Method for personalizing adjustment of bluetooth key calibration parameters and cloud synchronization of habit data

Abstract

The application provides a kind of bluetooth key calibration parameter personalized adjustment and habit data cloud synchronization method, belong to data processing technical field, specifically includes: with the identification processing result of abnormal behavior identification user, when the adjustment result of calibration parameter of abnormal behavior identification user is determined to exist suspected anomaly, according to the coincidence of the adjustment result of calibration parameter and the identification processing result, the determination of the synchronous identification processing strategy of user habit data in different distance intervals of abnormal behavior identification user is carried out, improve the security of bluetooth key calibration parameter in the adjustment process.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of data processing, and particularly relates to a method for individual adjustment of calibration parameters of a Bluetooth key and synchronization of habit data in the cloud. BACKGROUND

[0002] The Bluetooth key can be used to control the vehicle at different distance thresholds, such as automatic unlocking and locking, starting of the away mode, triggering of the trunk, and the like, through calibration of parameters. In the prior art, the individual adjustment of the calibration parameters, i.e. the distance threshold, of the Bluetooth key is performed by means of a smart terminal. However, the prior art has the following technical problems.

[0003] When setting the calibration parameters, the user needs to determine whether the original vehicle behavior matches the calibration parameters, thereby determining whether the calibration parameters have certain safety risks. For example, the user often moves within the distance interval corresponding to the calibration parameters but does not start the vehicle. Therefore, if the unlocking process is performed within the distance interval corresponding to the calibration parameters, there may be a safety risk. Therefore, how to determine the identification scheme of the user behavior according to the adjustment data of the calibration parameters of the Bluetooth key so as to timely and effectively identify the calibration parameters with safety risks becomes a technical problem to be solved.

[0004] Therefore, there is an urgent need for a method for individual adjustment of calibration parameters of a Bluetooth key and synchronization of habit data in the cloud. SUMMARY

[0005] To achieve the object of the application, the application adopts the following technical solutions.

[0006] Specifically, the application provides a method for individual adjustment of calibration parameters of a Bluetooth key and synchronization of habit data in the cloud, which specifically comprises the following steps.

[0007] S1 determining an abnormal behavior identification user based on adjustment data of calibration parameters of a Bluetooth key, and determining a distance interval in which the abnormal behavior of the abnormal behavior identification user is identified based on a historical adjustment result of the calibration parameters of the abnormal behavior identification user.

[0008] S2 when it is determined that the adjustment result of the calibration parameters of the abnormal behavior identification user is suspiciously abnormal based on the identification result of the abnormal behavior identification user, determining a synchronization identification processing strategy of user habit data of the abnormal behavior identification user in different distance intervals based on coincidence of the adjustment result and the identification result of the calibration parameters.

[0009] The application has the following beneficial effects.

[0010] According to the historical adjustment result of the calibration parameter of the abnormal behavior identification user, the determination of the identification processing distance interval of the abnormal behavior of the abnormal behavior identification user is performed, so as to realize the determination of the distance interval of the distance threshold value of the calibration parameter, the identification processing distance interval of the abnormal behavior of the abnormal behavior identification user, thereby ensuring the pertinence of the identification processing of the abnormal behavior, and reducing the power consumption of the vehicle during parking caused by unnecessary identification.

[0011] According to the identification processing result of the abnormal behavior identification user, it is determined whether the adjustment result of the calibration parameter of the abnormal behavior identification user is suspicious, so as to realize the identification of the safety risk caused by the adjustment result of the calibration parameter from the identification processing result of the user habit data in advance, and through the identification of the safety risk, the habit data of the user in different vehicles is analyzed and processed in the cloud platform, thereby laying a foundation for further reducing the safety risk caused by the deviation of the distance threshold value setting.

[0012] Further, the calibration parameter includes automatic unlocking, off-vehicle mode start, and distance threshold value of Bluetooth key triggered by trunk.

