A fingerprint-based communication state recognition method, system, device and medium

Abstract

The application provides a fingerprint-based communication state recognition method, system, device and medium, and belongs to the technical field of vehicle-mounted communication. The method comprises the following steps: collecting original communication data of each slave node in multiple communication periods in a normal communication state of a bus; creating a multi-dimensional feature vector as a communication fingerprint of the slave node based on the original communication data; storing the communication fingerprint in association with an identifier corresponding to the slave node to form a fingerprint library; collecting real-time communication data of a target slave node, extracting a current feature vector according to the real-time communication data; and matching and comparing the current feature vector with the fingerprint library, and determining the communication state of the target slave node according to the matching result. The application accurately locates the fault type of a single slave node in the bus, the diagnosis process does not affect the normal use of the vehicle, and no additional hardware cost is required.

Description

Technical Field

[0001] This invention relates to the field of vehicle communication technology, specifically to a fingerprint-based communication status identification method, system, device, and medium. Background Technology

[0002] LIN (Local Interconnect Network) bus, as a low-cost and simple in-vehicle serial communication protocol, has become a core communication standard in the field of automotive body control. It is widely used in distributed control scenarios where real-time requirements are not high, such as window operation, wiper control, and interior and exterior lighting adjustment. With the increasing complexity of automotive electronic and electrical architectures, the reliability of the LIN bus network directly affects the normal operation of related body functions and user experience. Therefore, effective monitoring of its operating status and rapid fault diagnosis are of great significance.

[0003] Currently, the industry's commonly used technologies for detecting and diagnosing LIN bus communication status primarily focus on macroscopic monitoring of the bus physical and protocol layers. Specifically, common methods include: monitoring bus levels through the master node or external diagnostic devices to determine if there are hardware connection faults such as power or ground short circuits or open circuits; performing checksum and identifier checks on messages to identify communication format errors or frame loss; and counting the number of bus error frames to assess overall communication quality. These methods can detect communication interruptions or serious anomalies at the system level.

[0004] However, the existing diagnostic technologies mentioned above have significant limitations: First, their diagnostic granularity remains at the "bus level," only able to determine whether the overall bus has failed, but unable to pinpoint the specific sensor or actuator node malfunctioning. Second, existing methods lack effective detection and identification means for node-level "soft" faults or performance degradation caused by internal node software errors, slight crystal frequency deviations, or increased contact resistance at line terminals. This results in technicians still needing to manually inspect each harness and node individually during actual maintenance, leading to low diagnostic efficiency and difficulty in achieving early warning and preventative maintenance. Therefore, a new method is urgently needed to achieve accurate, online, and non-invasive intelligent diagnostics at the LIN bus node level. Summary of the Invention

[0005] In view of this, it is necessary to provide a fingerprint-based communication status identification method, system, device and medium to solve the technical problem that the existing technology can only identify bus-level faults and cannot locate specific node abnormalities, resulting in low maintenance efficiency.

[0006] To address the aforementioned technical problems, in a first aspect, the present invention provides a fingerprint-based communication status identification method, comprising: Under normal bus communication conditions, collect raw communication data from each slave node over multiple communication cycles; Based on the original communication data, a multi-dimensional feature vector is created as the communication fingerprint of the slave node; The communication fingerprint is associated with the identifier of the corresponding slave node and stored to form a fingerprint database; Collect real-time communication data from the target node, and extract the current feature vector based on the real-time communication data; The current feature vector is compared with the fingerprint database, and the communication status of the target slave node is determined based on the matching result.

[0007] In one possible implementation, creating a multi-dimensional feature vector as the communication fingerprint of the slave node based on the original communication data includes: A predetermined number of valid data samples are collected from each of the slave nodes, and outliers that exceed a preset statistical range are removed. Based on the processed valid data samples, the multidimensional feature vector is calculated and created. The multidimensional feature vector includes at least the following dimensions: the standard deviation of the rising edge time of the frame start signal, the average value of the data bit transmission delay, the parity distribution rate of the check code, and the statistical rate of frame retransmission.

[0008] One possible implementation also includes: Determine whether a preset trigger event is detected during vehicle operation; the preset trigger event includes the target slave node having a fingerprint matching deviation greater than a first threshold in a predetermined number of consecutive diagnostic cycles; If so, the communication fingerprint of the target slave node in the fingerprint database is updated based on the new incremental data.

[0009] In one possible implementation, the data to be collected from the node's real-time communication data includes: Calculate the average bus communication load rate over a predetermined number of consecutive communication cycles; Determine whether the average load rate of the bus communication is lower than a preset safety threshold; If so, the real-time communication data is collected during the communication gap after the predetermined number of consecutive communication cycles and before the start of the next communication cycle.

[0010] In one possible implementation, the calculation of the average bus communication load rate over a predetermined number of consecutive communication cycles includes: Determine whether the target slave node has a communication abnormal event. The communication abnormal event includes at least one of the following: frame response timeout for a preset number of consecutive times, or the statistical value of the message verification error rate within a preset time exceeds a second threshold. If so, collect the real-time communication data of the target slave node; If not, calculate the average load rate of the bus communication.

[0011] In one possible implementation, the step of matching and comparing the current feature vector with the fingerprint database, and determining the communication status of the target slave node based on the matching result, includes: The feature values ​​of each dimension of the current feature vector are compared with the preset threshold range of the communication fingerprint of the target slave node in the fingerprint database in the corresponding dimension. If all dimensions of the current feature vector are within their respective preset threshold ranges, the communication status of the target slave node is determined to be normal. If the value of any dimension in the current feature vector exceeds its corresponding preset threshold range, the communication status of the target slave node is determined to be abnormal.

