Log analysis uploading method and system based on network state and electronic equipment

By judging the network status of the vehicle computer, local storage and batch upload of the vehicle computer logs are realized, and uploaded according to the importance and characteristics of the logs are filtered and uploaded, the difficulty of uploading vehicle computer logs in a weak or unnetted environment is solved, and the upload efficiency and security are improved sex.

CN118972412APending Publication Date: 2024-11-15CHINA FAW CO LTD +1
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411207788.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-30
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

In a weak or no network environment, it is difficult to upload vehicle computer logs. The existing methods take a long time and are unsafe, and cannot effectively reduce dependence on vehicle computer networks.

Method used

By obtaining the network status of the vehicle terminal, we can determine whether the traffic-free transmission conditions are met. If they are met, store locally and upload the log in batches; if they are not met, filter and verify whether there are machine behavior characteristics in the log according to the log upload progress and importance level to ensure that Safe upload.

Benefits of technology

It reduces the dependence of the vehicle computer network, shortens the log upload time, ensures the security and integrity of data, and provides a reliable upload solution for vehicle computer logs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118972412A_ABST
    Figure CN118972412A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of vehicle-mounted software management, in particular to a log analysis uploading method and system based on a network state and electronic equipment, and the method comprises the steps: judging whether the current network state meets a traffic-free transmission condition or not; if yes, locally storing the in-vehicle machine logs at the in-vehicle machine end and uploading the in-vehicle machine logs in batches; if not, according to the in-vehicle log uploading progress of the in-vehicle terminal, determining the in-vehicle logs which are not uploaded by the in-vehicle terminal; the method comprises the following steps: defining a vehicle machine log which is not uploaded by a vehicle machine end as a to-be-uploaded task, determining a log importance level of the to-be-uploaded task, screening the vehicle machine log of the to-be-uploaded task according to the importance level, verifying whether a machine behavior feature exists in the vehicle machine log, and uploading the vehicle machine log without the feature. According to the scheme, the network resources and the in-vehicle machine logs can be managed more efficiently, the dependence on the in-vehicle machine network is effectively reduced, the influence on the in-vehicle machine network due to improper uploading of the in-vehicle machine logs is reduced, and the uploading safety of the in-vehicle machine log data is ensured.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of vehicle-mounted software management, and in particular relates to a log analysis and uploading method, system and electronic equipment based on network status. Background Art

[0002] With the rapid development of the automobile industry, vehicle intelligence has become an irreversible trend, and the widespread application of vehicle networking technology has greatly enriched the driving experience and improved driving safety and efficiency. However, while enjoying the convenience brought by intelligent connectivity, how to efficiently and securely obtain and upload vehicle logs to the cloud in weak or even no network environments such as basements and remote areas has become a key issue that needs to be solved.

[0003] At present, the methods for obtaining vehicle logs and uploading them to the cloud in the above-mentioned weak network or no network conditions are usually:

[0004] 1. R&D test vehicles: Testers use a USB flash drive to export the vehicle logs. When the test task is completed, they upload the logs to the cloud server through a networked computer. This takes too long, and R&D personnel cannot obtain the vehicle logs in time to analyze the problem.

[0005] 2. User vehicle: A dedicated after-sales service representative will go to the vehicle to retrieve the log file, and then upload it to the cloud server through an Internet-connected computer. This has high labor costs and low efficiency.

[0006] Through the above method, even if the vehicle log is uploaded, the security of the vehicle log upload cannot be guaranteed. Therefore, a solution is urgently needed that can not only reduce the dependence on the vehicle network, but also ensure the security and reliability of the vehicle log upload. Summary of the invention

[0007] Based on this, it is necessary to provide a network status-based log analysis and uploading method, system and electronic device to address the above-mentioned technical problems, which can more efficiently manage network resources and vehicle logs, reduce the impact of improper vehicle log uploading on the vehicle network, effectively reduce the dependence on the vehicle network, and at the same time ensure the integrity and security of vehicle log data upload, providing reliable technical support for the machine behavior feature identification and data analysis of vehicle logs that threaten network security.