[0013] Further, the adjustment data of the calibration parameter includes the number of adjustments of the calibration parameter in history.

[0014] Further, the method for determining the abnormal behavior identification user of the calibration parameter includes:

[0015] Based on the adjustment data of the calibration parameter of the Bluetooth key, the adjustment time of the calibration parameter of the Bluetooth key of the user is determined;

[0016] Based on the interval length between adjacent adjustment times, the mean value of the interval length between adjacent adjustment times of the user is determined;

[0017] Based on the mean value of the interval length between adjacent adjustment times of the user, it is determined whether the user is an abnormal behavior identification user of the calibration parameter.

[0018] Further, it is determined that the adjustment result of the calibration parameter of the abnormal behavior identification user is suspicious, specifically including:

[0019] According to the identification processing result of the abnormal behavior identification user, it is determined that the adjustment result of the calibration parameter of the abnormal behavior identification user is suspicious

[0020] According to the adjustment result of the calibration parameter of the abnormal behavior identification user, the distance interval corresponding to the adjustment result is determined and taken as a matching distance interval.

[0021] According to the identification result of the abnormal behavior in the matching distance interval, it is determined whether the adjustment result of the calibration parameter of the abnormal behavior identification user is suspiciously abnormal.

[0022] Other features and advantages will be set forth in the accompanying claims, the drawings and the description of the application.

[0023] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the following preferred embodiments are specifically described below, and the accompanying drawings are described in detail. BRIEF DESCRIPTION OF DRAWINGS

[0024] The above and other features and advantages of the present application will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings in which:

[0025] Figure 1 A flowchart of a method for personalizing adjustment of calibration parameters of a Bluetooth key and cloud synchronization of habit data;

[0026] Figure 2 A flowchart of a method for determining calibration parameters of an abnormal behavior identification user;

[0027] Figure 3 A flowchart of a method for determining an identification processing distance interval of abnormal behavior of an abnormal behavior identification user;

[0028] Figure 4 A flowchart of determining that the adjustment result of the calibration parameter of the abnormal behavior identification user is suspiciously abnormal. DETAILED DESCRIPTION

[0029] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the following preferred embodiments are specifically described below, and the accompanying drawings are described in detail.

[0030] Embodiment 1

[0031] As shown in Figure 1 The present application provides a method for personalizing adjustment of calibration parameters of a Bluetooth key and cloud synchronization of habit data, which specifically comprises:

[0032] S1 determines the user of the abnormal behavior of the calibration parameter based on the adjustment data of the calibration parameter of the Bluetooth key, and determines the adjustment of the abnormal behavior of the calibration parameter of the user according to the historical adjustment result of the calibration parameter of the abnormal behavior of the user. The identification processing distance interval of the abnormal behavior of the calibration parameter is determined.

[0033] Further, the calibration parameter includes the distance threshold of the Bluetooth key of automatic unlocking, off mode opening and trunk triggering.

[0034] Further, the adjustment data of the calibration parameter includes the number of adjustments of the calibration parameter in history.

[0035] Specifically, as shown in Figure 2 The method for determining the user of the abnormal behavior of the calibration parameter is:

[0036] Based on the adjustment data of the calibration parameter of the Bluetooth key, the adjustment time of the calibration parameter of the Bluetooth key of the user is determined.

[0037] Based on the interval length between adjacent adjustment time points, the mean value of the interval length between adjacent adjustment time points of the user is determined.

[0038] The mean value of the interval length between adjacent adjustment time points of the user is used to determine whether the user is the user of the abnormal behavior of the calibration parameter.

[0039] It should be noted that when the mean value of the interval length between adjacent adjustment time points of the user is within the preset time interval, then at this time, because the interval length between the adjustment time points of the user is too frequent, in order to determine whether the adjustment data of the calibration parameter matches the behavior habit of the user, it is determined that the user is the user of the abnormal behavior of the calibration parameter.

