Vehicle consumable supply method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of vehicles, and discloses a vehicle consumable supply method and device, electronic equipment and a storage medium. The invention provides a vehicle consumable non-inductive supply method based on a large model. The core of the vehicle consumable non-inductive supply method is to construct an intelligent system architecture which is in end-cloud cooperation and is driven by the large model. According to the system architecture, through integration of multi-source information such as vehicle sensor data, user behavior data, environment data and supply chain data, the powerful analysis, prediction, decision-making and interaction capabilities of a large model can be utilized to realize whole-process non-sensitive replenishment from consumable state perception, demand prediction, personalized recommendation, automatic ordering and intelligent logistics. The application at least can improve user experience and satisfaction, improve consumable supply efficiency, reduce time cost, optimize consumable selection, reduce error rate, promote vehicle intelligence and ecological interconnection, reduce operation cost, improve supply chain efficiency, increase user stickiness and expand an Internet of Vehicles business mode.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and in particular to a method, apparatus, electronic device, and storage medium for replenishing vehicle consumables. Background Technology

[0002] In routine vehicle maintenance and consumable parts replenishment, current technology primarily relies on a combination of passive detection and manual intervention. Vehicle owners typically learn about and replenish consumable parts through the following methods:

[0003] (1) Warning lights and information display on the vehicle dashboard: Vehicles are generally equipped with various sensors to monitor the level or lifespan of consumables such as engine oil, coolant, brake fluid, and windshield washer fluid. When the consumables are close to being depleted, the dashboard will light up a warning light or display a text message to inform the owner that the consumables are low.

[0004] (2) Regular maintenance and inspection: During routine vehicle maintenance, the mechanic will check the condition of various consumables and add or replace them. Some vehicle service providers will remind vehicle owners to perform maintenance via telephone, SMS or application.

[0005] (3) User manual inspection and purchase: Experienced car owners may regularly inspect vehicle consumables themselves and purchase them online or offline as needed.

[0006] (4) Third-party application reminders: Some car service or e-commerce platforms offer reminders for consumable purchases and maintenance, but these reminders are often based on preset time or mileage rather than real-time consumable consumption data.

[0007] (5) Telematics: Some high-end models integrate basic remote diagnostic functions. For example, when a specific fault code is detected, the system may send a notification to the owner or dealer. However, these services usually focus on fault diagnosis and emergency assistance, and have limited predictive replenishment capabilities for daily consumables.

[0008] More specifically, for example, in terms of windshield washer fluid replenishment, current market solutions mainly rely on dashboard warnings and manual purchase by the user. When the windshield washer fluid level is too low, the vehicle will issue a warning, and the owner needs to determine which type and brand of windshield washer fluid to buy, complete the purchase through a physical store or online e-commerce platform, and then add it themselves or have someone else do it.

[0009] It is evident that although existing technologies have solved the problem of monitoring vehicle consumables to some extent, their passivity and high dependence on human intervention have led to a series of user pain points and efficiency issues. Specifically, these include untimely replenishment and a decline in the user experience, blind and mismatched selection of consumables, cumbersome replenishment process and high time cost, lack of personalization and predictability, data silos and insufficient collaboration, and low intelligence level that makes it unable to understand complex contexts. Summary of the Invention

[0010] The purpose of this invention is to provide a vehicle consumables replenishment method, device, electronic device, and storage medium, which can at least improve user experience and satisfaction, increase consumables replenishment efficiency and reduce time costs, optimize consumables selection and reduce error rates, promote vehicle intelligence and ecological interconnection, reduce operating costs and improve supply chain efficiency, and help increase user stickiness and expand the vehicle network business model.

[0011] To address the aforementioned technical problems, in a first aspect, the present invention provides a method for replenishing vehicle consumables, comprising at least:

[0012] Use vehicle sensor modules to collect key usage data for at least one vehicle consumable.

[0013] Using a pre-set large model platform, at least based on user historical data and the key usage data of each vehicle consumable, the multi-dimensional consumption trend of the corresponding vehicle consumable is analyzed, thereby predicting at least the depletion time of each vehicle consumable.

[0014] At least when the depletion time of any of the vehicle consumables is detected to reach a preset replenishment threshold, a preset decision engine is triggered, and then the preset decision engine generates corresponding consumable replenishment decision information by at least combining vehicle information, user historical data and preset consumable knowledge graph.

[0015] The platform uses the preset large model to query at least one e-commerce platform, offline store or logistics service for consumable inventory, consumable price, delivery time and usage evaluation, thereby generating at least one purchase channel and delivery plan.

[0016] The system utilizes the pre-defined large model platform to generate consumable replenishment recommendations based at least on the consumable replenishment decision information, the purchase channels, and the delivery plan, and notifies the user of the consumable replenishment recommendations through a pre-defined method.

[0017] After obtaining user authorization, at least through the preset decision engine, a consumables order is submitted based on the user's historical data, and the logistics status of the consumables is tracked in real time, and logistics update information is pushed through the user's preferred channels until the consumables are delivered.

[0018] Optionally, after collecting key usage data of at least one vehicle consumable using the vehicle sensing module, the method further includes at least:

[0019] The on-board edge computing unit performs at least the data cleaning, format integration, and data encryption operations on the critical usage data.

[0020] Optionally, after obtaining user authorization, submitting a consumable order based on the user's historical data through the preset decision engine, tracking the consumable logistics status in real time, and pushing logistics update information through the user's preferred channels until the consumable is delivered, the method further includes at least:

[0021] In response to the delivery of any consumable, the preset large model platform shall, based at least on the consumable information and the vehicle information, recommend and push consumable usage tutorials and / or illustrated guides to the user.

[0022] Optionally, after responding to the delivery of any consumable and using the preset large model platform to recommend and push consumable usage tutorials and / or illustrated guides to the user based at least on the consumable information and the vehicle information, the method further includes at least:

[0023] In response to the use of any consumable, feedback information on the user's use of consumables is obtained through the preset method, and the feedback information is input into the preset large model platform for iterative updates.