[0012] In one possible implementation, after determining that the communication state of the target slave node is abnormal, the process includes: Based on the target dimension, a preset mapping relationship table is queried to determine at least one fault type; the target dimension is the dimension in the current feature vector where the feature value exceeds its corresponding preset threshold range. Generate and output a diagnostic report, which includes at least the identifier of the target slave node, the target dimension, and its corresponding fault type.

[0013] Secondly, the present invention also provides a fingerprint-based communication status recognition system, comprising: The acquisition module is used to collect the raw communication data of each slave node in multiple communication cycles under normal bus communication conditions. A creation module is used to create a multi-dimensional feature vector as the communication fingerprint of the slave node based on the original communication data; A generation module is used to associate and store the communication fingerprint with the identifier of the corresponding slave node to form a fingerprint database; The acquisition and extraction module is used to acquire real-time communication data of the target slave node and extract the current feature vector based on the real-time communication data. The processing module is used to match and compare the current feature vector with the fingerprint database, and determine the communication status of the target slave node based on the matching result.

[0014] Thirdly, the present invention also provides an electronic device, including a memory and a processor, wherein, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the fingerprint-based communication state recognition method described in any of the above implementations.

[0015] Fourthly, the present invention also provides a computer-readable storage medium for storing a computer-readable program or instruction, which, when executed by a processor, can implement the steps of the fingerprint-based communication status identification method described in any of the above implementations.

[0016] The beneficial effects of this invention are as follows: The fingerprint-based communication status identification method provided by this invention first creates a multi-dimensional feature vector as the communication fingerprint of the slave node based on the original communication data corresponding to different slave nodes. Then, the current feature vector obtained from the real-time communication data of the target slave node is compared with the fingerprint database. Based on the matching result, the communication status of the target slave node is determined, which can directly locate the specific faulty node and indicate the abnormality type, greatly shortening the maintenance and troubleshooting time. Furthermore, the entire solution is a software algorithm upgrade, without the need to add additional hardware sensors or complex diagnostic modules. Only the existing master node software needs to be upgraded to be compatible with the existing LIN network. It has excellent adaptability and large-scale application value, effectively overcoming the difficulties of deep diagnostics of the LIN bus. While improving the reliability and maintainability of vehicle electronic systems, it is low-cost and easy to deploy. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A schematic flowchart of an embodiment of the fingerprint-based communication status recognition method provided by the present invention; Figure 2 For the present invention Figure 1 A schematic diagram of an embodiment of S102; Figure 3 A schematic flowchart of another embodiment of the fingerprint-based communication status recognition method provided by the present invention; Figure 4 For the present invention Figure 1 A schematic diagram of an embodiment of S104; Figure 5 For the present invention Figure 1 A schematic diagram of an embodiment of S105; Figure 6 For the present invention Figure 5 A flowchart of an embodiment following S503; Figure 7 A schematic diagram of an embodiment of the fingerprint-based communication status recognition system provided by the present invention; Figure 8 A schematic diagram of an embodiment of the electronic device provided by the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0020] In the description of the embodiments of the present invention, unless otherwise stated, "multiple" means two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0021] The terms "first," "second," etc., used in the embodiments of this invention are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a technical feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature.

[0022] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0023] This invention provides a fingerprint-based communication status identification method, system, device, and medium, which are described below.

[0024] Figure 1 The following is a schematic flowchart of an embodiment of the fingerprint-based communication status recognition method provided by the present invention, as shown below. Figure 1 As shown, the fingerprint-based communication status recognition method includes: S101. Under normal bus communication conditions, collect the raw communication data of each slave node in multiple communication cycles.

[0025] It should be noted that in the architecture of a Local Area Network (LIN) bus, devices in the network are clearly distinguished as master nodes and slave nodes based on their communication roles. The master node is the manager, scheduler, and communication initiator in the LIN; there is one and only one master node in a LIN. Slave nodes are the responders and task executors in the LIN; there can be one or more slave nodes in a LIN. During the pre-delivery testing phase of a vehicle, or when the vehicle is in a stable communication state such as stationary or running, the master node (such as the Body Control Module, BCM) listens to and records the raw communication data of each slave node on the bus (such as the window motor controller or lighting controller) over N consecutive communication cycles (e.g., 1000). The raw communication data includes, but is not limited to, the precise time of the rising edge of the break field (t1), the transmission delay time of each data bit (t2), the frame checksum type, and the number of frame retransmissions (n).

[0026] S102. Based on the original communication data, create a multi-dimensional feature vector as the communication fingerprint of the slave node.

[0027] It should be noted that: based on the original communication data of each slave node, a unique multidimensional feature vector is created for each slave node as its communication fingerprint.

[0028] S103. The communication fingerprint is associated with the identifier of the corresponding slave node and stored to form a fingerprint database.

[0029] It should be noted that the calculated multidimensional feature vector (communication fingerprint) is bound to the corresponding unique identifier of the slave node (such as the node address) and stored in the non-volatile memory (such as Flash) of the master node. The old communication fingerprints of the corresponding nodes in the fingerprint database can be updated periodically to adapt to component aging or environmental changes.

[0030] S104. Collect real-time communication data from the target slave node, and extract the current feature vector based on the real-time communication data.

