Accompanying device white list self-learning method and system for mobile carrier

Abstract

The invention relates to the technical field of carrier safety, and discloses an accompanying equipment white list self-learning method and system for a mobile carrier, and the method comprises the steps: monitoring a static state and a geographic position of the mobile carrier, and carrying out the condition conformity judgment of the static state and the geographic position, so as to trigger the mobile carrier to enter an automatic learning mode; analyzing equipment identifiers of wireless signals emitted by accompanying equipment around the mobile carrier, and performing time-frequency domain conjoint analysis on the wireless signals to obtain intensity and an occurrence rule; performing multi-dimensional credibility evaluation on the accompanying equipment to obtain a candidate credibility score; based on the candidate trust degree score and a preset trust threshold value, determining a high-credibility candidate device; carrying out strategy directional preferential selection on the high-credibility candidate equipment to obtain a white list adding strategy; performing white list updating operation on the mobile carrier; according to the invention, the accompanying device white list self-learning efficiency for the mobile carrier can be improved.

Description

Technical Field

[0001] This invention relates to the field of vehicle safety technology, and in particular to a self-learning method and system for a whitelist of accompanying equipment for mobile vehicles. Background Technology

[0002] The existing methods for constructing whitelists of accompanying equipment for mobile vehicles mostly rely on manual intervention, requiring manual input of equipment identification information. This makes it impossible to dynamically adjust the whitelists based on the actual accompanying relationship between the equipment and the vehicle, resulting in poor adaptability and difficulty in dealing with scenarios where equipment is added, removed, or replaced.

[0003] Current technologies for assessing the trustworthiness of accompanying devices lack in-depth analysis of wireless signal characteristics and rely on a single trustworthiness evaluation metric. They fail to comprehensively consider key factors such as signal stability, location stability, and continuity, resulting in insufficient accuracy in identifying trustworthy devices and impacting the effectiveness of whitelists. Therefore, improving the accuracy and dynamic update capability of automatically constructing whitelists for accompanying devices on mobile vehicles has become an urgent problem to be solved. Summary of the Invention

[0004] This invention provides a self-learning method and system for a whitelist of accompanying devices for mobile vehicles, in order to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides a self-learning method for a whitelist of accompanying devices for mobile vehicles, comprising: S1. Monitor the stationary state and geographical location of the mobile vehicle, and make a condition compliance judgment on the stationary state and geographical location to trigger the mobile vehicle to enter the automatic learning mode. S2. In the automatic learning mode, the device identifier of the wireless signal emitted by the accompanying device around the mobile vehicle is parsed, and based on the device identifier, the time-frequency domain joint analysis of the wireless signal is performed to obtain the signal strength and occurrence pattern. S3. Based on the intensity and the occurrence pattern, perform a multi-dimensional credibility assessment on the accompanying device to obtain a candidate credibility score for the accompanying device; S4. Based on the candidate trust score and the preset trust threshold, perform a binary decision on the accompanying device to confirm the high-trust candidate device among the accompanying devices. S5. Based on a preset configuration strategy library, perform strategy-oriented optimization on the high-trust candidate devices to obtain the whitelist addition strategy for the high-trust candidate devices; S6. Based on the whitelist addition strategy, perform a whitelist update operation on the mobile vehicle.

[0006] In a preferred embodiment, monitoring the stationary state and geographical location of the mobile vehicle, and performing a conditional compliance judgment on the stationary state and geographical location to trigger the mobile vehicle to enter an automatic learning mode, includes: Continuously monitor the speed and position coordinates of mobile vehicles; The speed information is used to perform zero-speed state timing to obtain the duration of the stationary state of the mobile vehicle; Displacement accumulation analysis is performed on the position coordinate information to obtain the position change of the moving vehicle; When the duration of the stationary state exceeds a preset duration threshold and the change in position is less than a preset distance threshold, the scene safety compliance determination result of the mobile vehicle is obtained. Based on the scenario safety compliance determination result, the mobile vehicle is triggered to enter the automatic learning mode.

[0007] In a preferred embodiment, the device identifier for parsing wireless signals emitted by accompanying devices around the mobile vehicle in the automatic learning mode includes: Receive wireless signals from accompanying devices around the mobile vehicle, and perform baseband signal demodulation on the wireless signals to obtain the wireless signal data stream of the wireless signals; The wireless signal data stream is parsed to obtain the communication protocol type and frame structure of the wireless signal data stream; Based on the communication protocol type and the frame structure, metadata fields of the wireless signal data stream are determined to obtain the device identifier field of the wireless signal data stream. The device identifier field is decoded using protocol semantics to obtain the device identifier of the wireless signal.

[0008] In a preferred embodiment, the step of performing joint time-frequency domain analysis on the wireless signal based on the device identifier to obtain the strength and occurrence pattern of the wireless signal includes: Based on the device identifier, the wireless signals are matched and associated to filter out target signals in the wireless signals that are associated with the device identifier; Time-frequency domain features are extracted from the target signal to obtain the joint time-frequency distribution features of the target signal; Based on the aforementioned time-frequency joint distribution characteristics, the power spectral density of the target signal is analyzed to obtain the strength of the wireless signal; Based on the aforementioned time-frequency joint distribution characteristics, the time distribution statistics of the target signal are performed to obtain the occurrence pattern of the wireless signal.

[0009] In a preferred embodiment, the step of performing a multi-dimensional credibility assessment on the accompanying device based on the intensity and the occurrence pattern to obtain a candidate trust score for the accompanying device includes: Based on the intensity, statistical fluctuation analysis is performed on the accompanying device to obtain the signal stability index of the accompanying device; Based on the intensity distribution characteristics, the relative position change of the accompanying equipment is evaluated to obtain the positional stability index of the accompanying equipment; Based on the aforementioned pattern, the percentage of time the accompanying device's signal is present during the automatic learning mode is statistically analyzed. The duration of the signal is continuously quantitatively evaluated to obtain the signal persistence index of the accompanying device; The signal stability index, the location fixity index, and the signal persistence index are weighted and fused to obtain the candidate trust score of the accompanying device.