[0040] Specifically, it can include the following possible specific embodiments:

[0041] 1. This embodiment constructs an abnormal user identification system based on multi-dimensional time series analysis. The system first establishes a user behavior database to record the historical parameter adjustment data of all users, including adjustment timestamp, adjustment parameter type, adjustment value before and after, session ID and other detailed information. The system uses distributed architecture to store data to ensure data integrity under high concurrency.

[0042] The system sets the preset time interval as [0, 20 days]. The system monitors the user adjustment behavior in real time, and automatically calculates the moving average of the interval length between adjacent adjustment time points of each user every day. When it is detected that the average interval of user adjustment falls within the preset interval, it is determined that it belongs to the user of the abnormal behavior of the calibration parameter.

[0043] In addition, the system can also start multi-dimensional anomaly analysis: first, compare the user's historical data with the same period data, calculate the adjusted frequency of the same period change rate; second, analyze the adjustment time distribution characteristics, check whether there is an abnormal period of concentrated adjustment; finally, evaluate the adjustment parameter type distribution, identify abnormal parameter combination. When two or more of the three dimensions show abnormalities, the system determines that the user is a parameter adjustment abnormal behavior recognition user.

[0044] In addition, the system also establishes an auxiliary judgment mechanism based on the number of times of adjusting the parameter of the Bluetooth key. The system counts the total number of times of adjusting the parameter of the Bluetooth key of the user in the historical period (such as 90 days), and calculates the number of times of adjustment in the last 7 days. The preset number of times interval is set to [0, 2] times / week. When the number of times of adjustment per week of the user exceeds this interval, the system automatically marks it as a parameter adjustment abnormal behavior recognition user.

[0045] 2, this embodiment develops an intelligent anomaly detection system based on behavior pattern recognition. The system uses machine learning method to establish user normal behavior baseline, realizes accurate identification of abnormal behavior.

[0046] The system implements the following detection process: first, through cluster analysis, the users are divided into different types (such as high-frequency users, ordinary users, and low-frequency users), and a personalized behavior model is established for each type of user. For adjustment time interval analysis, the system uses a hidden Markov model to capture the user's normal adjustment time rule. When it is detected that the continuous three adjustment intervals fall into the preset interval [0, 10 days], an abnormal warning is triggered, and the system automatically marks it as a parameter adjustment abnormal behavior recognition user.

[0047] Specifically, as shown in Figure 3 The method for determining the identification processing distance interval of the abnormal behavior of the abnormal behavior recognition user is as follows:

[0048] Based on the historical adjustment results of the parameter of the abnormal behavior recognition user, the number of times of adjustment of the adjustment result of the parameter of the abnormal behavior recognition user within a target distance range is determined, and it is taken as a target adjustment number;

[0049] Based on the historical adjustment results of the parameter of the abnormal behavior recognition user, the number of times of adjustment of the abnormal behavior recognition user within different identification processing distance intervals is determined, and based on the proportion of the number of times of adjustment within the gathered distance interval in all the adjustment times of the abnormal behavior recognition user, the adjustment gathering coefficient within the gathered distance interval is determined;

[0050] Based on the adjustment gathering coefficient within the gathered distance interval and the target adjustment number, the identification processing distance interval of the abnormal behavior of the abnormal behavior recognition user is determined.

[0051] 1、This embodiment constructs an abnormal behavior recognition processing system based on multi-dimensional distance analysis. The system first establishes a complete history database of abnormal behavior recognition users, which records all calibration parameter adjustment records in detail, including core data such as adjustment timestamp, parameter value before adjustment, and parameter value after adjustment. The system defines the target distance range as a distance interval greater than 10 meters, specifically including 10 meters to 15 meters, and up to 25 meters to 30 meters, which is divided into equal intervals with an interval of 5 meters. Through data mining algorithm, the number of adjustments of each abnormal user in the target distance range is counted and recorded as N_target. At the same time, the system uses kernel density estimation method to analyze the distribution of all adjustment distance data of the user, identifies the recognition processing distance interval with the most concentrated adjustment distance distribution as the aggregation distance interval, that is, the recognition processing distance interval with the most adjustment times as the aggregation distance interval, and calculates the proportion of the number of adjustments in this interval in the total number of adjustments of the user to obtain the adjustment aggregation coefficient C_agg.

