A vehicle-cloud communication breakpoint detection method and related device

Abstract

The application discloses a kind of car cloud communication breakpoint detection method and related device, it is related to car cloud communication technical field, it is applied to car end, obtains vehicle operation data, and according to vehicle operation data, the first communication state of communication channel between prediction and cloud end;In the case where first communication state is communication breakpoint, generate session recovery identifier, and cache communication session data, simultaneously determine the second communication state of communication channel by interrupt detection;In the case where second communication state is communication breakpoint, enable session recovery identifier, load communication session data, using session recovery identifier recovers communication channel, and communication session data is uploaded to cloud end by communication channel.The application can cache communication session data in advance to avoid data loss and affect service continuity, and using session recovery identifier and cloud end recovers reconnection, avoids rehandshake, realizes quick recovery, guarantees recovery efficiency, improves the continuity and stability of car cloud communication.

Description

Technical Field

[0001] This application relates to the field of vehicle-to-cloud communication technology, and in particular to a method and related device for detecting breakpoints in vehicle-to-cloud communication. Background Technology

[0002] At present, communication interruptions are unavoidable in the data interaction between the vehicle and the cloud in the vehicle-cloud communication system, especially in situations such as tunnels, mountainous areas, and base station switching intervals.

[0003] Communication interruptions often lead to data loss on the vehicle side, significantly impacting service continuity, such as causing navigation errors and delays in emergency services. Furthermore, current vehicle-side solutions primarily rely on passive reconnection, triggering a handshake with the cloud only after a communication interruption is detected. However, this handshake process is relatively complex, resulting in low recovery efficiency. Summary of the Invention

[0004] In view of the above problems, this application provides a method and related apparatus for detecting vehicle-to-cloud communication breakpoints, so as to solve the problems of poor service continuity and low recovery efficiency caused by existing vehicle-to-cloud communication breakpoints. The specific solution is as follows:

[0005] The first aspect of this application provides a method for detecting breakpoints in vehicle-to-cloud communication, wherein the method is applied to the vehicle side and includes:

[0006] Acquire vehicle operation data and predict the first communication state of the communication channel with the cloud based on the vehicle operation data;

[0007] In the case of a communication interruption in the first communication state, a session recovery identifier is generated and communication session data is cached. At the same time, the second communication state of the communication channel is determined by interruption detection.

[0008] When the second communication state is a communication interruption, the session recovery identifier is activated, the communication session data is loaded, the communication channel is restored using the session recovery identifier, and the communication session data is uploaded to the cloud through the communication channel.

[0009] In one possible implementation, the communication session data includes session data from multiple communication sessions. After caching the communication session data, the vehicle-to-cloud communication breakpoint detection method further includes:

[0010] The upload order of the multiple communication sessions is determined based on the service priority of the multiple communication sessions;

[0011] According to the upload order, the session data of each communication session is uploaded to the cloud sequentially by switching the communication protocol of the communication channel;

[0012] Delete the session data of the successfully uploaded communication session from the communication session data.

[0013] In one possible implementation, predicting the first communication state of the communication channel with the cloud based on the vehicle operation data includes:

[0014] When the vehicle operation data is multimodal data, the data features of each mode in the vehicle operation data are extracted, and the extracted data features are fused.

[0015] The feature fusion result is input into the trained prediction model, and the first communication state output by the prediction model is obtained. The prediction model is trained based on a machine learning algorithm.

[0016] In one possible implementation, the cached communication session data includes:

[0017] Determine the data type of the communication session data;

[0018] The communication session data is cached according to the data type described.

[0019] In one possible implementation, restoring the communication channel using the session recovery identifier includes:

[0020] The communication channel is restored using the session recovery identifier at a first time interval;

[0021] If the recovery time of the communication channel reaches the corresponding time threshold, an early warning message is output, the communication session data is persistently saved, and the communication channel is restored using the session recovery identifier according to a second time interval, wherein the second time interval is greater than the first time interval.