[0024] Based on the same concept, in a second aspect, the present invention also provides a vehicle consumables replenishment device for performing the vehicle consumables replenishment method described in any one of the first aspects;

[0025] The vehicle consumables replenishment device includes at least:

[0026] The data acquisition module is used to collect key usage data of at least one vehicle consumable using the vehicle sensor module;

[0027] The exhaustion prediction module is used to analyze the multi-dimensional consumption trend of the corresponding vehicle consumables based on user historical data and key usage data of each vehicle consumable using a preset large model platform, and then predict the exhaustion time of each vehicle consumable.

[0028] The replenishment decision module is at least used to trigger a preset decision engine when it is detected that the depletion time of any of the vehicle consumables reaches a preset replenishment threshold, and then generate corresponding consumable replenishment decision information by the preset decision engine in combination with at least vehicle information, user historical data and preset consumable knowledge graph.

[0029] The solution generation module is used to query at least one e-commerce platform, offline store or logistics service for consumable inventory, consumable price, delivery time and usage evaluation through the preset large model platform, and then generate at least one purchase channel and delivery solution.

[0030] The suggestion notification module is used to generate consumable replenishment suggestions using the preset large model platform based at least on the consumable replenishment decision information, the purchase channel and the delivery plan, and to notify the user of the consumable replenishment suggestions in a preset manner;

[0031] The logistics tracking module is used to submit consumable orders based on the user's historical data through the preset decision engine after obtaining user authorization, and to track the logistics status of consumables in real time, and to push logistics update information through the user's preferred channels until the consumables are delivered.

[0032] Optionally, it may also include at least a data processing module;

[0033] The data processing module is at least used to perform data cleaning, format integration, and data encryption on the key usage data through the vehicle-mounted edge computing unit.

[0034] Optionally, it should at least include a tutorial push module;

[0035] The tutorial push module is used at least to respond to the delivery of any consumable, and to recommend and push consumable usage tutorials and / or illustrated guides to the user based on the consumable information and the vehicle information using the preset large model platform.

[0036] Optionally, it may also include at least an iterative update module;

[0037] The iterative update module is at least used to respond to the use of any consumable, obtain feedback information on the user's use of consumables through the preset method, and input the feedback information into the preset large model platform for iterative updates by the preset large model platform.

[0038] Based on the same concept, in a third aspect, the present invention also provides an electronic device, including a memory and a processor, the memory storing a computer program executable on the processor, the processor executing the program to implement the steps of the vehicle consumables replenishment method of any one of the first aspects.

[0039] Based on the same concept, in a fourth aspect, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the vehicle consumables replenishment method according to any one of the first aspects.

[0040] The technical solution provided by this invention firstly collects key usage data of at least one vehicle consumable using a vehicle sensing module; further, it uses a preset large model platform to analyze the multi-dimensional consumption trend of the corresponding vehicle consumable based on user historical data and key usage data of each vehicle consumable, thereby predicting at least the depletion time of each vehicle consumable; further, it triggers a preset decision engine at least when the depletion time of any vehicle consumable reaches a preset replenishment threshold, and then generates corresponding consumable replenishment decision information by combining vehicle information, user historical data, and a preset consumable knowledge graph through the preset decision engine; further... First, by querying at least one e-commerce platform, offline store, or logistics service for consumable inventory, prices, delivery time, and user reviews through a pre-set large model platform, at least one purchase channel and delivery plan are generated. Next, based on consumable replenishment decision information, purchase channels, and delivery plans, a consumable replenishment suggestion is generated using the pre-set large model platform, and this suggestion is notified to the user through a pre-set method. Finally, after obtaining user authorization, a consumable order is submitted based on the user's historical data through a pre-set decision engine, and the consumable logistics status is tracked in real time, with logistics updates pushed through the user's preferred channels until the consumable is delivered.

[0041] Therefore, the embodiments of this invention propose a seamless vehicle consumable replenishment method based on a large model. Its core lies in constructing an intelligent system architecture driven by a large model and collaborating with the cloud. This system architecture integrates multi-source information such as vehicle sensor data, user behavior data, environmental data, and supply chain data. Leveraging the powerful analysis, prediction, decision-making, and interaction capabilities of the large model, it achieves seamless replenishment throughout the entire process, from consumable status perception, demand prediction, personalized recommendation, automated ordering, and intelligent logistics. The embodiments of this invention can at least improve user experience and satisfaction, increase consumable replenishment efficiency and reduce time costs, optimize consumable selection and reduce error rates, promote vehicle intelligence and ecological interconnection, reduce operating costs and improve supply chain efficiency, and facilitate increased user stickiness and expansion of vehicle-to-everything (V2X) business models. Attached Figure Description

[0042] Figure 1 This is a flowchart of a vehicle consumables replenishment method provided in an embodiment of the present invention;

[0043] Figure 2 This is a flowchart of another vehicle consumables replenishment method provided in an embodiment of the present invention;

[0044] Figure 3 This is a schematic diagram of the structure of a vehicle consumables replenishment device provided in an embodiment of the present invention;

[0045] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0047] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the application. The singular forms “a,” “said,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0048] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0049] It should be understood that although the terms first, second, third, etc., may be used in the embodiments of this application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, first may also be referred to as second without departing from the scope of the embodiments of this application, and similarly, second may also be referred to as first.

[0050] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0051] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the article or device that includes said element.

[0052] It should be noted that any symbols and / or numbers present in the specification that are not marked in the accompanying drawings are not reference numerals.

[0053] As mentioned in the background section, existing vehicle consumables suffer from several technical problems, including untimely replenishment leading to a decreased user experience, blind and mismatched consumable selection, cumbersome replenishment processes and high time costs, lack of personalization and predictability, data silos and insufficient collaboration, and low intelligence levels preventing the understanding of complex contexts. After careful research, the inventors discovered that the specific reasons for these technical problems are as follows:

[0054] (1) Delayed replenishment and decreased driving experience: Existing systems mostly provide delayed warnings, that is, they only issue a warning when the consumable is about to run out. This may result in car owners being unable to replenish the windshield washer fluid in time in inconvenient or emergency situations (for example, suddenly finding that the windshield washer fluid is empty while driving on the highway), affecting driving safety and experience. For example, in the face of bad weather, insufficient windshield washer fluid can obstruct vision and increase driving risks.

[0055] (2) Blindness and mismatch in consumable selection: When purchasing consumables, car owners often lack professional knowledge and find it difficult to determine which model, brand, or specification of consumables is most suitable for their vehicle or personal needs. The market is flooded with products of varying quality, which may lead to the purchase of inferior or incompatible products, or even damage to the vehicle.

