Vehicle maintenance reminding method and system, storage medium and vehicle

Abstract

The invention relates to the technical field of vehicle maintenance, in particular to a vehicle maintenance reminding method and system, a storage medium and a vehicle. The method comprises the following steps: acquiring vehicle data, wherein the vehicle data at least comprises target part state information and historical maintenance information; the target part state information is the state information of parts needing to be maintained of the vehicle; inputting target part state information and historical maintenance information of the target part into a corresponding prediction model according to an attribute tag of the target part to obtain a part maintenance time interval of the target part; the prediction model corresponds to the attribute tag; inputting the part maintenance time interval of each target part into a maintenance model to obtain a vehicle maintenance reminding time set; and outputting reminding information based on the vehicle maintenance reminding time set. According to the method, the unnecessary maintenance frequency is reduced, the maintenance cost of a vehicle owner is reduced, and meanwhile, the pertinence and effectiveness of maintenance are improved through data acquisition and data analysis.

Description

Technical Field

[0001] This invention relates to the field of vehicle maintenance technology, and in particular to a vehicle maintenance reminder method, system, storage medium, and vehicle. Background Technology

[0002] Users need to maintain their vehicles during use. Traditional maintenance methods mainly rely on fixed maintenance cycles and manual reminders. These reminder times are relatively fixed and cannot provide accurate maintenance reminders based on the characteristics of vehicle parts.

[0003] Therefore, how to provide accurate maintenance reminders based on the characteristics of vehicle parts has become an urgent technical problem to be solved. Summary of the Invention

[0004] In view of the above problems, this disclosure provides a vehicle maintenance reminder method, system, storage medium and vehicle that overcomes or at least partially solves the above problems, with the aim of providing accurate maintenance reminder times, reducing unnecessary maintenance frequency, lowering maintenance costs for vehicle owners, and improving the targeting and effectiveness of maintenance through data collection and analysis.

[0005] The objective of this invention can be achieved through the following technical solutions: A first aspect of the present invention provides a vehicle maintenance reminder method, the method comprising: Acquire vehicle data, which includes at least target part status information and historical maintenance information; the target part status information is the status information of the parts of the vehicle that require maintenance. Based on the attribute tags of the target part, the target part status information and historical maintenance information of the target part are input into the corresponding prediction model to obtain the part maintenance time interval of the target part; the prediction model corresponds to the attribute tags. Input the maintenance time interval of each target part into the maintenance model to obtain the vehicle maintenance reminder time set; Based on the set of vehicle maintenance reminder times, a reminder message is output.

[0006] In some embodiments, The attribute tags include natural duration depletion type and working duration depletion type. Specifically, based on the attribute tags of the target part, the target part's status information and historical maintenance information are input into the corresponding prediction model to obtain the predicted maintenance time interval for the target part, including: The target part is identified as having a natural time-depletion type attribute label. The target part status information, historical maintenance information and predicted vehicle environment data are input into the first prediction model to obtain the first predicted maintenance time interval of the target part. The target part is identified as having a working time consumption type attribute label. The target part status information, historical maintenance information and predicted vehicle operation data are input into the second prediction model to obtain the first predicted maintenance time interval of the target part. Based on the first predicted maintenance time interval of the target part, the maintenance time interval of the part is determined.

[0007] In some embodiments, inputting the target part status information and historical maintenance information of the target part into the corresponding prediction model to obtain the part maintenance time interval of the target part includes: Based on the vehicle maintenance manual and historical maintenance information, a second predicted maintenance interval is determined for each of the target parts; Based on the first predicted maintenance time interval and the second predicted maintenance interval, the maintenance time interval for each target part is obtained.

[0008] In some embodiments, obtaining the maintenance time interval for each target part based on the first predicted maintenance time interval and the second predicted maintenance interval includes: Obtain the earliest and latest dates in the first and second predicted maintenance time intervals for the target part, and determine the part maintenance time interval based on the earliest and latest dates.

[0009] In some embodiments, The step of inputting the target part's status information, historical maintenance information, and predicted vehicle environment data into the first prediction model to obtain the first predicted maintenance time interval for the target part includes: Based on historical vehicle operation data, the vehicle's user profile, and seasonal information, predictive vehicle environmental data is determined; the predictive vehicle environmental data includes at least one of air quality information, temperature information, and humidity information within a preset time period. The target part's status information, historical maintenance information, and predicted vehicle environment data are input into the first prediction model to obtain the first predicted maintenance time interval for the target part.

[0010] In some embodiments, The step of inputting the target part's status information, historical maintenance information, and predicted vehicle operation data into the second prediction model to obtain the first predicted maintenance time interval for the target part includes: Based on historical vehicle operation data, user profiles of the vehicle, and seasonal information, predicted vehicle operation data is obtained; the predicted vehicle operation data includes at least one of the working duration of the target part within a preset time period and the average working intensity of the target part. The target part's status information, historical maintenance information, and predicted vehicle operation data are input into the second prediction model to obtain the first predicted maintenance time interval for the target part.