[0031] It should be noted that the master node quickly collects real-time communication data of the target slave node's response messages, and calculates and generates a current feature vector in real time according to the same algorithm as S102.

[0032] S105. The current feature vector is matched and compared with the fingerprint database, and the communication status of the target slave node is determined based on the matching result.

[0033] It should be noted that the current feature vector obtained in S104 is compared with the baseline fingerprint of the target slave node stored in the fingerprint database (i.e., the existing communication fingerprint of the target slave node in the fingerprint database), and the real-time communication status (normal or abnormal) of the target slave node is finally determined based on the matching result.

[0034] In summary, the fingerprint-based communication status identification method provided by this invention first creates a multi-dimensional feature vector as the communication fingerprint of the slave node based on the original communication data corresponding to each slave node. Then, the current feature vector obtained from the real-time communication data of the target slave node is compared with the fingerprint database. Based on the matching result, the communication status of the target slave node is determined, which can directly locate the specific faulty node and indicate the abnormality type, greatly shortening the maintenance and troubleshooting time. Furthermore, the entire solution is a software algorithm upgrade, without the need to add additional hardware sensors or complex diagnostic modules. Only the existing master node software needs to be upgraded to be compatible with the existing LIN network. It has excellent adaptability and large-scale application value, effectively overcoming the difficulties of deep diagnostics of the LIN bus. While improving the reliability and maintainability of vehicle electronic systems, it is low-cost and easy to deploy.

[0035] To construct a digital communication fingerprint for each stage that can be used for accurate identification and status diagnosis, in some embodiments of the present invention, such as... Figure 2 As shown, step S102 includes: S201. Collect a predetermined number of valid data samples for each slave node and remove outliers that exceed the preset statistical range.

[0036] It should be noted that, for each slave node, under a stable communication environment, a significantly larger number of raw data samples than the predetermined number (e.g., 1200 sets) are continuously collected. For each collected parameter, the arithmetic mean (μ) and standard deviation (σ) of all samples are calculated. The statistical 3σ criterion is used to classify samples whose values ​​fall outside the interval [μ-3σ, μ+3σ] as extreme outliers. Samples that do not exceed their respective 3σ ranges across all parameter dimensions are retained to form a predetermined number (e.g., 1000 sets) of effective data samples for subsequent modeling.

[0037] S202. Based on the processed valid data samples, calculate and create the multidimensional feature vector, which includes at least the following dimensions: the standard deviation of the rising edge time of the frame start signal, the average value of the data bit transmission delay, the parity distribution rate of the check code, and the statistical rate of frame retransmission.

[0038] It should be noted that a set of quantitative feature values ​​with clear physical or logical meaning are calculated from the cleaned valid samples and combined into a multidimensional feature vector. The multidimensional feature vector includes feature values ​​of the timing stability dimension (characterizing the jitter and stability of the node's internal clock), feature values ​​of the response speed dimension (characterizing the inherent processing and response delay of the node's hardware circuits such as transceivers and MCUs), feature values ​​of the logical consistency dimension (characterizing the stability and consistency of the node's software configuration or operating logic), and feature values ​​of the communication reliability dimension (characterizing the signal quality of the node's communication link or the node's own response reliability).

[0039] Among them, the standard deviation of the frame start rising edge time is used as a feature value of the temporal stability dimension. The calculation formula is as follows: Where N is the sample size. The rising edge time of the start bit of the i-th frame (in μs). Let N be the arithmetic mean of the rise times. =(t 11 +t12+t13…+t1N) / N.

[0040] The average value of the data bit transmission delay (t2) is calculated as a feature value of the response speed dimension. The calculation formula is as follows: ,in, The transmission delay of the i-th data bit group is in milliseconds.

[0041] The parity distribution rate of the check code is calculated as a feature value of the logical consistency dimension. The formula for calculating the parity distribution rate of the check code is as follows: ,in, for The number of times the odd parity code appears in the set of data.

[0042] The statistical rate of frame retransmission count is used as a feature value of the communication reliability dimension. The calculation formula is as follows: ,in, The number of times the frame of the i-th data group is retransmitted (0 or a positive integer).

[0043] The calculation results of the above four dimensions [ , , , The features are combined in a preset order to construct a multi-dimensional feature vector (communication fingerprint) that uniquely identifies the target node. The preset order can be, in order: the standard deviation of the rising edge time of the frame start signal, the average data bit transmission delay, the parity distribution rate of the checksum, and the statistical rate of frame retransmissions; or, in order: the average data bit transmission delay, the standard deviation of the rising edge time of the frame start signal, the parity distribution rate of the checksum, and the statistical rate of frame retransmissions; or, in order: the parity distribution rate of the checksum, the standard deviation of the rising edge time of the frame start signal, the average data bit transmission delay, and the statistical rate of frame retransmissions. Any preset order is within the scope of protection of this invention.

[0044] In this embodiment, the collected raw communication data undergoes standardized preprocessing to eliminate the influence of occasional interference. Subsequently, for the preprocessed valid data, a specific statistical algorithm is executed to extract and calculate a set of feature values ​​that can characterize the unique behavioral patterns of nodes from different aspects (timing stability, response speed, logical consistency, and communication reliability). The raw communication data is transformed into a multi-dimensional feature vector representing the intrinsic characteristics of the node, which is finally combined to form a unique digital identifier for the node, making the features of each node highly unique and comparable. Furthermore, outlier cleaning effectively filters out occasional and extreme noise caused by electromagnetic pulses, instantaneous power supply fluctuations, etc., ensuring that the extracted features reflect the inherent and stable characteristics of the node itself, rather than environmental noise, significantly reducing the false judgment rate and improving the anti-interference and stability of node communication status judgment. Furthermore, the node state is characterized from four levels: clock source, hardware circuit, software logic, and communication link, and corresponding multi-dimensional feature vectors are generated. This not only identifies the node's identity but also, when an anomaly occurs, effectively infers the cause of the fault based on the changed dimensional features, achieving dual identification of node identity and abnormal state.