[0010] In a preferred embodiment, the formula for calculating the candidate trust score is as follows: ; In the formula, This represents the candidate trust score. The signal stability index, The signal persistence index, The positional stability index This represents the preset stable dimension weight coefficient. This represents the preset weight coefficients for the continuous dimension. This represents the preset fixed-dimensional weight coefficients. This represents a pre-defined, extremely small positive number. This represents the maximum value function.

[0011] In a preferred embodiment, the step of performing a binary decision on the accompanying devices based on the candidate trust score and a preset trust threshold to identify high-trust candidate devices among the accompanying devices includes: The candidate trust score is correlated with the preset trust threshold within an interval to obtain the membership relationship between the candidate trust score and the trust threshold; Based on the aforementioned affiliation, a reliable classification determination is made for the accompanying devices to obtain the category attribution information of the accompanying devices; Based on the category attribution information, high-confidence candidate devices among the accompanying devices are identified.

[0012] In a preferred embodiment, the step of performing policy-oriented optimization on the high-trust candidate devices based on a preset configuration policy library to obtain a whitelist addition policy for the high-trust candidate devices includes: Retrieve the device type attribute and candidate trust score of the highly trustworthy candidate device; The device type attribute and the candidate trust score are used as query conditions, and the query conditions are input into a preset configuration strategy library; In the configuration strategy library, based on the query conditions, strategy matching is performed on the high-confidence candidate devices to obtain the initial strategy set of the high-confidence candidate devices; The initial strategy set is optimized to obtain the whitelist addition strategy for the highly reliable candidate devices.

[0013] In a preferred embodiment, the step of updating the whitelist for the mobile vehicle based on the whitelist addition strategy includes: The whitelist addition strategy is subjected to targeted parameter extraction to obtain the operation control parameters of the mobile vehicle; The operation control parameters are encoded into operation control commands for the mobile vehicle; The operation control command is parsed to determine the automatic addition type of the operation control command; When the automatic addition type is automatic silent addition, the device identifier of the highly reliable candidate device is silently written into the accompanying device whitelist of the mobile vehicle; When the automatic addition type requires user confirmation, a device addition confirmation request for the mobile vehicle is generated. After the confirmation request is authorized by the user, the device identifier of the highly reliable candidate device is written into the accompanying device whitelist of the mobile vehicle.

[0014] To address the aforementioned problems, the present invention also provides a self-learning system for a whitelist of accompanying equipment for mobile vehicles, the system comprising: The signal feature extraction module is used to parse the device identifier of the wireless signal emitted by the accompanying device around the mobile vehicle in the automatic learning mode, and perform time-frequency domain joint analysis on the wireless signal based on the device identifier to obtain the signal strength and occurrence pattern. The credibility assessment module is used to perform a multi-dimensional credibility assessment of the accompanying device based on the intensity and the occurrence pattern, and obtain a candidate credibility score for the accompanying device. The high-confidence screening module is used to perform a binary decision on the accompanying devices based on the candidate trust score and a preset trust threshold, and to confirm the high-confidence candidate devices among the accompanying devices. The strategy decision module is used to perform strategy-oriented optimization on the high-trust candidate devices based on a preset configuration strategy library, and obtain the whitelist addition strategy for the high-trust candidate devices; The whitelist update execution module is used to perform whitelist update operations on the mobile vehicle based on the whitelist addition strategy.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention triggers an automatic learning mode by monitoring the stationary state and geographical location of mobile vehicles, and combines time-frequency domain joint analysis to deeply analyze the strength and occurrence patterns of wireless signals. Then, it generates candidate trust scores through multi-dimensional credibility assessment of signal stability, location fixity, and signal persistence, which significantly improves the accuracy of screening high-trust candidate devices and ensures the credibility and compatibility of whitelisted devices.

[0016] 2. This invention performs targeted selection of highly reliable candidate devices based on a preset configuration strategy library, generates a dedicated whitelist addition strategy, and supports differentiated update methods such as automatic silent addition and user-confirmed addition. This not only improves the automation efficiency of whitelist updates, but also adapts to different usage scenarios and enhances the flexibility and practicality of the technology application. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating a self-learning method for a whitelist of accompanying devices for a mobile vehicle, provided in an embodiment of the present invention. Figure 2 This is a functional block diagram of a whitelist self-learning system for accompanying equipment of a mobile vehicle, provided in an embodiment of the present invention. The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0018] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0019] This application provides a self-learning method for a whitelist of accompanying devices for mobile vehicles. The executing entity of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the self-learning method for a whitelist of accompanying devices for mobile vehicles can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0020] Reference Figure 1 The diagram shown is a flowchart illustrating a self-learning method for a whitelist of accompanying devices for a mobile vehicle, according to an embodiment of the present invention. In this embodiment, the self-learning method for a whitelist of accompanying devices for a mobile vehicle includes: S1. Monitor the stationary state and geographical location of the mobile vehicle, and make a condition compliance judgment on the stationary state and geographical location to trigger the mobile vehicle to enter the automatic learning mode. In this embodiment of the invention, monitoring the stationary state and geographical location of the mobile vehicle, and performing a conditional compliance judgment on the stationary state and geographical location to trigger the mobile vehicle to enter an automatic learning mode, includes: Continuously monitor the speed and position coordinates of mobile vehicles; The speed information is used to perform zero-speed state timing to obtain the duration of the stationary state of the mobile vehicle; Displacement accumulation analysis is performed on the position coordinate information to obtain the position change of the moving vehicle; When the duration of the stationary state exceeds a preset duration threshold and the change in position is less than a preset distance threshold, the scene safety compliance determination result of the mobile vehicle is obtained. Based on the scenario safety compliance determination result, the mobile vehicle is triggered to enter the automatic learning mode.

