Vehicle data processing method, device, and storage medium

Abstract

This application discloses a vehicle data processing method, device, and storage medium, relating to the field of data processing technology. The method includes: acquiring vehicle signal data of a target vehicle; performing feature perception on the vehicle signal data to determine a target signal feature parameter set; based on the target signal feature parameter set, using a preset fuzzy matching algorithm to match an optimal processing strategy from a preset strategy knowledge base; and processing the vehicle signal data according to the optimal processing strategy and the target signal feature parameter set. This application achieves adaptive data processing for diverse vehicle signal data by dynamically matching data processing strategies based on signal feature parameters, effectively improving the data processing efficiency of vehicle signal data.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a vehicle data processing method, device, and storage medium. Background Technology

[0002] With the rapid development of intelligent connected vehicles, the amount of signal data generated by vehicles is exploding. This signal data not only includes vehicle operating status information but also encompasses autonomous driving sensor data, vehicle-to-everything (V2X) communication data, and user behavior information, resulting in a daily data volume per vehicle reaching the terabyte (TB) level. However, traditional vehicle data processing methods cannot adapt to the diverse needs of vehicle signal data processing, thus hindering efficient data processing.

[0003] Therefore, it is necessary to propose a vehicle data processing method to improve the data processing efficiency of vehicle signal data.

[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this application is to provide a vehicle data processing method, device, and storage medium, aiming to solve the technical problem of how to improve the data processing efficiency of vehicle signal data.

[0006] To achieve the above objectives, this application proposes a vehicle data processing method, which includes: Acquire vehicle signal data of the target vehicle; The vehicle signal data is subjected to feature perception to determine the target signal feature parameter set; Based on the target signal feature parameter set, the optimal processing strategy is obtained by matching from the preset strategy knowledge base using a preset fuzzy matching algorithm. The vehicle signal data is processed according to the optimal processing strategy and the target signal feature parameter set.

[0007] In one embodiment, before the step of processing the vehicle signal data according to the optimal processing strategy and the target signal feature parameter set, the method includes: Based on the resource demand calculation model, the target resource demand of the vehicle signal data is calculated according to the target signal feature parameter set and the optimal processing strategy. Allocate target computing resources according to the target resource requirements; The step of processing the vehicle signal data according to the optimal processing strategy and the target signal feature parameter set includes: Based on the target computing resources, the vehicle signal data is processed according to the optimal processing strategy and the target signal feature parameter set.

[0008] In one embodiment, the preset strategy knowledge base stores the mapping relationship between signal feature parameters and several processing strategies. The step of obtaining the optimal processing strategy from the preset strategy knowledge base based on the target signal feature parameter set using a preset fuzzy matching algorithm includes: Traverse each processing strategy in the preset strategy knowledge base, and determine the signal feature parameter set of the processing strategy based on the mapping relationship between signal feature parameters and several processing strategies; The matching score between the signal feature parameter set of the processing strategy and the target signal feature parameter set is calculated according to a preset fuzzy matching algorithm. The processing strategy with the highest matching score is selected as the optimal processing strategy. If there are multiple processing strategies with the highest matching scores, the optimal processing strategy is determined based on the business priority.

[0009] In one embodiment, the target signal feature parameter set includes signal feature parameters of several feature dimensions, and the step of calculating the matching score between the signal feature parameter set of the processing strategy and the target signal feature parameter set according to a preset fuzzy matching algorithm includes: For any feature dimension, calculate the similarity between the signal feature parameter set of the target signal and the signal feature parameter set of the processing strategy on the feature dimension, and obtain the similarity score of the signal feature parameters of the feature dimension; The similarity scores of the signal feature parameters of the several feature dimensions are weighted according to preset weight coefficients to obtain the matching score between the signal feature parameter set of the processing strategy and the target signal feature parameter set.

[0010] In one embodiment, the target signal feature parameter set includes at least one of the following: signal data type, service attribute, data frequency, data volume, timeliness requirements, service priority, and associated vehicle identifier.

[0011] In one embodiment, the step of processing the vehicle signal data according to the optimal processing strategy and the target signal feature parameter set includes: Based on the operator logic template of the optimal processing strategy and the target signal feature parameter set, generate Flink operator data processing logic; The Flink operator data processing logic is dynamically loaded into the Flink compute node so that the Flink compute node executes the Flink operator data processing logic on the vehicle signal data.

[0012] In one embodiment, after the step of generating Flink operator data processing logic based on the operator logic template of the optimal processing strategy and the target signal feature parameter set, the method further includes: Monitor whether the optimal processing strategy has changed; When the optimal processing strategy changes, the following steps are re-executed: generating Flink operator data processing logic based on the operator logic template of the optimal processing strategy and the target signal feature parameter set.

[0013] In one embodiment, the target signal feature parameter set includes data frequency, data volume, and timeliness requirements. The step of calculating the target resource requirements of the vehicle signal data based on the resource requirement calculation model, according to the target signal feature parameter set and the optimal processing strategy, includes: The data transmission rate is determined based on the data frequency and data volume. Using the resource requirement calculation model, the strategy complexity of the optimal processing strategy, the data transmission rate, and the timeliness requirement are weighted and calculated to obtain the target resource requirement, which includes the number of processor cores and memory capacity.

