A method for providing an energy saving information of an at least in part electrically operated motor vehicle, a computer program product, as well as an energy saving system

Abstract

A method to provide energy saving information 10 to a user of an at least in part electrically operated motor vehicle 12 by an energy saving system 14 having a first electronic computing device 18 and

Description

FIELD OF THE INVENTION

[0001] The present invention relates to the field of automobiles. More specifically, the present invention relates to a method for providing an energy saving information of an at least in part electrically operated motor vehicle for a user of the motor vehicle by an energy saving system. Furthermore, the present invention relates to a corresponding computer program product, as well as to a corresponding energy saving system. BACKGROUND INFORMATION

[0002] Electric vehicles (EV) have a plurality of advantages compared to conventional gasoline or diesel-powered cars, such as low emissions and reduced fuel costs. However, one critical aspect of the EVs is energy conservation, which directly impacts their driving range and overall efficiency. There are several reasons why energy saving is crucial for electric vehicles. One of the most significant concerns for electric vehicle owners is range anxiety, or the fear of running out of battery power before reaching their destination. By optimizing energy use, EV-Drivers can extend their driving range introducing the frequency of charging stops. The battery used in electric vehicles are expensive and have a limited life span, typically lasting between 8 to 10 years or more, depending on usage and maintenance. By reducing the stress on the battery through energy-efficient driving, EV-Owners can prolong its life and reduce replacement costs. Although, EVs produce zero tail pipe emissions, their overall environmental impact depends on how they are charged. By using renewable energy sources such as solar or windpower to charge EVs, drivers can further reduce their carbon footprint and contribute a more sustainable feature. Energy-efficient driving can help EV-Owners save money on charging costs, as well as maintenant expenses. By reducing the frequency of charging stops, EV-Drivers can also save time and increase productivity. As the EV-market continues to grow, there is a need for innovative solutions to improve energy efficiency and reduce range anxiety. Developing new technologies such as regenerative breaking, adaptive cruise control and smart grid integration can help optimize energy use and enhance the overall driving experience.

[0003] Therefore, it is a need in the art to provide a solution to help a driver / user to save electric energy inside a motor vehicle in order to overcome the above mentioned problems. SUMMARY OF THE INVENTION

[0004] Therefore is an object of the present invention to provide a method, a corresponding computer program product, as well as a corresponding energy saving system, by which an energy saving information of an at least in part electrically operated motor vehicle can be provided for a user.

[0005] This object is solved by a method, a corresponding computer program product, as well as to a corresponding energy saving system according to the independent claims. Advantageous embodiments are presented in the dependent claims.

[0006] One aspect of the invention relates to a method for providing an energy saving information of an at least in part electrically operated motor vehicle for a user of the motor vehicle by an energy saving system. At least a destination input of the user is received by an input device of a first electronic computing device of the energy saving system. At least the destination input is transmitted to a second electronic computing device of the energy saving system, which is arranged outside of the motor vehicle. A potential route depending in at least the destination input is determined by the second electronic computing device. A first energy consumption of the motor vehicle is determined by the second electronic computing device depending on the potential route and depending on at least one current condition alongside the determined potential route by the second electronic computing device. At least the first energy consumption and the potential route are transmitted to the first electronic computing device by the second electronic computing device. A second energy consumption is determined depending on the first energy consumption and an individual user parameter by the first electronic computing device. The energy saving information is generated depending on the second energy consumption and the potential route by the first electronic computing device. The energy saving information is provided for the user by an output device of the first electronic computing device.

[0007] Therefore, an energy saving information can be provided in an improved manner for the user. In particular, the energy saving information is therefore configured for adapting a driving behavior and / or a driving mode and / or a route of the motor vehicle in order to save energy. The energy saving information is generated depending on current conditions alongside the route, for example, a weather condition or a traffic condition, and then transmitted back to the motor vehicle. Inside the motor vehicle, for example, the energy consumption is further adapted, in particular with individual parameters of the user, for example a historic driving behavior of the user. The energy saving information may be outputted via an output device, for example, a speaker device and / or a display device, wherein a hint may be given in order to save energy while driving the route.