[0011] In some embodiments, The step of inputting the target part status information and historical maintenance information of the target part into the corresponding prediction model to obtain the part maintenance time interval of the target part includes: Input the target part status information and historical maintenance information of the target part into the corresponding prediction model to obtain the first predicted maintenance time interval and the optimal part maintenance date of the target part; Based on the user profile of the vehicle, determine the vehicle tag; based on the vehicle tag, determine the key target parts of the vehicle; Based on the earliest date of the first predicted maintenance time interval and the optimal part maintenance date, the part maintenance time interval of the key target part is determined.

[0012] In some embodiments, The step involves inputting the maintenance time interval of each target part into the maintenance model to obtain a set of vehicle maintenance reminder times, including: Based on the clustering algorithm and the preset number of reminders, all the maintenance time intervals of the parts are clustered to obtain the first reminder time cluster, and the number of the first reminder time cluster is the preset number of reminders; The reminder date is obtained based on the earliest date in the first reminder time cluster; Based on each of the aforementioned reminder dates, the set of vehicle maintenance reminder times is obtained.

[0013] In some embodiments, Based on the aforementioned set of vehicle maintenance reminder times, reminder information is output, including: If the reminder date in the vehicle maintenance reminder time set is reached, output the target part maintenance content and the corresponding part maintenance time interval corresponding to the first reminder time cluster.

[0014] A second aspect of the technical solution of the present invention provides a vehicle maintenance reminder system. The system includes: Data acquisition module: Acquires vehicle data, which includes at least target part status information and historical maintenance information; the target part status information is the status information of the parts of the vehicle that require maintenance. The parts maintenance time interval module inputs the target part status information and historical maintenance information of the target part into the corresponding prediction model based on the attribute tags of the target part to obtain the parts maintenance time interval of the target part; the prediction model corresponds to the attribute tags. The reminder information module inputs the maintenance time interval of each target part into the maintenance model to obtain a set of vehicle maintenance reminder times; The sending module outputs reminder information based on the set of vehicle maintenance reminder times.

[0015] A third aspect of the present invention provides a computer-readable storage medium having instructions stored thereon, which, when executed by one or more processors, cause the processors to perform the vehicle maintenance reminder method as described in the first aspect.

[0016] A fourth aspect of the present invention provides a vehicle comprising: Memory, used to store executable program code; A processor is configured to call and run the executable program code from the memory, causing the vehicle to perform the method as described in any of the examples of the first aspect above.

[0017] The technical solution proposed in this application can bring the following beneficial effects: 1. This invention uses different algorithms to predict the maintenance time of different types of vehicle parts based on their different types of wear and tear, thus avoiding the prediction deviation caused by a single algorithm for different part types.

[0018] 2. Based on the predicted maintenance time of parts, this invention combines the data recorded in the maintenance manual to determine whether the predicted maintenance time of parts is reasonable, and organizes the data according to the constructed maintenance model to obtain a set of maintenance times, thus ensuring the pertinence and effectiveness of the maintenance time of each part.

[0019] 3. Based on the different maintenance times of different parts, this invention uses a clustering algorithm to evaluate the appropriate reminder dates within a preset reminder period, reducing unnecessary maintenance frequency and lowering maintenance costs for car owners; furthermore, in terms of user experience, it provides convenient maintenance services for car owners, enhancing their satisfaction.

[0020] The above description is merely an overview of the technical solution disclosed herein. In order to better understand the technical means of this disclosure and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this disclosure more apparent and understandable, specific embodiments of this disclosure are described below. Attached Figure Description

[0021] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this disclosure. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 This is a flowchart illustrating the steps of a vehicle maintenance reminder method provided in the embodiments of this specification; Figure 2 This is a schematic diagram of the structure of a vehicle maintenance reminder system provided in the embodiments of this specification; Figure 3 This is a structural schematic diagram of a vehicle provided in the embodiments of this specification. Detailed Implementation

[0022] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. The technical solutions provided by various embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0023] Figure 1 This is a flowchart illustrating the steps of a vehicle maintenance reminder method provided in one or more embodiments of this specification.

[0024] The technical solution described in this method aims to provide accurate maintenance reminders, reducing unnecessary maintenance frequency and lowering maintenance costs for car owners. Simultaneously, through data collection and analysis, it improves the targeting and effectiveness of maintenance. Compared to traditional vehicle maintenance reminder methods, this solution designs a vehicle maintenance reminder system that, based on vehicle data and maintenance manual data, personalized predictions of maintenance times for various parts can be made, allowing maintenance to be completed within the set frequency and schedule within the maintenance cycle. In terms of efficiency, it reduces unnecessary maintenance frequency, lowering maintenance costs for car owners. Regarding accuracy, data collection and analysis significantly improve the targeting and effectiveness of maintenance. In terms of user experience, the intelligent reminder system provides convenient maintenance services for car owners, enhancing their satisfaction.