[0008] In order to achieve the above-mentioned object of the invention, the present invention adopts the following technical scheme:

[0009] In a first aspect, the present invention provides a log analysis and uploading method based on network status, comprising:

[0010] Obtain the network status of the vehicle terminal and determine whether the current network status meets the traffic-free transmission condition; if so, store the vehicle logs locally on the vehicle terminal and upload them in batches; if not, determine the vehicle logs that have not been uploaded by the vehicle terminal according to the vehicle log upload progress of the vehicle terminal;

[0011] The vehicle computer logs that have not been uploaded by the vehicle computer are defined as tasks to be uploaded, the log importance levels of the tasks to be uploaded are determined, and the vehicle computer logs in the tasks to be uploaded are screened according to the log importance levels of the tasks to be uploaded;

[0012] After the screening is completed, verify whether there are machine behavior features in the vehicle logs of the task to be uploaded, and upload the vehicle logs that do not have machine behavior features.

[0013] Optionally, the obtaining of the network status of the vehicle terminal includes: a strong network status, a weak network status and a no network status;

[0014] In the above strong network condition, the vehicle log can be transmitted without traffic;

[0015] In the offline state, the vehicle cannot connect to the Internet of Vehicles service platform and cannot perform related functions; wherein the related functions include remote control function, navigation online update function, and real-time traffic information acquisition function;

[0016] In the weak network state, the vehicle is connected to the Internet of Vehicles service platform, and whether the data transmission rate, transmission time, and number of disconnection occurrences exceed preset thresholds is used to determine the delay in the transmission process.

[0017] Optionally, before storing the vehicle computer log locally on the vehicle computer side and uploading it in batches, the process also includes: obtaining relevant vehicle computer log data according to the vehicle's log upload requirements, filtering the vehicle computer log data, and then comparing it with the local data on the vehicle computer side to obtain incremental log data that is different from the local data, and when the data volume reaches a preset threshold, calling a text preprocessing word segmenter to convert the format of the incremental log data to generate vehicle computer logs for batch upload.

[0018] Optionally, before determining the vehicle logs that have not been uploaded by the vehicle terminal according to the vehicle log upload progress of the vehicle terminal, the step further includes:

[0019] Maintain connection with the Internet of Vehicles service platform through the MQTT protocol, monitor the network status regularly according to pre-defined time intervals, and determine the vehicle's log upload needs; when it is detected that the vehicle-side is in a weak network state and the vehicle has a log upload need, query the Internet of Vehicles service platform for the vehicle-side log upload progress.

[0020] Optionally, determining the log importance level of the task to be uploaded includes:

[0021] Using the Pearson correlation coefficient, the importance factors of the vehicle log in each task to be uploaded are analyzed, and the occurrence frequency of each influencing factor in the vehicle log data of the task to be uploaded is calculated; the occurrence frequency of the importance factor in the vehicle log data of the task to be uploaded is used as the basis for the log importance level allocation, and a first log importance level allocation result proportional to the occurrence frequency is obtained;

[0022] The main variables among the influencing factors are taken as key factors, and the linear regression method is used to estimate the influence of each key factor on the first log importance level allocation result; and based on the influence of the key factors, the log importance level of the task to be uploaded is allocated to obtain a second log importance level allocation result that is proportional to the influence of the key factors;

[0023] The log importance level of the task to be uploaded is determined based on the first and second log importance level allocation results.

[0024] Optionally, the verifying whether there is a machine behavior feature in the vehicle log of the task to be uploaded includes:

[0025] Read the vehicle logs in the filtered tasks to be uploaded, and traverse each URL parameter of the vehicle log data through predefined deterministic rules; the predefined deterministic rules include: test behavior identification, crawler behavior identification, and Track-Peer node communication behavior identification;

[0026] By traversing the deterministic rules, the vehicle log data containing the machine behavior characteristics is identified; the vehicle log data carrying the deterministic identification is obtained by marking and stored in the database;

[0027] The unlabeled vehicle log data is recorded as uncertain vehicle log data, the URL parameters in the uncertain vehicle log data are obtained, and the pre-established Bi-LSTM recognition model is input to identify the machine behavior characteristics in the uncertain vehicle log data.

[0028] Optionally, the pre-construction of the Bi-LSTM recognition model includes:

[0029] Obtain historical vehicle log data uploaded on the network, annotate URL parameters in the historical vehicle log data, remove abnormal characters in the URL parameters through data cleaning, and obtain URL text; generate corresponding character encoding based on the characters in the URL text to realize URL text vectorization;

[0030] The parameter feature conformity, time feature conformity and domain name feature conformity are used as probability judgment indicators for evaluating the presence of machine behavior features in vehicle log data. The vectorized URL text input is introduced into the Bi-LSTM model of the Attention neural network mechanism, and training is performed based on the probability judgment indicators to obtain the Bi-LSTM recognition model.