[0022] In one possible implementation, restoring the communication channel using the session recovery identifier further includes:

[0023] When the first communication state changes from a communication breakpoint to a non-communication breakpoint, the communication channel is restored using the session recovery identifier according to a third time interval, the third time interval being less than the first time interval.

[0024] A second aspect of this application provides a vehicle-to-cloud communication breakpoint detection device, which is applied to a vehicle and includes:

[0025] The breakpoint prediction module is used to acquire vehicle operation data and predict the first communication state of the communication channel with the cloud based on the vehicle operation data.

[0026] The breakpoint detection module is used to generate a session recovery identifier and cache communication session data when the first communication state is a communication breakpoint, and at the same time determine the second communication state of the communication channel through interruption detection.

[0027] The data upload module is used to enable the session recovery identifier, load the communication session data, restore the communication channel using the session recovery identifier, and upload the communication session data to the cloud through the communication channel when the second communication state is a communication interruption.

[0028] A third aspect of this application provides a computer program product including computer-readable instructions that, when executed on an electronic device, cause the electronic device to implement the vehicle-to-cloud communication breakpoint detection method described in the first aspect or any implementation thereof.

[0029] A fourth aspect of this application provides an electronic device, including at least one processor and a memory connected to the processor, wherein:

[0030] The memory is used to store computer programs;

[0031] The processor is used to execute the computer program so that the electronic device can implement the vehicle-to-cloud communication breakpoint detection method of the first aspect or any implementation thereof.

[0032] The fifth aspect of this application provides a computer storage medium carrying one or more computer programs, which, when executed by an electronic device, enable the electronic device to implement the vehicle-to-cloud communication breakpoint detection method described in the first aspect or any implementation thereof.

[0033] Using the above technical solution, this application provides a vehicle-to-cloud communication breakpoint detection method and related device, applied to the vehicle end, to acquire vehicle operation data and predict the first communication state of the communication channel with the cloud based on the vehicle operation data; if the first communication state is a communication breakpoint, a session recovery identifier is generated and communication session data is cached, while a second communication state of the communication channel is determined through interruption detection; if the second communication state is a communication breakpoint, the session recovery identifier is enabled, communication session data is loaded, the communication channel is restored using the session recovery identifier, and the communication session data is uploaded to the cloud through the communication channel. This application, after predicting a possible communication breakpoint with the cloud based on vehicle operation data, generates a session recovery identifier and caches communication session data, while simultaneously determining the actual communication breakpoint with the cloud through interruption detection. This allows for the generation of a recovery strategy before a communication interruption occurs, and after detecting a real communication breakpoint, the session recovery identifier can be enabled, the cached communication session data can be loaded, and the communication session data can be successfully uploaded after reconnecting to the cloud using the session recovery identifier. Therefore, this application can cache communication session data in advance to avoid data loss and affect service continuity. Furthermore, by using session recovery identifiers to restore and reconnect with the cloud, it avoids re-handshaking, achieves rapid recovery, ensures recovery efficiency, and improves the continuity and stability of vehicle-cloud communication. Attached Figure Description

[0034] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0035] Figure 1 A flowchart illustrating a vehicle-to-cloud communication breakpoint detection method provided in an embodiment of this application;

[0036] Figure 2 This is a partial flowchart illustrating a vehicle-to-cloud communication breakpoint detection method provided in an embodiment of this application.

[0037] Figure 3 This is another schematic flowchart of a vehicle-to-cloud communication breakpoint detection method provided in an embodiment of this application;

[0038] Figure 4 This is another schematic flowchart of a vehicle-to-cloud communication breakpoint detection method provided in an embodiment of this application;

[0039] Figure 5 This is a schematic diagram of the structure of a vehicle-to-cloud communication breakpoint detection device provided in an embodiment of this application;

[0040] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0041] The embodiments of this application are described below with reference to the accompanying drawings. The terminology used in the implementation section of this application is for explaining specific embodiments only and is not intended to limit the scope of this application.

[0042] The embodiments of this application will now be described with reference to the accompanying drawings. Those skilled in the art will recognize that, with technological advancements and the emergence of new scenarios, the technical solutions provided in the embodiments of this application are equally applicable to similar technical problems.