[0025] For example, such as Figure 1 As shown, a vehicle maintenance reminder method includes: S101. Obtain vehicle data, wherein the vehicle data includes at least target part status information and historical maintenance information; the target part status information is the status information of the parts of the vehicle that require maintenance. By acquiring vehicle data, especially target part status information and historical maintenance information, the current status of the target parts of the vehicle can be fully reflected. The target part status information is collected by vehicle sensors and serves as the data basis for training various models in this method. In one specific embodiment, The status information of vehicle parts that require maintenance is collected through vehicle sensors, including at least the status information of powertrain parts. For example, engine oil pressure / temperature, oil level / quality (via dielectric constant sensor), air-fuel ratio, knock signal, etc., and battery health status, current charge, charge-discharge cycle count, individual cell voltage / temperature, etc. Component status information of the chassis and braking system, for example, the braking system, such as brake pad thickness, brake disc temperature, brake fluid level, etc. Information on the status of components in the vehicle body and other systems, for example, the air conditioning system, such as refrigerant pressure, compressor operating status, etc. Historical maintenance information should include at least the vehicle's historical maintenance time, the details of the historical maintenance, and the vehicle's historical mileage. The historical maintenance time includes the date of each maintenance, and the historical mileage includes the total mileage driven and the mileage since the last maintenance. S102. Based on the attribute tags of the target part, input the target part status information and historical maintenance information of the target part into the corresponding prediction model to obtain the part maintenance time interval of the target part; the prediction model corresponds to the attribute tags. Based on the attribute labels of the target parts, the target parts are classified. According to the different characteristics of the parts corresponding to different attribute labels, the data is input into the corresponding prediction model, making the prediction model more targeted and the training data more accurate. Therefore, depending on the attribute labels of the target parts, different prediction models can be used to output the corresponding maintenance time intervals for different target parts, ensuring the stability and accuracy of the prediction results.

[0026] The attribute tags include natural duration depletion type and working duration depletion type, for example: Natural time-degradation type is characterized by gradual and cumulative wear and tear over natural time. The performance degradation of this type of component is a continuous time series process. For example, in power batteries, the state of health (SOH) of the battery is closely related to the number of charge and discharge cycles, depth of charge and discharge, and temperature history throughout its entire life cycle. Engine oil: The degradation of engine oil is related to the engine's operating hours, speed load, and temperature history. Working time-related wear and tear occurs with working time and intensity. Its characteristic is that the wear and tear is related to the statistical features of working time and usage intensity, rather than a strict chronological order. For example, spark plugs: aging is related to total fuel consumption, total engine working time, and number of ignitions. Air filter: The degree of clogging is related to the total mileage and the average dust concentration in the driving environment (which can be summarized into a statistical value).

[0027] Furthermore, The step of inputting the target part's status information and historical maintenance information into the corresponding prediction model based on the target part's attribute tags to obtain the predicted maintenance time interval for the target part includes: The target part is identified as having a natural time-depletion type attribute label. The target part status information, historical maintenance information and predicted vehicle environment data are input into the first prediction model to obtain the first predicted maintenance time interval of the target part. Based on historical vehicle operation data, the vehicle's user profile, and seasonal information, predictive vehicle environmental data is determined; the predictive vehicle environmental data includes at least one of air quality information, temperature information, and humidity information within a preset time period. When the attribute label of the target part is natural time-depletion type, more consideration is given to the wear and tear accumulated over natural time. Therefore, the first prediction model is trained by the target part status information, historical maintenance information and predicted vehicle environment data. Then, the first prediction model is used to predict the first predicted maintenance time interval of the natural time-depletion type target part. Based on the predicted vehicle environment data, the characteristics of the natural time-depletion type target part are better reflected, and the prediction is more stable and accurate.

[0028] For example, Historical vehicle operation data includes sensor data of the target parts, mileage data, driving behavior, running time, fault information, etc. The mileage data includes total mileage, mileage per trip, and average daily / monthly mileage. Driving behavior includes statistics on the frequency and intensity of rapid acceleration, emergency braking, and high-speed cornering, average vehicle speed, engine high-speed operation time, and energy management (hybrid / electric). Among them, energy management (hybrid / electric) includes the percentage of pure electric driving range, engine intervention frequency, charging habits (fast charging / slow charging ratio, charging depth), etc. Operating time includes total operating hours and the operating time of each system (such as air conditioning); Fault information includes the time, mileage, and symptoms of the fault, as well as the fault diagnosis results and replaced parts.

[0029] For example, The vehicle user profile includes vehicle identification number, production information (brand, model, series, production year, batch), powertrain configuration (engine model, displacement, transmission type, drive type), key component information, initial registration information, etc.

[0030] For example, Seasonal information includes average ambient temperature, humidity, altitude, etc.