[0014] In one embodiment, the step of allocating target computing resources according to the target resource requirement includes: Compare the target resource requirements with the remaining computing resources of the Flink compute node; When the remaining computing resources of the Flink computing node meet the target resource requirements, the target computing resources are allocated on the Flink computing node to execute the Flink operator data processing logic on the vehicle signal data based on the target computing resources.

[0015] In one embodiment, after the step of comparing the target resource requirement with the remaining computing resources of the Flink compute node, the method further includes: When the remaining computing resources of the Flink computing node do not meet the target resource requirements, the data processing task of the vehicle signal data is split into several sub-tasks. The subtasks are scheduled to several idle Flink compute nodes, and target computing resources are allocated on the idle Flink compute nodes to execute the subtasks.

[0016] In addition, to achieve the above objectives, this application also provides a vehicle data processing device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the vehicle data processing method as described above.

[0017] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and which, when executed by a processor, implements the steps of the vehicle data processing method described above.

[0018] One or more technical solutions proposed in this application have at least the following technical effects: The vehicle data processing method, device, and storage medium proposed in this application specifically involve: acquiring vehicle signal data of a target vehicle; performing feature perception on the vehicle signal data to determine a target signal feature parameter set; using a preset fuzzy matching algorithm to obtain an optimal processing strategy from a preset strategy knowledge base based on the target signal feature parameter set; and processing the vehicle signal data according to the optimal processing strategy and the target signal feature parameter set.

[0019] This application obtains a target signal feature parameter set by sensing the features of vehicle signal data. Based on the target signal feature parameter set, it obtains the optimal processing strategy from a preset strategy knowledge base through a fuzzy matching algorithm. Then, it processes the vehicle signal data according to the optimal processing strategy and the target signal feature parameter set. By dynamically matching the data processing strategy based on the signal feature parameters, it achieves adaptive data processing for diverse vehicle signal data, which can effectively improve the intelligence level and data processing efficiency of vehicle signal data. Attached Figure Description

[0020] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0021] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart illustrating an embodiment of the vehicle data processing method of this application. Figure 2 This is a flowchart illustrating Embodiment 2 of the vehicle data processing method of this application; Figure 3 This is a flowchart illustrating Embodiment 3 of the vehicle data processing method of this application; Figure 4 This is a flowchart illustrating Embodiment 4 of the vehicle data processing method of this application; Figure 5 This is a flowchart illustrating Embodiment 5 of the vehicle data processing method of this application; Figure 6 This is a schematic diagram of the hardware operating environment involved in the vehicle data processing method in this application embodiment.

[0023] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0024] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0025] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0026] The main solution of this application embodiment is: to acquire vehicle signal data of the target vehicle; to perform feature perception on the vehicle signal data and determine the target signal feature parameter set; to obtain the optimal processing strategy from the preset strategy knowledge base using the preset fuzzy matching algorithm based on the target signal feature parameter set; and to process the vehicle signal data according to the optimal processing strategy and the target signal feature parameter set.

[0027] In this embodiment, for ease of description, the vehicle data processing device will be used as the execution subject in the following description.

[0028] With the rapid development of intelligent connected vehicles, the amount of signal data generated by vehicles is growing explosively. The signal data generated by vehicles not only includes vehicle operating status information, but also covers autonomous driving sensor data, vehicle-to-everything (V2X) communication data and user behavior information, resulting in the daily data volume of a single vehicle reaching the terabyte (TB) level.

[0029] However, the industry generally uses data processing operators with fixed logic to process the above-mentioned diverse and large-volume data streams, which makes it impossible to adapt to the diverse needs of vehicle signal data processing, and thus impossible to achieve efficient data processing.

[0030] Therefore, it is necessary to propose a vehicle data processing method to improve the data processing efficiency of vehicle signal data.

[0031] This application provides a solution that obtains a target signal feature parameter set by sensing the features of vehicle signal data. Based on the target signal feature parameter set, an optimal processing strategy is obtained by matching from a preset strategy knowledge base using a fuzzy matching algorithm. Then, the vehicle signal data is processed according to the optimal processing strategy and the target signal feature parameter set. By dynamically matching the data processing strategy based on the signal feature parameters, adaptive data processing for diverse vehicle signal data can be achieved, which can effectively improve the intelligence level and data processing efficiency of vehicle signal data.

[0032] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device or vehicle data processing device capable of performing the above functions. The following description uses a vehicle data processing device as an example to illustrate this embodiment and the subsequent embodiments.

[0033] Based on this, embodiments of this application provide a vehicle data processing method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the vehicle data processing method of this application. The vehicle data processing method includes steps S110 to S140: Step S110: Obtain vehicle signal data of the target vehicle; It should be noted that vehicle signal data refers to the raw data stream generated in real time by various sensors, controllers and on-board systems on the target vehicle.