[0021] The vehicle's speed data is collected in real time at a frequency of 10 times per second by a speed sensor mounted on the mobile vehicle. At the same time, the latitude, longitude and altitude data are obtained in real time by the positioning module mounted on the Beidou satellite positioning system, forming complete location coordinate information. The entire collection process is strictly continuous and uninterrupted to ensure that the vehicle's motion status changes at different times can be captured comprehensively and accurately.

[0022] When the speed sensor collects a speed data of 0, the timing device, which measures time in milliseconds, is immediately started. During subsequent continuous data collection, if the speed data collected each time remains 0, the timing device will continuously accumulate the time with millisecond-level precision. Once the collected speed data is not 0, the timing device will immediately reset the accumulated time to 0. Through this real-time response and precise timing method, the continuous time when the vehicle's speed is 0 is continuously recorded, and the duration of the stationary state of the moving vehicle is finally obtained.

[0023] First, the complete location coordinates of the first acquisition are recorded as the reference coordinates. Then, each time a new location coordinate is acquired, the latitude and longitude of the new location coordinates and the reference coordinates are converted into planar distances using the Earth coordinate system as the reference. Then, combined with the altitude difference, the three-dimensional straight-line distance between the two is calculated using the principles of spatial geometry to obtain the single displacement. Each calculation result is accurate to centimeters. Then, all single displacements are accumulated sequentially according to the acquisition time. The accumulation process is retained to two decimal places. The final total value is the change in position of the mobile vehicle during the monitoring period.

[0024] The preset duration threshold is set to 5 minutes, which is determined based on the stable stationary period after the mobile vehicle is normally parked. The preset distance threshold is set to 1 meter, which is set in combination with the error range of the positioning module and the allowable displacement range of the vehicle when stationary in the actual scenario. The previously obtained duration of the stationary state is compared with 300 seconds, and the change in position is compared with 100 centimeters. When both conditions are met, the mobile vehicle meets the scenario safety requirements. If either condition is not met, the mobile vehicle does not meet the scenario safety requirements.

[0025] When the scenario safety compliance determination result is that the scenario safety requirements are met, the system transmits the determination result to the control unit of the mobile vehicle through the data bus. Within 1 second of receiving the signal, the control unit activates the relevant functional modules such as signal reception and data parsing in the automatic learning mode, so that each module enters the ready state, and the mobile vehicle officially enters the automatic learning mode. If the determination result is that the scenario does not meet the requirements, the system does not send a start signal to the control unit, the control unit maintains the normal working state of each functional module, and the mobile vehicle continues to maintain the current normal working mode.

[0026] The beneficial effects are that, through a clear collection method, a well-defined judgment standard, and a rigorous triggering logic, the automatic learning mode can only be activated in a safe scenario where the mobile vehicle is in a stable and stationary position for a long period of time with no significant changes in location. This effectively avoids problems such as invalid data collection and resource waste caused by activating learning when the vehicle is moving or in an unstable position. It provides a reliable scenario foundation for subsequent steps such as wireless signal analysis and reliability assessment of accompanying devices, significantly improves the rationality, security, and accuracy of activating the automatic learning mode, and ensures the efficiency and quality of subsequent whitelist construction.

[0027] S2. In the automatic learning mode, the device identifier of the wireless signal emitted by the accompanying device around the mobile vehicle is parsed, and based on the device identifier, the time-frequency domain joint analysis of the wireless signal is performed to obtain the signal strength and occurrence pattern. In this embodiment of the invention, the device identifier for parsing wireless signals emitted by accompanying devices around the mobile vehicle in the automatic learning mode includes: Receive wireless signals from accompanying devices around the mobile vehicle, and perform baseband signal demodulation on the wireless signals to obtain the wireless signal data stream of the wireless signals; The wireless signal data stream is parsed to obtain the communication protocol type and frame structure of the wireless signal data stream; Based on the communication protocol type and the frame structure, metadata fields of the wireless signal data stream are determined to obtain the device identifier field of the wireless signal data stream. The device identifier field is decoded using protocol semantics to obtain the device identifier of the wireless signal.

[0028] The step of performing joint time-frequency domain analysis on the wireless signal based on the device identifier to obtain the strength and occurrence pattern of the wireless signal includes: Based on the device identifier, the wireless signals are matched and associated to filter out target signals in the wireless signals that are associated with the device identifier; Time-frequency domain features are extracted from the target signal to obtain the joint time-frequency distribution features of the target signal; Based on the aforementioned time-frequency joint distribution characteristics, the power spectral density of the target signal is analyzed to obtain the strength of the wireless signal; Based on the aforementioned time-frequency joint distribution characteristics, the time distribution statistics of the target signal are performed to obtain the occurrence pattern of the wireless signal.

[0029] The wireless signal receiving module mounted on the mobile vehicle captures the signals transmitted by accompanying devices in the surrounding common wireless communication frequency bands such as 2.4GHz and 5GHz. The captured analog wireless signals are transmitted to the baseband demodulation module. The demodulation module removes the high-frequency carrier components from the signal and retains the baseband signal carrying the effective information. Then, the analog-to-digital conversion circuit converts the continuous analog baseband signal into a discrete digital signal sequence to form a complete wireless signal data stream.

[0030] The wireless signal data stream is segmented into 16-byte segments. The start field and length identifier field of each segment are extracted and compared with a preset communication protocol feature library. The feature library contains standard information such as frame header identifiers, data length field formats, and verification methods for common protocols such as Bluetooth, Wi-Fi, and ZigBee. The communication protocol type corresponding to the data stream is determined by field matching. Based on the determined protocol type, the arrangement order, field length, and functional definition of each field in the data stream are parsed to clarify the specific position and number of bytes of the frame header, control segment, data segment, and frame tail, thus obtaining the frame structure of the wireless signal data stream.

