by calculating the arithmetic mean μ of the maximum acceleration of all samples. A The arithmetic mean of the acceleration rise time of all samples, μ T The arithmetic mean μ of the tension energy of all samples E The three average values ​​mentioned above constitute the three-dimensional feature vector [μ]. A μ T μ E This yields the mean vector, which reflects the average characteristics of the effective tightening action.

[0084] Based on the mean vector, calculate each element in the covariance matrix. For the three diagonal elements, σ ​​represents the variance of the maximum acceleration. AA σ, the variance of acceleration rise time TT and the variance σ of the tension energy EE For the three off-diagonal elements, let σ be the covariance σ of the maximum acceleration and the tension energy. AE The covariance σ between maximum acceleration and rise time AT The covariance σ between rise time and tension energy TE Where σ represents variance or covariance, subscript A represents maximum acceleration, subscript T represents acceleration rise time, and subscript E represents tension energy.

[0085] In one possible implementation, the pull-out dynamics features include maximum acceleration, acceleration rise time, and tensioning energy; based on the pull-out dynamics features and pre-stored reference features, the usage status of the seat belt is determined, including steps 307 and 308.

[0086] Step 307: Based on the maximum acceleration, acceleration rise time, and tensioning energy in the pull-out dynamics characteristics, obtain the feature vector to be detected.

[0087] Here, the maximum acceleration A, acceleration rise time T, and tensioning energy E extracted from the current pulling process are combined in a preset order to form a three-dimensional feature vector X to be detected. test =[A, T, E]. This feature vector has the same dimensions and feature arrangement order as the pull feature vector used when constructing the baseline features, so as to facilitate subsequent consistency comparison.

[0088] Step 308: Determine the usage status of the seat belt based on the degree of matching between the feature vector to be detected and the reference vector and fluctuation range of the pull-out dynamics feature.

[0089] Here, the feature vector X to be detected test The system is matched against pre-established baseline features, including the baseline vector of pull-up dynamics and the fluctuation range of pull-up dynamics, and the degree of matching between the two is calculated. This degree of matching is used to measure the difference between the current pull-up behavior and the statistical distribution of effective tightening behavior.

[0090] Optionally, preset conditions are set to determine the seat belt's usage status based on the relationship between the matching degree and the preset conditions: when the matching degree meets the preset conditions, the seat belt is determined to be effectively tightened; when the matching degree does not meet the preset conditions, the seat belt is determined to be not effectively tightened. The preset conditions can be set according to the actual application scenario and the method used to measure the matching degree.

[0091] In one possible implementation, the matching degree includes the Mahalanobis distance determined based on the feature vector to be detected, the reference vector of the pull-up dynamics feature, and the range of fluctuation of the pull-up dynamics feature, as well as the cosine similarity determined based on the feature vector to be detected and the reference vector of the pull-up dynamics feature. Step 308, based on the matching degree between the feature vector to be detected and the reference vector of the pull-out dynamics feature and the fluctuation range of the pull-out dynamics feature, determine the usage status of the seat belt, including: (1.1) If the Mahalanobis distance is less than or equal to the preset distance threshold and the cosine similarity is greater than or equal to the preset similarity threshold, then the seat belt is determined to be in a fastened state. (1.2) If the Mahalanobis distance is greater than the preset distance threshold, or the cosine similarity is less than the preset similarity threshold, then the seat belt is determined to be in a virtual insertion state.

[0092] In this implementation, the matching degree includes two dimensions: Mahalanobis distance and cosine similarity. Mahalanobis distance measures the overall deviation between the detected feature vector and the baseline feature distribution, while cosine similarity measures the directional similarity between the detected feature vector and the baseline vector of the pull-pull dynamics feature.

[0093] Here, Mahalanobis distance is a distance metric that considers the distribution characteristics of data. Optionally, the mean vector is used as the reference vector of the pull dynamics feature, and the covariance matrix is ​​used as the fluctuation range of the pull dynamics feature. The Mahalanobis distance is determined as follows: based on the difference between the feature vector to be detected and the mean vector, the difference vector is determined; the covariance matrix is ​​inverted to obtain the inverse matrix; the difference vector, the transpose of the difference vector, and the inverse matrix are multiplied and then the square root is taken.

[0094] For example, the formula for calculating Mahalanobis distance is as follows:

[0095] Where μ is the mean vector, X test Let be the feature vector to be detected, and Σ be the covariance matrix. The difference vector is (X... test -μ).