[0052] The system sets a preset proportion threshold θ_ratio = 0.1 and a preset aggregation coefficient threshold θ_agg = 0.5. In actual operation, the system determines the final recognition processing distance interval according to multi-condition judgment logic. When the proportion of the target adjustment number in the total adjustment number exceeds 0.1, the system sets the recognition processing distance interval to [0, 0.5], that is, all abnormal behaviors in the distance interval less than the maximum value of the end point of the target distance range are recognized and processed. When the target adjustment number proportion does not exceed 0.1 and the adjustment aggregation coefficient does not exceed 0.5, the system also recognizes and processes all abnormal behaviors in the distance interval less than the maximum value of the end point of the target distance range. However, when the target adjustment number proportion does not exceed 0.1 but the adjustment aggregation coefficient exceeds 0.5, the system sets the recognition processing distance interval to [0, D_cluster_max], where D_cluster_max is the upper limit value of the aggregation distance interval, ensuring that the system can focus on monitoring the abnormal behavior distance interval that the user appears most frequently.

[0053] 2、This embodiment constructs a dual-criterion recognition distance interval determination system based on quarterly cycles (90 days). The system first determines the target distance range [D_min, D_max] and the aggregation distance interval [D_cluster_min, D_cluster_max] through statistical analysis, where D_max and D_cluster_max will be the upper limit of the recognition processing distance interval.

[0054] At the beginning of the quarter, the system collects all the calibration parameter adjustment records of the user in the past 90 days, calculates the Euclidean distance of each adjustment, and uses the DBSCAN clustering algorithm to identify the adjustment distance cluster interval. By optimizing the clustering parameters, the core area with the highest density is found, and the range of this area is the clustering distance interval. Based on the above parameters, the system determines the specific identification processing distance interval according to the user type:

[0055] For users who adjust frequently (quarterly adjustment times > 6) and are scattered (adjustment clustering coefficient < 0.5), the identification processing distance interval is [0, D_max], and for other users, the identification processing distance interval is [0, D_cluster_max]. The system updates these parameters once a quarter to ensure that the identification strategy keeps pace with changes in user behavior.

[0056] 3、This embodiment constructs an identification distance interval optimization system based on multi-dimensional weighted evaluation. The system not only considers the adjustment frequency and dispersion, but also introduces more dimensional features to determine the optimal identification distance interval through weighted evaluation.

[0057] The system collects the following dimensional data within a quarter: adjustment frequency: quarterly total adjustment times, average daily adjustment times; adjustment dispersion: distance coefficient of variation, Gini coefficient; adjustment mode stability: shape change of distance distribution, persistence of clustering interval;

[0058] Behavioral risk level: risk assessment based on adjustment timing and parameter sensitivity, calculate a score for each dimension, then weighted sum to get the comprehensive evaluation score S. The weights are obtained by training historical data, for example: adjustment frequency weight 0.3, dispersion weight 0.3, stability weight 0.25, risk level weight 0.15.

[0059] Determination rule of identification processing distance interval:

[0060] When S > 0.8 (high frequency, high dispersion, high risk), the identification processing distance interval is [0, D_max]

[0061] When 0.5 < S ≤ 0.8, the identification processing distance interval is [0, (D_max + D_cluster_max) / 2]

[0062] When S ≤ 0.5, the identification processing distance interval is [0, D_cluster_max]

[0063] Where D_max and D_cluster_max are determined similarly as in the first embodiment, but more seasonal features are considered. For example, D_max can take the 90% quantile, while D_cluster_max is obtained by a clustering algorithm that considers time weights, with higher weights for more recent data.