[0034] First, the vehicle data processing equipment needs to acquire the vehicle signal data of the target vehicle in real time so that it can perform adaptive data processing on the vehicle signal data in the future.

[0035] Step S120: Perform feature perception on the vehicle signal data to determine the target signal feature parameter set; In this embodiment, in order to achieve adaptive data processing for diverse vehicle signal data and adapt to the diverse processing needs of vehicle signal data, the aforementioned acquired vehicle signal data is parsed and analyzed in real time using signal processing algorithms or statistical analysis methods to extract various signal feature parameters and construct a set of signal feature parameters corresponding to the vehicle signal data, namely the target signal feature parameter set.

[0036] The target signal feature parameter set contains a structured collection of signal feature parameters across multiple dimensions. These signal feature parameters include, but are not limited to, signal mean, signal variance, business attribute feature parameters (such as business attribute tags, business priority, etc.), metadata feature parameters (such as data reception timestamp, data sending node, data target node, protocol version number), signal validity flags, signal credibility score, and signal change rate.

[0037] In one implementable manner, the target signal feature parameter set includes at least one of signal data type, service attribute, data frequency, data volume, timeliness requirements, service priority, and associated vehicle identifier, and step 120 includes steps A1 to A6: Step A1: Parse the vehicle signal data to determine the signal data type; And / or step A2, based on a preset service attribute tag library, to match and obtain the service attributes of the vehicle signal data; In this embodiment, the vehicle data processing device collects seven dimensions of signal characteristic parameters from the acquired vehicle signal data, specifically signal data type, service attribute, data frequency, data volume, timeliness requirements, service priority, and associated vehicle identifier.

[0038] It should be noted that the preset business attribute tag library refers to a pre-built business semantic knowledge base, which stores a set of tags corresponding to the business domain, function affiliation, and application scenarios of various types of vehicle signal data.

[0039] Specifically, the protocol parsing engine performs syntactic structure analysis and semantic recognition on the byte stream of the original vehicle signal data, classifying the vehicle signal data into specific categories within a predefined data type classification system to obtain the signal data type. This predefined data type classification system is pre-set by relevant personnel based on actual needs and includes, but is not limited to, vehicle safety, entertainment information, general data, and driving behavior categories. It is understood that in this embodiment, the protocol parsing engine supports mainstream data formats such as avro, json, csv, and protobuf.

[0040] Then, based on the service attribute fields carried by the vehicle signal data, the corresponding service attributes are matched from the preset service attribute tag library.

[0041] And / or step A3, calculate the data frequency of the vehicle signal data based on the data reception frequency of the vehicle signal data within a preset time period; And / or step A4, count the number of bytes in a single data entry in the vehicle signal data to determine the data volume of the vehicle signal data; Then, within a pre-set time period (e.g., per unit time), the data frequency of vehicle signal data is calculated by statistically analyzing the data reception frequency of vehicle signal data, where the unit of data frequency is Hertz.

[0042] By calculating the average number of bytes in multiple data points within a pre-set time period, the number of bytes in a single data point can be determined, thereby determining the total data volume of the vehicle signal data.

[0043] And / or step A5, determine the corresponding timeliness requirements and service priorities based on the service attributes of the vehicle signal data; And / or step A6, extract the associated vehicle identifier from the metadata of the vehicle signal data.

[0044] Specifically, based on the aforementioned determined service attributes of the vehicle signal data and referring to preset service standards, the timeliness requirements and service priorities corresponding to the vehicle signal data are determined. The preset service standards include a pre-defined mapping relationship between service attributes and service requirements. Service requirements include service processing priority (i.e., service priority) and timeliness requirements. Timeliness requirements include, but are not limited to, processing time requirements (such as milliseconds, seconds, or tiers) and maximum permissible delay time.

[0045] Finally, the contextual description information associated with the vehicle signal data is parsed to obtain an identification code or identification information that can uniquely identify the vehicle from which the data originates (i.e., the target vehicle), i.e., the associated vehicle identifier.

[0046] Step S130: Based on the target signal feature parameter set, the optimal processing strategy is obtained by matching from the preset strategy knowledge base using a preset fuzzy matching algorithm; It should be noted that the preset fuzzy matching algorithm refers to a similarity measurement algorithm that does not rely on precise equality judgment. This fuzzy matching algorithm can handle the imprecision, uncertainty, and partial matching problems of signal feature parameters. It measures the degree of matching between the target signal feature parameter set and the corresponding signal feature parameters of each processing strategy in the strategy knowledge base by defining a fuzzy similarity function. Fuzzy similarity calculation can be implemented using functions such as Euclidean distance, Mahalanobis distance, and cosine similarity.

[0047] A pre-built strategy knowledge base refers to a set of pre-constructed strategy rules. This knowledge base contains mapping relationships between various signal feature patterns and corresponding processing strategies. Each processing strategy includes at least fields such as feature parameter matching conditions, strategy execution logic, and strategy priority. The strategy knowledge base can be pre-built through expert experience input, historical data mining, or automatic generation using reinforcement learning.