[0096] Here, the preset distance threshold is the boundary value for determining whether the feature vector to be tested belongs to the effective tightness statistical distribution range. By comparing the Mahalanobis distance with the preset distance threshold, it can be determined whether the current pulling behavior belongs to the effective tightness statistical distribution range. The smaller the Mahalanobis distance, the closer the detected feature vector X is to the effective tightness statistical distribution range. test The closer it is to the baseline characteristic distribution.

[0097] A feasible method for determining the preset distance threshold is as follows: calculate the Mahalanobis distance between each sample and the baseline feature, and determine the corresponding Mahalanobis distance quantile as the preset distance threshold based on a preset confidence level. Assuming a preset confidence level of 95%, the Mahalanobis distance that would allow 95% of the samples to be considered to have their seatbelts effectively fastened would be used as the preset distance threshold.

[0098] Optionally, cosine similarity is a metric that measures the degree of similarity between two vectors in a direction. Using the mean vector as the reference vector for pull dynamics features, the cosine similarity is determined as follows: based on the dot product of the feature vector to be detected and the mean vector, the cosine similarity is determined according to the dot product, the magnitude of the feature vector to be detected, and the magnitude of the mean vector. Specifically, the formula for calculating cosine similarity is as follows:

[0099] Here, θ represents the angle between the two vectors. Cosine similarity is typically between 0 and 1; the closer the value is to 1, the more similar the direction of the current pulling action is to the effective tightening action. The preset similarity threshold can be an empirical value, such as 0.9.

[0100] This implementation employs a dual verification mechanism. When the Mahalanobis distance is less than or equal to a preset distance threshold, and the cosine similarity is greater than or equal to a preset similarity threshold, it indicates that the current pulling action falls within the statistical distribution range of effective fastening and is consistent with effective fastening action in direction. Therefore, the seatbelt is determined to be in a fastened state. When the Mahalanobis distance is greater than the preset distance threshold, or the cosine similarity is less than the preset similarity threshold, it indicates that the current pulling action either deviates from the statistical distribution range of effective fastening or is inconsistent with effective fastening action in direction. Therefore, the seatbelt is determined to be in a loosely inserted state, not effectively tightened. Compared to methods that rely solely on Mahalanobis distance or cosine similarity for verification, this approach improves the accuracy and robustness of the identification.

[0101] In one possible implementation, after determining the usage status of the seat belt based on the pull-out dynamics characteristics and pre-stored reference characteristics, steps 309 and 310 are further included.

[0102] Step 309: If the seat belt is in a loose insertion state, determine the initial alarm priority and obtain the seat pressure of the seat corresponding to the seat belt within a preset time period.

[0103] Optionally, when it is determined that the current seat belt is in a loose insertion state, the seat belt usage status detection device first determines an initial alarm priority. At the same time, in order to further assess the actual risk level of the loose insertion behavior, it acquires the pressure signal collected by the seat pressure sensor on the seat within a preset time period to determine whether there is an occupant in the seat.

[0104] Here, the initial alarm priority can be a preset primary priority, and the corresponding alarm mode is a voice prompt or an alarm light flashing.

[0105] Step 310: If the seat pressure is within the preset seat pressure range within the preset time period, the initial alarm priority is corrected to increase the alarm priority.

[0106] Optionally, if the seat pressure value is continuously monitored within a preset seat pressure range for a preset time period, it indicates that there is indeed an occupant sitting in the seat. In this case, the false insertion behavior will directly threaten the safety of the occupant, so the initial alarm priority is adjusted upwards, for example, from low priority to high priority, to remind the occupant to properly fasten the seat belt. If there is no occupant in the seat, the initial alarm priority can be maintained to provide an alarm prompt, or no alarm can be triggered.

[0107] Here, the preset seat pressure range is determined in advance based on the seat pressure values ​​when an occupant is seated, and is used to determine whether there is an occupant in the seat. For example, seat pressure values ​​can be collected from multiple occupants of different body types in their normal seated state, and the pressure characteristic range when the seat is occupied can be statistically analyzed and used as the preset seat pressure range. When the measured pressure value falls within this range, it indicates that there is an occupant in the seat; when the measured pressure value is significantly lower than this range, it indicates that there is no occupant in the seat.

[0108] In one possible implementation, to further enhance personalized adaptation capabilities, individual baseline characteristics can be established for different occupants. Therefore, there are multiple baseline characteristics, with different users corresponding to different baseline characteristics. Typically, the vehicle is initially configured with default baseline characteristics. Optionally, after a user establishes a usage relationship with the vehicle, the vehicle can be instructed to modify the default baseline characteristics based on the user's own characteristics, thereby obtaining baseline characteristics that are more suitable for that user.