[0031] Based on the established communication protocol type, consult the official standard specifications of the protocol to determine the preset offset position and fixed field length of the device identification information in the protocol frame. For example, in the Wi-Fi protocol, the MAC address field is located in bytes 4 to 9 after the frame header and has a length of 6 bytes. Combined with the parsed frame structure, determine the start and end indices of the device identification field in the wireless signal data stream. Use a field extraction tool to accurately extract the fields within the index range from the data stream to obtain the device identification field of the wireless signal data stream.

[0032] Based on the semantic encoding rules corresponding to the determined communication protocol type, the binary data in the device identifier field is split into 8-bit bytes. Each 8-bit binary number of each byte is converted to hexadecimal, for example, binary 11001010 is converted to hexadecimal CA. Then, according to the byte concatenation order specified by the protocol, the hexadecimal results of each byte are combined in sequence to form a unique identifier string composed of hexadecimal characters, thus obtaining the device identifier of the wireless signal.

[0033] The system iterates through all received wireless signals around the mobile vehicle and extracts the device identification information contained in each wireless signal using a signal analysis tool. This information is then compared character by character with the previously obtained device identifier. If the device identification information of a wireless signal is completely consistent with the device identifier in the character sequence, the wireless signal is determined to be a signal associated with the device identifier. All wireless signals that meet this consistency condition are then filtered out to obtain the target signal.

[0034] The target signal is segmented into fixed time windows, with the length of each time window set to 10 milliseconds based on the signal sampling frequency to ensure complete capture of the short-term variation characteristics of the signal. A Fourier transform is performed on the signal within each time window to convert the time-domain signal into a frequency-domain signal, obtaining all frequency components contained in the signal within that time period and the corresponding amplitude values ​​of each frequency component. The frequency-amplitude distribution results corresponding to all time windows are arranged in chronological order to form a two-dimensional time-frequency matrix containing three-dimensional information of time, frequency, and amplitude. This matrix is ​​the time-frequency joint distribution characteristic of the target signal.

[0035] From the time-frequency matrix corresponding to the joint time-frequency distribution characteristics, the amplitude value of each frequency point in all time windows is extracted. The amplitude value of each frequency point is squared to obtain the power value of that frequency point in each time window. Then, the arithmetic mean of the power values ​​of each frequency point is calculated to obtain the average power distribution of the target signal at different frequencies, i.e., the power spectral density distribution. The power value with the largest value in this distribution is selected as the strength of the wireless signal.

[0036] Starting from the start time of the automatic learning mode, a fixed statistical period of 1 second is set. All statistical periods during the duration of the automatic learning mode are traversed. It is determined whether there is an effective signal component with an amplitude greater than 0.01 volts in the joint time-frequency distribution characteristics within each statistical period. If so, the period is marked as a signal presence period. The total number of all signal presence periods is counted, and the ratio of the total number to the total number of automatic learning mode periods is calculated to obtain the signal presence time ratio. At the same time, the consecutively occurring signal presence period segments, the number of duration periods of each segment, and the number of interval periods between signal presence periods are recorded. The occurrence pattern of wireless signals is obtained by combining these statistical information.

[0037] The beneficial effects are that the step-by-step, standardized signal analysis and time-frequency domain analysis process ensures the uniqueness and accuracy of device identifier extraction, achieves precise screening of target signals, and objectively and comprehensively obtains the signal strength and occurrence patterns through specific and operable feature extraction and statistical methods. This provides high-quality and quantifiable basic data for subsequent accompanying device trust assessment, effectively improves the rigor and reliability of data processing during the whitelist self-learning process, and ensures the accuracy of subsequent trust scoring.

[0038] S3. Based on the intensity and the occurrence pattern, perform a multi-dimensional credibility assessment on the accompanying device to obtain a candidate credibility score for the accompanying device; In this embodiment of the invention, the step of performing a multi-dimensional credibility assessment on the accompanying device based on the intensity and the occurrence pattern to obtain a candidate trust score for the accompanying device includes: Based on the intensity, statistical fluctuation analysis is performed on the accompanying device to obtain the signal stability index of the accompanying device; Based on the intensity distribution characteristics, the relative position change of the accompanying equipment is evaluated to obtain the positional stability index of the accompanying equipment; Based on the aforementioned pattern, the percentage of time the accompanying device's signal is present during the automatic learning mode is statistically analyzed. The duration of the signal is continuously quantitatively evaluated to obtain the signal persistence index of the accompanying device; The signal stability index, the location fixity index, and the signal persistence index are weighted and fused to obtain the candidate trust score of the accompanying device.

[0039] The formula for calculating the candidate trust score is as follows: ; In the formula, This represents the candidate trust score. The signal stability index, The signal persistence index, The positional stability index This represents the preset stable dimension weight coefficient. This represents the preset weight coefficients for the continuous dimension. This represents the preset fixed-dimensional weight coefficients. This represents a pre-defined, extremely small positive number. This represents the maximum value function.

[0040] To obtain all the strength data of the wireless signal obtained in automatic learning mode, first calculate the arithmetic mean of these strength data, then calculate the difference between each strength data and the mean, square each difference and sum them, and divide the sum by the total number of strength data to obtain the variance of the strength data. Determine the signal stability index based on the variance: the signal stability index is 100 when the variance is less than 0.5, 80 when the variance is between 0.5 and 1.0, 60 when the variance is between 1.0 and 1.5, and 40 when the variance is greater than 1.5.

[0041] The duration of the automatic learning mode is evenly divided into 10 time periods. The average value of the wireless signal strength in each time period is calculated to obtain the average strength of the 10 time periods. The maximum and minimum values ​​of these 10 average strengths are found, and the difference between the maximum and minimum values ​​is calculated. When the difference is less than 0.3, the location fixity index is 100; when the difference is between 0.3 and 0.6, the index is 80; when the difference is between 0.6 and 0.9, the index is 60; and when the difference is greater than 0.9, the index is 40.

[0042] Starting from the start time of the automatic learning mode, and taking 1 second as a statistical unit, we iterate through all statistical units during the entire duration of the automatic learning mode, determine whether there is a valid wireless signal in each statistical unit, count the total number of statistical units with valid wireless signals, multiply the total number by 1 second to get the total signal existence time, and divide the total signal existence time by the total duration of the automatic learning mode to get the percentage of signal existence time of the accompanying device during the automatic learning mode.

