Update system for updating software in a motor vehicle and procedures

Abstract

The invention relates to an update system (10) for updating software in a motor vehicle (OBJ.1), comprising: a connection module configured to establish a communication link between a mobile device (OBJ.2) and the motor vehicle (OBJ.1), an information retrieval module configured to receive vehicle-specific metadata, including a vehicle identification number, from the motor vehicle (OBJ.1), a transmission module configured to transfer corresponding vehicle-specific software and / or a vehicle-specific anomaly detection model from a manufacturer's backend (OBJ.3) to the mobile device (OBJ.2), and an update module configured to transmit software updates from the mobile device (OBJ.2) to at least one control unit of the motor vehicle (OBJ.1).1) to transfer and initiate the installation of an AI module, which is designed to analyze vehicle-related data and / or personal data locally on the vehicle's mobile device (OBJ.2) and to detect anomalies in real time and, depending on the detected anomalies, to automatically request a software update via an over-the-air method. Furthermore, the invention relates to a method.

Description

[0001] The invention relates to an update system for updating software in a motor vehicle according to claim 1. Furthermore, the invention relates to a method for operating an update system for updating software in a motor vehicle.

[0002] Such update systems are used in vehicle design to provide software versions of a control unit via a mobile device and a backend, thereby enabling timely adjustments to functional scopes and / or corrections.

[0003] US patent application US20150230044A1 discloses a smartphone-based update system that transfers software files from a manufacturer's server to a mobile phone, which then transmits the data to a control unit via Bluetooth and / or USB. This describes a cloud-based concept in which analysis and decision-making take place on the server, while the mobile phone essentially serves as a transmission station.

[0004] The object of the invention is to further develop an update system that enables improved processing and control of software-related update processes in the environment of a motor vehicle.

[0005] This problem is solved by means of an update system with the features of claim 1, and by means of a method according to the invention. Advantageous embodiments of the update system according to the invention are to be regarded as advantageous embodiments of the method according to the invention, wherein the means of the update system can be used to carry out the respective method steps. Furthermore, advantageous developments of the invention are described by the dependent claims, the following description, and by exemplary embodiments.

[0006] One aspect of the invention relates to an update system designed for software-based communication between a mobile device and a motor vehicle, in particular a passenger car. The update system comprises a connection module that establishes a data connection between the mobile device and the motor vehicle. Furthermore, an information retrieval module is provided that receives vehicle-specific metadata, including a vehicle identification number, from the motor vehicle. A transmission module is configured to transfer corresponding vehicle-specific software and / or a vehicle-specific anomaly detection model from a backend to the mobile device. An update module forwards software updates to at least one control unit of the motor vehicle and initiates their installation.An AI module performs a local analysis of vehicle-related and / or personal data on the mobile device, enabling the real-time detection of anomalies. Depending on the detected anomalies, the AI ​​module automatically requests over-the-air (OTA) updates. These modules are interconnected via data and / or signal technology, thus providing a closed-loop process for data acquisition, analysis, and updates. The term "AI module" used in the claim is also equivalent to "on-device AI," specifically referring to an implementation where all processing takes place entirely on the mobile device.

[0007] In order to solve the problem of the invention and thus provide improved processing and control of software-related update processes in the environment of a motor vehicle, it is provided according to the invention that an AI module analyzes vehicle-related data and / or personal data locally on the mobile device and automatically requests an OTA update depending on detected anomalies.

[0008] The AI ​​module can include an evaluation pipeline running on the mobile device, which can, for example, receive sensor data streams from the vehicle. An internal interface can provide, for instance, a model for anomaly detection that is tailored to vehicle-specific parameters. Additionally, control logic can be included, which, for example, implements threshold evaluation and / or a decision-making process to trigger an update request.

[0009] The interaction between the AI ​​module and the transmission module can take place via a defined application programming interface (API), thereby generating, for example, a structured and consistent request to the backend. This design enables decentralized, vehicle-side analysis, where processing essentially occurs locally on the mobile device, thus reducing dependence on a cloud and increasing the security of data transmission.

[0010] In a particularly advantageous embodiment of the invention, the AI ​​module employs differential privacy mechanisms to protect personal data and to perform a data-minimized, low-latency, and / or privacy-compliant update of the vehicle, thereby reducing the exposure of sensitive information. For this purpose, the AI ​​module can, for example, inject noise according to a defined budget or use aggregations, whereby parameter selection and / or output limitation are designed to ensure that a usable model output remains. The connection to the transmission module is established via a metadata format that provides exclusively aggregated and / or anonymized information, thus preventing any inferences about individuals.