[0008] In particular, the first electronic computing device may be arranged inside the motor vehicle. It is also possible, that, for example, for planning a route before driving the motor vehicle the first electronic computing device may be a personal computer or a mobile phone or a tablet. It is also possible, that, for example, the destination can be input via a smartphone and / or a tablet and the generating of the second energy consumption may be provided by an electronic computing device inside the motor vehicle.

[0009] Therefore, a holistic integration for generating the energy saving information is provided. The energy saving system combines for example cloud computing, in-vehicle modelling, and for example large language models to deliver real-time, dynamic efficiency recommendations. The energy saving system utilizes extensive data sets, including realtime traffic, weather, and road conditions, alongside vehicle-specific parameters and battery specifications. The energy saving system reduces energy consumption by optimizing route planning and driving behavior. It enhances battery life and reduces environmental impacts through the intelligent management of energy resources. The energy saving system may personalize the driving experience by adapting to individual habits and preferences, promoting more efficient EV usage.

[0010] According to an embodiment, the energy saving information is provided by a large language model. By using the large language model, a communication between the user and the first electronic computing device can be provided in an improved manner. Furthermore, the “conversation”, for example for providing the energy saving information, between the electronic computing device and the person can be provided with a large language model. A large language model, which may also be called language model, is in particular be referred to the context of natural language processing (NLP) and artificial intelligence (Al). A large language model is a type of artificial intelligence model that is trained on large amounts of text data to understand patterns, structures, and meaning in human language. A large language model typically refers to a model that has been trained on an extremely large dataset, often consisting of billions or even trillions of words. These models are capable of generating human-like texts, translating languages, summarizing documents, answering questions, and performing other language-related tasks with high accuracy and fluency. Large language models have many potential applications in areas such as a customer service, content creation, education and research. However, they also raise ethical, and society consensus related to bias, misinformation, and job displacement. As such, a large language model is an important approach to develop deployment of large language models with care under consideration of their potential impacts on individuals and society as a whole. Therefore, a large language model is used to train the systematic questioning techniques of the person.

[0011] In another embodiment, the first energy consumption is determined depending on a current weather condition alongside the potential route and / or a current traffic condition alongside the route and / or a road condition alongside the route. For example, beyond conventional navigation, the energy saving system analyzes real-time traffic, weather, and road conditions to recommend the most energy efficient routes. For longer journeys, the artificial intelligence predicts and incorporates optimal charging stops based on route energy consumption and available charging structure. Furthermore, offering alternative route proactively when the battery level is predicted to fall below a certain threshold, with recommended charging stops if necessary, is provided.

[0012] In another embodiment, as the individual user parameter a driving behavior of the user and / or usage of a comfort function of the motor vehicle is provided. For example, a driving habit of the user can be analyzed. For example, patterns in acceleration, breaking, and speed maintenance to adjust energy consumption estimates more precisely are integrated to the driver style / habit. Furthermore, the in vehicle feature usage can be used which considers the energy impact of using air condition, heating, entertainment systems, and other features, adjusting estimates accordingly. Furthermore, the vehicle load and conditions may be used. Factors like vehicle load, for example, passengers and cargo weight, and current battery health are additionally used for energy use predictions.

[0013] In another embodiment, as the energy saving information an alternative route to the potential route and / or a user specific driving behavior and / or a driving mode of the motor vehicle and / or the usage of a comfort function of the motor vehicle is provided. In particular, customized-energy-saving-tips can be provided. This offers personalized advice on adjusting driving habits, like speed modulation and acceleration patterns and optimizing vehicle feature used, for example climate control settings or furthermore to conserve energy. Furthermore, a scenario-based suggestion is provided. In particular, tailored recommendations for different driving scenarios, such as a city traffic versus highway, to maximize the efficiency are provided.