[0064] The system generates an evaluation report every quarter, showing the score changes and interval adjustments, providing a basis for subsequent optimization.

[0065] S2 identifies the user's identification processing result of the abnormal behavior, determines that the adjustment result of the calibration parameter of the abnormal behavior identification user is suspected to be abnormal, and according to the coincidence of the adjustment result of the calibration parameter and the identification processing result, determines the synchronous identification processing strategy of the user habit data of the abnormal behavior identification user in different distance intervals.

[0066] Further, as shown in Figure 4 Determine that the adjustment result of the calibration parameter of the abnormal behavior identification user is suspected to be abnormal, specifically including:

[0067] Determine the distance interval corresponding to the adjustment result of the calibration parameter of the abnormal behavior identification user, and take it as the matching distance interval;

[0068] According to the identification result of the abnormal behavior in the matching distance interval, determine whether the adjustment result of the calibration parameter of the abnormal behavior identification user is suspected to be abnormal.

[0069] It can be understood that the abnormal behavior is the behavior of sensing the Bluetooth key in the identification processing distance interval but not unlocking the vehicle.

[0070] It should be noted that when the number of abnormal behaviors in the matching distance interval is within the preset number of times, if the adjustment result is set at this time, it may often lead to the situation that the vehicle has been unlocked but the personnel have not gotten on the vehicle, which is an abnormal unlocking at this time, and therefore it is determined that the adjustment result of the calibration parameter of the abnormal behavior identification user is suspected to be abnormal.

[0071] In a possible embodiment, the embodiment constructs a suspected abnormality judgment system based on matching distance interval statistical analysis. The specific calculation process is as follows: the system records the abnormal behavior of the user in the matching distance interval in real time with 30 days as a monitoring period. The judgment standard of the abnormal behavior is that the Bluetooth key signal strength greater than -70dBm is continuously detected in the matching distance interval, and the vehicle unlocking is not triggered within 2 minutes. The system uses a sliding time window statistical method to update the number of abnormal behaviors in the last 30 days every day. When the statistics show that the number of abnormal behaviors N_abnormal is greater than or equal to 2, the system starts the suspected abnormality analysis process.

[0072] Specifically, the method for determining the synchronous identification processing strategy of the user habit data of the user in different distance intervals based on the abnormal behavior is:

[0073] The adjustment result of the calibration parameter is determined based on the coincidence of the adjustment result of the calibration parameter and the identification processing result, and the distance interval corresponding to the adjustment result of the calibration parameter is determined as the matching distance interval.

[0074] The distance interval in which the abnormal behavior exists is determined based on the identification processing result of the user in the latest preset time length, and the distance interval in which the abnormal behavior exists is determined as the abnormal behavior distance interval.

[0075] Based on the identification result of the abnormal behavior in the matching distance interval and the identification result of the abnormal behavior in the abnormal behavior distance interval, the abnormal behavior risk value of the abnormal behavior user is determined, and the synchronous identification processing strategy of the user habit data of the user in different distance intervals based on the abnormal behavior is determined based on the abnormal behavior risk value.

[0076] Specifically, when the abnormal behavior risk value of the abnormal behavior user is greater than a preset risk threshold, it is determined that the user habit data of the abnormal behavior user in different distance intervals needs to be identified and processed in real time in different vehicles, so that when the number of abnormal behaviors is too large, a warning signal is output to the abnormal behavior identification user, so that the calibration parameter adjustment processing is performed as soon as possible.

[0077] In addition, it can be understood that when the abnormal behavior risk value of the abnormal behavior user is not greater than a preset risk threshold, when abnormal behavior occurs in the matching distance interval of any vehicle, the user habit data of the abnormal behavior user in different distance intervals needs to be identified and processed in real time in different vehicles, so that when the number of abnormal behaviors in the matching distance interval or the distance interval less than the maximum value of the end point of the matching aggregation interval is too large, a warning signal is output to the abnormal behavior identification user, so that the calibration parameter adjustment processing is performed as soon as possible.