[0011] In a further advantageous embodiment of the invention, the AI ​​module loads and executes a vehicle-specific machine learning model provided by the backend locally on the mobile device. Processing takes place exclusively on the mobile device, enabling network-independent analysis. The loading process can be versioned and / or signature-verified, for example, with a model cache provided. The connection to the information retrieval module uses the vehicle identification number (VIN) to select a suitable model. Interaction with the update module ensures that recognized patterns can be immediately translated into an update request.

[0012] In a further advantageous embodiment of the invention, the AI ​​module correlates sensor data and / or diagnostic error codes of the motor vehicle with locally stored personal data, in particular health data, driving behavior data, or appointment information, thus enabling personalized driving or maintenance recommendations. Correlation can be achieved, for example, via timestamps and / or event IDs, with an assignment module merging the data streams. The connection to the connection module provides the continuous input of sensor data, while a local data domain for personal information remains strictly on the mobile device.

[0013] In a further advantageous embodiment of the invention, the transmission module automatically transmits an OTA update request to the backend in the event of an anomaly detected by the AI ​​module. Upon receiving approval, the corresponding software update is then transferred to the update module, thus enabling closed-loop control. The transmission module can provide a secure protocol path and / or include acknowledgment logic for this purpose. The connection to the update module is established via a package management system that performs integrity checks and / or version control.

[0014] In a further advantageous embodiment of the invention, the AI ​​module transmits the results of local anomaly detection to the backend in aggregated and / or anonymized form to support the improvement of vehicle-specific models and software versions, without transmitting raw data or personal information, thus enabling feedback for development. The aggregation can be provided, for example, as a histogram and / or as a quantized time series. The relationship to the information retrieval module ensures that the aggregation is assigned to the correct vehicle class.

[0015] Another aspect of the invention relates to a method for operating an update system for updating software in a motor vehicle, in which a communication link is established between a mobile device and the motor vehicle by means of a connection module, vehicle-specific metadata including a vehicle identification number is received by means of an information retrieval module, corresponding vehicle-specific software and / or a vehicle-specific anomaly detection model is transferred from a backend to the mobile device by means of a transmission module, software updates are transferred to at least one control unit and the installation is initiated by means of an update module, and vehicle-related data and / or personal data are analyzed locally by means of an AI module, whereby anomalies are detected in real time and OTA updates are requested.The interaction of the process steps takes place via modular interfaces between the aforementioned modules, thereby providing a reproducible process logic and / or enabling operation adapted to the vehicle architecture.

[0016] In other words, the update system is intended to not only include the aforementioned modules, but also to provide signature verification and / or version control within the update module, which supports consistency of the installed software version.

[0017] Additionally, intermediate storage can be integrated within the transmission module, enabling packet-wise transmission of the software data.

[0018] The interaction between the AI ​​module and the transmission module can take place via a prioritizable event interface, which allows, for example, urgent anomalies to be handled preferentially.

[0019] This comprehensive design essentially leads to a more vehicle-centric, decentralized, and security-protected update that goes beyond the known state of the art, particularly since cloud dependency is avoided and / or local anomaly detection can be provided.

[0020] The invention takes into account the increasing demand for intelligent, connected vehicles that improve aspects of safety, user support, and driving comfort. Modern vehicles generate a wealth of data through sensors and telematics systems, which has so far only been used to a limited extent for directly improving the driving experience. At the same time, personal mobile devices equipped with powerful AI chips possess valuable user data such as health data, schedules, and preferences, which have not yet been technically linked to the vehicle's systems.

[0021] Well-known automotive solutions predominantly rely on cloud-based processing, which entails both data protection risks and leads to latency in safety-relevant applications, such as anomaly detection.

[0022] Furthermore, existing systems lack seamless integration between vehicle data and personal data, which limits holistic and personalized operation.

[0023] The present invention closes this gap by providing the mobile device as a central interface through which vehicle and personal data can be combined.

[0024] Local processing using on-device AI allows this data to be analyzed in real time, thereby improving data protection and response speed in particular.

[0025] The mobile device acts as an intelligent processing unit, detecting anomalies and initiating update processes without requiring cloud-based analysis.

[0026] Furthermore, the update system can enable proactive maintenance through over-the-air (OTA) updates, allowing vehicle problems to be detected and resolved early.

[0027] This approach aligns with current trends towards connected mobility, data-reduced communication, and enhanced data protection, thus meeting the requirements of both manufacturers (OEMs) and end users. By combining these technological concepts, a novel solution is provided that enables smarter, safer, and more flexible updates of software components in the vehicle environment.