[0045] To prevent the established communication fingerprint from gradually becoming invalid due to node hardware aging, software updates, or long-term slow changes in the working environment, and to improve the continuous accuracy of the fingerprint throughout its entire lifecycle, in some embodiments of the present invention, such as... Figure 3 As shown, it also includes: S301. Determine whether a preset trigger event is detected during vehicle operation; the preset trigger event includes the target slave node having a fingerprint matching deviation greater than a first threshold in a predetermined number of consecutive diagnostic cycles.

[0046] It should be noted that in each diagnostic cycle, after the current feature vector is matched with the standard fingerprint, a quantified match deviation (D) is calculated. The match deviation can be a weighted sum of the number of out-of-limit feature dimensions, or the sum of the normalized offset distances of all feature values ​​relative to their threshold values. Two key parameters are preset: a first threshold (the deviation threshold value used to determine significant anomalies in a single diagnosis) and a predetermined number of consecutive diagnostic cycles (e.g., 3 or 5 consecutive diagnostic cycles). The system maintains a short-term historical record for each slave node. When it is detected that the calculated match deviation D of the target slave node is greater than the first threshold in the most recent K consecutive diagnostic cycles, the preset trigger condition is determined to be met.

[0047] S302. If so, update the communication fingerprint of the target slave node in the fingerprint database based on the new incremental data.

[0048] It should be noted that once the preset triggering conditions are met, the master node immediately initiates a new round of data collection for the target slave node, obtaining new incremental data. Using the exact same algorithm as the initial feature extraction (S102 / S202), the newly collected incremental data is cleaned and calculated to generate a new multidimensional feature vector for the target slave node. Then, the newly calculated multidimensional feature vector is used to directly replace the old fingerprint associated with the target slave node identifier in the fingerprint database, completing the fingerprint update. This ensures that subsequent diagnostic matching by the system will automatically use the updated fingerprint as the standard.

[0049] In this embodiment, when the fingerprint matching deviation of the target slave node exceeds a first threshold for a predetermined number of consecutive diagnostic cycles, an incremental data acquisition and feature recalculation for the target slave node is automatically initiated. The newly generated fingerprint overwrites the old fingerprint in the database, ensuring that the fingerprint database remains synchronized with the vehicle's current hardware status and guaranteeing the reliability of long-term diagnostics. Furthermore, incremental data acquisition is only performed when the fingerprint matching deviation of the target slave node exceeds the first threshold for a predetermined number of consecutive diagnostic cycles. This significantly saves bus bandwidth and master node computing and storage resources, avoiding a large amount of unnecessary and repetitive background data acquisition and calculation, achieving an optimal balance between update efficiency and resource overhead. Moreover, it significantly improves the system's robustness and intelligence: this mechanism enables the system to distinguish between instantaneous interference (single or accidental deviation) and continuous trend deviation. Incremental data acquisition and fingerprint updates are only performed when the fingerprint matching deviation of the target slave node exceeds the first threshold for a predetermined number of consecutive diagnostic cycles, effectively preventing the risk of erroneous updates due to temporary strong interference, which could contaminate the fingerprint database.

[0050] On the premise of continuously maintaining the normal body control function of the LIN bus, in order to obtain real-time and effective communication data and achieve completely imperceptible data acquisition. In some embodiments of the present invention, such as Figure 4 shown, step S104 includes: S401. Calculate the average bus communication load rate within a continuously predetermined number of communication cycles.

[0051] It should be noted that the master node continuously monitors the bus activity, and uses a continuously predetermined number (such as M = 10) of complete communication cycles as the basic observation window. Each communication cycle is defined according to the LIN schedule. Within this basic observation window, the total time occupied by all the messages used for normal service communication (body control instructions, status reports, etc.) is accumulated, and then divided by the total duration of the basic observation window to calculate the average bus communication load rate L_avg during this period. The calculation formula for the average bus communication load rate L_avg can be: L_avg = (Σ time occupied by service messages) / (M × communication cycle duration).

[0052] S402. Determine whether the average bus communication load rate is lower than a preset safety threshold.

[0053] It should be noted that a dynamic or static preset safety threshold L_th is set. The preset safety threshold L_th is set through system optimization and is usually much lower than the theoretical maximum load of the bus to ensure that during diagnostic acquisition, the bus still has sufficient bandwidth margin to handle sudden or high-priority service messages. Compare the calculated average bus communication load rate L_avg with the preset safety threshold L_th. Only when the average bus communication load rate is less than the safety threshold (i.e., L_avg < L_th), it indicates that the current bus is in a low-load state and meets the trigger condition for diagnostic acquisition. When the average bus communication load rate is greater than or equal to the preset safety threshold, the system will suspend or postpone the planned polling diagnostic data acquisition for this time and continue to monitor the bus load status until the average bus communication load rate is less than the preset safety threshold.

[0054] S403. If so, collect the real-time communication data during the communication gap after the continuously predetermined number of communication cycles and before the start of the next communication cycle.