[0078] Specifically, the embodiment constructs a synchronous identification processing system based on multi-distance interval risk quantification. The system first analyzes the historical data of calibration parameter adjustment records and identification processing results, calculates the coincidence degree of the matching distance interval and the abnormal behavior distance interval.

[0079] Based on the above two intervals, the system calculates the abnormal behavior risk value R. The specific calculation process is as follows: first, count the number of abnormal behaviors in each abnormal behavior distance interval, and then weight and sum according to the weight coefficient. The determination rule of the weight coefficient is as follows: when the maximum value of the distance interval corresponding to the abnormal behavior is less than the maximum value of the matching distance interval, the weight coefficient is 0.02; otherwise, it is 0.01. Finally, divide the weighted sum by the total number of abnormal behaviors to obtain the standardized risk value. For example, a user has 20 abnormal behaviors in the matching distance interval, of which 15 are in the interval with a weight of 0.02 and 5 are in the interval with a weight of 0.01, then the risk value R = (15x0.02 + 5x0.01) = 0.35.

[0080] When the system detects that the risk value R > 0.03, it immediately starts the global synchronous processing mode. In this mode, the system synchronizes the user habit data in all vehicles associated with the user in real time, including historical behavior patterns, calibration parameter preferences, abnormal behavior characteristics, etc. The synchronization process uses a distributed consistency protocol to ensure real-time consistency of data among multiple terminals. At the same time, the system will increase the monitoring frequency to 1 per second, and when it detects that any vehicle has more than 3 abnormal behaviors within 1 hour, it will immediately send a warning signal to the user through multiple channels (including mobile application push, SMS reminder, etc.), prompting the user to adjust the calibration parameters in time.

[0081] In addition, it should be noted that when the abnormal behavior risk value R of the abnormal behavior user is not greater than 0.03, when any vehicle has an abnormal behavior in the matching distance interval, the user habit data of the abnormal behavior user in different distance intervals needs to be synchronized and identified in real time in different vehicles, so that when the number of abnormal behaviors in the matching distance interval or the distance interval less than the maximum value of the endpoint of the matching aggregation interval is too large, an early warning signal is output to the abnormal behavior identification user, so that the calibration parameter adjustment processing can be performed as soon as possible.

[0082] Embodiment 2

[0083] Further, the method for determining the synchronous identification processing strategy of the user habit data of the abnormal behavior identification user in different distance intervals is as follows:

[0084] Determine the distance interval corresponding to the adjustment result of the calibration parameter according to the coincidence of the adjustment result of the calibration parameter and the identification processing result, and take it as the matching distance interval;

[0085] According to the identification processing result of the abnormal behavior of the user in the recent preset time length, a distance interval in which the abnormal behavior exists is determined as an abnormal behavior distance interval;

[0086] Based on the identification result of the abnormal behavior in the matching distance interval and the identification result of the abnormal behavior in the abnormal behavior distance interval, a synchronous identification processing strategy of the user habit data of the abnormal behavior identification user in different distance intervals is determined.

[0087] Further, when the number of times of the abnormal behavior of the abnormal behavior user in the matching distance interval is greater than a preset abnormal behavior number threshold in the recent preset time length, it is determined that the user habit data of the abnormal behavior user in different distance intervals needs real-time synchronous identification processing in different vehicles, so as to output a warning signal to the abnormal behavior identification user when the number of times of the abnormal behavior is too large, so as to quickly perform the adjustment processing of the calibration parameters.

[0088] Further, when the number of times of the abnormal behavior of the abnormal behavior user in the matching distance interval is not greater than a preset abnormal behavior number threshold in the recent preset time length, when the number of the abnormal behavior distance intervals in the recent preset time length does not meet the requirement, it is determined that the user habit data of the abnormal behavior user in different distance intervals needs real-time synchronous identification processing in different vehicles, so as to output a warning signal to the abnormal behavior identification user when the number of times of the abnormal behavior is too large, so as to quickly perform the adjustment processing of the calibration parameters.