[0043] The terms "first," "second," etc., used in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms are interchangeable where appropriate; this is merely a way of distinguishing objects with the same attributes in the embodiments of this application. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, so that a process, method, system, product, or apparatus that comprises a series of units is not necessarily limited to those units, but may include other units not explicitly listed or inherent to those processes, methods, products, or apparatuses.

[0044] See Figure 1 , Figure 1 This is a flowchart illustrating a vehicle-to-cloud communication breakpoint detection method provided in an embodiment of this application. Figure 1 As shown in the embodiment of this application, a vehicle-to-cloud communication breakpoint detection method can be applied to the vehicle side, specifically to the HU (Head Unit), XCU (Cross-domain Control Unit), or FSD (Full Self-Driving) of the vehicle side. It can include steps S101 to S103, which are described in detail below.

[0045] S101, acquire vehicle operation data, and predict the first communication state of the communication channel with the cloud based on the vehicle operation data.

[0046] Generally, the impact of vehicle movement on the communication channel with the cloud can be categorized into motion, communication, and geographical dimensions. Specifically, in terms of motion, the signal quality of the communication channel fluctuates when the vehicle accelerates or travels at high speeds; in terms of communication, the signal quality of the communication channel also varies when the vehicle uploads different types of data packets; and in terms of geographical dimensions, the signal quality of the communication channel is relatively poor when the vehicle travels in special geographical areas such as tunnels, mountainous regions, and base station switching areas.

[0047] To address this, based on the impact of vehicle operating states on network signals in different dimensions, a correspondence between vehicle operating states and communication channel states in different dimensions can be generated. This allows for the determination of whether the communication state corresponding to a vehicle operating state in a different dimension (such as speed, acceleration, and direction in the motion dimension) represents a communication breakpoint. During vehicle operation, vehicle motion information at the current time can be acquired. This vehicle operation data includes the vehicle operating state in a specific dimension, which can be used to predict whether the corresponding communication state (i.e., the first communication state) represents a communication breakpoint. This allows for advance prediction of whether a communication breakpoint will occur with the cloud.

[0048] In one possible implementation, artificial intelligence technology can be used to predict the first communication state corresponding to vehicle operation data. See also Figure 2 , Figure 2 This is a partial flowchart illustrating a vehicle-to-cloud communication breakpoint detection method provided in an embodiment of this application. Figure 2 As shown in the embodiment of this application, a vehicle-to-cloud communication breakpoint detection method is provided. Step S101, "predicting the first communication state of the communication channel between the vehicle and the cloud based on vehicle operation data", may include steps S1011 to S1012. These steps are described in detail below.

[0049] S1011, when the vehicle operation data is multimodal data, extract the data features of each mode in the vehicle operation data, and perform feature fusion on the extracted data features.

[0050] In this embodiment, the vehicle operation data is multimodal data, which includes vehicle operation states in different dimensions. For ease of understanding, it is assumed that the vehicle operation data includes vehicle operation states in the motion dimension (such as speed and acceleration), vehicle operation states in the communication dimension (such as communication type, data packet size, etc.), and vehicle operation states in the geographical dimension (such as latitude and longitude). For vehicle operation states in different dimensions of the vehicle operation data, data cleaning and preprocessing are first performed to ensure data quality. Then, feature engineering is used to extract data features under each modality and feature fusion is performed for use by the AI ​​model.

[0051] S1012, input the feature fusion result into the trained prediction model and obtain the first communication state output by the prediction model. The prediction model is trained based on a machine learning algorithm.

[0052] In this embodiment, the prediction model is an AI model, trained based on a machine learning algorithm. Specifically, historical vehicle operation data can be collected, and the corresponding communication states can be labeled to indicate whether there are communication breakpoints. The collected vehicle operation data is then used as training data, and the labeled communication states are used as targets to iteratively train the base model to obtain the prediction model. The base model can be selected according to the actual scenario; this embodiment does not limit this selection.