[0031] In a second aspect, the present invention provides a log analysis and uploading system based on network status, the system comprising:

[0032] A judgment module is used to obtain the network status of the vehicle terminal and judge whether the current network status meets the traffic-free transmission condition; if so, the vehicle logs are stored locally on the vehicle terminal and uploaded in batches; if not, the vehicle logs that have not been uploaded by the vehicle terminal are determined according to the vehicle log upload progress of the vehicle terminal;

[0033] The log processing module is used to define the vehicle computer logs that have not been uploaded by the vehicle computer as tasks to be uploaded, determine the log importance level of the tasks to be uploaded, and filter the vehicle computer logs in the tasks to be uploaded according to the log importance level of the tasks to be uploaded;

[0034] The verification module is used to verify whether the vehicle log of the task to be uploaded has machine behavior characteristics after the screening is completed, and upload the vehicle log without machine behavior characteristics.

[0035] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method steps described in any one of the first aspects.

[0036] In a fourth aspect, the present invention provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the method steps described in any one of the first aspects.

[0037] Compared with the closest prior art, the present invention has the following beneficial effects:

[0038] The log analysis and uploading method, system and electronic device based on network status proposed by the present invention include judging whether the current network status meets the traffic-free transmission condition; if it meets the condition, the vehicle log is locally stored and uploaded in batches on the vehicle end; if it does not meet the condition, the vehicle log that has not been uploaded by the vehicle end is determined according to the vehicle log upload progress of the vehicle end; the vehicle log that has not been uploaded by the vehicle end is defined as a task to be uploaded, the log importance level of the task to be uploaded is determined, and after the screened task to be uploaded is determined according to the importance level, it is verified whether there is a machine behavior feature in the screened vehicle log, and the vehicle log without the feature is uploaded. The above content can judge the network status of the vehicle end before executing the log upload task, and when the traffic-free transmission condition is met, the vehicle log to be uploaded is stored and transmitted locally on the vehicle end, thereby greatly reducing the pressure on uploading a large number of vehicle log data. In the case of weak network or no network, a "traffic-free upload" channel is added to realize the upload of vehicle logs to the cloud, avoiding the dependence of vehicle log upload on the vehicle network and shortening the time of uploading vehicle logs to the cloud.

[0039] If not, the upload operation is determined to continue according to the appropriate network status, demand conditions and the importance of the log, and its safety is verified; especially when the vehicle has a weak network or no network, the vehicle interconnection technology is used to realize the automatic connection and interconnection between the vehicle and the mobile phone, create the upload log task to the mobile terminal and automatically transfer the collected log files to the mobile terminal. The mobile terminal uses the user-defined network link to transfer the vehicle log to the cloud. It can effectively avoid data transmission when the network is poor, and at the same time ensure the security and integrity of the data upload link.

[0040] The network status-based log analysis and uploading method, system and electronic device proposed in the present invention can realize the URL recognition of the vehicle computer log, and detect the deterministic machine behavior and uncertain machine behavior in the vehicle computer log URL; it can more efficiently manage network resources and vehicle computer logs, reduce the impact of improper vehicle computer log uploading on the vehicle computer network, and effectively reduce the dependence on the vehicle computer network. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings are only used to illustrate specific embodiments and are not considered to limit the present invention. In the entire drawings, the same reference symbols represent the same components. Obviously, the drawings described below are only some embodiments described in the embodiments of the present invention. For those skilled in the art, other drawings can also be obtained based on these drawings;

[0042] Figure 1 This is a flow chart of a log analysis and uploading method based on network status according to an embodiment of the present invention;

[0043] Figure 2This is a schematic diagram of the implementation principle of free traffic and log upload that does not meet the free traffic conditions in an embodiment of the present invention;

[0044] Figure 3 A schematic diagram of the structure of a log analysis and uploading system based on network status according to an embodiment of the present invention;

[0045] Figure 4 The figure is a schematic diagram of the structure of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The following embodiments of the technical solution of the present invention are described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and are therefore only used as examples, and cannot be used to limit the protection scope of the present invention.

[0047] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application should have the common meanings understood by those skilled in the art to which the present invention belongs.

[0048] Based on the above problems, the present invention provides a log analysis and uploading method, system and electronic device based on network status. Through this embodiment, the invention purpose of avoiding the dependence of vehicle log uploading on the vehicle network is brought about, shortening the time of uploading vehicle log to the cloud, and also ensuring the security of the vehicle log uploading link.