[0109] Optionally, the usage status of the seat belt is determined based on the pull-out dynamics characteristics and pre-stored reference characteristics, including: (2.1) Obtain the user identification identifier on the seat corresponding to the seat belt; (2.2) Based on user identity, determine the target benchmark feature from multiple benchmark features; (2.3) Determine the usage status of the seat belt based on the pull-out dynamics characteristics and the target reference characteristics.

[0110] In this implementation, the user's identification on the seat corresponding to the seat belt can be obtained through methods such as facial recognition, fingerprint recognition, or Bluetooth pairing with a mobile phone. Based on the user's identification, a target reference feature corresponding to that user is determined from multiple pre-stored reference features. Then, the target reference feature is matched with the real-time extracted pull-out dynamic features to determine the seat belt's usage status. This process can improve the accuracy of personalized vehicle adaptation, avoid misjudgments caused by individual differences, and further improve detection accuracy.

[0111] In this embodiment, the pulling dynamics features extracted based on acceleration signals include the maximum acceleration amplitude, acceleration rise time, and total energy input during the pulling process. The maximum acceleration amplitude reflects the maximum pulling force of the occupant, the acceleration rise time reflects the urgency of the pulling, and the total energy comprehensively reflects the overall effect of the pulling force and duration. These three features jointly characterize the essential features of the pulling behavior from different dimensions. During the comparison of the extracted dynamics features with pre-stored benchmark features, a dual determination of the matching degree is made using Mahalanobis distance and cosine similarity between the dynamics features and the benchmark features, which helps improve the accuracy of seatbelt usage status detection. Additionally, seat pressure is detected to assist in determining whether there is an occupant in the seat, enabling accurate alarms and avoiding misjudgments that could interfere with alarms.

[0112] Figure 4 This is a flowchart of a seatbelt usage status detection method provided in another embodiment of this application. It provides a method for determining seatbelt usage status based on feature parameters and set feature thresholds, compared to... Figure 3 The method for determining seatbelt usage status based on feature vector matching in this embodiment reduces computational load and improves efficiency. In practical applications, the two methods for determining seatbelt usage status can be combined to improve the flexibility and applicability of the seatbelt usage status detection method. Cross-validation can also improve the reliability of the determination results.

[0113] in addition, Figure 4 In determining the seat belt usage status, the embodiment identifies not only the loose insertion state but also the abnormal rapid pulling state of the seat belt, enriching the detection dimensions of the seat belt usage status. When an alarm is triggered because the seat belt is not effectively fastened, distinguishing between the loose insertion state and the abnormal rapid pulling state can improve the accuracy of the alarm.

[0114] like Figure 4 As shown, the method includes: Step 401: Obtain the status signal of the seat belt buckle and the acceleration signal during the seat belt pulling process; Step 402: Determine whether the seat belt buckle is in the inserted state based on the status signal.

[0115] Here, the implementation methods for steps 401 and 402 are described in [reference needed]. Figure 2 The relevant descriptions in the embodiments will not be repeated here.

[0116] In one possible implementation, after determining in step 402 whether the seatbelt buckle is in the inserted state based on the status signal, the method further includes: Step 403: If the seatbelt buckle is in the inserted state, the maximum acceleration and tension energy are obtained based on the acceleration signal.

[0117] Here, the maximum acceleration and tension energy are the same as those mentioned above. Figure 3 The maximum acceleration and tensioning energy in the pull-out dynamics characteristics of the embodiment are the same, and will not be repeated here.

[0118] Step 404: Determine the usage status of the seat belt based on the maximum acceleration and tension energy, as well as the pre-stored maximum acceleration reference value and tension energy reference value. The maximum acceleration reference value and tension energy reference value are determined based on the acceleration signals during the pulling process corresponding to the seat belt being tightened in different usage situations.

[0119] In this implementation, the maximum acceleration benchmark value can be an average value determined statistically based on the maximum acceleration during the pulling process when the seat belt is effectively tightened under different usage conditions. This average value serves as a reference threshold for judging whether the real-time pulling force is effective. For example, the arithmetic mean of the maximum accelerations in all samples can be used as the maximum acceleration benchmark value.