[0053] Taking a single iteration training as an example, data samples for this iteration training are selected from the training data; the data samples are cleaned and preprocessed, and features are extracted and fused to obtain the corresponding feature fusion results; the feature fusion results are input into the base model to obtain the communication state predicted by the base model; the loss function value of the local iteration training is calculated based on the predicted communication state and the communication state labeled for the data samples; the weight parameters of the base model are adjusted according to the loss function value, and the next iteration training is started until the loss function value converges, at which point the iteration training ends, and the trained base model is used as the prediction model.

[0054] Therefore, in this embodiment, the AI ​​model can adapt to dynamic scene changes through training and updating. Furthermore, the lightweight design of the AI ​​model ensures efficient operation of the prediction model on the vehicle.

[0055] S102, when the first communication state is a communication interruption, a session recovery identifier is generated and the communication session data is cached. At the same time, the second communication state of the communication channel is determined by interrupt detection.

[0056] In this embodiment, if the first communication state is a communication interruption, it indicates that the communication channel with the cloud is about to be interrupted. To address this, a corresponding SRI (Session Recovery Identifier) ​​can be generated for the communication session, and the current communication session data (containing session data from at least one communication session) can be cached to prevent data loss and ensure service continuity. Simultaneously, interruption detection is triggered to determine the actual communication state of the communication channel (i.e., the second communication state). Of course, in practical applications, the signal strength of the communication signal can be monitored, and interruption detection can be triggered when the signal strength is less than a corresponding strength threshold.

[0057] It should be noted that the session recovery identifier is a lightweight session management mechanism primarily used to reduce recovery time caused by network outages. It can be applied to various network protocols, such as TCP (Transmission Control Protocol), QUIC (Quick UDP Internet Connection, a low-latency internet transport layer protocol based on UDP developed by Google), and custom communication protocols. The SRI-based communication session recovery mechanism is as follows:

[0058] 1) Session initialization: During normal communication, the client and server negotiate and generate an SRI, which may include session keys, authentication information, handshake status, etc. In this embodiment, the vehicle is the client and the cloud is the server; 2) Cache session data: After the SRI is generated, the context data of the communication session (i.e., communication session data) will be stored in the cache of the client and server; 3) Communication recovery: When communication is interrupted, the client can directly request recovery through the SRI without having to re-execute the complete handshake process; 4) Server verification: After receiving the SRI, the server will verify it according to the cached communication session data. After confirming that the SRI is valid, the communication session will be directly restored.

[0059] Traditional handshake processes (such as the TLS handshake) typically involve multiple rounds of interaction, including authentication, key exchange, and cryptographic negotiation. The SRI mechanism, however, allows for: 1) reusing previous communication session data, avoiding key renegotiation; 2) directly restoring the previous cryptographic context, reducing handshake latency; and 3) quickly locating the session via SRI, improving recovery speed. This means that after network recovery, the client can immediately initiate data transmission using SRI without re-establishing a connection, thus skipping the complex handshake process.

[0060] It should also be noted that in determining the second communication state through interruption detection, methods such as increased latency and packet loss rate can be used. For example, if the packet loss rate is greater than the corresponding first loss rate threshold, the second communication state indicates a communication interruption; if the packet loss rate is less than the first loss rate threshold, the second communication state indicates a non-communication interruption. Furthermore, in practical applications, to ensure the accuracy of the interruption detection results, multiple signal sources (such as 4G, 5G, and Wi-Fi) can be used for cross-validation to determine whether the second communication state is a communication interruption or a brief fluctuation.

[0061] It should be noted that if the first communication state is not a communication breakpoint, the previous first communication state needs to be considered. If the previous first communication state was not a communication breakpoint, no operation is performed. However, if the previous first communication state was a communication breakpoint, the first communication state switching from a communication breakpoint to a non-communication breakpoint indicates that the vehicle is about to leave the communication blind spot. The specific implementation of this application embodiment will be described later.