[0049] In one embodiment, an adaptive business data compliance risk assessment method is provided in an embodiment of the present invention. The embodiment of the present invention is described below with reference to the accompanying drawings. Figure 1 , the specific steps include:

[0050] S101 obtains the network status of the vehicle terminal and determines whether the current network status meets the traffic-free transmission condition; if so, the vehicle logs are locally stored on the vehicle terminal and uploaded in batches; if not, the vehicle logs that have not been uploaded by the vehicle terminal are determined according to the vehicle log upload progress of the vehicle terminal;

[0051] S102 defines the vehicle computer logs that have not been uploaded by the vehicle computer as tasks to be uploaded, determines the log importance level of the tasks to be uploaded, and filters the vehicle computer logs in the tasks to be uploaded according to the log importance level of the tasks to be uploaded;

[0052] After the screening is completed, S103 verifies whether there are machine behavior features in the vehicle log of the task to be uploaded, and uploads the vehicle log without machine behavior features.

[0053] Based on the above method steps, it can be known that in step S101, the network status of the vehicle terminal is obtained, including: strong network status, weak network status and no network status;

[0054] In the above strong network condition, the vehicle log can be transmitted without traffic;

[0055] In the offline state, the vehicle cannot connect to the Internet of Vehicles service platform and cannot perform related functions; wherein the related functions include remote control function, navigation online update function, and real-time traffic information acquisition function;

[0056] In the weak network state, the vehicle is connected to the Internet of Vehicles service platform, and whether the data transmission rate, transmission time, and number of disconnection occurrences exceed preset thresholds is used to determine the delay in the transmission process.

[0057] It can be understood that in step S101, when the vehicle network is weak or there is no network, a "traffic-free upload" channel is added to upload the vehicle log to the cloud, avoiding the dependence of the vehicle log upload on the vehicle network, shortening the time for uploading the vehicle log to the cloud, and also ensuring the security of the vehicle log upload link.

[0058] In the above embodiment, when it is determined that the traffic-free upload is satisfied, the vehicle log can be stored locally on the vehicle side and uploaded in batches. Before uploading, the following steps are also included: obtaining relevant vehicle log data according to the vehicle log upload requirements, filtering the vehicle log data, and then comparing it with the local data on the vehicle side to obtain incremental log data that is different from the local data, and when the data volume reaches a preset threshold, calling the text preprocessing word segmenter to convert the incremental log data into a format, and generating vehicle logs for batch upload.

[0059] Optionally, in addition to comparing with the local data on the vehicle computer, it is also possible to compare with the local unsafe log data to obtain incremental log data that is different from the local unsafe vehicle computer log data.

[0060] Furthermore, when it is determined that the conditions for traffic-free upload are not met, that is, when the vehicle network is weak or there is no network; the car interconnection technology can be used to achieve automatic connection and interconnection between the vehicle and the mobile phone. The vehicle will create an upload log task to the mobile terminal and automatically transfer the collected log files to the mobile terminal. The mobile terminal will automatically transmit the vehicle log to the cloud through the existing two-way authentication security mechanism between the mobile app and the Internet of Vehicles service platform or the cloud under the user-defined network connection.

[0061] Specifically, the MQTT protocol can be used to maintain a connection with the Internet of Vehicles service platform or the cloud, monitor the network status regularly according to predefined time intervals, and determine the vehicle's log upload needs; when it is detected that the vehicle-side is in a weak network state and the vehicle has a log upload need, the Internet of Vehicles service platform is queried for the vehicle-side log upload progress.

[0062] Through the above steps, a specific application scenario is simulated to further illustrate the specific implementation examples of free-flow log upload and log upload when the free-flow upload conditions are not met: as shown in Question 2.

[0063] 1. The vehicle has unfinished log upload tasks. Identify the current network conditions as the judgment condition for entering the "free traffic upload" process:

[0064] (1) Weak network: The weak network status of a vehicle means that although the vehicle has established a network connection, the connection quality is poor, resulting in low data transmission rate, high latency or frequent disconnection, thus affecting normal data exchange and service experience. The criteria for weak network can be judged from the following aspects:

[0065] ①The data transmission rate is lower than 128kbps;

[0066] ②Network delay is higher than 300ms;

[0067] (2) No network: Modern smart vehicles are usually equipped with Internet of Vehicles functions, which allow the vehicle to access the Internet through a built-in communication module (such as 4G / 5G, LTE, etc.). If the vehicle cannot connect to the Internet of Vehicles service platform and cannot realize functions such as remote control, online navigation updates, and real-time traffic information acquisition, it is considered to be without network.