[0120] Similarly, the tension energy benchmark can be an average value determined statistically based on the tension energy during the pull-out process when the seat belt is effectively tightened under different usage conditions. This average value serves as a reference threshold for judging whether the total real-time pull-out energy is effective. For example, the arithmetic mean of the tension energy in all samples can be used as the tension energy benchmark.

[0121] Optionally, the above-mentioned benchmark value can be directly used as the judgment threshold of the corresponding feature parameter to determine the seat belt usage status; alternatively, the above-mentioned benchmark value can be scaled by a preset multiple and used as the judgment threshold of the corresponding feature parameter to determine the seat belt usage status.

[0122] This implementation determines the seatbelt usage status by combining a single dynamic characteristic parameter with a corresponding reference threshold. Compared to methods that use a feature vector composed of multiple dynamic characteristic parameters, a reference vector of the pull-out dynamic characteristic, and the fluctuation range of the pull-out dynamic characteristic to determine the seatbelt usage status, the above implementation is simpler and more intuitive, with less computation and faster judgment speed. However, due to the single criterion, it is prone to misjudgment. Therefore, the two methods for determining the seatbelt usage status can be flexibly configured to balance the accuracy and efficiency of seatbelt usage status detection.

[0123] Optionally, step 403 determines the usage status of the seatbelt based on the maximum acceleration and tension energy, as well as pre-stored maximum acceleration reference values ​​and tension energy reference values, including: If the maximum acceleration is less than a first preset multiple of the maximum acceleration reference value, or if the tensioning energy is less than a second preset multiple of the tensioning energy reference value, then the seat belt is determined to be in a loose insertion state. The first preset multiplier is determined based on the minimum acceleration required for the seat belt to be tightened under different usage conditions, and the second preset multiplier is determined based on the minimum tension energy required for the seat belt to be tightened under different usage conditions.

[0124] Understandably, both the first and second preset multiples are positive numbers less than 1, used to further lower the judgment threshold based on the benchmark value in order to identify significantly insufficient interpolation behavior, rather than normal fluctuations caused by individual differences.

[0125] The first preset multiplier is determined based on the minimum acceleration required for the seatbelt to be effectively tightened under different usage conditions. Physically, for the seatbelt to be effectively tightened, the pulling process must overcome the retractor's return force and body resistance, requiring a minimum peak acceleration value. This minimum acceleration value is the physical lower limit for effective tightening. The first preset multiplier is used to convert this physical lower limit into a proportional coefficient relative to the maximum acceleration reference value. If the current maximum acceleration is lower than the product of the maximum acceleration reference value and the first preset multiplier, it indicates that the pulling force is insufficient to achieve effective tightening, i.e., a weak insertion state.

[0126] Similarly, the second preset multiplier is determined based on the minimum tension energy required for the seatbelt to be effectively tightened under different usage conditions. The minimum tension energy refers to the lower limit of energy required to effectively tighten the seatbelt. The second preset multiplier is used to convert this lower energy limit into a proportional coefficient relative to a baseline tension energy value. If the current tension energy is lower than the product of the baseline tension energy value and the second preset multiplier, it indicates that the pulling energy is insufficient to achieve effective tightening, i.e., a false insertion state.

[0127] In some embodiments, in addition to the false insertion state, the seat belt also has an abnormally rapid pull-out state, which also shows a low degree of matching with the baseline features. In order to further distinguish between the false insertion state and the abnormally rapid pull-out state, specific feature parameters can be used for confirmation.

[0128] In one possible implementation, after determining in step 402 whether the seatbelt buckle is in the inserted state based on the status signal, the method further includes: Step 405: If the seatbelt buckle is in the inserted state, the acceleration rise time is obtained based on the acceleration signal.

[0129] Here, the acceleration rise time and maximum acceleration are used to determine the abnormally rapid pulling state. Based on the aforementioned knowledge, the acceleration rise time refers to the time elapsed from the preset start threshold or the moment when the acceleration signal begins to increase until the maximum acceleration is reached, which is used to reflect the urgency or smoothness of the pulling action.

[0130] Step 406: If the maximum acceleration is greater than a third preset multiple of the maximum acceleration reference value, and the acceleration rise time is less than a fourth preset multiple of the acceleration rise time reference value, then the seat belt is determined to be in an abnormally rapid pull-out state. The acceleration rise time reference value is determined based on the acceleration signal during the pull-out process corresponding to the seat belt being tightened in different usage situations. The third preset multiple is determined based on the maximum acceleration required for the seat belt to be tightened in different usage situations. The fourth preset multiple is determined based on the minimum acceleration rise time required for the seat belt to be tightened in different usage situations.