[0031] Based on historical vehicle operation data, user profiles of the vehicles, and seasonal information, a deep learning network is trained. Based on the trained deep learning network, predicted vehicle environmental data is determined. The predicted vehicle environmental data includes at least one of air quality information, temperature information, and humidity information within a preset time period. For example, the preset time period is 10 to 60 days, and the air quality information is the predicted PM2.5 value within the preset time period. In this embodiment, a long short-term memory network is used for the deep learning network. After training the model with data, the predicted vehicle environmental data can be output. The deep learning network and its training method are existing technologies and will not be described in detail here.

[0032] The target part is identified as having a working time consumption type attribute label. The target part status information, historical maintenance information and predicted vehicle operation data are input into the second prediction model to obtain the first predicted maintenance time interval of the target part. Based on historical vehicle operation data, user profiles of the vehicle, and seasonal information, predicted vehicle operation data is obtained; the predicted vehicle operation data includes at least one of the working duration of the target part within a preset time period and the average working intensity of the target part. When the attribute label of the target part is working time wear type, more consideration is given to the wear caused by the working time and intensity of the part. Therefore, by using the target part status information, historical maintenance information and predicted vehicle operation data, the data features of the part's working time and intensity are extracted, and a second prediction model is trained. Then, the second prediction model is used to predict the first predicted maintenance time interval of the working time wear type target part. Based on the predicted vehicle operation data, the severity of wear of the target part is better identified, and the safety and maintenance cost of the target part are better balanced.

[0033] For example, Historical vehicle operation data includes sensor data of the target parts, mileage data, driving behavior, running time, fault information, etc. Sensor data for the target component includes operating temperature, peak temperature, hydraulic or braking pressure, motor operating current, voltage, actuator stroke, valve opening, etc.; directly reflecting the working status and load of the component, and the average working intensity of the target component. Among them, the mileage data includes total mileage, single trip mileage, and daily / monthly average mileage; it indirectly reflects the frequency of use and wear accumulation of parts, and is combined with working time to predict the average working intensity of target parts; Driving behaviors include the frequency of rapid acceleration or deceleration, the frequency of sharp turns, the duration of high-speed cruising, and the time the engine runs at high speeds; these behaviors directly affect the working strength of parts, and aggressive driving will significantly increase the load on parts (such as brake pads, engine, and transmission). Operating time includes total operating hours and power-on time for specific systems (such as air conditioning compressors and hydraulic systems); this is a direct indicator for calculating working hours. Fault information includes the time, mileage, and symptoms of the fault, fault diagnosis results, and replaced parts; it indicates the health degradation process of the part, and frequent faults indicate that the average workload of the target part is too high.

[0034] For example, Vehicle user profiles include: usage patterns, vehicle type, user information, route preferences, maintenance awareness, etc. Usage patterns: Commuting frequency (daily commuting distance), frequency of long-distance travel, proportion of nighttime driving, etc. Vehicle types: private cars, commercial vehicles, etc.; User information: age, gender, occupation (affects usage intensity); Route preferences: city roads, highways, off-road sections; Maintenance awareness: Whether regular maintenance is performed and the level of attention paid to the vehicle's condition; User profiles are typically extracted from vehicle usage data, user surveys, or third-party data and encoded as numerical or categorical features.

[0035] For example, Seasonal information includes average ambient temperature, humidity, altitude, etc.

[0036] Based on historical vehicle operation data, user profiles of the vehicle, and seasonal information, a deep learning network is trained, and the trained deep learning network is used to determine predicted vehicle operation data. The predicted vehicle operation data includes at least one of the working time of the target part within a preset time period and the average working intensity of the target part. For example, Working time of the target part: The expected cumulative operating time of the target part within a preset time period; for example, for engine parts, it can be the number of engine operating hours; for brake pads, it can be the brake usage time. Average working intensity of the target part: The average load or pressure on the target part during operation over a preset time period. For example: For engine parts, average workload may be expressed as average engine speed or average torque. For brake pads, average working intensity may be expressed as average braking pressure or braking frequency / mileage.

[0037] For a transmission, average workload may be expressed as average shift frequency or load factor; For example, The preset duration is 10 to 60 days. In this embodiment, a long short-term memory network and a fully connected layer are used to train the model through data. The working time of the target part and the average working intensity of the target part can be output. The deep learning network and its training method are existing technologies and will not be described in detail here.

[0038] Based on the first predicted maintenance time interval of the target part, the maintenance time interval of the part is determined.