[0028] In summary, the invention relates to a mobile-based update system that integrates vehicle and personal data and can detect anomalies in real time using on-device sensors.

[0029] The system enables automated and vehicle-related control of software updates via OTA procedures, thereby contributing to improved safety and functionality of the vehicle.

[0030] Local data processing on the mobile device ensures a high level of data protection, while at the same time aggregated and anonymized insights can be transmitted to the manufacturer to further develop future software versions and vehicle-specific models.

[0031] Further advantages, features, and details of the invention will become apparent from the following description of a preferred embodiment and from the drawing. The features and combinations of features mentioned above in the description, as well as those mentioned below in the figure description and / or shown in the figure alone, can be used not only in the combinations specified, but also in other combinations or individually, without departing from the scope of the invention.

[0032] This shows: Fig. 1 A block diagram illustrating a possible embodiment of an update system for updating software in a motor vehicle.

[0033] In the figure, identical or functionally equivalent elements are provided with the same reference symbols.

[0034] Fig. Figure 1 shows a block diagram illustrating a possible embodiment of an update system 10 for updating software in a motor vehicle.

[0035] The update system 10 includes, in particular: - a connection module designed to establish a communication link between a mobile device and a motor vehicle OBJ.1, - an information retrieval module trained to receive vehicle-specific metadata, including a vehicle identification number, from the motor vehicle OBJ.1, - a transmission module designed to transfer corresponding vehicle-specific software and / or a vehicle-specific anomaly detection model from a manufacturer's backend OBJ.3 to the mobile device OBJ.2, - an update module designed to transfer software updates from the mobile device OBJ.2 to at least one control unit of the motor vehicle OBJ.1 and to initiate their installation, and - an AI module that is trained to analyze vehicle-related data and / or personal data locally on the mobile device OBJ.2 and to detect anomalies in real time and to automatically request a software update via an over-the-air (OTA) procedure depending on the detected anomalies.

[0036] The update system 10 thus comprises three overarching functional components: the vehicle OBJ.1, the mobile device OBJ.2 with integrated AI module, and the backend OBJ.3, which is designed as the manufacturer's server infrastructure. Several communication and processing steps, designated FUNC.1 to FUNC.10, are provided between these three components and illustrate the process of the update system 10.

[0037] The vehicle OBJ.1 is designed to provide vehicle-related data, vehicle-specific metadata, and encrypted protocols, as well as to receive and install software updates. The mobile device OBJ.2 is designed to establish a data connection with the vehicle OBJ.1, analyze received vehicle data locally, and, depending on detected anomalies, transmit a software request to the backend OBJ.3. The backend OBJ.3 is designed to provide vehicle-specific software, anomaly detection models, and approvals for over-the-air (OTA) updates, and to transmit these to the mobile device OBJ.2 and / or directly to the vehicle OBJ.1.

[0038] In a first process step FUNC.1, the mobile device OBJ.2 sends a communication request to the vehicle OBJ.1 via the connection module in order to establish a data connection.

[0039] In a second process step FUNC.2, vehicle-specific information, in particular a vehicle identification number (VIN) and other metadata, is transmitted from the motor vehicle OBJ.1 to the mobile device OBJ.2 using the information retrieval module.

[0040] In a third process step FUNC.3, the mobile device OBJ.2 requests a vehicle-specific anomaly detection model from the backend OBJ.3 via the transmission module.

[0041] In a fourth process step FUNC.4, the backend OBJ.3 transmits the requested model to the mobile device OBJ.2, whereby a signature-secured and encrypted transmission is provided.

[0042] In a fifth process step FUNC.5, the mobile device OBJ.2 requests current vehicle data from the motor vehicle OBJ.1, in particular sensor data, diagnostic error codes or operating parameters.

[0043] In a sixth process step FUNC.6, the motor vehicle OBJ.1 transmits encrypted protocols to the mobile device OBJ.2 to provide additional context information for local analysis.

[0044] Within the OBJ.2 mobile device, two internal process loops are provided that map the operation of the AI ​​module.

[0045] In a first loop FUNC.7.1, the AI ​​module can apply differential privacy mechanisms to protect personal data and enable privacy-compliant analysis.

[0046] In a second loop FUNC.7.2, the AI ​​module performs real-time anomaly detection, combining vehicle-related data with locally stored personal data to identify deviations or optimization potentials.

[0047] If an anomaly is detected during the analysis, the mobile device OBJ.2 transmits a software request to the backend OBJ.3 via the OTA procedure in an eighth process step FUNC.8.