[0062] In one possible implementation, to reduce the impact of communication breakpoints on the vehicle, embodiments of this application may also attempt to prioritize uploading important session data to the cloud after predicting a communication breakpoint. To this end, embodiments of this application provide a vehicle-to-cloud communication breakpoint detection method, where the communication session data includes session data from multiple communication sessions. After caching the communication session data, the method may further include the following steps:

[0063] The upload order of multiple communication sessions is determined based on their service priorities; the session data of each communication session is uploaded to the cloud sequentially by switching the communication protocol of the communication channel according to the upload order; and the session data of successfully uploaded communication sessions is deleted from the communication session data.

[0064] In this embodiment, after the session data of multiple communication sessions has been cached, the upload order of the multiple communication sessions is determined by comparing the service priorities of each communication session. The higher the service priority of a communication session, the earlier it appears in the upload order. For example, the communication session data includes session data of communication session A (hereinafter referred to as session data a), communication session B (hereinafter referred to as session data b), and communication session C (hereinafter referred to as session data c). After session data a, session data b, and session data c have been cached, the service priorities of communication sessions A, B, and C can be compared, and the communication sessions can be sorted in descending order of service priority to obtain the upload order.

[0065] Assuming the upload order of communication sessions A, B, and C is: A → C → B, then session data a is uploaded first, followed by c, and finally b. Taking session data a as an example, when uploading session data a through the communication channel, different communication protocols can be switched. For example, HTTP can be used initially; if that fails, MQTT can be used; if that also fails, SOCKET can be used, and so on, until all defined communication protocols have been used. This determines whether session data a was successfully uploaded. In practical applications, a successful upload is confirmed by receiving a response from the cloud regarding session data a. If session data a is successfully uploaded, it is deleted from the cached communication session data.

[0066] In one possible implementation, communication session data can be cached individually according to different data types. See also Figure 3 , Figure 3 This is another schematic flowchart illustrating a vehicle-to-cloud communication breakpoint detection method provided in an embodiment of this application. Figure 3 As shown in the embodiment of this application, a vehicle-to-cloud communication breakpoint detection method is provided. In step S102, "caching communication session data" may include steps S1021 to S1022. These steps are described in detail below.

[0067] S1021, Determine the data type of the communication session data.

[0068] S1022, cache communication session data according to data type.

[0069] In this embodiment of the application, for the session data of each communication session in the communication session data, the data type of the session data can be determined. For example, the data type can be divided into sensitive data (i.e. data related to user security, such as user identity data), temporary data (i.e. data that can be lost, such as periodically generated GPS data) and plaintext data (mainly log data).

[0070] If the session data is sensitive, it can be encrypted and stored using an encrypted database to protect user privacy. If the session data is temporary, it can be stored in memory to improve access speed and reduce storage costs. If the session data is plaintext, it can be packaged into a file and stored on the hard drive to enable the storage of large amounts of data.

[0071] S103, when the second communication state is a communication interruption, enable the session recovery identifier, load the communication session data, use the session recovery identifier to restore the communication channel, and upload the communication session data to the cloud through the communication channel.

[0072] In this embodiment, if the second communication state is a communication interruption, it indicates that the communication channel with the cloud has indeed been interrupted. In this case, SRI is enabled, cached communication session data is loaded, and an attempt is made to restore the communication channel with the cloud using SRI. During the session recovery process, the cloud performs context recovery based on SRI, which mainly includes:

[0073] 1) SRI parsing: When the client reconnects, the cloud receives the SRI and checks its validity; 2) Loading cache: The cloud will look up session data related to the SRI (such as authentication status, encryption keys, etc.); 3) Resuming communication: If the SRI is valid and the data is complete, the cloud directly resumes the connection without needing to re-verify the identity or exchange keys; 4) Deduplication mechanism: The cloud can identify the transmitted data through the SRI, avoiding the generation of duplicate data and improving communication efficiency.

[0074] The use of SRI has significantly improved network recovery efficiency, especially in scenarios with high real-time requirements such as autonomous driving, remote control, and IoT devices.

[0075] Furthermore, once the communication channel with the cloud is restored, communication session data can be successfully uploaded to the cloud through this channel. Therefore, SRI can be used to quickly restore the communication channel with the cloud, skipping the traditional handshake process and avoiding data loss that could affect service continuity.