[0039] In one specific embodiment, The target part's status information, historical maintenance information, and predicted vehicle environment data are input into the first prediction model to obtain the first predicted maintenance time interval for the target part: For example, if the attribute label of the target part is determined to be of the natural time-depletion type, such as a power battery, and the sensor data of the part includes charge and discharge cycles, average temperature, etc., then the target part status information is formed, which is represented as {power battery, charge and discharge cycles 100, average temperature 50}. Historical maintenance information includes the name of the part being maintained, the date of the last maintenance, the mileage since the last maintenance, and the contents of the last part maintenance, represented as {Power Battery, last maintenance date 2024-5-16, mileage since the last maintenance 500km}. The predicted vehicle environmental data includes air quality information, temperature information, and humidity information. For example, it can be represented as {Air quality information PM2.5: 180µg / m³, temperature information 10 degrees Celsius, humidity information 35%}. The above information is input into the first prediction model, which is an LSTM model, short for Long Short-Term Memory Network. A time series dataset is constructed based on the target part's state information, historical maintenance information, and predicted vehicle environment data, and the corresponding time series features are extracted. The input dimension, network structure, prediction target, etc. are set, and the first predicted maintenance time interval of each part is output respectively. For example, the SOH value of the power battery can be used to obtain the number of charge-discharge cycles, the average depth of charge and discharge (DOD), the operating temperature sequence, the last maintenance time (May 16, 2024), air quality information (PM2.5 180µg / m³, temperature 10 degrees Celsius, humidity 35%), etc. Input dimensions: 8 features; Network structure: including LSTM layer, Dropout layer, fully connected layer, and output layer; Prediction target: SOH value and the required time; Output: SOH value drops to 80% in 3 months; The first predicted maintenance time interval is obtained through the first prediction model.

[0040] In one specific embodiment, The target part's status information, historical maintenance information, and predicted vehicle operation data are input into the second prediction model to obtain the first predicted maintenance time interval for the target part: For example, if the attribute label of the target part is determined to be working time loss type, such as spark plug, and the part sensor data includes fuel consumption, total engine working time, and number of ignitions, then the target part status information is formed, which is represented as {spark plug, fuel consumption 10L / km, total engine working time 200h, number of ignitions 50}. Historical maintenance information includes the name of the part being maintained, the date of the last maintenance, the mileage since the last maintenance, and the contents of the last part maintenance, represented as {Power Battery, last maintenance date 2024-5-16, mileage since the last maintenance 500km}. The predicted vehicle operation data includes the working time of the target part and the average working intensity of the target part within a preset time period; for example, it is expressed as {working time 100h, average working intensity 60%}. For example, the average workload is the ratio of the part's workload to the total working time within a time interval T; wherein the part's workload within the time interval T is obtained by using data collected by the part's sensors through a deep learning model. For example, the second prediction model is a random forest model; based on the target part's status information, historical maintenance information, and predicted vehicle operation data, a part feature vector dataset is constructed; the number of trees, maximum depth, minimum number of samples required for internal node splitting, minimum number of samples for leaf nodes, number of features considered in this split, etc. are set, the current part feature vector is input, and the first predicted maintenance time interval is output; For example, in brake pad maintenance prediction, the features used include at least the mileage of the brake pads, the installation time of the brake pads, and the number of braking operations; the number of trees is set to 200, the maximum depth is 15, the minimum number of samples required for internal node splitting is 20, the minimum number of samples for leaf nodes is 10, and the number of features considered in this split is 20; the training data consists of 1000 complete life cycle records of brake pads; the feature vector of the brake pad is input, and the first predicted maintenance time interval is output. The training of LSTM and random forest models is an existing technology and will not be described in detail in this embodiment.

[0041] In one specific embodiment, Based on the vehicle maintenance manual and historical maintenance information, a second predicted maintenance interval is determined for each of the target parts; The vehicle maintenance manual includes maintenance time intervals and / or maintenance mileage intervals. Since different parts require maintenance reminders based on the earlier of the two—maintenance time and maintenance mileage—the second predicted maintenance interval ensures accuracy and avoids the limitations of considering only a single predicted maintenance time interval. Ignoring maintenance mileage may lead to overly late predictions. Therefore, fully considering both the first and second predicted maintenance intervals for the target part ensures accuracy. When determining the second predicted maintenance interval, the maintenance mileage of all parts requiring maintenance needs to be converted into predicted maintenance time. For example, if the vehicle maintenance manual specifies that spark plugs should be replaced every 45,000 to 50,000 kilometers, then the current maintenance mileage is 45,000 to 50,000 kilometers. The vehicle maintenance manual specifies a maintenance interval of 12 to 18 months; Get the vehicle's mileage since the last spark plug maintenance and the current mileage, and calculate the difference to get the vehicle's mileage since the last maintenance, such as 20,000 kilometers. The remaining maintenance mileage is then 25,000 to 30,000 kilometers; Based on the vehicle's operating data, determine the average monthly mileage over 6 months, such as an average monthly mileage of 2000 kilometers for the car owner. The maintenance mileage for the parts requiring maintenance is converted to a predicted maintenance interval of 12.5 to 15 months. The second predicted maintenance interval is the combination of the maintenance time interval and the maintenance mileage interval, that is, the second predicted maintenance interval for spark plugs is 12 to 15 (months).