[0056] (3) The supply process is complicated and time-consuming: From receiving the warning to purchasing and then to installation (such as adding windshield washer fluid or replacing wipers), the whole process requires car owners to invest a lot of time and energy in information inquiry, price comparison, ordering, waiting for delivery and personal operation. For busy modern car owners, this undoubtedly adds an extra burden.

[0057] (4) Lack of personalization and predictability: Existing technologies cannot make personalized consumption predictions based on the driver's driving habits (such as frequent use of windshield wipers, driving in dusty areas, etc.), vehicle usage environment, and historical consumption data. Therefore, it is impossible to proactively and accurately provide replenishment solutions before consumables are exhausted, leaving the replenishment process still in a passive mode of "discovering problems - solving problems".

[0058] (5) Data silos and insufficient collaboration: Vehicle sensor data, user consumption data, e-commerce platform product data, and logistics information are scattered across different systems and platforms, lacking effective information sharing and intelligent collaboration. This makes it difficult to form a complete closed loop from monitoring and prediction to purchasing, delivery, and installation. For example, a vehicle may sense that its windshield washer fluid is low, but it cannot directly and seamlessly connect with the user's shopping preferences, logistics preferences, and e-commerce platform inventory information to achieve automated ordering and delivery.

[0059] (6) Low intelligence level and inability to understand complex contexts: The existing in-vehicle systems or applications have limited intelligence and are unable to interact deeply with users through natural language, understand users' complex intentions, or provide more detailed service suggestions. For example, when a user replies "I want to change to an antifreeze windshield washer fluid this time," the existing system has difficulty understanding and automatically adjusting the recommended solution.

[0060] To address the aforementioned technical problems, the present invention proposes the following solutions:

[0061] Figure 1 This is a flowchart of a vehicle consumables replenishment method provided by an embodiment of the present invention. This embodiment is applicable to at least any vehicle consumables replenishment scenario. The vehicle consumables replenishment method can be, but is not limited to, executed by the vehicle consumables replenishment device in this embodiment as the execution subject. This execution subject can be implemented in software and / or hardware. Figure 1 As shown, the vehicle consumables replenishment method includes at least the following steps:

[0062] S1. Collect key usage data of at least one vehicle consumable using a vehicle sensor module.

[0063] The vehicle sensing module can include various vehicle sensors, such as level sensors (e.g., for detecting the levels of windshield washer fluid, engine oil, coolant, brake fluid, etc.), mileage sensors, temperature sensors, tire pressure sensors, ambient light sensors, and rain sensors. Correspondingly, vehicle consumables can refer to windshield washer fluid, engine oil, coolant, brake fluid, brake pads, windshield wipers, car air fresheners, etc.; key usage data can refer to the level, pressure, and temperature of vehicle consumables.

[0064] S2. Using a pre-set large model platform, analyze the multi-dimensional consumption trend of consumables for each vehicle based on user historical data and key usage data of consumables for each vehicle, and then predict the depletion time of consumables for each vehicle.

[0065] Among them, the pre-set large model platform can deploy and run any existing large-scale pre-trained model (such as the GPT series, Llama series or other customized vertical large models), and through fine-tuning, reinforcement learning and other technologies, make it at least focus on the vehicle consumables replenishment process.

[0066] For example, user historical data may include historical driving habits, frequently used driving routes, climate conditions, historical shopping records, user-preferred consumable brands / types, payment methods, delivery addresses, etc.

[0067] In one specific implementation, step S2 can be specifically described as follows:

[0068] The platform utilizes a pre-defined large-scale model to deeply integrate historical user data, including driving habits, common routes, climate conditions, shopping records, preferred consumable brands / types, payment methods, and delivery addresses. This integrated massive dataset is then used for deep learning and pattern recognition. The platform can predict the actual consumption rate and estimated depletion time of various consumables (e.g., windshield washer fluid depletion time, engine oil expiration time, brake pad wear to a preset level) by analyzing historical trends in consumable consumption, user driving behavior, vehicle load, ambient temperature, geographical location, and weather forecasts. For example, by analyzing user driving frequency in dusty areas, wiper usage time, and local rainfall predictions, the large-scale model can more accurately determine the windshield washer fluid consumption rate.

[0069] S3. At least when the depletion time of any vehicle consumable reaches the preset replenishment threshold, the preset decision engine is triggered, and then the preset decision engine is used to generate corresponding consumable replenishment decision information by combining vehicle information, user historical data and preset consumable knowledge graph.

[0070] The preset replenishment threshold can be configured according to the actual adaptability of the vehicle. The preset replenishment thresholds for consumables vary from vehicle to vehicle, and this invention does not limit this.

[0071] In another specific implementation, when the large model predicts that a certain consumable (e.g., windshield washer fluid) is about to reach a preset replenishment threshold (e.g., expected to run out within 3 days), a preset decision engine is triggered. The preset decision engine combines the large model's prediction results with information from the user's preferences and historical behavior database to generate a personalized consumable replenishment plan. This plan may specifically include recommendations for consumable categories and specifications; for example, based on vehicle model, maintenance requirements, and the user's historical purchase preferences, the large model intelligently matches the most frequently used windshield washer fluid brand, model, or environmentally friendly / antifreeze type from its internal consumable knowledge graph.

[0072] S4. By using a pre-set large model platform, query at least one e-commerce platform, offline store or logistics service for consumable inventory, consumable price, delivery time and usage evaluation, and then generate at least one purchase channel and delivery plan.

[0073] E-commerce platforms could include Tmall, JD.com, Amazon, Pinduoduo, etc., and logistics services could include SF Express, JD.com, ZTO Express, etc.

[0074] In yet another specific implementation, step S4 can be specifically described as follows:

[0075] The large-scale model uses e-commerce / logistics platform interfaces to query the inventory, prices, delivery times, and user reviews of consumables on multiple partner e-commerce platforms or offline service stores in real time. It then recommends the most cost-effective or most suitable purchasing channels for users (e.g., brand loyalty, price sensitivity). Furthermore, delivery methods can be tailored to the user's address and the urgency of the consumables, recommending the fastest delivery method or a self-pickup option.