[0076] It should be noted that if the second communication state is not a communication breakpoint, no operation will be performed.

[0077] In one possible implementation, during the communication channel interruption and waiting for recovery, the operation to restore the communication channel can be automatically retried periodically. See also Figure 4 , Figure 4 This is another schematic flowchart illustrating a vehicle-to-cloud communication breakpoint detection method provided in an embodiment of this application. Figure 4 As shown in the embodiment of this application, a vehicle-to-cloud communication breakpoint detection method is provided. In step S103, "using a session recovery identifier to restore the communication channel" may include steps S1031 to S1032. These steps are described in detail below.

[0078] S1031, The communication channel is restored using the session recovery identifier according to the first time interval.

[0079] In this embodiment of the application, after determining that the second communication state is a communication breakpoint, and enabling SRI and loading communication session data, the operation of restoring the communication channel using the session recovery identifier can be performed periodically according to the first time interval.

[0080] S1032, when the recovery time of the communication channel reaches the corresponding time threshold, output the warning information, persist the communication session data, and restore the communication channel using the session recovery identifier according to the second time interval, the second time interval being greater than the first time interval.

[0081] In this embodiment, the recovery time of restoring the communication channel according to the first time interval is recorded. If the recovery time reaches the corresponding time threshold, it indicates that the communication channel interruption time with the cloud is too long. At this time, on the one hand, a warning message can be output to remind the driver and the problem log can be sent to the support center. On the other hand, the communication session data is persisted locally (i.e., saved on the local hard disk) to avoid data loss. Furthermore, the operation of restoring the communication channel using the session recovery identifier is executed periodically according to the second time interval. The second time interval is longer than the first time interval, which can reduce the performance consumption of the vehicle.

[0082] For example, after determining that the second communication state is a communication breakpoint, enabling SRI, and loading communication session data, the operation of restoring the communication channel using the session recovery identifier is performed every 2 seconds. After accumulating 2 minutes, an early warning message is output, the communication session data is persisted, and the operation of restoring the communication channel using the session recovery identifier is performed every 1 minute until the communication channel is restored.

[0083] In one possible implementation, if it is predicted that the vehicle is about to leave the communication blind spot, reconnection to the cloud can be more frequent to restore cloud services more quickly. To this end, this application provides a vehicle-to-cloud communication breakpoint detection method, wherein step S103, "using a session recovery identifier to restore the communication channel," may further include the following steps:

[0084] When the first communication state changes from a communication breakpoint to a non-communication breakpoint, the communication channel is restored using a session recovery identifier according to a third time interval, which is shorter than the first time interval.

[0085] In this embodiment of the application, if the first communication state changes from a communication breakpoint to a non-communication breakpoint, it indicates that the communication channel with the cloud is about to be restored and the vehicle is about to leave the communication blind spot. At this time, the operation of restoring the communication channel using the session restoration identifier can be performed periodically according to the third time interval, which is less than the first time interval.

[0086] To continue with the example above, after performing the operation of restoring the communication channel using the session recovery identifier every 1 minute, after predicting that the vehicle is about to leave the communication blind spot, the operation of restoring the communication channel using the session recovery identifier is performed every 1 second to restore the communication channel with the cloud in the shortest possible time.

[0087] Based on the above description, the vehicle-to-cloud communication breakpoint detection method provided in this application can pre-cachate communication session data to avoid data loss affecting service continuity. Furthermore, by using a session recovery identifier to restore reconnection with the cloud, it avoids re-handshaking, achieving rapid recovery, ensuring recovery efficiency, and improving the continuity and stability of vehicle-to-cloud communication. In addition, it can provide users with more reliable communication services in complex terrains such as tunnels and mountainous areas.

[0088] The above describes a vehicle-to-cloud communication breakpoint detection method provided by the embodiments of this application. The following will describe the apparatus for performing the above vehicle-to-cloud communication breakpoint detection method.