[0131] Here, the maximum acceleration reference value is the same as the maximum acceleration reference value in step 404, and will not be repeated. The third preset multiple is determined based on the maximum acceleration required for the seat belt to be effectively tightened under different usage conditions. Physically speaking, abnormally rapid pulling usually occurs in emergency situations, where the occupant pulls the seat belt with great force, at which point the maximum acceleration is significantly higher than the normal tightening level. The third preset multiple is used to identify this abnormally large pulling force, and its value is greater than 1, for example, 1.5. If the currently obtained maximum acceleration is greater than the product of the maximum acceleration reference value and the third preset multiple, it indicates that the pulling force is abnormally large, thus it can be inferred that the occupant has encountered an emergency or that the device has misjudged the situation.

[0132] Furthermore, the acceleration rise time benchmark can be an average value determined statistically based on the acceleration rise time during the pulling process when the seat belt is effectively tightened under different usage conditions. This average value can be used as a reference standard to judge whether the urgency of the pulling action is abnormal. For example, the arithmetic mean of the acceleration rise time in all samples can be used as the acceleration rise time benchmark value.

[0133] The fourth preset multiplier is determined based on the minimum acceleration rise time required for the seatbelt to be effectively tightened under different usage conditions. During an abnormally rapid pull, the occupant pulls the seatbelt sharply, causing the acceleration to rapidly climb to its peak value, with a rise time significantly shorter than the normal tightening level. The fourth preset multiplier is used to identify this abnormally short rise time, and its value is less than 1, for example, 0.3. When the acceleration rise time is less than the product of the baseline acceleration rise time and the fourth preset multiplier, it indicates an abnormally rapid pull.

[0134] In this implementation, an abnormally rapid pull is only identified when both the maximum acceleration is abnormally high and the acceleration rise time is abnormally short. This is because during normal fastening, even if individual occupants pull with great force, the rise time is usually still within the normal range; only when both abnormal conditions are met simultaneously can an emergency pull be reliably identified.

[0135] In some embodiments, a user alarm is not directly triggered after an abnormally rapid pull-out is detected, in order to avoid unnecessary interference to occupants in emergency situations. In this case, an event snapshot, such as the vehicle speed and acceleration a few seconds before the pull-out, can be stored in the vehicle event data logger for subsequent diagnostic analysis or accident tracing.

[0136] It should be noted that, Figure 4 The implementation provides a rapid identification capability for dummy insertion states with lower computational cost and implementation complexity, while also extending the detection of abnormal rapid pull-out states, and has good engineering practical value.

[0137] Figure 4 The threshold determination method in the embodiment and Figure 3 The feature vector matching methods in the embodiments are not mutually exclusive; they can be flexibly configured according to the actual application scenario. For example, a cascaded strategy can be adopted: first use the computationally less computationally intensive method. Figure 4 The method performs rapid filtering, and for blurry samples near the threshold boundary, it calls... Figure 3 One approach involves precise judgment; another is to employ a parallel strategy: running both methods simultaneously and cross-validating the results to improve reliability. This combination of methods achieves both accuracy and efficiency in seatbelt usage status detection.

[0138] In summary, this application embodiment, by acquiring the seatbelt buckle status signal and the acceleration signal during the pulling process, extracts multi-dimensional dynamic features and matches or compares them with benchmark features, which can accurately distinguish between a valid fastening state and a loose insertion state, and further identify abnormally rapid pulling states. This application embodiment can accurately and efficiently identify the actual usage state of the seatbelt, effectively solve the problem of difficulty in detecting loose insertion behavior, and improve the intelligence level of the vehicle's passive safety system and the occupant safety protection capability.

[0139] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0140] Figure 5 This is a schematic diagram of the structure of a seat belt usage status detection device provided in an embodiment of this application. Figure 5 As shown, the seat belt usage status detection device provided in this embodiment may include: an acquisition module 501 and a processing module 502.

[0141] The acquisition module 501 is used to acquire the status signal of the seat belt buckle and the acceleration signal during the seat belt pulling process. The processing module 502 is used to determine whether the seat belt buckle is in the inserted state based on the status signal; The processing module 502 is also used to obtain the pulling dynamic characteristics of the pulling process based on the acceleration signal if the seat belt buckle is in the inserted state. The processing module 502 is also used to determine the usage status of the seat belt based on the pull-out dynamic characteristics and the pre-stored reference characteristics; wherein, the reference characteristics are determined based on the acceleration signals during the pull-out process corresponding to the seat belt being tightened under different usage conditions.