[0043] A preset signal persistence evaluation standard is established. When the signal presence time accounts for more than 90%, it is judged as continuous and stable, and the signal persistence index is 100; when the proportion is between 70% and 90%, it is judged as relatively continuous, and the index is 80; when the proportion is between 50% and 70%, it is judged as generally continuous, and the index is 60; when the proportion is less than 50%, it is judged as discontinuous, and the index is 40. The signal presence time proportion is quantitatively evaluated according to this standard to obtain the signal persistence index of the accompanying equipment.

[0044] The preset weighting coefficients for stability, persistence, and fixed dimensions are 0.4, 0.3, and 0.3, respectively. The preset minimum positive number is 0.001. First, the signal stability index is multiplied by the stability dimension weighting coefficient, and then the product is divided by the larger of the signal stability index and the minimum positive number to obtain the stability dimension evaluation result. Next, the signal persistence index is multiplied by the persistence dimension weighting coefficient, and then divided by the larger of the signal persistence index and the minimum positive number to obtain the persistence dimension evaluation result. Then, the location fixity index is multiplied by the fixed dimension weighting coefficient, and then divided by the larger of the location fixity index and the minimum positive number to obtain the fixed dimension evaluation result. Finally, the evaluation results for the stability, persistence, and fixed dimensions are added together, and the sum is the candidate trust score for the accompanying device.

[0045] The beneficial effects are that by using specific evaluation standards and quantification methods across multiple dimensions, signal stability indicators, location fixity indicators, and signal persistence indicators can be accurately obtained. Then, through clear weight allocation and reasonable fusion calculation, the impact of each dimension on the credibility of the accompanying equipment is fully reflected, while avoiding the situation where the denominator is zero during the calculation process. This ensures that the candidate trust score can comprehensively and objectively reflect the credibility of the accompanying equipment, providing accurate and reliable data support for the subsequent selection of high-credibility candidate equipment, and improving the rigor and scientific nature of the credibility assessment during the whitelist self-learning process.

[0046] S4. Based on the candidate trust score and the preset trust threshold, perform a binary decision on the accompanying device to confirm the high-trust candidate device among the accompanying devices. In this embodiment of the invention, the step of performing a binary decision on the accompanying devices based on the candidate trust score and a preset trust threshold to identify high-trust candidate devices among the accompanying devices includes: The candidate trust score is correlated with the preset trust threshold within an interval to obtain the membership relationship between the candidate trust score and the trust threshold; Based on the aforementioned affiliation, a reliable classification determination is made for the accompanying devices to obtain the category attribution information of the accompanying devices; Based on the category attribution information, high-confidence candidate devices among the accompanying devices are identified.

[0047] The preset trust threshold is 70 points. This value is determined based on the multi-dimensional trustworthiness assessment, which has a maximum score of 100 points. It also takes into account the actual application scenarios of the mobile vehicle accompanying device whitelist. After statistical analysis of the trustworthiness test data of thousands of different types of accompanying devices, it is clear that high-trustworthiness devices must meet core requirements such as stable signal, fixed location, and continuous signal. The minimum trust standard derived from these requirements is 70 points, which ensures that the threshold not only conforms to the quantitative logic of the assessment system, but also adapts to the basic needs of trustworthy devices in actual use.

[0048] From the trustworthiness assessment result storage unit of the mobile vehicle, candidate trustworthiness scores for each accompanying device are extracted one by one in the order of device identifiers. During the extraction process, the numerical precision of each score is ensured to be consistent with that during the assessment. Then, each extracted score is compared byte by byte with a preset trust threshold of 70. If the value of the candidate trustworthiness score is greater than or equal to 70, the score is directly determined to belong to the range above the trust threshold; if the value of the candidate trustworthiness score is less than 70, the score is determined to belong to the range below the trust threshold. Through this device-by-device, precise direct comparison method, a unique affiliation relationship between the candidate trustworthiness score of each accompanying device and the preset trust threshold is obtained.

[0049] Based on the core requirement of whitelist construction, a fixed and unique trusted classification judgment rule is formulated. The rule is based on whether the accompanying device meets the core criteria for whitelist access. It is clearly stipulated that the affiliation relationship belonging to the range above the trust threshold uniquely corresponds to the high-trust candidate device category, and the affiliation relationship belonging to the range below the trust threshold uniquely corresponds to the non-high-trust candidate device category. According to this clear and unambiguous rule, the classification judgment work is carried out for each accompanying device in sequence, and each accompanying device is assigned a unique category label. This category label is bound one-to-one with the device identifier, which is the category affiliation information of the accompanying device.

[0050] The system retrieves the category classification information of all accompanying devices from the local database of the mobile vehicle. This information is stored in order by device identifier. The system comprehensively traverses each record in the database and performs character recognition and content verification on the category label of each accompanying device. When the character content of the category label is identified as a high-confidence candidate device category, the device identifier and related information corresponding to the label are extracted and collected into a dedicated storage list. These devices collected in the dedicated storage list are the high-confidence candidate devices among the accompanying devices.

[0051] The beneficial effects are as follows: By analyzing the full score range of the multi-dimensional credibility assessment system and the core requirements for high-credibility devices in practical applications in detail, and combining a large amount of test data, specific and practical preset trust thresholds are determined, ensuring the scientific and reasonable nature of the threshold setting. Then, by adopting a clear and operable interval association method and classification rules based on whitelist admission standards, the determination of affiliation and category information is accurate and controllable, realizing efficient screening of high-credibility candidate devices. The whole process is logically rigorous, the steps are clear and reproducible, effectively improving the accuracy and reliability of high-credibility candidate device screening, and providing a high-quality and high-credibility device foundation for subsequent strategic selection of high-credibility candidate devices.