[0048] Specifically, the vehicle data processing equipment applies a preset fuzzy matching algorithm to measure the similarity between the target signal feature parameters and the signal feature parameters corresponding to each processing strategy in the preset strategy knowledge base, thereby selecting the processing strategy with the highest similarity as the optimal processing strategy, and realizing dynamic matching of data processing strategies based on signal feature parameters.

[0049] Step S140: Process the vehicle signal data according to the optimal processing strategy and the target signal feature parameter set.

[0050] Finally, the vehicle data processing equipment determines the specific processing parameters in the data processing logic according to the data processing logic indicated by the optimal processing strategy, combined with the business priority, timeliness requirements, data frequency, and data volume in the aforementioned target signal characteristic parameter set, and obtains the executable data processing logic.

[0051] Alternatively, multiple processing branches can be predefined within the optimal processing strategy. Each processing branch corresponds to a specific range of characteristic parameter conditions. Before execution, the target signal characteristic parameter set is compared with the characteristic parameter condition range corresponding to each processing branch to determine which processing branch logic meets the conditions for data processing.

[0052] Finally, the acquired vehicle signal data is processed according to the aforementioned executable data processing logic or the processing branch logic that meets the conditions, thereby achieving adaptive data processing for diverse vehicle signal data and effectively improving the intelligence level and data processing efficiency of vehicle signal data.

[0053] This application, through the above-mentioned scheme, obtains a target signal feature parameter set by perceiving the features of vehicle signal data. Based on the target signal feature parameter set, it obtains the optimal processing strategy from a preset strategy knowledge base using a fuzzy matching algorithm. Then, it processes the vehicle signal data according to the optimal processing strategy and the target signal feature parameter set. By dynamically matching the data processing strategy based on the signal feature parameters, it achieves adaptive data processing for diverse vehicle signal data, which can effectively improve the intelligence level and data processing efficiency of vehicle signal data.

[0054] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in Embodiment 1 above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 , Figure 2 This is a flowchart illustrating the second embodiment of the vehicle data processing method of this application. The preset strategy knowledge base stores the mapping relationship between signal feature parameters and several processing strategies. The step of obtaining the optimal processing strategy from the preset strategy knowledge base based on the target signal feature parameter set using a preset fuzzy matching algorithm includes steps S210~S240: Step S210: Traverse each processing strategy in the preset strategy knowledge base, and determine the signal feature parameter set of the processing strategy according to the mapping relationship between signal feature parameters and several processing strategies; Step S220: Calculate the matching score between the signal feature parameter set of the processing strategy and the target signal feature parameter set according to a preset fuzzy matching algorithm; Understandably, the preset strategy knowledge base uses a structured storage method to store the mapping relationship between signal feature parameters and several processing strategies, so as to obtain the optimal processing strategy based on the dynamic matching of signal feature parameters, which is used for adaptive data processing of vehicle signal data.

[0055] Specifically, the vehicle data processing equipment traverses each processing strategy in the preset strategy knowledge base to determine the signal feature parameter matching conditions corresponding to each processing strategy, forming a signal feature parameter set for each processing strategy. Each processing strategy's signal feature parameter set contains signal feature parameter values ​​or matching conditions for multiple feature dimensions.

[0056] Then, for each processing strategy, a preset fuzzy matching algorithm is invoked to calculate the similarity between the signal feature parameter set of that processing strategy and the target signal feature parameter set, thus obtaining the matching score MS. The similarity between the two parameter sets can be calculated using Manhattan distance similarity calculation, Mahalanobis distance similarity calculation, Jaccard similarity coefficient calculation, or by utilizing machine learning algorithms to measure similarity.

[0057] In one implementable manner, the target signal feature parameter set includes signal feature parameters of several feature dimensions, and the step of calculating the matching score between the signal feature parameter set of the processing strategy and the target signal feature parameter set according to a preset fuzzy matching algorithm includes steps B1 to B2: Step B1: For any feature dimension, calculate the similarity between the signal feature parameter set of the target signal and the signal feature parameter set of the processing strategy on the feature dimension, and obtain the similarity score of the signal feature parameters of the feature dimension. Step B2: The similarity scores of the signal feature parameters of the several feature dimensions are weighted according to the preset weight coefficients to obtain the matching score between the signal feature parameter set of the processing strategy and the target signal feature parameter set.

[0058] In this embodiment, the preset fuzzy matching algorithm uses a weighted summation algorithm to calculate similarity. The specific calculation process includes: first, for each feature dimension, calculating the similarity between the target signal feature parameter set and the signal feature parameter set of the processing strategy that are in the same feature dimension; then, multiplying each dimension's similarity by its preset weight coefficient; finally, summing the weighted similarities of all dimensions to obtain the final matching score. The above calculation process can be expressed as the following formula: MS=∑(i=1 to n) wi×Sim(fi,Fi) Where MS is the matching score; n is the dimension of the feature parameter, and in this embodiment, n=7; wi is the weight coefficient of the i-th feature; fi is the signal feature parameter in the target signal feature parameter set, Fi is the signal feature parameter of a certain strategy in the strategy knowledge base, and Sim (·) is the similarity calculation function. The preset weight coefficients are manually set; for example, the weight coefficient corresponding to timeliness requirements can be set to 0.3, the weight coefficient corresponding to data frequency to 0.25, the weight coefficient corresponding to business priority to 0.2, and the total weight coefficient for the remaining dimensions is 0.25.