[0014] In another embodiment, the energy saving information comprises an impact information about the energy saving of a suggested adaption. Therefore, a sustainable impact assessment is provided, which provides a real-time impact tracking. This provides the users with insights into how their driving habits and route choices impacts energy consumption and carbon footprint, encouraging more sustainable driving practices. Therefore, explainable adjustments and feature impact analysis are provided. The expendability utilizes techniques to make the models adjustments understandable to users, explaining how different behaviors and feature use may impact energy consumption. Furthermore, the energy saving system may highlight which features and habits have the most significant effects on efficiency, empowering drivers with knowledge to make energy saving-decisions.

[0015] According to another embodiment, a feedback from the user to the energy saving information is receivable by the first electronic computing device. Therefore, an interactive feedback loop may be provided which engages users with real-time insights and suggestions, encouraging adjustments that lead to immediate and long-term efficiency improvements. Furthermore, the user can feedback the recommendation, for example that the user might use this recommendation or might not use this recommendation. Therefore, the first electronic computing device can learn, which recommendations are useful for the user and therefore can for example disregard energy saving information’s which were already disregarded by the user. Therefore, a highly comfortable energy saving information can be provided for the user.

[0016] According to another embodiment, a future anomaly for the potential route and / or a current anomaly at the current driving is detected by the first electronic computing device and the energy saving information is generated depending on such a detected anomaly. In particular, the anomaly detection is provided for efficiency insights. The first computing device as it generates the energy consumption estimates, it is also equipped with anomaly detection tool that lets it detect anomalies in vehicle status, features or user driving habits. This can be anomaly in vehicle status like tire pressure, vehicle load or user driving habits like acceleration or braking that are all features used to get more accurate energy consumption estimates in vehicle. Anomaly detection algorithms may help identify an alert uses to unusual patterns that may indicate inefficiencies or potential issues with vehicle performance. An impact analyzes may be performed. This assesses the energy impact of detected anomalies, providing target recommendations for addressing the issues. Additionally, the anomaly detection is done with respect to the data from pool of users on the cloud, so it is independent of the route. Therefore, the system can be adapted in real time in order to save energy in the electric vehicle.

[0017] In particular, the method is a computer-implemented method. Therefore, another aspect of the invention relates to a computer program product comprising program code means for performing a method according to the proceeding aspect.

[0018] Furthermore, the present invention relates to a non-transitory computer-readable storage medium comprising at least the computer program product according to the preceding aspect.

[0019] Furthermore, the present invention relates to an energy saving system for providing an energy saving information of an at least in part electrically operated motor vehicle for a user of the motor vehicle, comprising at least one first electronic computing device, one second electronic computing device, wherein the energy saving device is configured for performing a method according to the preceding aspect. In particular, the method is performed by the energy saving system.

[0020] Advantageous embodiments of the method are to be regarded as advantageous embodiments of the computer program product, the non-transitory computer-readable storage medium, as well as the energy saving system. The energy saving system therefore comprises means for performing the method.

[0021] A computing unit / electronic computing device may in particular be understood as a data processing device, which comprises processing circuitry. The computing unit can therefore in particular process data to perform computing operations. This may also include operations to perform indexed accesses to a data structure, for example a look-up table, LUT.

[0022] In particular, the computing unit may include one or more computers, one or more microcontrollers, and / or one or more integrated circuits, for example, one or more application-specific integrated circuits, ASIC, one or more field-programmable gate arrays, FPGA, and / or one or more systems on a chip, SoC. The computing unit may also include one or more processors, for example one or more microprocessors, one or more central processing units, CPU, one or more graphics processing units, GPU, and / or one or more signal processors, in particular one or more digital signal processors, DSP. The computing unit may also include a physical or a virtual cluster of computers or other of said units.

[0023] In various embodiments, the computing unit includes one or more hardware and / or software interfaces and / or one or more memory units.