[0089] See Figure 5 , Figure 5 This is a schematic diagram of a vehicle-to-cloud communication breakpoint detection device provided in an embodiment of this application. Figure 5 As shown in the figure, an embodiment of this application provides a vehicle-to-cloud communication breakpoint detection device, comprising:

[0090] The breakpoint prediction module 501 is used to acquire vehicle operation data and predict the first communication state of the communication channel with the cloud based on the vehicle operation data.

[0091] The breakpoint detection module 502 is used to generate a session recovery identifier and cache communication session data when the first communication state is a communication breakpoint, and at the same time determine the second communication state of the communication channel through interruption detection.

[0092] The data upload module 503 is used to enable the session recovery identifier, load the communication session data, restore the communication channel using the session recovery identifier, and upload the communication session data to the cloud through the communication channel when the second communication state is a communication interruption.

[0093] In one possible implementation, the communication session data includes session data from multiple communication sessions, and the breakpoint detection module 502 is further used for:

[0094] The upload order of multiple communication sessions is determined based on their service priorities; the session data of each communication session is uploaded to the cloud sequentially by switching the communication protocol of the communication channel according to the upload order; and the session data of successfully uploaded communication sessions is deleted from the communication session data.

[0095] In one possible implementation, the breakpoint prediction module 501, used to predict the first communication state of the communication channel with the cloud based on vehicle operation data, is specifically used for:

[0096] When the vehicle operation data is multimodal, the data features of each modality in the vehicle operation data are extracted and the extracted data features are fused. The feature fusion result is input into the trained prediction model and the first communication state output by the prediction model is obtained. The prediction model is trained based on machine learning algorithm.

[0097] In one possible implementation, the breakpoint detection module 502 for caching communication session data is specifically used for:

[0098] Determine the data type of the communication session data; cache the communication session data according to the data type.

[0099] In one possible implementation, the data upload module 503 for restoring the communication channel using a session recovery identifier is specifically used for:

[0100] The communication channel is restored using the session recovery identifier according to the first time interval;

[0101] If the recovery time of the communication channel reaches the corresponding time threshold, an early warning message is output, the communication session data is persistently saved, and the communication channel is restored using the session recovery identifier according to the second time interval, which is greater than the first time interval.

[0102] In one possible implementation, the data upload module 503, used to restore the communication channel using a session recovery identifier, is also used for:

[0103] When the first communication state changes from a communication breakpoint to a non-communication breakpoint, the communication channel is restored using a session recovery identifier according to a third time interval, which is shorter than the first time interval.

[0104] It should be noted that the detailed functions of each module in the embodiments of this application can be found in the corresponding disclosure of the above-mentioned vehicle-cloud communication breakpoint detection method embodiments, and will not be repeated here.

[0105] This application also provides an electronic device in its embodiments. See also... Figure 6 , Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device in this embodiment may include, but is not limited to, fixed terminals such as mobile phones, laptops, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, etc. Figure 6 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0106] like Figure 6As shown, the electronic device may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. When the electronic device is powered on, the RAM 603 also stores various programs and data required for the operation of the electronic device. The processing unit 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0107] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 607 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 608 including, for example, memory cards, hard drives, etc.; and communication devices 609. Communication device 609 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 6 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have alternatively.

[0108] This application also provides a computer program product including computer-readable instructions, which, when executed on an electronic device, cause the electronic device to implement any of the vehicle-to-cloud communication breakpoint detection methods provided in this application.

[0109] This application also provides a computer-readable storage medium that carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement any of the vehicle-to-cloud communication breakpoint detection methods provided in this application.

[0110] It should also be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. In addition, in the device embodiment drawings provided in this application, the connection relationship between modules indicates that they have a communication connection, which can be implemented as one or more communication buses or signal lines.

[0111] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware, or it can be implemented by special-purpose hardware including application-specific integrated circuits, special-purpose CPUs, special-purpose memory, special-purpose components, etc. Generally, any function performed by a computer program can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be diverse, such as analog circuits, digital circuits, or special-purpose circuits. However, for this application, software program implementation is more often the preferred implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium, such as a computer floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk, or optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, training equipment, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0112] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product.