[0055] It should be noted that when the average bus communication load rate is less than the safety threshold, the system immediately anchors the timing of the acquisition action at the end of the current basic observation window (i.e., the above-mentioned continuous M communication cycles, such as t0 + t M , where t0 is the current time and t M is the duration of the continuous M communication cycles), and after the end of the current basic observation window, the next communication cycle (i.e., the first t after the continuous M communication cycles M+1The communication gap preceding the start of each communication cycle. During this gap, the master node rapidly triggers and completes real-time data acquisition of the response messages from the target slave node. Since the bus is determined to be idle at this time and is within the interval specified by the protocol, this acquisition operation does not cause any delay or conflict to the subsequent normal service message transmission.

[0056] In this embodiment, by continuously monitoring the bus communication load, the system intelligently selects to execute diagnostic tasks during relatively idle time windows (i.e., communication gaps). Specifically, the system calculates the recent average communication load level and only initiates data acquisition during the first protocol-allowed communication gap after determining that it is below a preset safety threshold. This ensures that the impact of diagnostic behavior on normal business is minimized, avoiding competition for bus bandwidth between diagnostic tasks and vehicle control functions. This allows users to perform operations such as raising and lowering windows and switching lights without any noticeable lag or delay, improving the driving experience and enabling online diagnostics to run routinely in the background, achieving zero-perception diagnostics. Furthermore, data acquisition during low-load communication gaps significantly reduces the impact of transmission delay jitter caused by bus contention and message queuing on the acquired data. Moreover, the extracted current feature vector more accurately reflects the characteristics of the target slave node itself, rather than being a false impression due to network congestion, thus significantly improving the accuracy of subsequent fingerprint matching and status determination.

[0057] In some embodiments of the present invention, prior to calculating the average load rate of bus communication over a predetermined number of consecutive communication cycles, the method includes: Determine whether the target slave node has a communication abnormal event. The communication abnormal event includes at least one of the following: frame response timeout for a preset number of consecutive times, or the statistical value of the verification error rate within a preset time exceeds a second threshold. If so, collect the real-time communication data of the target slave node; If not, calculate the average load rate of the bus communication.

[0058] It should be noted that after sending a request frame, the master node starts a timer to wait for the slave node's response. It determines whether the target slave node has failed to return a valid response frame within the time specified in the protocol after a preset number of consecutive requests (e.g., N=3). If so, it determines that the frame response timeout has occurred for the preset number of consecutive requests (i.e., consecutive frame response timeouts), indicating that event A has occurred. The master node continuously counts the number of checksum errors from the target slave node and calculates whether the statistical value of checksum errors occurring within a preset duration (e.g., T=10 seconds) (such as the number of errors per minute or the percentage of error frames) exceeds a second threshold. When the statistical value exceeds the set second threshold, it determines that the checksum error rate has exceeded the limit, indicating that event B has occurred. Based on the anomaly monitoring results, different data acquisition strategies are executed. The system monitors the two types of events (event A and event B) in parallel. Once either event is determined to be true (i.e., a high-priority communication anomaly event exists), the anomaly response process is immediately triggered, bypassing subsequent load judgments (i.e., S401 to S403), and directly collecting the target slave node's real-time communication data in the next communication interval. If neither of the above two types of events is true, the system will first calculate the average bus communication load rate over a predetermined number of consecutive communication cycles and determine whether it is below a safety threshold. Data acquisition will only be performed when the low load condition is met.

[0059] In this embodiment, the system does not employ a single strategy for all diagnostic requests. Instead, it dynamically selects the optimal data acquisition path based on the urgency of the detected communication anomalies. When a high-priority, sudden communication failure event (such as continuous no response or a spike in error rate) is detected, the system immediately initiates diagnostic data acquisition to ensure rapid fault detection and response. Conversely, in the absence of urgent events, the system switches to resource optimization mode, first assessing the bus load status and performing acquisition only under low load conditions. This ensures timely diagnosis while minimizing interference with normal communication services, guaranteeing that the vehicle control function enjoys the highest communication resource priority at all times, and ensuring a smooth user experience and overall system operation. Furthermore, by constraining most routine, preventative diagnostic activities to be performed during system idle periods (i.e., communication gaps), the average occupancy of bus bandwidth and master node computing resources is significantly reduced. This allows the diagnostic solution to be seamlessly integrated into the existing vehicle network as a silent, background service without requiring additional resources to handle peak diagnostic demands, optimizing system resource utilization and reducing the complexity and cost of the overall system design. Furthermore, it can flexibly adapt to various complex scenarios, from preventive health monitoring during smooth vehicle operation to emergency diagnosis when encountering sudden interference or component failure. It avoids the chain of problems that may be caused by forcibly inserting diagnostic tasks when the bus is busy, and ensures the reliable triggering of diagnostic functions when they are really needed, thus improving the practicality and reliability of the whole system in the actual and ever-changing vehicle environment.

[0060] In some embodiments of the present invention, such as Figure 5 As shown, step S105 includes: S501. The feature values ​​of each dimension of the current feature vector are compared with the preset threshold range of the communication fingerprint of the target slave node in the fingerprint database in the corresponding dimension.