[0042] In one specific embodiment, Based on the first predicted maintenance time interval and the second predicted maintenance interval, the maintenance time interval for each target part is obtained, including: Obtain the earliest and latest dates in the first and second predicted maintenance time intervals for the target part, and determine the maintenance time interval for the part based on the earliest and latest dates; For example, if the first predicted maintenance interval for a spark plug is 10 to 13 months and the second predicted maintenance interval is 12 to 15 months, then the maintenance interval for the part is 10 to 15 months, which means that the spark plug needs to be maintained within 10 to 15 months since the last maintenance.

[0043] In one specific embodiment, The target part's status information and historical maintenance information are input into the corresponding prediction model to obtain the target part's maintenance time interval, including: Input the target part status information and historical maintenance information of the target part into the corresponding prediction model to obtain the first predicted maintenance time interval and the optimal part maintenance date of the target part; Based on the user profile of the vehicle, determine the vehicle tag; based on the vehicle tag, determine the key target parts of the vehicle; As a better approach, the importance of key target parts needs to be considered, and therefore, the weight of their safety needs to be given more weight. The optimal maintenance date of the target parts can be predicted by the model to better ensure the safety of key target parts. The minimum value of the first predicted maintenance time interval focuses more on the safety of the parts, while the maximum value focuses more on the cost of the parts. The optimal maintenance date better balances the safety and maintenance cost of key target parts.

[0044] For example, based on the user profile of a vehicle, vehicle tags can be determined, such as sedan, SUV, off-road vehicle, etc.; based on different vehicle tags, key target parts can be determined, such as the engine, shock absorbers, transmission, etc. for SUVs.

[0045] Based on the earliest date of the first predicted maintenance time interval and the optimal part maintenance date, the part maintenance time interval of the key target part is determined; the optimal part maintenance date is the optimal part maintenance date predicted by the model, taking into account the safety and cost of the part; the minimum value of the part maintenance time interval of the key target part is the earliest date of the first predicted maintenance time interval, and the maximum value is the optimal part maintenance date.

[0046] For example, by obtaining the first predicted maintenance time interval through the above LSTM model or random forest model, the optimal maintenance date of the part can be further predicted. For example, if the first predicted maintenance time interval for the spark plug is 10 to 13 (months) according to the model, the corresponding time point is from September 12, 2025 to December 12, 2025; the optimal maintenance date of the part is November 26, 2025. Then the time point corresponding to the maintenance time interval of the key target part is from September 12, 2025 to November 26, 2025.

[0047] S103. Input the maintenance time interval of each target part into the maintenance model to obtain a set of vehicle maintenance reminder times, including: Based on the clustering algorithm and the preset number of reminders, all the maintenance time intervals of the parts are clustered to obtain the first reminder time cluster, and the number of the first reminder time cluster is the preset number of reminders; The reminder date is obtained based on the earliest date in the first reminder time cluster; Based on each of the aforementioned reminder dates, the set of vehicle maintenance reminder times is obtained.

[0048] Clustering algorithms can better determine the reminder dates for target parts, assess the appropriate reminder dates within the preset reminder cycle, reduce unnecessary maintenance frequency, and lower maintenance costs for car owners. Furthermore, in terms of user experience, it provides convenient maintenance services for car owners, enhancing their satisfaction.

[0049] In one specific embodiment, The maintenance model uses the k-means clustering algorithm to determine the reminder time, avoiding reminding every single part and ensuring that all parts can remind the car owner for maintenance within a preset period. The k-means clustering algorithm is also known as the k-means clustering algorithm. Based on the maintenance time interval of the target part, the reminder time is determined as the difference between the maintenance time interval and the preset advance time; reminder times outside the reminder cycle are filtered out to obtain a primary reminder time set; Based on the k-means clustering algorithm and a preset number of reminders, the initial reminder time set is clustered to obtain the first reminder time cluster. The center value of the first reminder time cluster and the minimum reminder time of each first reminder time cluster are calculated. Determine the difference between the center values ​​of the first reminder time cluster. If the difference is less than the set reminder threshold, merge the first reminder time cluster to obtain the second reminder time cluster. The vehicle maintenance reminder time set is obtained based on the minimum reminder time of the first reminder time cluster (which is not merged) and the minimum reminder time of the second reminder time cluster.