[0024] A memory unit may be implemented as a volatile data memory, for example a dynamic random access memory, DRAM, or a static random access memory, SRAM, or as a non-volatile data memory, for example a read-only memory, ROM, a programmable read-only memory, PROM, an erasable programmable read-only memory, EPROM, an electrically erasable programmable read-only memory, EEPROM, a flash memory or flash EEPROM, a ferroelectric random access memory, FRAM, a magnetoresistive random access memory, MRAM, or a phase-change random access memory, PCRAM.

[0025] Further advantages, features, and details of the invention derive from the following description of preferred embodiments as well as from the drawings. The features and feature combinations previously mentioned in the description as well as the features and feature combinations mentioned in the following description of the figures and / or shown in the figures alone can be employed not only in the respectively indicated combination but also in any other combination or taken alone without leaving the scope of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The novel features and characteristic of the disclosure are set forth in the appended claims. The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and together with the description, serve to explain the disclosed principles. The same numbers are used throughout the figures to reference like features and components. Some embodiments of system and / or methods in accordance with embodiments of the present subject matter are now described below, by way of example only, and with reference to the accompanying figures.

[0027] The drawings show in:

[0028] Fig. 1 a schematic flow chart according to the embodiment of the method; and

[0029] Fig. 2 a schematic bloc diagram according to the embodiment of an energy saving system for performing an embodiment of a method.

[0030] In the figures the same elements or elements having the same function are indicated by the same reference signs. DETAILED DESCRIPTION

[0031] In the present document, the word "exemplary" is used herein to mean "serving as an example, instance, or illustration". Any embodiment or implementation of the present subject matter described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

[0032] While the disclosure is susceptible to various modifications and alternative forms, specific embodiments thereof have been shown by way of example in the drawing and will be described in detail below. It should be understood, however, that it is not intended to limit the disclosure to the particular forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternatives falling within the scope of the disclosure.

[0033] The terms “comprises”, “comprising”, or any other variations thereof, are intended to cover a non-exclusive inclusion so that a setup, device or method that comprises a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such setup or device or method. In other words, one or more elements in a system or apparatus preceded by “comprises” or “comprise” does not or do not, without more constraints, preclude the existence of other elements or additional elements in the system or method.

[0034] In the following detailed description of the embodiment of the disclosure, reference is made to the accompanying drawing that forms part hereof, and in which is shown by way of illustration a specific embodiment in which the disclosure may be practiced. This embodiment is described in sufficient detail to enable those skilled in the art to practice the disclosure, and it is to be understood that other embodiments may be utilized and that changes may be made without departing from the scope of the present disclosure. The following description is, therefore, not to be taken in a limiting sense.

[0035] Fig. 1 shows a schematic flow chart according to an embodiment of the method. In particular, Fig. 1 shows a method for providing an energy saving information 10 (Fig. 2) for an at least in part electrically operated motor vehicle 12 (Fig. 2) for a user of the motor vehicle 12 by an energy saving system 14 (Fig. 2). In a first step S1 at least a destination input of the user is received by an input device 16 (Fig. 2) of a first electronic computing device 18 (Fig. 2) of the energy saving system 14. In a second step S2 at least the destination input is transmitted to a second electronic computing device 20 (Fig. 2) of the energy saving system 14, which is arranged outside of the motor vehicle 12. A potential route depending on at least the destination input is determined by the second electronic computing device 20 in a third step S3. A first energy consumption 22 of the motor vehicle 12 is determined by the second electronic computing device 20 depending on the potential route and depending on at least one current condition alongside the determined potential route by the second electronic computing device 20 in a fourth step S4. In a fifth step S5 at least the first energy consumption 22 and the potential route is transmitted to the first electronic computing device 18 by the second electronic computing device 20. In a sixth step S6 a second energy consumption is determined depending on the first energy consumption 22 and an individual user parameter 24 by the first electronic computing device 18. The energy saving information 10 is generated depending on the second energy consumption and the potential route by the first electronic computing device 18 in a seventh S7 and in an eighth step S8 the energy saving information 10 is provided for the user by an output device 48 of the first electronic computing device 18.