[0113] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, training device, or data center to another website, computer, training device, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives (SSDs)).

Claims

1. A method for detecting breakpoints in vehicle-to-cloud communication, characterized in that, The vehicle-to-cloud communication breakpoint detection method is applied to the vehicle side, and the vehicle-to-cloud communication breakpoint detection method includes: Acquire vehicle operation data and predict the first communication state of the communication channel with the cloud based on the vehicle operation data; In the case of a communication interruption in the first communication state, a session recovery identifier is generated and communication session data is cached. At the same time, the second communication state of the communication channel is determined by interruption detection. When the second communication state is a communication interruption, the session recovery identifier is activated, the communication session data is loaded, the communication channel is restored using the session recovery identifier, and the communication session data is uploaded to the cloud through the communication channel.

2. The vehicle-to-cloud communication breakpoint detection method according to claim 1, characterized in that, The communication session data includes session data from multiple communication sessions. After caching the communication session data, the vehicle-to-cloud communication breakpoint detection method further includes: The upload order of the multiple communication sessions is determined based on the service priority of the multiple communication sessions; According to the upload order, the session data of each communication session is uploaded to the cloud sequentially by switching the communication protocol of the communication channel; Delete the session data of the successfully uploaded communication session from the communication session data.

3. The vehicle-to-cloud communication breakpoint detection method according to any one of claims 1 to 2, characterized in that, The first communication state of the communication channel between the vehicle and the cloud, predicted based on the vehicle operation data, includes: When the vehicle operation data is multimodal data, the data features of each mode in the vehicle operation data are extracted, and the extracted data features are fused. The feature fusion result is input into the trained prediction model, and the first communication state output by the prediction model is obtained. The prediction model is trained based on a machine learning algorithm.

4. The vehicle-to-cloud communication breakpoint detection method according to any one of claims 1 to 3, characterized in that, The cached communication session data includes: Determine the data type of the communication session data; The communication session data is cached according to the data type described.

5. The vehicle-to-cloud communication breakpoint detection method according to any one of claims 1 to 4, characterized in that, The step of restoring the communication channel using the session recovery identifier includes: The communication channel is restored using the session recovery identifier at a first time interval; If the recovery time of the communication channel reaches the corresponding time threshold, an early warning message is output, the communication session data is persistently saved, and the communication channel is restored using the session recovery identifier according to a second time interval, wherein the second time interval is greater than the first time interval.

6. The vehicle-to-cloud communication breakpoint detection method according to claim 5, characterized in that, The step of restoring the communication channel using the session recovery identifier further includes: When the first communication state changes from a communication breakpoint to a non-communication breakpoint, the communication channel is restored using the session recovery identifier according to a third time interval, the third time interval being less than the first time interval.

7. A vehicle-to-cloud communication breakpoint detection device, characterized in that, The vehicle-to-cloud communication breakpoint detection device is applied to the vehicle end, and the vehicle-to-cloud communication breakpoint detection device includes: The breakpoint prediction module is used to acquire vehicle operation data and predict the first communication state of the communication channel with the cloud based on the vehicle operation data. The breakpoint detection module is used to generate a session recovery identifier and cache communication session data when the first communication state is a communication breakpoint, and at the same time determine the second communication state of the communication channel through interruption detection. The data upload module is used to enable the session recovery identifier, load the communication session data, restore the communication channel using the session recovery identifier, and upload the communication session data to the cloud through the communication channel when the second communication state is a communication interruption.

8. A computer program product, characterized in that, It includes computer-readable instructions that, when executed on an electronic device, cause the electronic device to implement the vehicle-to-cloud communication breakpoint detection method as described in any one of claims 1 to 6.

9. An electronic device, characterized in that, It includes at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program so that the electronic device can implement the vehicle-to-cloud communication breakpoint detection method as described in any one of claims 1 to 6.

10. A computer storage medium, characterized in that, The storage medium carries one or more computer programs, which, when executed by an electronic device, enable the electronic device to implement the vehicle-to-cloud communication breakpoint detection method as described in any one of claims 1 to 6.

Images