[0059] Understandably, this implementation adopts different similarity calculation methods for different types of signal feature parameters. For example, for feature parameters of structured data (such as data frequency, data volume, etc.), a similarity calculation based on numerical distance is used, such as a similarity calculation function based on Euclidean distance; for feature parameters of unstructured data (such as business attributes, signal data types, etc.), a similarity calculation based on vector space model is used, such as a cosine similarity calculation function.

[0060] Step S230: Select the processing strategy with the highest matching score as the optimal processing strategy; Step S240: If there are multiple processing strategies with the highest matching scores, the optimal processing strategy is determined according to the business priority.

[0061] Specifically, the vehicle data processing equipment selects the processing strategy with the highest matching score (MS) as the optimal processing strategy.

[0062] If multiple processing strategies have the same and highest matching score (MS), the processing strategy with the higher business priority adaptation will be selected as the optimal processing strategy.

[0063] This embodiment, through the above-described scheme, traverses the strategy knowledge base and calculates the matching score between the signal feature parameter matching conditions corresponding to each processing strategy and the target signal feature parameter set, thereby achieving a quantitative evaluation of all candidate strategies and ensuring accurate data processing decisions. In the case of a tie for optimal processing strategy, business priority is introduced as the decision criterion, ensuring that the processing needs of high-priority businesses are prioritized even in fuzzy scenarios. This enhances the robustness and business adaptability of the processing strategy decision logic and effectively improves the intelligence level and data processing efficiency of vehicle signal data.

[0064] Based on the above embodiments of this application, in the third embodiment of this application, the same or similar content as the above embodiments can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3The step of processing the vehicle signal data according to the optimal processing strategy and the target signal feature parameter set includes steps S310-S320: Step S310: Generate Flink operator data processing logic based on the operator logic template of the optimal processing strategy and the target signal feature parameter set; In this embodiment, the processing strategies in the preset strategy knowledge base include "feature parameter matching conditions," "operator logic templates," and "strategy complexity levels." The feature parameter matching conditions cover all extracted signal feature parameter dimensions. The operator logic templates include, but are not limited to, processing window types (e.g., sliding window, session window, windowless), data aggregation granularity (e.g., millisecond, second, minute), data cleaning rules, feature extraction algorithms, scheduling methods (e.g., batch scheduling, queue scheduling), and data output formats. The number of strategy complexity levels can be manually set; in this embodiment, the strategy complexity levels are divided into 1 to 10 levels. A preset strategy knowledge base is shown in the table below:

[0065] Specifically, the vehicle data processing equipment can obtain the operator logic template corresponding to the optimal processing strategy, and then fill in the corresponding parameter placeholders (such as data processing priority, processing window size, data filtering condition threshold, etc.) in the operator logic template according to the signal feature parameters (such as business priority, data frequency, timeliness requirements, etc.) in the target signal feature parameter set. The operator logic template is then instantiated to generate specific task code or configuration that can be directly executed by the Apache Flink computing framework, i.e., Flink operator data processing logic.

[0066] Apache Flink is an open-source distributed stream processing framework whose core features are unified batch and stream processing and low-latency processing. Apache Flink adopts a native stream computing model, supports millisecond-level real-time data processing, and is compatible with batch processing; it provides exact-once fault-tolerant semantics to ensure that data is not lost or duplicated; its state management mechanism supports complex stateful computation, allowing the maintenance and processing of massive amounts of state data in a distributed environment.

[0067] Step S320: Dynamically load the Flink operator data processing logic into the Flink computing node so that the Flink computing node executes the Flink operator data processing logic on the vehicle signal data.

[0068] Then, using the dynamic execution engine, the newly generated Flink operator data processing logic is loaded onto a Flink compute node without restarting the existing Flink job or cluster. Here, a Flink compute node refers to a server instance in the Apache Flink cluster that actually executes the computation task.

[0069] The Flink compute node executes the Flink operator data processing logic on the vehicle signal data and transmits the processed data to Paimon. In Paimon, the data is hash-bucketed according to the associated vehicle identifier and finally persisted to OSS (Object Storage Service) in Parquet file format. Paimon is a streaming data lake storage technology that supports unified streaming and batch processing by the Flink engine, providing incremental data ingestion, real-time streaming reads, and historical batch reads, with millisecond-level query latency.

[0070] The above technical solution transforms abstract policy descriptions into executable Flink computing tasks, achieving automated conversion from policy to code. This significantly improves the automation and efficiency of policy execution, avoiding delays and errors caused by manual coding.

[0071] Furthermore, after step S310, steps C1~C2 are included: Step C1: Monitor whether the optimal processing strategy has changed; Step C2: When the optimal processing strategy changes, re-execute the following step: Generate Flink operator data processing logic based on the operator logic template of the optimal processing strategy and the target signal feature parameter set.