[0036] Fig. 2 shows a schematic block diagram according to an embodiment of the energy saving system 14. In particular, Fig. 2 shows that the energy saving information 10 is provided by a large language model 26. Furthermore, it is shown, that the first energy consumption 22 may be determined depending on a current weather condition alongside the potential route and / or a current traffic condition alongside the route and / or a road condition alongside the route, which is shown in Fig. 2 with so-called real time features 28. Furthermore, road conditions 30 are shown.

[0037] Furthermore, Fig. 2 shows that as the individual user parameter 24 a driving behavior 32 of the user and / or the usage of a comfort function 34 of the motor vehicle 12 is provided.

[0038] Furthermore, Fig. 2 shows that as the energy saving information 10 an alternative route to the potential route and / or a user specific driving behavior and / or a driving mode of the motor vehicle 12 and / or the usage of the comfort function 34 of the motor vehicle 12 is provided.

[0039] Furthermore, the energy saving information 10 may comprise an impact information about the energy saving of an adjusted adaption. In another embodiment, a feedback from the user to the energy saving information 10 is receivable by the first electronic computing device 18. Furthermore, an anomaly detector 36 is shown. With the anomaly detector 36, a feature anomaly for the potential route and / or a current anomaly at the driving is detected by the first electronic computing device 18 and the energy saving information 10 is generated depending on such a detected anomaly.

[0040] Fig. 2 further shows a so-called model explainer 38 as well as a so-called in-vehicle model 40. Furthermore, an in-cloud model 42 is shown. The model explainer 38 may estimate the impact of each feature on a SOC (State of charge) estimation of the battery of the motor vehicle 12.

[0041] With the shown embodiment of the energy saving system 14 a dynamic and efficient route, planning can be provided. In particular, a context-sensitive navigation is provided. Beyond conventional navigation, the energy saving system 14 analyzes realtime traffic, weather, and road conditions 30 to recommend the most energy-efficient routes. Furthermore, predictive charging stop integration is provided. For example, for longer journeys, the energy saving system 14 intelligently predicts and incorporates optimal charging stops based on route energy consumption and available charging infrastructure. The energy saving system 14 may further offer alternative routes proactively when the battery level is predicted to fall below a certain threshold, with recommended charging stops if necessary.

[0042] Furthermore, personalized driving efficiency recommendations can be provided by the energy saving system 14. Therefore, customized energy-saving tips can be provided. The energy saving system 14 offers personalized advice on adjusting driving habits, like speed modulation and acceleration patterns, and for optimizing vehicle feature used for example climate control settings, in order to conserve energy. Furthermore, scenario-based suggestions can be provided. The energy saving system 14 generates individual recommendations for different driving scenarios, such as city traffic versus highway to maximize efficiency.

[0043] Furthermore, an interactive learning and feedback loop is provided by the energy saving system 14. The driving behavior of the user can continuously monitored by the energy saving system 14. The energy saving system 14 continuously learns from the user’s actions and preferences to refine its recommendations, making each trip more efficient than the last. The user can provide feedback on recommendations, further personalizing the energy saving system 14 enhancing its accuracy over time. A real-time impact tracking can be provided by the energy saving system 14. The energy saving system 14 therefore provides users with insights into how their driving habits and route choices impact energy consumptions and carbon footprint, encouraging more sustainable driving practices.

[0044] In particular, a user interface 44 can be used to provide the energy saving information 10. The user interface 44 ensures to an intuitive and easy navigation, displaying essential information such as estimated battery usage, and range prominently. Graphical representation of routes with color-coded segments indicating energy consumption levels may be provided. Furthermore, real-time data can be integrated and can be updated for traffic and weather, reflecting instant changes in energy consumption on each segment of the route and consequently changes in route recommendations..