[0050] For example, Based on the maintenance time T for each part, assuming the current time is T0 and the preset advance time is L, if L is 30 days, then the reminder time di is T0+TL; in order to cover the parts that the car owner should maintain with fewer reminders, a reminder cycle is set. If the reminder cycle is 1 year, then the reminder cycle range is [T0, T0+365]. First, filter the reminder time di for each part, and select the reminder time di within the reminder cycle interval [T0, T0+365] to obtain the initial reminder time set; The primary reminder time set is determined. If the reminder time di of all parts is not within the reminder cycle range, the primary reminder time set is empty and no reminder information is generated. If it is determined that the primary reminder time set contains only one reminder time di, then only the reminder time di will be output, and one reminder message will be generated. If the set of primary reminder times is determined to be greater than or equal to two reminder times di, then k-means clustering is used for identification; in this embodiment, the car owner is reminded twice within the reminder cycle interval, and the parts that should be maintained are covered in the two reminders; Then, the set of primary reminder times can be represented as Tr={tr1, tr2, tr3, ..., trN}, where trN represents the primary reminder time of the Nth part that meets the reminder requirements; Clustering algorithms are used to merge N initial reminder times into K reminder groups. In this embodiment, K=2, where K is the preset number of reminders. The objective function is then expressed as: ; Where C k Represents the k-th reminder cluster; ti is the reminder time point for the i-th part, μ k It is the center of the kth cluster (i.e., the average value of all time points in the cluster); pass C was calculated k In this embodiment, K=2, so the two reminder clusters are C1 and C2. This represents the minimum reminder time for cluster C1 and the minimum reminder time for cluster C2, specifically including: For each cluster C k The earliest reminder time is selected as the reminder time for this cluster, represented as: TS k =min{t:t∈C k}; then we finally get TS={TS1,TS2}, where TS1 represents the minimum reminder time for reminder cluster C1; and TS2 represents the minimum reminder time for reminder cluster C2.

[0051] When the preset number of reminders is greater than 1, multiple reminder time clusters are obtained; The primary reminder time set is clustered to obtain the first reminder time cluster, and the center value of the first reminder time cluster and the minimum reminder time of each first reminder time cluster are calculated; Determine the difference between the center values ​​of the first reminder time cluster. If the difference is less than the set reminder threshold, merge the first reminder time cluster to obtain the second reminder time cluster. The vehicle maintenance reminder time set is obtained based on the minimum reminder time of the first reminder time cluster (which is not merged) and the minimum reminder time of the second reminder time cluster. Sort the minimum reminder times of the first and second reminder time clusters (which are not merged) in ascending order to obtain a reminder time sequence arranged in ascending order, denoted as the vehicle maintenance reminder time set.

[0052] For example, The initial set of reminder times is clustered to obtain reminder time clusters. If multiple reminder time clusters are obtained, such as C1, C2, C3, and C4, the center point of each reminder time cluster is calculated, and then the difference between each pair of clusters is calculated. If the difference between reminder time clusters C1 and C2 is less than the set reminder threshold, such as 90 days, then reminder time clusters C1 and C2 are merged and denoted as reminder time cluster C. 11 The minimum reminder time between reminder time clusters C1 and C2 is taken as the reminder time cluster C. 11 The reminder time is calculated as follows: TS 11 =min(TS1, TS2), reminding time cluster C 11 This is the second reminder time cluster; and so on, until all reminder time clusters cannot be merged. The minimum reminder time of each reminder time cluster is then sorted to obtain the reminder time set. For example, reminder time clusters C3 and C4 cannot be merged, so reminder time cluster C... 11 The minimum reminder time is TS 11 The minimum reminder time for reminder time cluster C3 is TS3, and the minimum reminder time for reminder time cluster C4 is TS4. Arranged in ascending order of time, we get {TS3, TS4}. 11 TS4} is denoted as the set of vehicle maintenance reminder times; S104. Based on the vehicle maintenance reminder time set, output reminder information; if the reminder date in the vehicle maintenance reminder time set is reached, output the target part maintenance content and the corresponding part maintenance time interval corresponding to the first reminder time cluster; In this embodiment, based on the maintenance time T of each part, assuming the current time is T0 and the preset advance time is L, the target parts that need to be reminded within the preset time and their reminder times are obtained; this avoids reminding parts too early, ensures the relative concentration of reminders, and balances the safety and cost of part maintenance. To balance the number of reminders, when multiple reminder time clusters are obtained, if the center points of two adjacent reminder time clusters are close to each other and less than the set reminder threshold, it can be considered that the reminder times for the target parts in the two adjacent reminder time clusters are close. In this case, the two reminder time clusters can be merged so that the reminder dates for the target parts meet the requirements while avoiding reminder times that are too close, which would increase the maintenance costs for car owners.

[0053] In one specific embodiment, a vehicle maintenance reminder system is provided. Figure 2 This is a schematic diagram of the structure of a vehicle maintenance reminder system provided in the embodiments of this specification; For example, such as Figure 2As shown, the system 200 includes: Data acquisition module 201: Acquires vehicle data, which includes at least target part status information and historical maintenance information; the target part status information is the status information of the parts of the vehicle that require maintenance. The parts maintenance time interval module 202 inputs the target part status information and historical maintenance information of the target part into the corresponding prediction model according to the attribute tags of the target part to obtain the parts maintenance time interval of the target part; the prediction model corresponds to the attribute tags. The reminder information module 203 inputs the maintenance time interval of each target part into the maintenance model to obtain a set of vehicle maintenance reminder times; The sending module 204 outputs reminder information based on the set of vehicle maintenance reminder times.