[0072] Specifically, changes in the signal characteristic parameters of vehicle signal data may lead to changes in the optimal processing strategy.

[0073] Therefore, the vehicle data processing equipment needs to monitor the optimal processing strategy update signal in real time to determine whether the optimal processing strategy has changed. When the optimal processing strategy changes, data processing needs to be performed according to the latest optimal processing strategy. Therefore, the following steps need to be repeated: generating Flink operator data processing logic based on the operator logic template of the optimal processing strategy and the target signal feature parameter set, realizing real-time updating of the Flink operator data processing logic, and dynamically loading the updated Flink operator data processing logic into the Flink computing node.

[0074] This embodiment, through the above-described scheme, automatically generates executable Flink operator data processing logic by combining operator logic templates with real-time signal feature parameter sets. This transforms abstract policy descriptions into executable computational tasks, achieving automated conversion from policy to code. This improves the automation and efficiency of policy execution and avoids response delays caused by manual coding. Simultaneously, the generated Flink operator data processing logic is dynamically loaded onto Flink computing nodes, enabling hot updates and seamless switching of data processing logic. This ensures uninterrupted data processing when dealing with changing vehicle-side signals, enhancing the flexibility of data processing and further improving the intelligence and efficiency of vehicle signal data processing.

[0075] Based on the above embodiments of this application, in the fourth embodiment of this application, the same or similar content as the above embodiments can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 4 Before the step of processing the vehicle signal data according to the optimal processing strategy and the target signal feature parameter set, the method further includes steps S410 to S420: Step S410: Based on the resource demand calculation model, calculate the target resource demand of the vehicle signal data according to the target signal feature parameter set and the optimal processing strategy; It should be noted that the resource requirement calculation model refers to a mathematical model used to predict and estimate the amount of computing resources required to perform a specific data processing task.

[0076] Existing resource scheduling for vehicle signal data typically involves fixed resource allocation, which cannot accommodate fluctuations in data volume, leading to resource waste or processing bottlenecks. Therefore, to overcome these technical problems, vehicle data processing equipment utilizes a resource demand calculation model to achieve elastic scheduling of computing resources based on signal characteristic parameters and processing strategies.

[0077] Specifically, the vehicle data processing equipment inputs the target signal feature parameter set of the vehicle signal data to be processed and the strategy complexity of the optimal processing strategy into the resource demand calculation model, so that the resource demand calculation model outputs the quantitative value of the target resource demand.

[0078] In one feasible embodiment, the target signal feature parameter set includes data frequency, data volume, and timeliness requirements, and step S410 includes steps D1~D2: Step D1: Determine the data transmission rate based on the data frequency and data volume; Step D2: Using the resource requirement calculation model, the strategy complexity of the optimal processing strategy, the data transmission rate, and the timeliness requirement are weighted and calculated to obtain the target resource requirement, which includes the number of processor cores and memory capacity.

[0079] In this embodiment, the data transmission rate of vehicle signal data is first determined based on the data frequency and data volume, and the timeliness requirement is quantified into a numerical value, such as 10 for milliseconds and 1 for seconds.

[0080] Then, using the resource requirement calculation model, the quantitative values ​​of data transmission rate, timeliness requirements, and strategy complexity of the optimal processing strategy are weighted according to different weight coefficients to obtain the quantitative values ​​of processor cores and memory capacity requirements, i.e., the target resource requirements.

[0081] The resource demand calculation model refers to the following formula: Resource=α×DataRate+β×Complexity+γ×Timeliness Where Resource represents the target resource requirement, α, β, and γ are weighting coefficients, DataRate is the data transfer rate, Complexity is the level value of strategy complexity, and Timeliness is the quantified value of timeliness requirements. In this embodiment, when calculating the number of processor cores, α=0.4, β=0.3, and γ=0.3; when calculating the memory capacity, α=0.5, β=0.2, and γ=0.3.

[0082] Step S420: Allocate target computing resources according to the target resource requirements; Specifically, the vehicle data processing equipment will allocate corresponding target computing resources to the aforementioned vehicle signal data processing tasks according to the target resource requirements, thereby achieving flexible scheduling of computing resources and realizing efficient, low-latency, and low-cost data processing.

[0083] The step of processing the vehicle signal data according to the optimal processing strategy and the target signal feature parameter set includes step S430: Step S430: Based on the target computing resources, the vehicle signal data is processed according to the optimal processing strategy and the target signal feature parameter set.

[0084] Specifically, by utilizing the target computing resources of elastic scheduling and referring to the steps described in the foregoing embodiments, vehicle signal data is processed according to the optimal processing strategy to efficiently and stably complete the data processing task and improve the utilization efficiency of computing resources.

[0085] This embodiment, through the above-described scheme, specifically obtains the target computing resources through a resource requirement calculation model, allocates the target computing resources according to the target resource requirements, achieves precise matching between computing resources and data processing tasks, completes elastic scheduling of computing resources, and avoids waste of computing resources; then, based on the target computing resources, it completes the data processing of vehicle signal data according to the optimal processing strategy, ensuring the stability and efficiency of the data processing process, and further improving the data processing efficiency of vehicle signal data.