[0045] The system allows users to customize their route preferences, such as choosing between the fastest, most efficient, or a balanced route. Additionally, an adaptive algorithm can be implemented to personalize routes based on individual needs, providing battery usage predictions accordingly. The user interface 44 also offers optimized route options for energy efficiency, taking into account real-time traffic and weather conditions. Furthermore, the user interface 44 can display range estimates and suggest charging stops when needed. For instance, the in-cloud model 42 can provide a segmented navigation solution. This approach divides the route into distinct segments and predicts battery consumption for each segment by considering both static and dynamic route parameters, as well as the vehicle's status. By aggregating the energy consumption for each segment, the system can accurately estimate the total energy consumption for the entire trip with high precision. The in-cloud model 42 leverages road characteristics and real-time conditions to dynamically estimate battery consumption for specific routes. This cloud-based architecture enables model training and inference by utilizing cloud computing, ensuring access to real-time data. Detailed datasets can be integrated, such as road type conditions, which include information about road properties and current conditions, to enhance the precision of energy consumption predictions. Additionally, live traffic updates and real-time weather data such as temperature, precipitation, and wind speed are incorporated to adjust route recommendations dynamically. The model also takes into account specific vehicle and battery specifications, including vehicle model and battery capacity, to provide more accurate energy consumption estimates.”.

[0046] Comprehensive data collection is enabled for dataset 46, ensuring a robust foundation for model training. Diverse datasets 46 are utilized to train a highly accurate and reliable predictive model. Additionally, dynamic updates are incorporated through continuous integration of new data, allowing the model to be refined and updated regularly to maintain its relevance over time. Furthermore, detailed trip logs need to be compiled, including route coordinates, time stamps and battery level or state of charge for each coordinate. The goal is to understand patterns of battery consumption across various routes and conditions. Furthermore, real-time data ingestion is provided, for example by monitoring live traffic conditions to adjust route predictions and energy consumption estimates. Furthermore, incorporating temperature, precipitation and wind data to account for their impact on the battery efficiency is provided.

[0047] For a model training, a so-called delta state of charge (ASOC) calculation may be provided. The delta state of charge represents the change in battery level between two successive data points during a trip. This may be calculated per segment and then aggregated for the entirety of the trip. The calculation of the delta state of charge may be provided by subtracting the state of charge at the beginning of a segment from the state of charge at the end of the segment. A feature selection process is implemented based on the correlation of the features with the changes in the state of the charge and their impact on energy consumption. This ensures that the selected features have a direct or indirect influence on battery usage. Cloud-based models are trained to predict changes in the state of charge, learning the relationship between static and dynamic features for each road segment and the corresponding battery usage. Scalable cloud resources are utilized to handle extensive computations and storage, which is needed. Algorithms for this progression tasks are considered, such as Random Forest, Gradient Boosting or neuronal networks.

[0048] The predictive model can be deployed and utilized by dividing the entire trip into smaller, manageable segments that mirror the intervals used during the model training. To apply the model to each segment for individual delta state of charge predictions, enabling a detailed consumption profile is provided. The real-time features are extracted from each trip segment, such as traffic density, weather conditions, and road type. Historical data is utilized to account for features that do not need to be measured in real time but are known to affect energy consumption, such as road grade. The predicted delta state of charge from all segments to estimate total battery consumption for the trip is aggregated. The total consumption estimate is updated as the trip progresses and realtime data is refreshed.