[0076] S5. Utilize the pre-set large model platform to generate consumable replenishment suggestions based at least on consumable replenishment decision information, purchase channels, and delivery plans, and notify users of the consumable replenishment suggestions through a pre-set method.

[0077] The preset methods can include pop-up windows, voice messages, etc.

[0078] In yet another specific implementation, step S5 can be specifically described as follows:

[0079] Based on the generated refueling plan, the large model can proactively push refueling suggestions to users in a human-like and easily understandable natural language (such as voice broadcasts or text information) through its Natural Language Generation (NLG) capabilities. For example: "Hello car owner, we detected that your windshield washer fluid is expected to run out in three days. Based on your historical purchasing preferences, I have found [brand name] windshield washer fluid for you on [e-commerce platform], priced at [price], and expected to arrive tomorrow. Would you like to place an order automatically for you?" Furthermore, this information can be pushed to the user's in-vehicle screen or linked smartphone app through the pre-set large model platform's user interaction management function. In addition, the pre-set large model platform can also use Natural Language Understanding (NLU) technology to listen to and understand the user's voice or text replies in real time (e.g., "Okay, please place an order," "Wait a little longer," "I want another brand," etc.).

[0080] S6. After obtaining user authorization, submit consumable orders based on user historical data through a preset decision engine, track the consumable logistics status in real time, and push logistics update information through user preference channels until the consumables are delivered.

[0081] Specifically, step S6 can be described as follows:

[0082] If the user confirms the order, the pre-set decision engine will immediately generate and submit the order automatically through the e-commerce / logistics platform interface, using the user's authorized payment method. The entire process eliminates the need for users to manually select products, fill in addresses, or confirm payments. After the order is generated, the system will track the logistics status in real time and promptly push logistics updates through user-preferred channels (such as the App, SMS, and in-vehicle screens) until the consumables are safely delivered to the user's designated location.

[0083] The technical solution provided in this embodiment firstly collects key usage data of at least one vehicle consumable using a vehicle sensing module; further, it uses a preset large model platform to analyze the multi-dimensional consumption trend of the corresponding vehicle consumable based on user historical data and key usage data of each vehicle consumable, thereby predicting at least the depletion time of each vehicle consumable; further, it triggers a preset decision engine at least when the depletion time of any vehicle consumable reaches a preset replenishment threshold, and then generates corresponding consumable replenishment decision information by combining vehicle information, user historical data, and a preset consumable knowledge graph through the preset decision engine; further... The system uses a pre-set large-scale model platform to query at least one e-commerce platform, offline store, or logistics service for consumable inventory, prices, delivery time, and user reviews, thereby generating at least one purchase channel and delivery plan. Furthermore, it uses the pre-set large-scale model platform to generate consumable replenishment suggestions based on consumable replenishment decision information, purchase channels, and delivery plans, and notifies users of these suggestions through a pre-set method. Finally, after obtaining user authorization, it submits consumable orders based on user historical data through a pre-set decision engine, tracks the consumable logistics status in real time, and pushes logistics updates through user-preferred channels until the consumables are delivered.

[0084] Therefore, this embodiment proposes a seamless vehicle consumable replenishment method based on a large model. Its core lies in constructing an intelligent system architecture driven by a large model and collaborating with the cloud. This system architecture integrates multi-source information such as vehicle sensor data, user behavior data, environmental data, and supply chain data. Leveraging the powerful analysis, prediction, decision-making, and interaction capabilities of the large model, it achieves seamless replenishment throughout the entire process, from consumable status perception, demand forecasting, personalized recommendations, automated ordering, and intelligent logistics. This embodiment can at least improve user experience and satisfaction, increase consumable replenishment efficiency and reduce time costs, optimize consumable selection and reduce error rates, promote vehicle intelligence and ecosystem interconnection, reduce operating costs and improve supply chain efficiency, and facilitate increased user stickiness and expansion of vehicle-to-everything (V2X) business models.

[0085] Based on the above embodiments or implementation methods Figure 2 This is a flowchart of another vehicle consumables replenishment method provided by an embodiment of the present invention, such as... Figure 2 As shown, the vehicle consumables replenishment method includes at least the following steps:

[0086] S1. Collect key usage data of at least one vehicle consumable using a vehicle sensor module.

[0087] S7. Perform data cleaning, format integration, and data encryption on key usage data through the vehicle-mounted edge computing unit.

[0088] Specifically, step S7 can be described as follows:

[0089] The onboard edge computing unit performs preliminary cleaning, noise reduction, format standardization, and necessary encryption on the data, and filters out abnormal data. Then, the processed compressed data stream can be securely and efficiently transmitted to the cloud via wireless communication methods (such as 5G, LTE-V2X, Wi-Fi, etc.). This step ensures data transmission efficiency and quality.

[0090] S2. Using a pre-set large model platform, analyze the multi-dimensional consumption trend of consumables for each vehicle based on user historical data and key usage data of consumables for each vehicle, and then predict the depletion time of consumables for each vehicle.

[0091] S3. At least when the depletion time of any vehicle consumable reaches the preset replenishment threshold, the preset decision engine is triggered, and then the preset decision engine is used to generate corresponding consumable replenishment decision information by combining vehicle information, user historical data and preset consumable knowledge graph.

[0092] S4. By using a pre-set large model platform, query at least one e-commerce platform, offline store or logistics service for consumable inventory, consumable price, delivery time and usage evaluation, and then generate at least one purchase channel and delivery plan.

[0093] S5. Utilize the pre-set large model platform to generate consumable replenishment suggestions based at least on consumable replenishment decision information, purchase channels, and delivery plans, and notify users of the consumable replenishment suggestions through a pre-set method.

[0094] S6. After obtaining user authorization, submit consumable orders based on user historical data through a preset decision engine, track the consumable logistics status in real time, and push logistics update information through user preference channels until the consumables are delivered.

[0095] S8. In response to the delivery of any consumable, use the preset large model platform to recommend and push consumable usage tutorials and / or illustrated guides to the user based on consumable information and vehicle information.

[0096] S9. In response to the use of any consumable, obtain the user's feedback information on the use of consumables through a preset method, and input the feedback information into the preset large model platform for iterative updates.