[0068] If one of the conditions (1) and (2) is met, the system is deemed to have met the judgment conditions. If not, the system enters the "traffic upload" process.

[0069] 2. Check whether the vehicle computer and the mobile phone have established "hand-car interconnection".

[0070] (1) “Handcart interconnection” has not been established

[0071] ① The car computer prompts to establish "hand-car interconnection";

[0072] ② Users establish “handcart interconnection”;

[0073] (2) "Handcart interconnection" has been automatically established, proceed to step 3

[0074] 3. Check whether the "no-traffic-needed upload" function of the vehicle log is enabled on the mobile phone APP.

[0075] (1) Not enabled

[0076] ① The car machine and mobile phone APP prompt to turn on the "data-free upload" function of the car machine log;

[0077] ② Enable the "no-traffic upload" function of the vehicle log on the mobile APP;

[0078] (2) If enabled, proceed to step 4

[0079] 4. The vehicle computer creates a task to upload logs to the mobile terminal. The task information includes: vehicle vin, vehicle computer equipment number, log file name, log file MD5, and task validity period.

[0080] 5. The vehicle computer automatically transmits the collected log files to the mobile terminal.

[0081] 6. The mobile APP prompts the log file transfer results.

[0082] 7. Under the user-defined network connection, the mobile terminal automatically performs the log upload task in the dedicated upload channel and security mechanism, and uploads the log files collected by the target device in the local storage area to the cloud server.

[0083] 8. The mobile APP prompts the log file upload result.

[0084] In step S102 of the above embodiment, determining the log importance level of the task to be uploaded includes:

[0085] Using the Pearson correlation coefficient, the importance factors of the vehicle log in each task to be uploaded are analyzed, and the occurrence frequency of each influencing factor in the vehicle log data of the task to be uploaded is calculated; the occurrence frequency of the importance factor in the vehicle log data of the task to be uploaded is used as the basis for the log importance level allocation, and a first log importance level allocation result proportional to the occurrence frequency is obtained;

[0086] The main variables among the influencing factors are taken as key factors, and the linear regression method is used to estimate the influence of each key factor on the first log importance level allocation result; and based on the influence of the key factors, the log importance level of the task to be uploaded is allocated to obtain a second log importance level allocation result that is proportional to the influence of the key factors;

[0087] The log importance level of the task to be uploaded is determined based on the first and second log importance level allocation results.

[0088] In the above embodiment, after the log importance level is determined, the log importance level of the vehicle log itself can be compared with the upload standard pre-set in actual working conditions. If this standard is not met, the corresponding vehicle logs can be directly screened out, and only the log data with the importance level that meets the standard is retained.

[0089] After the screening is completed, in step S103, verifying whether there is a machine behavior feature in the vehicle log of the task to be uploaded includes:

[0090] Read the vehicle logs in the filtered tasks to be uploaded, and traverse each URL parameter of the vehicle log data through predefined deterministic rules; the predefined deterministic rules include: test behavior identification, crawler behavior identification, and Track-Peer node communication behavior identification;

[0091] By traversing the deterministic rules, the vehicle log data containing the machine behavior characteristics is identified; the vehicle log data carrying the deterministic identification is obtained by marking and stored in the database;

[0092] The unlabeled vehicle log data is recorded as uncertain vehicle log data, the URL parameters in the uncertain vehicle log data are obtained, and the pre-established Bi-LSTM recognition model is input to identify the machine behavior characteristics in the uncertain vehicle log data.

[0093] In a specific embodiment, the identification of uncertain machine behavior is due to the fact that the parameters representing traffic / buried point URLs in the vehicle log data are unclear and mostly in descriptive language, and there are many traffic statistics behaviors without unified rules and specifications. In order to achieve quantitative evaluation of descriptive features to behavior identification, the target problem is divided into multiple sub-problems, and a multi-factor, multi-level identification model is established. By quantifying qualitative information, complex evaluation problems can be quantitatively calculated.