[0049] Furthermore, the initial charge level of the battery of the motor vehicle 12 is taking into consideration. Furthermore, consistent checks are implemented to ensure predictions are within the physical battery limits. Cloud services are used that can dynamically allocate resources to handle the computational load of real-time inference. A robust data pipeline is established that can stream real-time data to the cloud. A seamless interface enables vehicles to transmit initial required parameters from the motor vehicle 12 to the cloud, query the model, receive route suggestions with estimated energy consumption, and update trip data accordingly. The in-vehicle model 40 refines cloudbased route and energy consumption estimates by incorporating data on the user driving habits, active vehicle features, and other relevant factors directly from the vehicle sensors and systems. The integration of the user-specific data may use the driving habits, which analyzes patterns in acceleration, breaking, and speed maintenance to adjust energy consumption estimates more accolated to the driver’s style. The in-vehicle feature usage considers the energy impact of using air-conditioning, heating, entertainment systems, and other features, adjusting estimates accordingly. Additional factors such as vehicle load and current battery health are also considered to further refine energy consumption predictions. The large language model 26 is in particular used in order to explain the adjustments and feature impacts. Furthermore, the large language model 26 integrates inputs from an anomaly detector, feature impacts, adjusted energy consumption estimates for various routes, real-time information on available charging stations, vehicle charge status, user preferences, and the instruction manual for energy efficiency. This enables the model to provide up-to-date recommendations to optimize energy consumption in the motor vehicle 12. After the in-vehicle model 40 enhances the energy consumption estimate provided by the in-cloud model, the feature explanation unit 38 is utilized to analyze the impact of each feature on the change in the state of charge. This analysis, combined with input from the anomaly detector that identifies unusual features, is processed by the large language model 26 to provide the user with recommendations on how different features or behaviors affect energy consumption, urthermore, it may be highlighted which features and habits have the most significant effects on efficiency, empowering drivers with knowledge to make energy-saving decisions. For example, the anomaly detection 36 helps identifying and alert the users to unusual patterns that may indicate inefficiencies or potential issues with vehicle performance. The impact analysis may assess the energy impact of detected anomalies, providing target recommendations for addressing these issues. Therefore, personalized recommendations can be provided, for example delivering customized advice on optimizing driver habits and feature usage for a better efficiency based on the models analysis. The interactive feedback loop engages the users with real-time insights and suggestions, encouraging adjustments that lead to immediate and long-term efficiency improvements.

[0050] Furthermore, data protection is provided. The energy saving system 14 therefore is designed to respect user privacy and secure personal data, ensuring that information processing is used to the highest security standards. The user has the control over the data, including what is collected and how it is used, reinforcing trust in the energy saving system 14.

[0051] The large language model 26 plays an essential role in transforming the in-vehicle experience by providing personalized recommendations and information through advanced natural language processing capabilities. The large language model 26 may receive and interprets data from the cloud and in-vehicle model 40, vehicle sensors, and direct user inputs, creating a comprehensive understanding of the driving context. The large language model 26 uses this data to generate tailored efficiency suggestions, route adjustments, and driving tips, that reflect the users’ habits, preferences, and the vehicles current state. Voice-enabled interactions can play a significant role in allowing users to communicate with the large language model assistant hands-free, making the driving experience safer and more intuitive. The well-designed user interface 44 that virtually presents the recommendations, alerts and efficiency matrix in an easily digestible format, enhancing user engagement is provided.

[0052] As an example, the user inputs the destination into the input device 16. The incloud model 42 evaluates the route considering current traffic, weather conditions, and road types, then sends a preliminary energy consumption estimate as the first energy consumption 22 to the motor vehicle 12. The in-vehicle model 40 adjusts the estimate based on the driving habits of the user, such as preferring a steady speed and using climate control conservatively. The large language model 26, through the Infotainment system communicates to the user that for example “based on today’s weather and your driving preferences, you likely use 15 percent less battery than on a typical trip to your destination”.