[0052] S5. Based on a preset configuration strategy library, perform strategy-oriented optimization on the high-trust candidate devices to obtain the whitelist addition strategy for the high-trust candidate devices; In this embodiment of the invention, the step of performing policy-oriented optimization on the high-trust candidate devices based on a preset configuration policy library to obtain a whitelist addition policy for the high-trust candidate devices includes: Retrieve the device type attribute and candidate trust score of the highly trustworthy candidate device; The device type attribute and the candidate trust score are used as query conditions, and the query conditions are input into a preset configuration strategy library; In the configuration strategy library, based on the query conditions, strategy matching is performed on the high-confidence candidate devices to obtain the initial strategy set of the high-confidence candidate devices; The initial strategy set is optimized to obtain the whitelist addition strategy for the highly reliable candidate devices.

[0053] Data on highly trustworthy candidate devices is retrieved from the local device information database of the mobile vehicle. This database is indexed by device identifiers, and the device identifier of each highly trustworthy candidate device is used as a search keyword to accurately locate the corresponding device's storage entry. The clearly labeled device type and attributes are extracted, such as in-vehicle navigation devices, Bluetooth connection devices, and wireless charging devices. At the same time, the candidate trust score generated by the device in the multi-dimensional trustworthiness assessment is extracted to ensure that the retrieved device type attributes correspond one-to-one with the candidate trust score without omission.

[0054] The preset configuration policy library is built based on the application scenarios, security level requirements, and actual user habits of common accompanying devices in mobile vehicles. The library stores multiple structured policies, each of which contains core fields such as device type matching items, trust score range, addition method, and security verification requirements. The retrieved device type attributes are converted into a standard character format consistent with the device type matching items in the policy library. After retaining the integer part of the candidate trust score, it is combined with the device type attributes according to the query data structure specified by the policy library and input to the query processing unit of the configuration policy library through the data transmission interface.

[0055] After receiving the query conditions, the query processing unit of the configuration strategy library first performs a complete character comparison between the device type attribute and the device type matching item of each strategy in the library to filter out candidate strategies with the same device type. Then, for these candidate strategies, it determines whether the input candidate trust score is within the preset trust score range of the strategy. The score range adopts the form of a closed interval. When the candidate trust score is greater than or equal to the lower limit of the interval and less than or equal to the upper limit of the interval, it is determined that the condition is met. All strategies that simultaneously meet the conditions of device type matching and score range matching are extracted to form the initial strategy set of the high-trust candidate device.

[0056] The system employs a pre-defined strategy selection rule, which clearly states that strategies with higher security verification levels and simpler operation steps have higher priority. Security verification levels are divided into three levels: no verification required, basic verification, and full verification. The number of operation steps is based on the number of instructions required to perform the addition operation. For each strategy in the initial strategy set, the security verification level is evaluated and the number of operation steps is counted. First, a subset of strategies with the highest security verification level is selected. If the subset contains only one strategy, it is directly identified as the whitelist addition strategy. If the subset contains multiple strategies, the strategy with the fewest operation steps is selected and identified as the whitelist addition strategy for high-trust candidate devices.

[0057] The beneficial effects are that, through clear information retrieval methods, standardized query condition input processes, precise strategy matching rules, and clear optimization decision logic, the whitelist addition strategies selected from the preset configuration strategy library not only conform to the attribute characteristics of high-trust candidate devices, but also adapt to the usage requirements and security standards of mobile vehicles. This improves the pertinence and rationality of the whitelist addition strategies, providing a reliable guarantee for the efficient and secure updates of the mobile vehicle whitelist in the future. At the same time, the entire process is clear and reproducible, enhancing the practicality and stability of the technical solution.

[0058] S6. Based on the whitelist addition strategy, perform a whitelist update operation on the mobile vehicle.

[0059] In this embodiment of the invention, the step of updating the whitelist of the mobile vehicle based on the whitelist addition strategy includes: The whitelist addition strategy is subjected to targeted parameter extraction to obtain the operation control parameters of the mobile vehicle; The operation control parameters are encoded into operation control commands for the mobile vehicle; The operation control command is parsed to determine the automatic addition type of the operation control command; When the automatic addition type is automatic silent addition, the device identifier of the highly reliable candidate device is silently written into the accompanying device whitelist of the mobile vehicle; When the automatic addition type requires user confirmation, a device addition confirmation request for the mobile vehicle is generated. After the confirmation request is authorized by the user, the device identifier of the highly reliable candidate device is written into the accompanying device whitelist of the mobile vehicle.

[0060] The whitelist addition policy is structured and parsed. This policy contains core fields such as addition type identifier, device identifier storage path, and write permission configuration. According to the policy's preset field definitions and data formats, the specific values ​​and configuration information corresponding to each field are extracted one by one to ensure that the extracted information is completely consistent with the policy description. These extracted specific information used to control the whitelist update operation are the operation control parameters of the mobile vehicle.

[0061] The standard instruction encoding format supported by the mobile vehicle control system is adopted. This format includes a fixed-length frame header, parameter data segment, check bit, and frame tail. Each operation control parameter is converted into binary data according to the corresponding encoding rules. All binary data are arranged and combined in the order of frame header first, parameter data segment in the middle, check bit and frame tail last to form a complete binary instruction sequence. This binary instruction sequence is the operation control instruction of the mobile vehicle.

[0062] After receiving the operation control command, the instruction parsing module of the mobile vehicle first verifies the correctness of the frame header and the validity of the check bit to ensure that the command has not been damaged or tampered with during transmission. After the verification is successful, the binary data corresponding to the addition type identifier is extracted from the parameter data segment of the command. This binary data has only two preset values: binary 01 corresponds to the automatic silent addition type, and binary 10 corresponds to the addition type that requires user confirmation. By identifying the specific value of this binary data, the automatic addition type of the operation control command is obtained.