[0094] The pre-construction of the Bi-LSTM recognition model includes:

[0095] First, the historical vehicle log data uploaded on the network is obtained, the URL parameters in the historical vehicle log data are marked, and the abnormal characters in the URL parameters are removed through data cleaning to obtain the URL text;

[0096] Optionally, the historical vehicle log data obtained above should have a certain time span. Otherwise, too few samples will have a certain impact on the training effect of the model. For example, the historical vehicle log data can be classified according to the first dimension index and the second dimension index. Suppose a time series divided by the first time dimension index and the second time dimension index is (x1, x2,…, x n ), where X represents a time series vector.

[0097] Secondly, the corresponding character encoding is generated based on the characters in the URL text to realize the vectorization of the URL text; for example, the URL parameters are processed using the word2Id method. Let U be a URL text, and the word embedding layer converts U into a feature vector, that is, its embedding matrix is ​​represented as U→ML×K, where L is the character length of a URL text and K is set to 50.

[0098] Finally, the parameter feature conformity, time feature conformity, and domain name feature conformity are used as probability judgment indicators to evaluate the existence of machine behavior features in vehicle log data; the vectorized URL text input is introduced into the Bi-LSTM model of the Attention neural network mechanism, and training is performed based on the probability judgment indicators to obtain the Bi-LSTM recognition model.

[0099] Based on the same inventive concept, the embodiment of the present application also provides a network status-based log analysis upload system of a network status-based log analysis upload method. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more network status-based log analysis upload systems provided below can refer to the limitations of the network status-based log analysis upload method above, and will not be repeated here.

[0100] In one embodiment, Figure 3 As shown, a log analysis and uploading system based on network status is provided, including: a judgment module 210, a log processing module 220, and an optimization module 230, wherein:

[0101] The judgment module 210 is used to obtain the network status of the vehicle terminal and judge whether the current network status meets the traffic-free transmission condition; if so, the vehicle logs are stored locally on the vehicle terminal and uploaded in batches; if not, the vehicle logs that have not been uploaded by the vehicle terminal are determined according to the vehicle log upload progress of the vehicle terminal;

[0102] The log processing module 220 is used to define the vehicle log that has not been uploaded by the vehicle end as a task to be uploaded, determine the log importance level of the task to be uploaded, and filter the vehicle log in the task to be uploaded according to the log importance level of the task to be uploaded;

[0103] The verification module 230 is used to verify whether there is a machine behavior feature in the vehicle log of the task to be uploaded after the screening is completed, and upload the vehicle log without the machine behavior feature.

[0104] At the same time, the present application also proposes a computer-readable storage medium and an electronic device. In one embodiment, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of any one of the methods in step S101 to step S103 are implemented.

[0105] In one embodiment, an electronic device is provided. The electronic device may be a terminal, and its internal structure diagram may be as follows: Figure 4As shown. The electronic device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the electronic device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, the method described in any one of S101 to S103 is implemented. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the housing of the electronic device, or an external keyboard, touchpad or mouse.

[0106] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0107] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0108] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory ROM, magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive memory ReRAM, magnetic memory MRAM, ferroelectric memory FRAM, phase change memory PCM, graphene memory, etc. Volatile memory may include random access memory RAM or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory SRAM or dynamic random access memory DRAM, etc. The database involved in the embodiments provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, etc., but is not limited thereto.

[0109] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0110] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A log analysis and uploading method based on network status, characterized in that: The method comprises: Obtain the network status of the vehicle terminal and determine whether the current network status meets the traffic-free transmission condition; if so, store the vehicle logs locally on the vehicle terminal and upload them in batches; if not, determine the vehicle logs that have not been uploaded by the vehicle terminal according to the vehicle log upload progress of the vehicle terminal; The vehicle computer logs that have not been uploaded by the vehicle computer are defined as tasks to be uploaded, the log importance levels of the tasks to be uploaded are determined, and the vehicle computer logs in the tasks to be uploaded are screened according to the log importance levels of the tasks to be uploaded; After the screening is completed, verify whether there are machine behavior features in the vehicle logs of the task to be uploaded, and upload the vehicle logs that do not have machine behavior features.

2. The method according to claim 1, characterized in that The network status of the vehicle terminal includes: strong network status, weak network status and no network status; In the above strong network condition, the vehicle log can be transmitted without traffic; In the offline state, the vehicle cannot connect to the Internet of Vehicles service platform and cannot perform related functions; wherein the related functions include remote control function, navigation online update function, and real-time traffic information acquisition function; In the weak network state, the vehicle is connected to the Internet of Vehicles service platform, and whether the data transmission rate, transmission time, and number of disconnection occurrences exceed preset thresholds is used to determine the delay in the transmission process.