[0097] Specifically, steps S8 and S9 can be described as follows:

[0098] After the consumables are delivered, the large-scale model can intelligently recommend and push corresponding installation tutorial videos or graphic guides to the user's terminal based on the consumable type and vehicle model, simplifying the installation process. Furthermore, the system collects user feedback data on consumable quality, delivery service, and installation experience. This feedback data is then fed back into the pre-set large-scale model platform as a basis for reinforcement learning, continuously optimizing the consumable prediction algorithm, recommendation strategy, and user interaction experience, forming a closed loop of continuous iteration and self-improvement.

[0099] In view of the above, this embodiment can achieve at least the following beneficial effects through the implementation of the above technical solution:

[0100] 1. Significantly improved timeliness of resupply and driving safety:

[0101] (1) Technical implementation: The large model accurately predicts consumable consumption by integrating multi-source data (sensors, driving behavior, environment, etc.), rather than providing delayed warnings. The system can predict in advance when consumables will run out and trigger replenishment at the optimal time.

[0102] (2) Beneficial effects: It can alleviate the inconvenience and safety hazards caused by the sudden exhaustion of consumables, ensure that the vehicle is always in the best operating condition, and help improve driving safety and user experience.

[0103] 2. Improved accuracy in consumable selection and increased user satisfaction:

[0104] (1) Technical implementation: The large model can have a huge consumable knowledge graph built in, and can deeply learn users’ historical purchase preferences and vehicle characteristics, and can provide highly personalized, adaptable and reliable consumable recommendations.

[0105] (2) Beneficial effects: Users no longer need to worry about choosing consumables, avoiding losses caused by purchasing the wrong or inferior products, ensuring the best matching of consumables and the best use effect, and improving users' trust and satisfaction with the service.

[0106] 3. Process automation and significant savings in time and effort:

[0107] (1) Technical implementation: The intelligent decision engine driven by the big model realizes full-process automation from demand identification to order placement, payment and logistics arrangement. Users only need simple confirmation, and can even set it to a "seamless" mode that requires no confirmation.

[0108] (2) Beneficial effects: It greatly simplifies the cumbersome process of replenishing consumables, transforms the time-consuming and labor-intensive task into an automatic background execution, saves users valuable time and energy, and improves the convenience of life.

[0109] 4. Enhanced personalized service and predictive management capabilities:

[0110] (1) Technical implementation: The large model has strong self-learning and adaptability, and can continuously analyze and understand each user's unique driving habits and vehicle usage scenarios, providing highly customized replenishment solutions.

[0111] (2) Beneficial effects: It transforms passive response into proactive service, making consumable management more intelligent and humanized, meeting the growing personalized needs of users, and enhancing the “feel-goodness” of the service.

[0112] 5. Data Interoperability and Ecosystem Efficiency Optimization:

[0113] (1) Technical implementation: The large model serves as the core hub, breaking down the data silos among vehicles, users, e-commerce, logistics, and other links, and realizing seamless information flow and intelligent collaboration.

[0114] (2) Beneficial effects: It has improved the operational efficiency of the entire consumables supply ecosystem, reduced operating costs, and laid a solid foundation for more data-based intelligent services and business model innovations in the future.

[0115] Based on the above embodiments or implementation methods, the following provides a specific scenario embodiment, taking the seamless replenishment of windshield washer fluid as an example.

[0116] 1. Vehicle status perception and data upload

[0117] Scenario: Car owner Xiao Li is driving a smart car equipped with the architecture of this invention on a highway in Berlin.

[0118] Sensor data: The vehicle's windshield washer fluid level sensor continuously monitors the amount of windshield washer fluid. At the same time, environmental sensors (such as rain sensors and temperature sensors) monitor the current weather conditions (e.g., no rain, temperature 20°C), and the vehicle's mileage sensor records the mileage traveled.

[0119] Vehicle edge computing unit processing: The vehicle edge computing unit (e.g., a high-performance processor integrated into the vehicle's T-Box or in-vehicle infotainment system) receives windshield washer fluid level data and performs preliminary processing; it filters out instantaneous fluctuations and compresses the data.

[0120] Data Upload: Preliminary processed data (e.g., windshield washer fluid level is 15%, 2000 km has been driven since the last refill, and the estimated usage time is 5 days) is encrypted and uploaded to the cloud in real time via the vehicle's 5G wireless communication.

[0121] 2. Cloud-based large-scale model analysis and prediction

[0122] Data Fusion: Cloud-based multimodal data storage integrates windshield washer fluid data uploaded from the vehicle's system with Xiao Li's personal information stored in a database of user preferences and historical behavior. This information may include:

[0123] Historical driving habits: Xiao Li often drives in dusty or pollen-rich areas, and uses the windshield wipers frequently.

[0124] Purchase history: Xiao Li prefers to buy antifreeze windshield washer fluid from a certain German local brand (such as Sonax) and is used to purchasing it on the Amazon platform, choosing next-day delivery service.

[0125] Vehicle Information: The vehicle is a European brand SUV, and it is recommended to use a specific type of windshield washer fluid.

[0126] Location information: The vehicle is currently located in Germany.

[0127] Large-scale model prediction: The large-scale model service platform (running on a high-performance cloud computing cluster) receives and analyzes this fused data, and makes a comprehensive judgment:

[0128] Current windshield washer fluid consumption rate: based on Xiao Li's high-frequency usage habits, vehicle model, and season (it may consume faster in summer).

[0129] Predicted depletion time: Based on the current consumption rate and remaining amount, the large model predicts that the windshield washer fluid will be depleted in 3 days.

[0130] Replenishment Timing Judgment: The large model determines that now is the best time to replenish, which can ensure timely replenishment without prematurely occupying user storage space.

[0131] 3. Intelligent decision-making and personalized solution generation

[0132] Intelligent Decision Engine: Based on the predictions of the large model, the intelligent decision engine triggers the replenishment process.

[0133] Personalized Recommendation: The large model generates the optimal resupply plan for Xiao Li based on his historical preferences (Sonax brand, Amazon platform, next-day delivery), vehicle model compatibility, and current market prices (real-time queries of Taobao and local offline auto parts stores via e-commerce / logistics platform interfaces).

[0134] Recommended product: Sonax Xtreme AntiFrost & Klarsicht Konzentrat (250ml concentrated formula, can be diluted with 5L of water).