[0053] For example, during a trip, the energy-saving system 14 detects that the battery is depleting faster than expected due to an unplanned detour. The in-vehicle model 40 identifies this anomaly and prompts the large language model 26 to offer advice: “To conserve energy, consider activating eco-mode and reducing your speed. This could extend battery life by up to 10 percent.” Additionally, as the user nears the destination, an event causes congestion on the planned route. The in-cloud model 42 updates the route in real-time, and the in-vehicle system suggests alternatives, such as a less congested route that also offers opportunities for regenerative braking. The large language model 26 confirms the user's preference for the new route, dynamically incorporating feedback: “Would you prefer a scenic route that could also optimize battery usage? It’s just a few minutes longer.Therefore, the energy saving system 14 integrates the cloud computing, in-vehicle models 40, and large language model 26 to offer dynamic, real-time efficiency recommendations tailed to individual drivers and driving conditions. The energy saving system 14 has the unique ability to synthesize fast amounts of real-time traffic, weather, road data, and personal driving habits to optimize route planning and energy use. The energy-saving system 14 positively impacts the motor vehicle 12 by improving efficiency and extending its range. These significant enhancements in battery usage and range predictability help reduce range anxiety and boost driver confidence. Furthermore, personalized recommendations and adaptive learning create a more engaging, safer and enjoyable driving experience, fostering a deeper connection between the driver and the electronic motor vehicle 12. The efficiency assistance can play a pivotal role in promoting more efficient usage of the motor vehicle 12, leading to lower energy consumption, reduced emissions, and a positive impact on the environment. Reference signs 10 12 14 16 18 20 22 24 26 28 30 32 34 36 38 40 42 44 46 48 S1 -S8 energy saving information motor vehicle energy saving system input device first electronic computing device second electronic computing device first energy consumption individual user parameter large language model real-time features road condition driving behavior comfort function anomaly detector model explainer in-vehicle model in-cloud model user interface data set output device steps of the method

Claims

1. A method for providing an energy saving information (10) of an at least in part electrically operated motor vehicle (12) for a user of the motor vehicle (12) by an energy saving system (14), comprising the steps of:- receiving at least a destination input of the user by an input device (16) of a first electronic computing device (18) of the energy saving system (14); (S1)- transmitting at least the destination input to a second electronic computing device (20) of the energy saving system (14), which is arranged outside of the motor vehicle (12); (S2)- determining a potential route depending on at least the destination input by the second electronic computing device (20); (S3)- determining a first energy consumption (22) of the motor vehicle (12) by the second electronic computing device (20) depending on the potential route and depending on at least one current condition alongside the determined potential route by the second electronic computing device (20); (S4)- transmitting at least the first energy consumption (22) and the potential route to the first electronic computing device (18) by the second electronic computing device (20); (S5)- determining a second energy consumption depending on the first energy consumption (22) and an individual user parameter (24) by the first electronic computing device (18); (S6)- generating the energy saving information (10) depending on the second energy consumption and the potential route by the first electronic computing device (18); (S7) and- providing the energy saving information (10) for the user by an output device (48) of the first electronic computing device (18). (S8)2. The method according to claim 1, characterized in thatthe energy saving information (10) is provided by a large language model (26).

3. The method according to claim 1 or 2, characterized in thatthe first energy consumption (22) is determined depending on a current weather condition alongside the potential route and / or a current traffic condition alongside the route and / or a road condition (30) alongside the route.

4. The method according to any one of claims 1 to 3, characterized in thatas the individual user parameter (24) a driving behavior (32) of the user and / or a usage of comfort function (34) of the motor vehicle (12) is provided.

5. The method according to any one of claims 1 to 4, characterized in thatas the energy saving information (10) an alternative route to the potential route and / or a user specific driving behavior and / or a driving mode of the motor vehicle (12) and / or the usage of a comfort function (34) of the motor vehicle (12) is provided.

6. The method according to any one of claims 1 to 5, characterized in thatthe energy saving information (10) comprises an impact information about the energy saving of a suggested adaption.

7. The method according to any one of claims 1 to 6, characterized in thata feedback from the user to the energy saving information (10) is receivable by the first electronic computing device (18).

8. The method according to any one of claims 1 to 6, characterized in thata future anomaly for the potential route and / or a current anomaly at the current driving is detected by the first electronic computing device (18) and the energy saving information (10) is generated depending on such a detected anomaly.

9. A computer program product comprising program code means for performing a method according to any one of claims 1 to 8.

10. An energy saving system (14) for providing an energy saving information (10) of an at least in part electrically operated motor vehicle (12) for a user of the motor vehicle (12), comprising at least one first electronic computing device (18), and one second electronic computing device (20), wherein the energy saving system (14) is configured for performing a method according to any one of claims 1 to 8.21

Images