3. The method according to claim 1, characterized in that Before storing the vehicle computer log locally on the vehicle computer side and uploading it in batches, the method also includes: obtaining relevant vehicle computer log data according to the vehicle log upload requirements, filtering the vehicle computer log data, and then comparing it with the local data on the vehicle computer side to obtain incremental log data that is different from the local data, and when the data volume reaches a preset threshold, calling the text preprocessing word segmenter to convert the format of the incremental log data to generate vehicle computer logs for batch upload.

4. The method according to claim 1, characterized in that: The step of determining the vehicle logs that have not been uploaded by the vehicle terminal according to the vehicle log upload progress of the vehicle terminal also includes: Maintain connection with the Internet of Vehicles service platform through the MQTT protocol, monitor the network status regularly according to pre-defined time intervals, and determine the vehicle's log upload needs; when it is detected that the vehicle-side is in a weak network state and the vehicle has a log upload need, query the Internet of Vehicles service platform for the vehicle-side log upload progress.

5. The method according to claim 4, characterized in that Determining the log importance level of the task to be uploaded includes: Using the Pearson correlation coefficient, the importance factors of the vehicle log in each task to be uploaded are analyzed, and the occurrence frequency of each influencing factor in the vehicle log data of the task to be uploaded is calculated; the occurrence frequency of the importance factor in the vehicle log data of the task to be uploaded is used as the basis for the log importance level allocation, and a first log importance level allocation result proportional to the occurrence frequency is obtained; The main variables among the influencing factors are taken as key factors, and the linear regression method is used to estimate the influence of each key factor on the first log importance level allocation result; and based on the influence of the key factors, the log importance level of the task to be uploaded is allocated to obtain a second log importance level allocation result that is proportional to the influence of the key factors; The log importance level of the task to be uploaded is determined based on the first and second log importance level allocation results.

6. The method according to claim 5, characterized in that The verification of whether there is a machine behavior feature in the vehicle log of the task to be uploaded includes: Read the vehicle logs in the filtered tasks to be uploaded, and traverse each URL parameter of the vehicle log data through predefined deterministic rules; the predefined deterministic rules include: test behavior identification, crawler behavior identification, and Track-Peer node communication behavior identification; By traversing the deterministic rules, the vehicle log data containing the machine behavior characteristics is identified; the vehicle log data carrying the deterministic identification is obtained by marking and stored in the database; The unlabeled vehicle log data is recorded as uncertain vehicle log data, the URL parameters in the uncertain vehicle log data are obtained, and the pre-established Bi-LSTM recognition model is input to identify the machine behavior characteristics in the uncertain vehicle log data.

7. The method according to claim 6, characterized in that The pre-built Bi-LSTM recognition model includes: Obtain historical vehicle log data uploaded on the network, annotate URL parameters in the historical vehicle log data, remove abnormal characters in the URL parameters through data cleaning, and obtain URL text; generate corresponding character encoding based on the characters in the URL text to realize URL text vectorization; The parameter feature conformity, time feature conformity and domain name feature conformity are used as probability judgment indicators for evaluating the presence of machine behavior features in vehicle log data. The vectorized URL text input is introduced into the Bi-LSTM model of the Attention neural network mechanism, and training is performed based on the probability judgment indicators to obtain the Bi-LSTM recognition model.

8. A log analysis and upload system based on network status, characterized in that: The system comprises: A judgment module is used to obtain the network status of the vehicle terminal and judge whether the current network status meets the traffic-free transmission condition; if so, the vehicle logs are stored locally on the vehicle terminal and uploaded in batches; if not, the vehicle logs that have not been uploaded by the vehicle terminal are determined according to the vehicle log upload progress of the vehicle terminal; The log processing module is used to define the vehicle computer logs that have not been uploaded by the vehicle computer as tasks to be uploaded, determine the log importance level of the tasks to be uploaded, and filter the vehicle computer logs in the tasks to be uploaded according to the log importance level of the tasks to be uploaded; The verification module is used to verify whether the vehicle log of the task to be uploaded has machine behavior characteristics after the screening is completed, and upload the vehicle log without machine behavior characteristics.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the method according to any one of claims 1 to 7.

Citation Information

Cited By

  • Network security detection method and apparatus for vehicle, vehicle, and storage medium

    WO2026179432A1