[0135] Recommended platform for purchase: Taobao (Amazon.de).

[0136] Recommended price: 8.9 yuan.

[0137] Estimated delivery date: November 11, 2025 (next day delivery).

[0138] 4. Proactive user interaction and automated order placement

[0139] Natural Language Generation: The large model translates the refill plan into a natural language prompt: "Hello, we detected that your windshield washer fluid is expected to run out in 3 days. Based on your past preferences, I have found Sonax antifreeze windshield washer fluid (€8.99) on Amazon for you, which is expected to arrive at your home tomorrow. Would you like to place an order automatically for you?"

[0140] Multi-channel push notification: The user interaction management system will simultaneously push this notification via voice broadcast (car audio) and text message (car screen, Xiao Li mobile app).

[0141] User confirmation: After hearing the prompt, Xiao Li can reply with a voice command: "Okay, please place the order."

[0142] Automated order placement: Upon receiving confirmation from Xiao Li, the intelligent decision engine automatically submits and processes the order on the Amazon platform via the e-commerce / logistics platform interface (assuming Xiao Li has authorized the system to bind a payment method). Xiao Li's mobile app will simultaneously receive the order confirmation information from Amazon.

[0143] 5. Logistics tracking and installation assistance

[0144] Logistics tracking: The system continuously tracks the logistics status of orders through e-commerce / logistics platform interfaces and pushes notifications to Xiao Li at key stages such as goods being shipped, in delivery, and delivered.

[0145] Installation Assistance: Once the windshield washer fluid has been delivered, the system will remind Xiao Li again: "Your windshield washer fluid has been delivered. Do you want us to send you a tutorial video on adding this type of windshield washer fluid?" If Xiao Li confirms, the system will retrieve relevant official or high-quality third-party tutorial videos from its knowledge base and send them to Xiao Li's mobile app or in-car screen.

[0146] 6. User Feedback and System Optimization

[0147] User feedback: After Xiao Li used the newly replenished windshield washer fluid, the system asked via an app pop-up or in-car voice prompt: "Are you satisfied with this windshield washer fluid replenishment service? Do you have any suggestions?" Xiao Li's feedback (e.g., "Very convenient, but it would be even better if you could recommend a larger bottle") was recorded.

[0148] System Optimization: This feedback data, along with new sensor data and purchase records, will serve as input for reinforcement learning and model fine-tuning on the large-scale model service platform. The large model will continuously optimize its prediction algorithms, recommendation strategies, and interaction patterns based on this information, in order to provide more accurate and personalized services to Xiao Li and other users in the future (for example, it might prioritize recommending larger-capacity windshield washer fluid next time).

[0149] Although the large-model-based method proposed in this invention has significant advantages, there are still alternatives that can achieve some or limited objectives of the invention in certain specific scenarios or without using large-scale pre-trained models, as follows:

[0150] 1. Alternatives based on rule engines and machine learning models:

[0151] (1) Objective: To enable predictive replenishment of consumables and partial automated ordering.

[0152] (2) Technical Solution: Instead of using a general large model, traditional machine learning (ML) models (such as time series analysis, regression models, and classification models) are adopted to predict consumable consumption. A hard-coded rule engine is used to handle decision-making logic (e.g., triggering an order if the windshield washer fluid level is below 10% and expected to be depleted within 2 days). User preferences can be simply matched using a user tagging system. In terms of interaction, interaction with users may be achieved through preset fixed template information and limited keyword recognition.

[0153] (3) Limitations (compared with large model solutions):

[0154] Low prediction accuracy: ML models are inferior to large models in handling multi-source heterogeneous, unstructured data and complex relationships. Their prediction accuracy and adaptability are poor.

[0155] Insufficient personalization: Rule engines and simple tagging systems struggle to achieve deep personalization and cannot understand subtle changes in user preferences.

[0156] Stiff interaction: Lacking natural language understanding and generation capabilities, the interactive experience is far inferior to systems driven by large models. It is unable to conduct multi-turn dialogues or understand complex contexts.

[0157] Poor scalability: Adding new consumable categories or more complex replenishment strategies requires a lot of manual rule writing and model retraining, resulting in high maintenance costs.

[0158] 2. Alternatives to Internet of Things (IoT) and traditional data analytics platforms:

[0159] (1) Objective: To enable remote monitoring and passive reminders of vehicle consumables.

[0160] (2) Technical Solution: Vehicle sensors upload data to a cloud-based IoT platform. The platform aggregates and stores the data, and notifies the vehicle owner via App or SMS when consumables are insufficient through a preset threshold alarm system. Ordering and purchasing still mainly rely on manual operation of the e-commerce platform by the user. Some advanced functions may be integrated into the vehicle system, but the interaction method is limited.

[0161] (3) Limitations (compared with large model solutions):

[0162] Lack of predictability: It mainly provides post-event warnings rather than advance predictions.

[0163] Low level of automation: It is impossible to achieve automated order placement, intelligent recommendations, and closed-loop management of the entire process.

[0164] Lack of personalization: Unable to provide customized services based on user preferences.

[0165] Lack of interaction: It only provides one-way information push and has no intelligent interaction capabilities.

[0166] 3. Solutions based on in-vehicle operating system integration:

[0167] (1) Objective: To deeply integrate the consumable supply function with the vehicle system and provide a relatively convenient experience.

[0168] (2) Technical solution: Vehicle manufacturers develop applications in the vehicle operating system (such as Android Automotive OS) to directly access vehicle data and may connect with specific partner e-commerce platforms via API. Users can directly view the status of consumables and make purchases on the vehicle's infotainment screen.

[0169] (3) Limitations (compared with large model solutions):

[0170] Limited data collaboration: Integration is usually limited to specific partners, making it difficult to break down broader data barriers (such as different e-commerce platforms and user historical behavior data).

[0171] Weak intelligent decision-making ability: It lacks the ability to perform multi-dimensional data analysis and complex reasoning with large models, making it difficult to provide in-depth predictions and highly personalized recommendations.

[0172] Poor versatility: It is usually limited to specific brand models and it is difficult to form an open ecosystem.