[0142] In one possible implementation, the reference features include a pull-out dynamics feature reference vector and a pull-out dynamics feature fluctuation range. Before determining the seat belt's usage status based on the pull-out dynamics feature and the pre-stored reference features, the processing module 502 is further configured to, for each acceleration signal during the pull-out process, determine the corresponding maximum acceleration, acceleration rise time, and tensioning energy based on the acceleration signal. The acceleration rise time is the time it takes for the acceleration signal to change to the maximum acceleration during the pull-out process, and the tensioning energy represents the total energy input to the seat belt during the pull-out process. The processing module 502 is also used to obtain corresponding feature vectors based on the maximum acceleration, acceleration rise time and tension energy corresponding to each acceleration signal; wherein, a feature vector is a vector composed of the maximum acceleration, acceleration rise time and tension energy during one pull of the seat belt; The processing module 502 is also used to perform cluster analysis on the feature vectors to determine the reference vector and fluctuation range of the pull-pull dynamics feature; wherein, the reference vector of the pull-pull dynamics feature is a statistical vector characterizing the central trend of the feature vector, and the fluctuation range of the pull-pull dynamics feature is a statistical matrix characterizing the fluctuation range of the feature vector.

[0143] In one possible implementation, the pull-up dynamics characteristics include maximum acceleration, acceleration rise time, and tension energy; Processing module 502 is specifically used to obtain the feature vector to be detected based on the maximum acceleration, acceleration rise time and tensioning energy in the pull-out dynamics characteristics; The processing module 502 is further used to determine the usage status of the seat belt based on the degree of matching between the feature vector to be detected and the reference vector of the pull-out dynamics feature and the fluctuation range of the pull-out dynamics feature.

[0144] In one possible implementation, the degree of matching includes the Mahalanobis distance between the feature vector to be detected and the reference vector of the pull-up dynamics feature and the range of the pull-up dynamics feature, as well as the cosine similarity between the feature vector to be detected and the reference vector of the pull-up dynamics feature. The processing module 502 is specifically used to determine the seat belt usage state as a fastened state if the Mahalanobis distance is less than or equal to a preset distance threshold and the cosine similarity is greater than or equal to a preset similarity threshold. The processing module 502 is further used to determine the seat belt usage state as a virtual insertion state if the Mahalanobis distance is greater than a preset distance threshold, or the cosine similarity is less than a preset similarity threshold.

[0145] In one possible implementation, after determining whether the seat belt buckle is in the inserted state based on the state signal, the processing module 502 is further configured to obtain the maximum acceleration and tension energy based on the acceleration signal if the seat belt buckle is in the inserted state. The processing module 502 is also used to determine the usage status of the seat belt based on the maximum acceleration and tension energy, as well as the pre-stored maximum acceleration reference value and tension energy reference value; wherein, the maximum acceleration reference value and tension energy reference value are determined based on the acceleration signal during the pulling process corresponding to the tightening of the seat belt in different usage situations.

[0146] In one possible implementation, the processing module 502 is specifically used to determine that the seat belt is in a false insertion state if the maximum acceleration is less than a first preset multiple of the maximum acceleration reference value, or if the tensioning energy is less than a second preset multiple of the tensioning energy reference value. The first preset multiplier is determined based on the minimum acceleration required for the seat belt to be tightened under different usage conditions, and the second preset multiplier is determined based on the minimum tension energy required for the seat belt to be tightened under different usage conditions.

[0147] In one possible implementation, the processing module 502 is also used to obtain the acceleration rise time based on the acceleration signal; The processing module 502 is also used to determine that the seat belt is in an abnormally rapid pull-out state if the maximum acceleration is greater than a third preset multiple of the maximum acceleration reference value and the acceleration rise time is less than a fourth preset multiple of the acceleration rise time reference value. The acceleration rise time reference value is determined based on the acceleration signal during the pull-out process corresponding to the seat belt being tightened in different usage situations. The third preset multiple is determined based on the maximum acceleration required for the seat belt to be tightened in different usage situations. The fourth preset multiple is determined based on the minimum acceleration rise time required for the seat belt to be tightened in different usage situations.