[0063] When the automatic addition type is set to automatic silent addition, the control unit of the mobile vehicle accurately locates the storage file of the accompanying device whitelist according to the storage path in the operation control parameters. The file is stored in text format, with each device identifier occupying a separate line and separated by a newline character. Without triggering any user interface prompts or voice broadcasts, the control unit opens the storage file and adds the device identifier of the highly reliable candidate device to the end of the file. After the addition is completed, the file is saved immediately and the memory index of the whitelist is updated to ensure that the device identifier is successfully written without affecting other device information that already exists in the whitelist.

[0064] When the automatic addition type requires user confirmation, the system generates a device addition confirmation request containing device type, candidate trust score, and device identifier summary based on the device-related information in the operation control parameters. The confirmation request content is displayed on the vehicle's in-vehicle display screen, and the user is informed by voice prompt that a new device is to be added to the whitelist. The user can complete the authorization through the confirmation button on the in-vehicle touch screen or the voice command "Confirm Add". After receiving the user's authorization signal, the system writes the device identifier of the high-trust candidate device into the accompanying device whitelist according to the same file format and storage path as the automatic silent addition. If the user does not perform any operation or issue a "Cancel Add" command within 30 seconds, the whitelist writing operation is terminated.

[0065] The beneficial effects include ensuring the accuracy and controllability of whitelist update operations through targeted parameter extraction, standardized encoding, and decoding. It also provides two differentiated update methods: automatic silent addition and addition requiring user confirmation. This satisfies the need for efficient updates without user intervention while ensuring the security of whitelist updates and the user's right to know through the user authorization mechanism. The entire update process is clear, specific, and reproducible, effectively improving the flexibility, reliability, and security of whitelist updates for mobile vehicle accompanying equipment, and ensuring the timeliness and accuracy of the whitelist.

[0066] like Figure 2 The diagram shown is a functional block diagram of a whitelist self-learning system for accompanying equipment of a mobile vehicle provided in an embodiment of the present invention.

[0067] The accompanying device whitelist self-learning system 100 for mobile vehicles described in this invention can be installed in an electronic device. Depending on the functions implemented, the accompanying device whitelist self-learning system 100 for mobile vehicles may include a scene security triggering module 101, a signal feature extraction module 102, a credibility assessment module 103, a high-credibility screening module 104, a strategy decision module 105, and a list update execution module 106. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.

[0068] In this embodiment, the functions of each module / unit are as follows: The scenario safety trigger module 101 is used to monitor the stationary state and geographical location of the mobile vehicle, and to make a condition compliance judgment on the stationary state and geographical location to trigger the mobile vehicle to enter the automatic learning mode. The signal feature extraction module 102 is used to parse the device identifier of the wireless signal emitted by the accompanying device around the mobile vehicle in the automatic learning mode, and perform time-frequency domain joint analysis on the wireless signal based on the device identifier to obtain the signal strength and occurrence pattern. The credibility assessment module 103 is used to perform a multi-dimensional credibility assessment of the accompanying device based on the intensity and the occurrence pattern, and obtain a candidate credibility score for the accompanying device. The high-confidence screening module 104 is used to perform a binary decision on the accompanying devices based on the candidate trust score and a preset trust threshold, and to confirm the high-confidence candidate devices among the accompanying devices. The strategy decision module 105 is used to perform strategy-oriented optimization on the high-trust candidate devices based on a preset configuration strategy library, so as to obtain the whitelist addition strategy for the high-trust candidate devices. The whitelist update execution module 106 is used to perform a whitelist update operation on the mobile vehicle based on the whitelist addition strategy.

[0069] In the several embodiments provided by this invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0070] The modules described as separate components may or may not be physically separate. The components shown as modules 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 modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0071] Furthermore, the functional modules in the various embodiments of the present invention 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 in the form of hardware plus software functional modules.

[0072] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0073] This application embodiment can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0074] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A self-learning method for a whitelist of accompanying equipment for mobile vehicles, characterized in that, The method includes: S1. Monitor the stationary state and geographical location of the mobile vehicle, and make a condition compliance judgment on the stationary state and geographical location to trigger the mobile vehicle to enter the automatic learning mode. S2. In the automatic learning mode, the device identifier of the wireless signal emitted by the accompanying device around the mobile vehicle is parsed, and based on the device identifier, the time-frequency domain joint analysis of the wireless signal is performed to obtain the signal strength and occurrence pattern. S3. Based on the intensity and the occurrence pattern, perform a multi-dimensional credibility assessment on the accompanying device to obtain a candidate credibility score for the accompanying device; S4. Based on the candidate trust score and the preset trust threshold, perform a binary decision on the accompanying device to confirm the high-trust candidate device among the accompanying devices. S5. Based on a preset configuration strategy library, perform strategy-oriented optimization on the high-trust candidate devices to obtain the whitelist addition strategy for the high-trust candidate devices; S6. Based on the whitelist addition strategy, perform a whitelist update operation on the mobile vehicle.

2. The self-learning method for a whitelist of accompanying equipment for a mobile vehicle as described in claim 1, characterized in that, The monitoring of the stationary state and geographical location of the mobile vehicle, and the conditional compliance judgment of the stationary state and geographical location to trigger the mobile vehicle to enter the automatic learning mode, includes: Continuously monitor the speed and position coordinates of mobile vehicles; The speed information is used to perform zero-speed state timing to obtain the duration of the stationary state of the mobile vehicle; Displacement accumulation analysis is performed on the position coordinate information to obtain the position change of the moving vehicle; When the duration of the stationary state exceeds a preset duration threshold and the change in position is less than a preset distance threshold, the scene safety compliance determination result of the mobile vehicle is obtained. Based on the scenario safety compliance determination result, the mobile vehicle is triggered to enter the automatic learning mode.