[0173] Figure 3 This is a schematic diagram of a vehicle consumable supply device provided in an embodiment of the present invention. This embodiment is applicable to at least any vehicle consumable supply scenario, and the vehicle consumable supply device can be implemented using software and / or hardware. Figure 3As shown, the vehicle consumables replenishment device is used to perform the vehicle consumables replenishment method of any of the foregoing embodiments or implementations.

[0174] Vehicle consumables replenishment equipment includes at least:

[0175] Data acquisition module 110 is used to collect key usage data of at least one vehicle consumable using the vehicle sensing module;

[0176] The exhaustion prediction module 120 is used to analyze the multi-dimensional consumption trend of consumables for each vehicle based on user historical data and key usage data of consumables for each vehicle using a preset large model platform, and then predict the exhaustion time of consumables for each vehicle.

[0177] The replenishment decision module 130 is used at least to trigger the preset decision engine when the depletion time of any vehicle consumable reaches the preset replenishment threshold, and then generate corresponding consumable replenishment decision information by at least combining vehicle information, user historical data and preset consumable knowledge graph through the preset decision engine.

[0178] The solution generation module 140 is used to query at least one e-commerce platform, offline store or logistics service consumable inventory, consumable price, delivery time and usage evaluation through a preset large model platform, and then generate at least one purchase channel and delivery plan.

[0179] The suggestion notification module 150 is used to generate consumable replenishment suggestions based on at least the consumable replenishment decision information, purchase channels and delivery plans using a preset large model platform, and to notify users of the consumable replenishment suggestions through a preset method;

[0180] The logistics tracking module 160 is used to submit consumable orders based on user historical data through a preset decision engine after obtaining user authorization, and to track the logistics status of consumables in real time, and to push logistics update information through user preferred channels until the consumables are delivered.

[0181] Optionally, it may also include at least a data processing module 170;

[0182] The data processing module 170 is used at least to perform data cleaning, format integration and data encryption operations on critical usage data via the vehicle-mounted edge computing unit.

[0183] Optionally, it may also include at least a tutorial push module 180;

[0184] The tutorial push module 180 is used to respond to the delivery of any consumable and, using a preset large model platform, recommend and push consumable usage tutorials and / or illustrated guides to users based on consumable information and vehicle information.

[0185] Optionally, it may also include at least an iterative update module 190;

[0186] The iterative update module 190 is used at least to respond to the use of any consumable, obtain feedback information on the user's use of consumables through a preset method, and input the feedback information into the preset large model platform for iterative updates.

[0187] The technical solution provided in this embodiment firstly collects key usage data of at least one vehicle consumable using a vehicle sensing module through a data acquisition module; further, it uses a pre-set large model platform to analyze the multi-dimensional consumption trend of the corresponding vehicle consumable based on user historical data and key usage data of each vehicle consumable, thereby predicting the depletion time of each vehicle consumable; further, it triggers a pre-set decision engine when the depletion time of any vehicle consumable reaches a pre-set replenishment threshold, and then uses the pre-set decision engine to generate corresponding consumable replenishment decision information by combining vehicle information, user historical data, and a pre-set consumable knowledge graph; further... The system utilizes a solution generation module to query at least one e-commerce platform, offline store, or logistics service for consumable inventory, prices, delivery time, and user reviews through a pre-set large model platform, thereby generating at least one purchase channel and delivery plan. Furthermore, the system uses a suggestion notification module to generate consumable replenishment suggestions based on consumable replenishment decision information, purchase channels, and delivery plans through the pre-set large model platform, and notifies users of these suggestions via a pre-defined method. Finally, the system uses a logistics tracking module to submit consumable orders based on user historical data through a pre-set decision engine after obtaining user authorization, tracks the consumable logistics status in real time, and pushes logistics updates through user-preferred channels until the consumables are delivered.

[0188] Therefore, this embodiment proposes a seamless vehicle consumable replenishment method based on a large model. Its core lies in constructing an intelligent system architecture driven by a large model and collaborating with the cloud. This system architecture integrates multi-source information such as vehicle sensor data, user behavior data, environmental data, and supply chain data. Leveraging the powerful analysis, prediction, decision-making, and interaction capabilities of the large model, it achieves seamless replenishment throughout the entire process, from consumable status perception, demand forecasting, personalized recommendations, automated ordering, and intelligent logistics. This embodiment can at least improve user experience and satisfaction, increase consumable replenishment efficiency and reduce time costs, optimize consumable selection and reduce error rates, promote vehicle intelligence and ecosystem interconnection, reduce operating costs and improve supply chain efficiency, and facilitate increased user stickiness and expansion of vehicle-to-everything (V2X) business models.

[0189] This embodiment provides an electronic device. Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. See also: Figure 4The electronic device 1000 includes a processor 1001 and a memory 1002. The memory 1002 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 1001, the steps in any of the above-described vehicle consumable replenishment methods are performed. Through the above technical solution, the processor 1001 and the memory 1002 are interconnected and communicate with each other via a communication bus and / or other forms of connection mechanisms (not shown). The memory 1002 stores a processor-executable computer program. When the electronic device 1000 is running, the processor 1001 executes the computer program to perform the vehicle consumable replenishment method in any optional implementation of the above embodiments, to at least achieve the following functions: collecting key usage data of at least one vehicle consumable using a vehicle sensing module; analyzing the multi-dimensional consumption trend of the corresponding vehicle consumable using a preset large model platform based at least on user historical data and key usage data of each vehicle consumable, thereby at least predicting the depletion time of each vehicle consumable; and at least when the depletion time of any vehicle consumable reaches a preset replenishment time... When a threshold is given, a preset decision engine is triggered. The preset decision engine then combines vehicle information, user historical data, and a preset consumables knowledge graph to generate corresponding consumables replenishment decision information. The preset large model platform queries at least one e-commerce platform, offline store, or logistics service for consumables inventory, prices, delivery time, and user reviews, thereby generating at least one purchase channel and delivery plan. The preset large model platform generates consumables replenishment suggestions based on the consumables replenishment decision information, purchase channels, and delivery plans, and notifies the user of the consumables replenishment suggestions through a preset method. After obtaining user authorization, the preset decision engine submits consumables orders based on user historical data, tracks the consumables logistics status in real time, and pushes logistics update information through user-preferred channels until the consumables are delivered.