[0061] It should be noted that: the current feature vector of the target slave node is obtained from step S104, denoted as... Vcurrent =[ f 1, f 2, f 3, f 4], of which f 1, f 2, f 3, f 4 corresponds to four predefined feature dimensions (e.g.: f 1: Standard deviation of frame start rising edge time; f 2: Average data bit transmission delay; f 3: Parity distribution rate of the check code; f4: Frame retransmission rate). Based on the identifier of the target slave node, its standard communication fingerprint is retrieved from the fingerprint database. This fingerprint is associated with each feature dimension. i The preset threshold range [ T low , T high These threshold ranges are typically determined through statistical learning during the initial modeling phase (e.g., confidence intervals based on a normal data distribution, such as mean ± 3 standard deviations) and can be adjusted in subsequent updates. For each feature dimension... i Determine real-time feature values fi Does it meet the following requirements: T low ≤ fi ≤ T high The system records the comparison results for each dimension as either "compliant" or "exceeding limits".

[0062] S502. If all dimensions of the current feature vector are within their respective preset threshold ranges, the communication status of the target slave node is determined to be normal. S503. If the value of any dimension in the current feature vector exceeds its corresponding preset threshold range, the communication status of the target slave node is determined to be abnormal.

[0063] It should be noted that: if step S501 applies to all dimensions i If all comparison results are compliant, then the overall judgment is that the communication status of the target node is normal. i =Nk, where Nk is a positive integer greater than 1. Let Nk be 4. i =1, 2, 3, 4. This indicates that the node's current key behavioral indicators are all within their historical normal fluctuation range, and no identifiable anomalies have been detected. If, in step S501, at least one dimension's comparison result shows that the value of any dimension in the current feature vector exceeds its corresponding preset threshold range, that is, at least one... i Make fi < T low or fi > T high If the communication status of the target slave node is determined to be abnormal, it indicates that the target slave node has deviated from the allowable range in at least one behavioral characteristic, and there is a potential risk of failure or performance degradation.

[0064] In this embodiment, the current feature vector of the node extracted in real time is compared with the pre-stored communication fingerprint, and a state determination is made according to predefined rules. This enables consistent and unambiguous determinations of the state of the same node, greatly improving the objectivity, standardization, and repeatability of diagnostic conclusions. Furthermore, multi-dimensional independent monitoring and comprehensive judgment are adopted. On the one hand, any significant anomaly in a single dimension can be effectively captured, ensuring high detection sensitivity for multiple potential fault modes (such as unstable clocks, slow response, logical errors, and link degradation). On the other hand, the communication state of the target slave node is determined to be normal only if all dimensions are normal, effectively filtering out single-dimensional accidental fluctuations caused by instantaneous and isolated interference, thereby reducing the false alarm rate of the system and enhancing the robustness of the diagnosis.

[0065] In some embodiments of the present invention, such as Figure 6 As shown, after determining that the communication status of the target slave node is abnormal, the process includes: S601. Query the preset mapping relationship table according to the target dimension to determine at least one fault type; the target dimension is the dimension in the current feature vector where the feature value exceeds its corresponding preset threshold range. S602. Generate and output a diagnostic report, the diagnostic report including at least the identifier of the target slave node, the target dimension and its corresponding fault type.

[0066] It should be noted that during the system development phase, based on the physical / logical meaning of each feature dimension (see S102 / S202) and the analysis of a large number of fault case libraries, a preset mapping table is created, which includes the correspondence between feature dimensions and fault types. The preset mapping table defines one or more high-probability suspected fault types associated with each dimension or combination of dimensions exceeding the limit. Based on the decision result of step S503, the mapping table is queried using the target dimension (e.g., [dimension 1, dimension 3]) as the index. The query returns one or more corresponding fault type descriptions. The diagnostic conclusion is formatted to generate a diagnostic report that is easy for the upper-layer system to process, store, or display. The diagnostic report at least includes the identifier of the target slave node, the target dimension and its corresponding fault type, and may also include environmental information such as timestamps, the time of the first occurrence of the anomaly, and the current bus voltage.

[0067] In this embodiment, by querying a preset mapping table, abstract numerical anomalies are intelligently mapped to one or more specific suspected fault types with clear maintenance guidance significance, and a structured diagnostic report is automatically generated. This allows maintenance personnel of different experience levels to obtain the same high-quality and targeted diagnostic suggestions, ensuring the uniformity and high level of maintenance service standards, while reducing reliance on specific senior technicians.

[0068] For example, the fingerprint-based communication status identification method mainly includes the following four steps: The first step is data acquisition (modeling stage), which involves the master node (such as BCM) collecting communication data from each slave node under normal LIN bus operation. Acquisition timing includes the initial modeling acquisition during the vehicle's off-line inspection phase, and subsequent incremental acquisitions automatically triggered every 3 months. The acquisition objects include the frame start bit rise time (t1), data bit transmission delay (t2), checksum type (odd / even), and frame retransmission count (n). Acquisition parameters include collecting N (e.g., 1000) sets of valid data from each node, and removing extreme interference values ​​(the extreme value judgment criterion is exceeding the mean of the parameter by ±3 times the standard deviation). The sampling frequency is consistent with the LIN bus communication frequency. The second step is feature extraction (fingerprint core construction), which involves performing mathematical operations on the 1000 sets of collected data to extract the core features of the above four acquisition objects: Feature 1: Standard deviation of frame start bit rise time (σ1), Feature 2: Average data bit transmission delay (μ2), Feature 3: Parity distribution rate of the checksum, and Feature 4: Frame retransmission rate. To ensure that the four features are of the same magnitude, the min-max normalization method is used to map each feature value to the interval [0, 1], as shown in the following formula: ,in, These are the original eigenvalues. The minimum statistical value of the feature value of this dimension across all LIN nodes (industry statistical range: σ1∈[0.01μs, 0.05μs], μ2∈[0.8ms, 1.5ms], odd-even distribution rate∈[0.4, 0.6], repetition rate∈[0, 0.1]). This represents the statistical maximum value of the feature value for this dimension across all LIN nodes.