[0148] In one possible implementation, after determining the usage status of the seat belt based on the pull-out dynamics characteristics and the pre-stored reference characteristics, the processing module 502 is further configured to determine the initial alarm priority and obtain the seat pressure of the seat corresponding to the seat belt within a preset time if the usage status of the seat belt is a false insertion state. The processing module 502 is also used to correct the initial alarm priority if the seat pressure is within the preset seat pressure range within a preset time period, so as to improve the alarm priority.

[0149] In one possible implementation, there are multiple baseline features, with different users corresponding to different baseline features; Processing module 502 is specifically used to obtain the user identification identifier on the seat corresponding to the seat belt; The processing module 502 is further configured to determine the target baseline feature from multiple baseline features based on the user's identity identifier; The processing module 502 is also used to determine the usage status of the seat belt based on the pull-out dynamics characteristics and the target reference characteristics.

[0150] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0151] Figure 6 This is a schematic diagram of the structure of a vehicle provided in one embodiment of this application. Figure 6 As shown, the vehicle in this embodiment includes a processor 610 and a memory 620, wherein the memory 620 stores a computer program 621 that can run on the processor 610. When the processor 610 executes the computer program 621, it implements the steps in any of the above method embodiments, for example... Figure 2 Steps 201 to 204 are shown. Alternatively, when processor 610 executes computer program 621, it implements the functions of each module / unit in the above-described device embodiments, for example... Figure 5 The functions of the acquisition module 501 and the processing module 502 are shown.

[0152] For example, computer program 621 may be divided into one or more modules / units, one or more of which are stored in memory 620 and executed by processor 610 to complete this application. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 621 in a vehicle.

[0153] Those skilled in the art will understand that Figure 6 This is merely an example of a vehicle and does not constitute a limitation on the vehicle. It may include more or fewer components than shown, or combinations of certain components, or different components, such as input / output devices, network access devices, buses, etc.

[0154] The processor 610 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0155] The memory 620 can be an internal storage unit of the vehicle, such as a hard drive or memory, or an external storage device, such as a plug-in hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc. The memory 620 can also include both internal and external storage devices. The memory 620 is used to store computer programs and other programs and data required by the vehicle. The memory 620 can also be used to temporarily store data that has been output or will be output.

[0156] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0157] An embodiment of this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described seatbelt usage status detection method.

[0158] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0159] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0160] In the embodiments provided in this application, it should be understood that the disclosed devices / vehicles and methods can be implemented in other ways. For example, the device / vehicle embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0161] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0162] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0163] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0164] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for detecting the usage status of a seatbelt, characterized in that, include: Acquire the status signal of the seat belt buckle and the acceleration signal during the seat belt pulling process; Based on the status signal, determine whether the seat belt buckle is in the inserted state; If the seatbelt buckle is in the inserted state, the pulling dynamics characteristics of the pulling process are obtained based on the acceleration signal; The usage state of the seat belt is determined based on the pull-out dynamic characteristics and the pre-stored reference characteristics; wherein, the reference characteristics are determined based on the acceleration signals during the pull-out process corresponding to the seat belt being tightened under different usage conditions.

2. The method for detecting the usage status of a seat belt according to claim 1, characterized in that, The reference features include the pull-out dynamics feature reference vector and the pull-out dynamics feature fluctuation range; Before determining the usage state of the seat belt based on the pull-out dynamics characteristics and pre-stored reference characteristics, the method further includes: For each acceleration signal during the pulling process, the corresponding maximum acceleration, acceleration rise time, and tensioning energy are determined based on the acceleration signal; wherein, the acceleration rise time is the time taken for the acceleration signal to change to the maximum acceleration during the pulling process, and the tensioning energy represents the total energy input to the seat belt during the pulling process; Based on the maximum acceleration, acceleration rise time, and tension energy corresponding to each acceleration signal, the corresponding feature vectors are obtained; among them, a feature vector is a vector composed of the maximum acceleration, acceleration rise time, and tension energy during one pull of the seat belt; Cluster analysis is performed on the feature vectors to determine the reference vector of the pull-pull dynamics feature and the fluctuation range of the pull-pull dynamics feature; wherein, the reference vector of the pull-pull dynamics feature is a statistical vector characterizing the central trend of the feature vector, and the fluctuation range of the pull-pull dynamics feature is a statistical matrix characterizing the fluctuation range of the feature vector.