[0190] This embodiment provides a computer-readable storage medium storing a computer program. When executed by a processor, the program implements the vehicle consumable replenishment method provided in all embodiments of this application: collecting key usage data of at least one vehicle consumable using a vehicle sensing module; analyzing the multidimensional consumption trend of the corresponding vehicle consumable using a preset large model platform based at least on user historical data and key usage data of each vehicle consumable, thereby predicting at least the depletion time of each vehicle consumable; triggering a preset decision engine at least when the depletion time of any vehicle consumable reaches a preset replenishment threshold, and then using the preset decision engine to combine at least vehicle information, user historical data, and key usage data of each vehicle consumable. The system uses a knowledge graph to generate corresponding consumable replenishment decision information. It queries at least one e-commerce platform, offline store, or logistics service for consumable inventory, prices, delivery times, and user reviews to generate at least one purchase channel and delivery plan. Based on the consumable replenishment decision information, purchase channels, and delivery plan, the system generates consumable replenishment suggestions and notifies users of these suggestions via a pre-defined method. After obtaining user authorization, the system submits consumable orders based on user history data using a pre-defined decision engine, tracks consumable logistics status in real time, and pushes logistics updates through user-preferred channels until the consumables are delivered.

[0191] Any combination of one or more computer-readable media may be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0192] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including—but not limited to—electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0193] The program code contained on a computer-readable medium may be transmitted using any suitable medium, including—but not limited to—wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0194] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, and C++—as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0195] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for replenishing vehicle consumables, characterized in that, At least including: Use vehicle sensor modules to collect key usage data for at least one vehicle consumable; Using a pre-set large model platform, at least based on user historical data and the key usage data of each vehicle consumable, the multi-dimensional consumption trend of the corresponding vehicle consumable is analyzed, thereby predicting at least the depletion time of each vehicle consumable. At least when the depletion time of any of the vehicle consumables is detected to reach a preset replenishment threshold, a preset decision engine is triggered, and then the preset decision engine is used to generate corresponding consumable replenishment decision information by at least combining vehicle information, user historical data and preset consumable knowledge graph. The platform uses the pre-defined large model to query at least one e-commerce platform, offline store or logistics service for consumable inventory, consumable price, delivery time and usage evaluation, thereby generating at least one purchase channel and delivery plan. The system utilizes the pre-defined large model platform to generate consumable replenishment recommendations based at least on the consumable replenishment decision information, the purchase channels, and the delivery plan, and notifies the user of the consumable replenishment recommendations through a pre-defined method. After obtaining user authorization, at least through the preset decision engine, a consumables order is submitted based on the user's historical data, and the logistics status of the consumables is tracked in real time, and logistics update information is pushed through the user's preferred channels until the consumables are delivered.

2. The vehicle consumables replenishment method according to claim 1, characterized in that, After collecting key usage data for at least one vehicle consumable using the vehicle sensing module, the method further includes at least: The onboard edge computing unit performs at least the data cleaning, format integration, and data encryption operations on the critical usage data.

3. The vehicle consumables replenishment method according to claim 1, characterized in that, After obtaining user authorization, submitting consumable orders based on the user's historical data through the preset decision engine, tracking the consumable logistics status in real time, and pushing logistics update information through user preference channels until the consumables are delivered, the method further includes at least: In response to the delivery of any consumable, the preset large model platform shall recommend and push consumable usage tutorials and / or illustrated guides to the user based on at least the consumable information and the vehicle information.

4. The vehicle consumables replenishment method according to claim 3, characterized in that, In response to the delivery of any consumable, after using the preset large model platform to recommend and push consumable usage tutorials and / or illustrated guides to the user based at least on the consumable information and the vehicle information, the process further includes at least: In response to the use of any consumable, feedback information on the user's use of consumables is obtained through the preset method, and the feedback information is input into the preset large model platform for iterative updates.

5. A vehicle consumables replenishment device, characterized in that, Used to perform the vehicle consumables replenishment method according to any one of claims 1-4; The vehicle consumables replenishment device includes at least: The data acquisition module is used to collect key usage data of at least one vehicle consumable using the vehicle sensor module; The exhaustion prediction module is used to analyze the multi-dimensional consumption trend of the corresponding vehicle consumables based on user historical data and key usage data of each vehicle consumable using a preset large model platform, and then predict the exhaustion time of each vehicle consumable. The replenishment decision module is at least used to trigger a preset decision engine when the depletion time of any of the vehicle consumables is detected to reach a preset replenishment threshold, and then generate corresponding consumable replenishment decision information by at least combining vehicle information, user historical data and preset consumable knowledge graph through the preset decision engine. The solution generation module is used to query at least one e-commerce platform, offline store or logistics service for consumable inventory, consumable price, delivery time and usage evaluation through the preset large model platform, and then generate at least one purchase channel and delivery solution. The suggestion notification module is used to generate consumable replenishment suggestions using the preset large model platform based at least on the consumable replenishment decision information, the purchase channel and the delivery plan, and to notify the user of the consumable replenishment suggestions in a preset manner; The logistics tracking module is used to submit consumable orders based on the user's historical data through the preset decision engine after obtaining user authorization, and to track the logistics status of consumables in real time, and to push logistics update information through the user's preferred channels until the consumables are delivered.

6. The vehicle consumables replenishment device according to claim 5, characterized in that, It should also include at least a data processing module; The data processing module is at least used to perform data cleaning, format integration, and data encryption on the key usage data through the vehicle-mounted edge computing unit.

7. The vehicle consumables replenishment device according to claim 5, characterized in that, It should also include at least a tutorial push module; The tutorial push module is used at least to respond to the delivery of any consumable, and to recommend and push consumable usage tutorials and / or illustrated guides to the user based on the consumable information and the vehicle information using the preset large model platform.

8. The vehicle consumables replenishment device according to claim 5, characterized in that, It should also include at least an iterative update module; The iterative update module is at least used to respond to the use of any consumable, obtain feedback information on the user's use of consumables through the preset method, and input the feedback information into the preset large model platform for iterative updates by the preset large model platform.

9. An electronic device comprising a memory and a processor, the memory storing a computer program executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the vehicle consumables replenishment method according to any one of claims 1 to 4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps in the vehicle consumables replenishment method according to any one of claims 1 to 4.

Images