[0089] Further, when the number of the abnormal behavior distance intervals in the recent preset time length meets the requirement, the identification result of the abnormal behavior in different abnormal behavior distance intervals in the recent preset time length is used to determine the total number of times of the abnormal behavior, and when the total number of times of the abnormal behavior does not meet the requirement, it is determined that the user habit data of the abnormal behavior user in different distance intervals needs real-time synchronous identification processing in different vehicles, so as to output a warning signal to the abnormal behavior identification user when the number of times of the abnormal behavior is too large, so as to quickly perform the adjustment processing of the calibration parameters.

[0090] Further, when the total number of abnormal behaviors meets the requirement, whether the maximum value of the endpoint values of the distance intervals corresponding to the abnormal behaviors in the latest preset time length is greater than the matching distance interval is determined to determine the weight coefficient of the abnormal behavior, and the abnormal behavior risk value of the abnormal behavior user is determined based on the sum of the weight coefficients of the abnormal behaviors. When the abnormal behavior risk value of the abnormal behavior user is greater than a preset risk threshold, the user habit data of the abnormal behavior user in different distance intervals needs to be identified in real time in different vehicles, so that when the number of abnormal behaviors is too large, a warning signal is output to the abnormal behavior identification user, so that the parameter adjustment processing is performed as soon as possible.

[0091] In addition, it can be understood that when the abnormal behavior risk value of the abnormal behavior user is not greater than the preset risk threshold, when abnormal behavior occurs in the matching distance interval in any vehicle, the user habit data of the abnormal behavior user in different distance intervals needs to be identified in real time in different vehicles, so that when the number of abnormal behaviors in the distance interval less than the maximum value of the endpoint of the matching aggregation interval is too large, a warning signal is output to the abnormal behavior identification user, so that the parameter adjustment processing is performed as soon as possible.

[0092] Each of the embodiments in the specification is described in a progressive manner, and the same and similar parts of each embodiment can be referred to each other. Each embodiment focuses on the difference from other embodiments. Especially, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiment.

[0093] The above describes specific embodiments of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different than the order in the embodiments and still achieve the desired result. In addition, the processes depicted in the figures do not necessarily require the particular order shown or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing can be advantageous or possible.

[0094] The above only describes one or more embodiments of the specification and does not limit the specification. One or more embodiments of the specification can have various changes and variations for those skilled in the art. Any modification, equivalent replacement, improvement, etc. within the spirit and principles of one or more embodiments of the specification should be included in the scope of the claims of the specification.

Claims

1. A method for personalized adjustment of Bluetooth key calibration parameters and cloud synchronization of habit data, characterized in that, Specifically, it includes: Based on the adjustment data of the calibration parameters of the Bluetooth key, the user with abnormal behavior of the calibration parameters is identified. Based on the historical adjustment results of the calibration parameters of the user with abnormal behavior, the distance range for identifying and processing the abnormal behavior of the user is determined. When it is determined that the adjustment result of the calibration parameters of the user with abnormal behavior identification is suspected to be abnormal based on the identification processing result of the user with abnormal behavior identification, the synchronous identification processing strategy of the user habit data of the user with abnormal behavior identification in different distance intervals is determined according to the overlap between the adjustment result of the calibration parameters and the identification processing result. The method for determining the distance range for identifying abnormal user behavior is as follows: Based on the historical adjustment results of the calibration parameters of the user identified by abnormal behavior, determine the number of times the calibration parameters of the user identified by abnormal behavior are adjusted within the target distance range, and use this number as the target number of adjustments; Based on the historical adjustment results of the calibration parameters of the user identified for abnormal behavior, determine the number of adjustments made to the user for abnormal behavior within different distance intervals; Based on the number of adjustments within different distance intervals and the target number of adjustments, the identification and processing distance interval for the abnormal behavior of the user is determined. The method for determining the synchronous identification and processing strategy of user habit data in different distance intervals for identifying abnormal behavior is as follows: Based on the overlap between the adjustment result of the calibration parameters and the recognition processing result, the distance interval corresponding to the adjustment result of the calibration parameters is determined, and it is used as the matching distance interval; Based on the identification and processing results of the abnormal behavior user within the most recent preset time period, the distance range where abnormal behavior exists is determined and used as the abnormal behavior distance range; Based on the identification results of abnormal behavior within the matching distance interval and the identification results of abnormal behavior within the abnormal behavior distance interval, the abnormal behavior risk value of the abnormal behavior user is determined. Based on the abnormal behavior risk value, a synchronous identification and processing strategy for user habit data of the abnormal behavior user in different distance intervals is determined.