[0048] The backend OBJ.3 is scheduled in a ninth process step FUNC.9 to transfer a new software version to the motor vehicle OBJ.1.

[0049] Finally, in a tenth process step FUNC.10, the motor vehicle OBJ.1 installs the received software via the update module, thereby updating the affected control units.

[0050] Through these in Fig. The interaction of the modules shown in Figure 1 provides a decentralized, vehicle-oriented and cloud-independent processing chain.

[0051] The AI ​​module of the OBJ.2 mobile device enables local analysis with low latency and reduced data outflow, resulting in a secure and directly operating update.

[0052] The Fig. Figure 1 thus illustrates the technical implementation of the update system 10 described in claim 1, in which all modules are interconnected via a signal coupling and form a closed sequence for software-supported maintenance and anomaly detection in the motor vehicle.

[0053] The in Fig. The embodiment shown in Figure 1 serves only for illustration and does not limit the scope of protection of the invention.

[0054] In summary, the proposal suggests an “AI-Based Vehicle & Personal Data Fusion for Vehicle Diagnostics Analysis and OTA Software Updates”. QUOTES INCLUDED IN THE DESCRIPTION

[0000] This list of documents cited by the applicant was automatically generated and is included solely for the reader's convenience. The list is not part of the German patent or utility model application. The DPMA accepts no liability for any errors or omissions. Cited patent literature

[0000] US 20150230044A1

[0003] Cited non-patent literature

[0000] Invention of an “AI-Based Vehicle & Personal Data Fusion for Vehicle Diagnostics Analysis and OTA Software Updates

[0054]

Claims

[1] Update system (10) for updating software in a motor vehicle (OBJ.1), comprising: - a connection module designed to establish a communication link between a mobile terminal (OBJ.2) and the motor vehicle (OBJ.1), - an information retrieval module which is trained to receive vehicle-specific metadata, including a vehicle identification number, from the motor vehicle (OBJ.1), - a transmission module designed to transfer corresponding vehicle-specific software and / or a vehicle-specific anomaly detection model from a manufacturer's backend (OBJ.3) to the mobile device (OBJ.2), and - an update module which is designed to transfer software updates from the mobile device (OBJ.2) to at least one control unit of the motor vehicle (OBJ.1) and to initiate their installation, - an AI module which is trained to analyze vehicle-related data and / or personal data locally on the mobile device (OBJ.2) on the vehicle side and to detect anomalies in real time and, depending on the detected anomalies, to automatically request a software update via an over-the-air procedure. [2] Update system (10) according to claim 1, characterized by , that the AI ​​module is trained to apply differential privacy mechanisms, which protect personal data and perform a data-minimized and / or low-latency and / or privacy-compliant update of the motor vehicle (OBJ.1). [3] Update system (10) according to any one of the preceding claims, characterized by, that the AI ​​module is trained to load and / or execute a vehicle-specific machine learning model provided by the backend (OBJ.3) locally on the mobile device (OBJ.2), with processing taking place exclusively on the mobile device (OBJ.2). [4] Update system (10) according to any one of the preceding claims, characterized by , that the AI ​​module is trained to correlate sensor data and / or diagnostic fault codes of the motor vehicle (OBJ.1) with locally stored personal data, in particular health data, driving behavior data or appointment information. [5] Update system (10) according to any one of the preceding claims, characterized bythat the transmission module is designed to automatically send an OTA update request to the backend (OBJ.3) in the event of an anomaly detected by the AI ​​module and, upon receipt of the release, to transfer the corresponding software update to the update module. [6] Update system (10) according to any of the preceding claims, characterized by that the AI ​​module is trained to transmit results of local anomaly detection to the backend (OBJ.3) in aggregated and / or anonymized form. [7] Method for operating an update system (10) for updating software in a motor vehicle (OBJ.1) wherein: - a communication connection is established between a mobile device (OBJ.2) and the motor vehicle (OBJ.1) by means of a connection module, - vehicle-specific metadata, including a vehicle identification number, are received from the motor vehicle (OBJ.1) by means of an information retrieval module, - corresponding vehicle-specific software and / or a vehicle-specific anomaly detection model is transferred from a manufacturer's backend (OBJ.3) to the mobile device (OBJ.2) by means of a transmission module, - software updates are transferred from the mobile device (OBJ.2) to at least one control unit of the motor vehicle (OBJ.1) via an update module and their installation is initiated, and - using an AI module, vehicle-related data and / or personal data are analyzed locally on the mobile device (OBJ.2) on the vehicle side in order to detect anomalies in real time and, depending on the detected anomalies, automatically request a software update via an over-the-air procedure.

Images