[0069] The third step is the establishment and management of the fingerprint database. This involves combining the four standardized features in a preset order [σ1′, μ2′, R4′, N5′] to form a multi-dimensional feature vector for each node. This multi-dimensional feature vector is used as a communication fingerprint, associated with the corresponding node ID, and stored in the master node's Flash chip. The fingerprint is re-collected and updated every three months to adapt to node aging and environmental changes. The fourth step is online fingerprint verification and fault diagnosis. The master node inserts micro-diagnostic time slots between LIN bus service frames to collect real-time communication data from slave nodes, extract real-time features, and perform the same standardization process. These features are then matched against the fingerprint vectors of the corresponding nodes in the fingerprint database. If all real-time feature values ​​are within a preset threshold range, the node is considered normal. If any feature value exceeds the preset threshold range, the node is marked as abnormal, triggering a fault diagnosis process to pinpoint the specific problem type based on the abnormal features.

[0070] This invention extracts multiple implicit features, such as the standard deviation of the rising edge time of the frame start bit and the mean of the data bit transmission delay, to construct a unique multi-dimensional feature vector as a communication fingerprint, achieving dual identification of node identity and abnormal status. This invention designs a complete feature extraction algorithm, including methods for calculating standard deviation, mean, parity distribution rate, and retransmission rate, as well as feature standardization formulas and fingerprint update mechanisms, ensuring the stability and uniqueness of the fingerprint. This invention establishes a fingerprint database management mechanism of "fingerprint modeling + regular updates," which can adapt to node hardware aging and changes in the automotive electromagnetic environment, effectively reducing the false positive rate. This invention requires no additional hardware, achieving node-level fault diagnosis solely through software algorithms, and the diagnosis process does not interrupt normal LIN bus services, making it fully adaptable to automotive embedded environments. This invention overcomes the limitation of existing technologies that can only detect bus-level faults, achieving precise location of "node ID + fault type" through communication fingerprints, significantly improving maintenance efficiency. This invention collects data through micro-diagnostic time slots (i.e., communication gaps), avoiding the occupation of complete bus time slots, not affecting normal bus services, and ensuring a smooth user experience when operating vehicle functions (such as window operation). This invention requires no additional hardware such as sensors or diagnostic modules; it can be implemented solely through software upgrades. It is compatible with all versions of the LIN bus from 2.0 to 2.2, is low in cost, has wide adaptability, and is easy to mass-produce.

[0071] To better implement the fingerprint-based communication state recognition method in this invention embodiment, based on the fingerprint-based communication state recognition method, correspondingly, as follows: Figure 7 As shown, this embodiment of the invention also provides a fingerprint-based communication status identification system 700, which includes: The acquisition module 701 is used to collect the raw communication data of each slave node in multiple communication cycles under normal bus communication conditions. The creation module 702 is used to create a multi-dimensional feature vector as the communication fingerprint of the slave node based on the original communication data; The generation module 703 is used to associate and store the communication fingerprint with the identifier of the corresponding slave node to form a fingerprint database; The acquisition and extraction module 704 is used to acquire real-time communication data of the target slave node and extract the current feature vector based on the real-time communication data; The processing module 705 is used to match and compare the current feature vector with the fingerprint database, and determine the communication status of the target slave node based on the matching result.

[0072] The fingerprint-based communication status recognition system 700 provided in the above embodiments can implement the technical solutions described in the above fingerprint-based communication status recognition method embodiments. The specific implementation principles of each module or unit can be found in the corresponding content in the above fingerprint-based communication status recognition method embodiments, and will not be repeated here.

[0073] like Figure 8 As shown, the present invention also provides an electronic device 800. The electronic device 800 includes a processor 801, a memory 802, and a display 803. Figure 8 Only some components of the electronic device 800 are shown, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.

[0074] In some embodiments, processor 801 may be a central processing unit (CPU), microprocessor or other data processing chip, used to run program code stored in memory 802 or process data, such as the fingerprint-based communication status identification method of the present invention.

[0075] In some embodiments, processor 801 may be a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, processor 801 may be local or remote. In some embodiments, processor 801 may be implemented on a cloud platform. In one embodiment, the cloud platform may include a private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, intranet, multi-cloud, etc., or any combination thereof.

[0076] In some embodiments, memory 802 may be an internal storage unit of electronic device 800, such as a hard disk or memory of electronic device 800. In other embodiments, memory 802 may also be an external storage device of electronic device 800, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. equipped on electronic device 800.

[0077] Furthermore, the memory 802 may include both internal storage units of the electronic device 800 and external storage devices. The memory 802 is used to store application software and various types of data installed on the electronic device 800.

[0078] In some embodiments, display 803 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. Display 803 is used to display information from electronic device 800 and to display a visual user interface. Components 801-803 of electronic device 800 communicate with each other via a system bus.