3. The method for detecting the usage status of a seatbelt according to claim 2, characterized in that, The pull-out dynamics characteristics include maximum acceleration, acceleration rise time, and tensioning energy; Determining the usage status of the seat belt based on the pull-out dynamics characteristics and pre-stored reference characteristics includes: Based on the maximum acceleration, acceleration rise time, and tensioning energy in the aforementioned pull-out dynamics characteristics, the feature vector to be detected is obtained; The usage status of the seat belt is determined based on the degree of matching between the feature vector to be detected and the reference vector of the pull-out dynamics feature and the fluctuation range of the pull-out dynamics feature.

4. The method for detecting the usage status of a seat belt according to claim 3, characterized in that, The matching degree includes the Mahalanobis distance determined based on the feature vector to be detected, the reference vector of the pull-up dynamics feature, and the fluctuation range of the pull-up dynamics feature, and the cosine similarity determined based on the feature vector to be detected and the reference vector of the pull-up dynamics feature; The determination of the seatbelt's usage status based on the matching degree between the detected feature vector and the pull-out dynamic feature reference vector and the pull-out dynamic feature fluctuation range includes: If the Mahalanobis distance is less than or equal to a preset distance threshold, and the cosine similarity is greater than or equal to a preset similarity threshold, then the seat belt is determined to be in a fastened state. If the Mahalanobis distance is greater than the preset distance threshold, or if the cosine similarity is less than the preset similarity threshold, then the seat belt is determined to be in a virtual insertion state.

5. The method for detecting the usage status of a seat belt according to any one of claims 1 to 4, characterized in that, After determining whether the seatbelt buckle is in the inserted state based on the status signal, the method further includes: If the seatbelt buckle is in the inserted state, the maximum acceleration and tension energy are obtained based on the acceleration signal; The usage status of the seat belt is determined based on the maximum acceleration and the tension energy, as well as the pre-stored maximum acceleration reference value and tension energy reference value; wherein, the maximum acceleration reference value and tension energy reference value are determined based on the acceleration signal during the pulling process corresponding to the tightening of the seat belt in different usage conditions.

6. The method for detecting the usage status of a seat belt according to claim 5, characterized in that, Determining the usage status of the seat belt based on the maximum acceleration and the tension energy, as well as pre-stored maximum acceleration reference values ​​and tension energy reference values, includes: If the maximum acceleration is less than a first preset multiple of the maximum acceleration reference value, or if the tensioning energy is less than a second preset multiple of the tensioning energy reference value, then the seat belt is determined to be in a loose insertion state. The first preset multiple is determined based on the minimum acceleration required for the seat belt to be tightened under different usage conditions, and the second preset multiple is determined based on the minimum tension energy required for the seat belt to be tightened under different usage conditions.

7. The method for detecting the usage status of a seat belt according to claim 5, characterized in that, The method further includes: If the seatbelt buckle is in the inserted state, the acceleration rise time is obtained based on the acceleration signal; If the maximum acceleration is greater than a third preset multiple of the maximum acceleration reference value, and the acceleration rise time is less than a fourth preset multiple of the acceleration rise time reference value, then the seat belt is determined to be in an abnormally rapid pull-out state. The acceleration rise time reference value is determined based on the acceleration signal during the pulling process corresponding to the tightening of the seat belt in different usage situations. The third preset multiple is determined based on the maximum acceleration required for the seat belt to be tightened in different usage situations. The fourth preset multiple is determined based on the minimum acceleration rise time required for the seat belt to be tightened in different usage situations.

8. The method for detecting the usage status of a seat belt according to any one of claims 1 to 4, characterized in that, After determining the usage state of the seat belt based on the pull-out dynamics characteristics and pre-stored reference characteristics, the method further includes: If the seat belt is in a loose insertion state, the initial alarm priority is determined, and the seat pressure of the seat corresponding to the seat belt within a preset time period is obtained. If the seat pressure remains within the preset seat pressure range for the preset duration, the initial alarm priority is adjusted to increase the alarm priority.

9. The method for detecting the usage status of a seat belt according to any one of claims 1 to 4, characterized in that, There are multiple benchmark features, and different users correspond to different benchmark features; Determining the usage status of the seat belt based on the pull-out dynamics characteristics and pre-stored reference characteristics includes: Obtain the user identification identifier on the seat corresponding to the seat belt; Based on the user identity identifier, the target benchmark feature is determined from multiple benchmark features; The usage status of the seat belt is determined based on the pull-out dynamics characteristics and the target reference characteristics.

10. A vehicle comprising a memory and a processor, the memory storing a computer program executable on the processor, characterized in that, When the processor executes the computer program, it implements the seat belt usage status detection method as described in any one of claims 1 to 9.

Images