2. The method for personalized adjustment of Bluetooth key calibration parameters and cloud synchronization of habit data as described in claim 1, characterized in that, The calibration parameters include the distance thresholds for automatic unlocking / locking, departure mode activation, and Bluetooth key triggering via the trunk.

3. The method for personalized adjustment of Bluetooth key calibration parameters and cloud synchronization of habit data as described in claim 1, characterized in that, The adjustment data for the calibration parameters includes the number of times the calibration parameters have been adjusted in history.

4. The method for personalized adjustment of Bluetooth key calibration parameters and cloud synchronization of habit data as described in claim 1, characterized in that, The method for identifying users with abnormal behavior in the calibration parameters is as follows: Based on the adjustment data of the calibration parameters of the Bluetooth key, the adjustment time of the calibration parameters of the user's Bluetooth key is determined; The average interval between adjacent adjustment times for the user is determined based on the interval duration between adjacent adjustment times. The average duration of the interval between adjacent adjustment times of the user is used to determine whether the user is an abnormal behavior identification user of the calibration parameters.

5. The method for personalized adjustment of Bluetooth key calibration parameters and cloud synchronization of habit data as described in claim 4, characterized in that, When the average duration of the interval between adjacent adjustment times for the user is within a preset duration range, the user is determined to be an abnormal behavior identification user of the calibration parameters.

6. The method for personalized adjustment of Bluetooth key calibration parameters and cloud synchronization of habit data as described in claim 1, characterized in that, When the number of target adjustments does not meet the requirements, abnormal behaviors within the distance range of the maximum value of the endpoints that are less than the target distance range are identified and processed.

7. The method for personalized adjustment of Bluetooth key calibration parameters and cloud synchronization of habit data as described in claim 1, characterized in that, When the target number of adjustments meets the requirements, the number of adjustments in different recognition processing distance intervals is determined based on the number of adjustments in different recognition processing distance intervals. The recognition processing distance interval with the most adjustments is taken as the clustering distance interval. When there is no target number of adjustments, it is only necessary to recognize and process abnormal behaviors in the distance interval that is less than the maximum value of the endpoint of the clustering distance interval.

8. The method for personalized adjustment of Bluetooth key calibration parameters and cloud synchronization of habit data as described in claim 1, characterized in that, The adjustment results of the calibration parameters for the user identifying abnormal behavior are suspected to be abnormal, specifically including: Based on the identification and processing results of the user with abnormal behavior, it is determined that the adjustment result of the calibration parameters of the user with abnormal behavior is suspected to be abnormal. Based on the adjustment results of the calibration parameters of the user identified by the abnormal behavior, the distance interval corresponding to the adjustment results is determined and used as the matching distance interval; Based on the identification results of abnormal behavior within the matching distance interval, determine whether there are any suspected abnormalities in the adjustment results of the calibration parameters of the user identifying abnormal behavior.

9. The method for personalized adjustment of Bluetooth key calibration parameters and cloud synchronization of habit data as described in claim 8, characterized in that, The abnormal behavior refers to the behavior of sensing the Bluetooth key within the identification and processing distance range but failing to unlock the vehicle.

Images