[0086] Based on the above embodiments of this application, in the fifth embodiment of this application, the same or similar content as the above embodiments can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 5 The step of allocating target computing resources according to the target resource requirements includes steps S510~S540: Step S510: Compare the target resource requirement with the remaining computing resources of the Flink computing node; Step S520: When the remaining computing resources of the Flink computing node meet the target resource requirements, the target computing resources are allocated on the Flink computing node to execute the Flink operator data processing logic on the vehicle signal data based on the target computing resources. Understandably, to ensure the stable operation of data processing tasks for vehicle signal data, it is necessary to determine whether the computing resources of the current Flink computing node are sufficient to support the completion of the data processing tasks.

[0087] Specifically, the vehicle data processing device obtains the amount of unused computing resources (i.e., remaining computing resources) of the current Flink compute node by querying the resource manager, and compares the remaining computing resources of the current Flink compute node with the target resource requirements of the data processing task to determine whether to trigger cross-node task scheduling.

[0088] When the quantized value of the remaining computing resources of the Flink compute node is greater than or equal to the quantized value of the target resource requirement, it means that the remaining computing resources of the Flink compute node meet the target resource requirement. The target computing resources can be directly allocated on the current Flink compute node to execute the aforementioned Flink operator data processing logic on the vehicle signal data.

[0089] Step S530: When the remaining computing resources of the Flink computing node do not meet the target resource requirements, the data processing task of the vehicle signal data is split into several sub-tasks. Step S540: Schedule the plurality of subtasks to a plurality of Flink compute nodes that are in an idle state, so as to allocate target computing resources on the plurality of Flink compute nodes that are in an idle state and execute the plurality of subtasks.

[0090] Specifically, when the quantized value of the remaining computing resources of a Flink compute node is less than the quantized value of the target resource requirement, it means that the remaining computing resources of the Flink compute node cannot meet the target resource requirement, and cross-node task scheduling needs to be triggered. This is achieved by splitting the data processing task for the vehicle signal data into multiple subtasks, and then scheduling these subtasks to multiple Flink compute nodes that are in an idle state.

[0091] On multiple Flink compute nodes that are in an idle state, computing resources corresponding to the subtasks to be executed are allocated to each node, so that the multiple Flink compute nodes in an idle state can complete the data processing task of vehicle signal data by executing multiple subtasks, thereby achieving resource load balancing.

[0092] This embodiment uses the above-described scheme to specifically determine whether to trigger cross-node task scheduling by comparing the target resource requirements with the remaining computing resources of the Flink computing nodes. When resources are sufficient, a local allocation strategy is adopted; when resources are insufficient, the data processing tasks are split to solve the resource bottleneck of a single computing node, achieve resource load balancing, ensure the reliable completion of complex data processing tasks, and further improve the data processing efficiency of vehicle signal data.

[0093] This application provides a vehicle data processing device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the vehicle data processing method of the above embodiment.

[0094] The following is for reference. Figure 6 The diagram illustrates a structural schematic of a vehicle data processing device suitable for implementing embodiments of this application. The vehicle data processing device in these embodiments may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 6The vehicle data processing device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of this application.

[0095] like Figure 6 As shown, the vehicle data processing device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory 1002 or a program loaded from a storage device 1003 into a random access memory 1004. The random access memory 1004 also stores various programs and data required for the operation of the vehicle data processing device. The processing unit 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An input / output interface 1006 is also connected to the bus. Typically, the following systems can be connected to the input / output interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. The communication device 1009 allows the vehicle data processing equipment to communicate wirelessly or wiredly with other devices to exchange data. Although the figures show vehicle data processing equipment with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0096] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0097] The vehicle data processing device provided in this application, employing the vehicle data processing method in the above embodiments, can solve the technical problem of how to improve the data processing efficiency of vehicle signal data. Compared with the prior art, the beneficial effects of the vehicle data processing device provided in this application are the same as those of the vehicle data processing method provided in the above embodiments, and other technical features in this vehicle data processing device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0098] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0099] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0100] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the vehicle data processing method in the above embodiments.

[0101] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0102] The aforementioned computer-readable storage medium may be included in the vehicle data processing equipment; or it may exist independently and not be installed in the vehicle data processing equipment.

[0103] The aforementioned computer-readable storage medium carries one or more programs that, when executed by a vehicle data processing device, cause the vehicle data processing device to: acquire vehicle signal data of a target vehicle; perform feature perception on the vehicle signal data to determine a target signal feature parameter set; based on the target signal feature parameter set, use a preset fuzzy matching algorithm to match and obtain an optimal processing strategy from a preset strategy knowledge base; and process the vehicle signal data according to the optimal processing strategy and the target signal feature parameter set.

[0104] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0105] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0106] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0107] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described vehicle data processing method, thereby solving the technical problem of how to improve the data processing efficiency of vehicle signal data. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the vehicle data processing method provided in the above embodiments, and will not be repeated here.