3. The self-learning method for a whitelist of accompanying equipment for a mobile vehicle as described in claim 1, characterized in that, In the automatic learning mode, the device identifier for parsing wireless signals emitted by accompanying devices around the mobile vehicle includes: Receive wireless signals from accompanying devices around the mobile vehicle, and perform baseband signal demodulation on the wireless signals to obtain the wireless signal data stream of the wireless signals; The wireless signal data stream is parsed to obtain the communication protocol type and frame structure of the wireless signal data stream; Based on the communication protocol type and the frame structure, metadata fields of the wireless signal data stream are determined to obtain the device identifier field of the wireless signal data stream. The device identifier field is decoded using protocol semantics to obtain the device identifier of the wireless signal.

4. The self-learning method for a whitelist of accompanying equipment for a mobile vehicle as described in claim 1, characterized in that, The step of performing joint time-frequency domain analysis on the wireless signal based on the device identifier to obtain the strength and occurrence pattern of the wireless signal includes: Based on the device identifier, the wireless signals are matched and associated to filter out target signals in the wireless signals that are associated with the device identifier; Time-frequency domain features are extracted from the target signal to obtain the joint time-frequency distribution features of the target signal; Based on the aforementioned time-frequency joint distribution characteristics, the power spectral density of the target signal is analyzed to obtain the strength of the wireless signal; Based on the aforementioned time-frequency joint distribution characteristics, the time distribution statistics of the target signal are performed to obtain the occurrence pattern of the wireless signal.

5. The self-learning method for a whitelist of accompanying equipment for a mobile vehicle as described in claim 1, characterized in that, The method of performing a multi-dimensional credibility assessment on the accompanying device based on the intensity and the occurrence pattern to obtain a candidate trust score for the accompanying device includes: Based on the intensity, statistical fluctuation analysis is performed on the accompanying device to obtain the signal stability index of the accompanying device; Based on the intensity distribution characteristics, the relative position change of the accompanying equipment is evaluated to obtain the positional stability index of the accompanying equipment; Based on the aforementioned pattern, the percentage of time the accompanying device's signal is present during the automatic learning mode is statistically analyzed. The duration of the signal is continuously quantitatively evaluated to obtain the signal persistence index of the accompanying device; The signal stability index, the location fixity index, and the signal persistence index are weighted and fused to obtain the candidate trust score of the accompanying device.

6. The self-learning method for a whitelist of accompanying equipment for a mobile vehicle as described in claim 5, characterized in that, The formula for calculating the candidate trust score is as follows: ； In the formula, This represents the candidate trust score. The signal stability index, The signal persistence index, The positional stability index This represents the preset stable dimension weight coefficient. This represents the preset weight coefficients for the continuous dimension. This represents the preset fixed-dimensional weight coefficients. This represents a pre-defined, extremely small positive number. This represents the maximum value function.

7. The self-learning method for a whitelist of accompanying equipment for a mobile vehicle as described in claim 1, characterized in that, The step of performing a binary decision on the accompanying devices based on the candidate trust score and a preset trust threshold, and identifying high-trust candidate devices among the accompanying devices, includes: The candidate trust score is correlated with the preset trust threshold within an interval to obtain the membership relationship between the candidate trust score and the trust threshold; Based on the aforementioned affiliation, a reliable classification determination is made for the accompanying devices to obtain the category attribution information of the accompanying devices; Based on the category attribution information, high-confidence candidate devices among the accompanying devices are identified.

8. The self-learning method for a whitelist of accompanying equipment for a mobile vehicle as described in claim 1, characterized in that, The system, based on a preset configuration strategy library, performs strategy-oriented optimization on the high-trust candidate devices to obtain a whitelist addition strategy for the high-trust candidate devices, including: Retrieve the device type attribute and candidate trust score of the highly trustworthy candidate device; The device type attribute and the candidate trust score are used as query conditions, and the query conditions are input into a preset configuration strategy library; In the configuration strategy library, based on the query conditions, strategy matching is performed on the high-confidence candidate devices to obtain the initial strategy set of the high-confidence candidate devices; The initial strategy set is optimized to obtain the whitelist addition strategy for the highly reliable candidate devices.

9. The self-learning method for a whitelist of accompanying equipment for a mobile vehicle as described in claim 1, characterized in that, The whitelist update operation for the mobile vehicle based on the whitelist addition strategy includes: The whitelist addition strategy is subjected to targeted parameter extraction to obtain the operation control parameters of the mobile vehicle; The operation control parameters are encoded into operation control commands for the mobile vehicle; The operation control command is parsed to determine the automatic addition type of the operation control command; When the automatic addition type is automatic silent addition, the device identifier of the highly reliable candidate device is silently written into the accompanying device whitelist of the mobile vehicle; When the automatic addition type requires user confirmation, a device addition confirmation request for the mobile vehicle is generated. After the confirmation request is authorized by the user, the device identifier of the highly reliable candidate device is written into the accompanying device whitelist of the mobile vehicle.

10. A self-learning system for a whitelist of accompanying equipment for mobile vehicles, characterized in that, The system for implementing the self-learning method for a whitelist of accompanying devices for a mobile vehicle as described in claim 1 includes: The scene safety trigger module is used to monitor the stationary state and geographical location of the mobile vehicle, and to make a condition compliance judgment on the stationary state and geographical location to trigger the mobile vehicle to enter the automatic learning mode. The signal feature extraction module is used to parse the device identifier of the wireless signal emitted by the accompanying device around the mobile vehicle in the automatic learning mode, and perform time-frequency domain joint analysis on the wireless signal based on the device identifier to obtain the signal strength and occurrence pattern. The credibility assessment module is used to perform a multi-dimensional credibility assessment of the accompanying device based on the intensity and the occurrence pattern, and obtain a candidate credibility score for the accompanying device. The high-confidence screening module is used to perform a binary decision on the accompanying devices based on the candidate trust score and a preset trust threshold, and to confirm the high-confidence candidate devices among the accompanying devices. The strategy decision module is used to perform strategy-oriented optimization on the high-trust candidate devices based on a preset configuration strategy library, and obtain the whitelist addition strategy for the high-trust candidate devices; The whitelist update execution module is used to perform whitelist update operations on the mobile vehicle based on the whitelist addition strategy.

Images