[0079] In one embodiment, when the processor 801 executes the fingerprint-based communication status recognition program in the memory 802, the following steps can be implemented: Under normal bus communication conditions, collect raw communication data from each slave node over multiple communication cycles; Based on the original communication data, a multi-dimensional feature vector is created as the communication fingerprint of the slave node; The communication fingerprint is associated with the identifier of the corresponding slave node and stored to form a fingerprint database; Collect real-time communication data from the target node, and extract the current feature vector based on the real-time communication data; The current feature vector is compared with the fingerprint database, and the communication status of the target slave node is determined based on the matching result.

[0080] It should be understood that when the processor 801 executes the fingerprint-based communication status identification program in the memory 802, in addition to the functions mentioned above, it can also implement other functions, as can be found in the description of the corresponding method embodiments above.

[0081] Furthermore, this embodiment of the invention does not specifically limit the type of electronic device 800 mentioned. Electronic device 800 can be a mobile phone, tablet computer, personal digital assistant (PDA), wearable device, laptop computer, or other portable electronic device. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices running iOS, Android, Microsoft, or other operating systems. The aforementioned portable electronic device can also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the invention, electronic device 800 may not be a portable electronic device, but rather a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0082] Accordingly, embodiments of this application also provide a computer-readable storage medium for storing computer-readable programs or instructions. When the programs or instructions are executed by a processor, they can implement the steps or functions of the fingerprint-based communication status identification method provided in the above-described method embodiments.

[0083] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.), and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0084] The fingerprint-based communication status identification method, system, device, and medium provided by the present invention have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A fingerprint-based communication status recognition method, characterized in that, include: Under normal bus communication conditions, collect raw communication data from each slave node over multiple communication cycles; Based on the original communication data, a multi-dimensional feature vector is created as the communication fingerprint of the slave node; The communication fingerprint is associated with the identifier of the corresponding slave node and stored to form a fingerprint database; Collect real-time communication data from the target node, and extract the current feature vector based on the real-time communication data; The current feature vector is compared with the fingerprint database, and the communication status of the target slave node is determined based on the matching result.

2. The fingerprint-based communication status identification method according to claim 1, characterized in that, The step of creating a multi-dimensional feature vector as the communication fingerprint of the slave node based on the original communication data includes: A predetermined number of valid data samples are collected from each of the slave nodes, and outliers that exceed a preset statistical range are removed. Based on the processed valid data samples, the multidimensional feature vector is calculated and created. The multidimensional feature vector includes at least the following dimensions: the standard deviation of the rising edge time of the frame start signal, the average value of the data bit transmission delay, the parity distribution rate of the check code, and the statistical rate of frame retransmission.

3. The fingerprint-based communication status recognition method according to claim 1, characterized in that, Also includes: Determine whether a preset trigger event is detected during vehicle operation; The preset trigger event includes the target slave node having a fingerprint matching deviation greater than a first threshold in a predetermined number of consecutive diagnostic cycles; If so, the communication fingerprint of the target slave node in the fingerprint database is updated based on the new incremental data.

4. The fingerprint-based communication status identification method according to claim 1, characterized in that, The real-time communication data collected from the target node includes: Calculate the average bus communication load rate over a predetermined number of consecutive communication cycles; Determine whether the average load rate of the bus communication is lower than a preset safety threshold; If so, the real-time communication data is collected during the communication gap after the predetermined number of consecutive communication cycles and before the start of the next communication cycle.

5. The fingerprint-based communication status identification method according to claim 4, characterized in that, Before calculating the average bus communication load rate over a predetermined number of consecutive communication cycles, the following steps are included: Determine whether the target slave node has a communication abnormal event. The communication abnormal event includes at least one of the following: frame response timeout for a preset number of consecutive times, or the statistical value of the message verification error rate within a preset time exceeds a second threshold. If so, collect the real-time communication data of the target slave node; If not, calculate the average load rate of the bus communication.

6. The fingerprint-based communication status identification method according to claim 1 or 2, characterized in that, The step of matching and comparing the current feature vector with the fingerprint database, and determining the communication status of the target slave node based on the matching result, includes: The feature values ​​of each dimension of the current feature vector are compared with the preset threshold range of the communication fingerprint of the target slave node in the fingerprint database in the corresponding dimension. If all dimensions of the current feature vector are within their respective preset threshold ranges, the communication status of the target slave node is determined to be normal. If the value of any dimension in the current feature vector exceeds its corresponding preset threshold range, the communication status of the target slave node is determined to be abnormal.

7. The fingerprint-based communication status recognition method according to claim 6, characterized in that, After determining that the communication status of the target slave node is abnormal, the following steps are included: Based on the target dimension, a preset mapping relationship table is queried to determine at least one fault type; the target dimension is the dimension in the current feature vector where the feature value exceeds its corresponding preset threshold range. Generate and output a diagnostic report, which includes at least the identifier of the target slave node, the target dimension, and its corresponding fault type.

8. A fingerprint-based communication status recognition system, characterized in that, include: The acquisition module is used to collect the raw communication data of each slave node in multiple communication cycles under normal bus communication conditions. A creation module is used to create a multi-dimensional feature vector as the communication fingerprint of the slave node based on the original communication data; A generation module is used to associate and store the communication fingerprint with the identifier of the corresponding slave node to form a fingerprint database; The acquisition and extraction module is used to acquire real-time communication data of the target slave node and extract the current feature vector based on the real-time communication data. The processing module is used to match and compare the current feature vector with the fingerprint database, and determine the communication status of the target slave node based on the matching result.

9. An electronic device, characterized in that, Including memory and processor, among which, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the fingerprint-based communication state recognition method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps in the fingerprint-based communication status identification method according to any one of claims 1 to 7.

Images