[0108] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A vehicle data processing method, characterized in that, The vehicle data processing method includes: Acquire vehicle signal data of the target vehicle; The vehicle signal data is subjected to feature perception to determine the target signal feature parameter set; Based on the target signal feature parameter set, the optimal processing strategy is obtained by matching from the preset strategy knowledge base using a preset fuzzy matching algorithm. The vehicle signal data is processed according to the optimal processing strategy and the target signal feature parameter set.

2. The vehicle data processing method as described in claim 1, characterized in that, Before the step of processing the vehicle signal data according to the optimal processing strategy and the target signal feature parameter set, the following steps are included: Based on the resource demand calculation model, the target resource demand of the vehicle signal data is calculated according to the target signal feature parameter set and the optimal processing strategy. Allocate target computing resources according to the target resource requirements; The step of processing the vehicle signal data according to the optimal processing strategy and the target signal feature parameter set includes: Based on the target computing resources, the vehicle signal data is processed according to the optimal processing strategy and the target signal feature parameter set.

3. The vehicle data processing method as described in claim 1, characterized in that, The preset strategy knowledge base stores the mapping relationship between signal feature parameters and several processing strategies. The step of obtaining the optimal processing strategy from the preset strategy knowledge base based on the target signal feature parameter set using a preset fuzzy matching algorithm includes: Traverse each processing strategy in the preset strategy knowledge base, and determine the signal feature parameter set of the processing strategy based on the mapping relationship between signal feature parameters and several processing strategies; The matching score between the signal feature parameter set of the processing strategy and the target signal feature parameter set is calculated according to a preset fuzzy matching algorithm. The processing strategy with the highest matching score is selected as the optimal processing strategy. If there are multiple processing strategies with the highest matching scores, the optimal processing strategy is determined based on the business priority.

4. The vehicle data processing method as described in claim 3, characterized in that, The target signal feature parameter set includes signal feature parameters of several feature dimensions. The step of calculating the matching score between the signal feature parameter set of the processing strategy and the target signal feature parameter set according to a preset fuzzy matching algorithm includes: For any feature dimension, calculate the similarity between the signal feature parameter set of the target signal and the signal feature parameter set of the processing strategy on the feature dimension, and obtain the similarity score of the signal feature parameters of the feature dimension; The similarity scores of the signal feature parameters of the several feature dimensions are weighted according to preset weight coefficients to obtain the matching score between the signal feature parameter set of the processing strategy and the target signal feature parameter set.

5. The vehicle data processing method as described in claim 4, characterized in that, The target signal feature parameter set includes at least one of the following: signal data type, service attribute, data frequency, data volume, timeliness requirements, service priority, and associated vehicle identifier.

6. The vehicle data processing method as described in claim 2, characterized in that, The step of processing the vehicle signal data according to the optimal processing strategy and the target signal feature parameter set includes: Based on the operator logic template of the optimal processing strategy and the target signal feature parameter set, generate Flink operator data processing logic; The Flink operator data processing logic is dynamically loaded into the Flink compute node so that the Flink compute node executes the Flink operator data processing logic on the vehicle signal data.

7. The vehicle data processing method as described in claim 6, characterized in that, After the step of generating Flink operator data processing logic based on the operator logic template of the optimal processing strategy and the target signal feature parameter set, the method further includes: Monitor whether the optimal processing strategy has changed; When the optimal processing strategy changes, the following steps are re-executed: generating Flink operator data processing logic based on the operator logic template of the optimal processing strategy and the target signal feature parameter set.

8. The vehicle data processing method as described in claim 2, characterized in that, The target signal feature parameter set includes data frequency, data volume, and timeliness requirements. The step of calculating the target resource requirements of the vehicle signal data based on the resource requirement calculation model, according to the target signal feature parameter set and the optimal processing strategy, includes: The data transmission rate is determined based on the data frequency and data volume. Using the resource requirement calculation model, the strategy complexity of the optimal processing strategy, the data transmission rate, and the timeliness requirement are weighted and calculated to obtain the target resource requirement, which includes the number of processor cores and memory capacity.

9. The vehicle data processing method as described in claim 6, characterized in that, The step of allocating target computing resources according to the target resource requirements includes: Compare the target resource requirements with the remaining computing resources of the Flink compute node; When the remaining computing resources of the Flink computing node meet the target resource requirements, the target computing resources are allocated on the Flink computing node to execute the Flink operator data processing logic on the vehicle signal data based on the target computing resources.

10. The vehicle data processing method as described in claim 9, characterized in that, Following the step of comparing the target resource requirement with the remaining computing resources of the Flink compute node, the method further includes: When the remaining computing resources of the Flink computing node do not meet the target resource requirements, the data processing task of the vehicle signal data is split into several sub-tasks. The subtasks are scheduled to several idle Flink compute nodes, and target computing resources are allocated on the idle Flink compute nodes to execute the subtasks.

11. A vehicle data processing device, characterized in that, The vehicle data processing device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the vehicle data processing method as described in any one of claims 1 to 10.

12. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the vehicle data processing method as described in any one of claims 1 to 10.

Images