[0054] Figure 3 This is a structural schematic diagram of a vehicle provided in the embodiments of this specification; For example, such as Figure 3 As shown, the vehicle 300 includes a memory 301 and a processor 302. The memory 301 stores executable program code 3011, and the processor 302 is used to call and execute the executable program code 3011 to perform a vehicle maintenance reminder method. include: Acquire vehicle data, which includes at least target part status information and historical maintenance information; the target part status information is the status information of the parts of the vehicle that require maintenance. Based on the attribute tags of the target part, the target part status information and historical maintenance information of the target part are input into the corresponding prediction model to obtain the part maintenance time interval of the target part; the prediction model corresponds to the attribute tags. Input the maintenance time interval of each target part into the maintenance model to obtain the vehicle maintenance reminder time set; Based on the set of vehicle maintenance reminder times, a reminder message is output.

[0055] A computer-readable storage medium is provided having instructions stored thereon, which, when executed by one or more processors, cause the processors to perform the vehicle maintenance reminder method as described in the first aspect; include: Acquire vehicle data, which includes at least target part status information and historical maintenance information; the target part status information is the status information of the parts of the vehicle that require maintenance. Based on the attribute tags of the target part, the target part status information and historical maintenance information of the target part are input into the corresponding prediction model to obtain the part maintenance time interval of the target part; the prediction model corresponds to the attribute tags. Input the maintenance time interval of each target part into the maintenance model to obtain the vehicle maintenance reminder time set.

[0056] This embodiment can divide the vehicle into functional modules according to the above method example. For example, each function can be assigned to a separate module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0057] When each function is divided into modules corresponding to its specific function, the vehicle may include: a data acquisition module, a data module, a predicted maintenance time module, a reminder information module, and a sending module. It should be noted that all relevant content of each step involved in the above method embodiments can be referenced from the functional descriptions of the corresponding modules, and will not be repeated here.

[0058] The vehicle provided in this embodiment is used to execute the vehicle maintenance reminder method described above, and thus can achieve the same effect as the above implementation method.

[0059] When using integrated units, the vehicle may include a processing module and a storage module. The processing module is used to control and manage the vehicle's actions. The storage module supports the vehicle in executing program code and data.

[0060] The processing module may be a processor or a controller, which can implement or execute various exemplary logic blocks, modules, and circuits as disclosed in this application. The processor may also be a combination of computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc., and the storage module may be a memory.

[0061] This embodiment also provides a computer-readable storage medium (including but not limited to disk storage, CD-ROM, optical storage, etc.) storing computer program code. When the computer program code is run on a computer, the computer executes the above-mentioned related method steps to implement the vehicle maintenance reminder method provided in the above embodiment.

[0062] This embodiment also provides a computer program product. When the computer program product is run on a computer, it causes the computer to perform the aforementioned steps to implement the vehicle maintenance reminder method provided in the above embodiment. The beneficial effects of the above embodiments can be found in the corresponding methods described above, and will not be repeated here.

[0063] Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0064] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules or units is merely a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms. In the description of this disclosure, it should be understood that if terms such as "upper," "lower," "front," "rear," "left," and "right" are used to indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, they are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the indicated position or element must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this disclosure.

[0065] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0066] The above are merely embodiments of this disclosure and are not intended to limit the scope of this disclosure. Various modifications and variations can be made to this disclosure by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the scope of the claims of this disclosure.

Claims

1. A vehicle maintenance reminder method, characterized in that, include: Acquire vehicle data, which includes at least target part status information and historical maintenance information; The target part status information refers to the status information of the parts of the vehicle that require maintenance. Based on the attribute tags of the target part, the target part status information and historical maintenance information of the target part are input into the corresponding prediction model to obtain the part maintenance time interval of the target part; the prediction model corresponds to the attribute tags. Input the maintenance time interval of each target part into the maintenance model to obtain the vehicle maintenance reminder time set; Based on the set of vehicle maintenance reminder times, output reminder information.

2. The method according to claim 1, characterized in that, The attribute tags include natural time-depletion type and working time-depletion type. Based on the attribute tags of the target part, the target part's status information and historical maintenance information are input into the corresponding prediction model to obtain the predicted maintenance time interval for the target part, including: The target part is identified as having a natural time-depletion type attribute label. The target part status information, historical maintenance information and predicted vehicle environment data are input into the first prediction model to obtain the first predicted maintenance time interval of the target part. The target part is identified as having a working time consumption type attribute label. The target part status information, historical maintenance information and predicted vehicle operation data are input into the second prediction model to obtain the first predicted maintenance time interval of the target part. Based on the first predicted maintenance time interval of the target part, the maintenance time interval of the part is determined.

3. The method according to claim 2, characterized in that, The step of inputting the target part status information and historical maintenance information of the target part into the corresponding prediction model to obtain the part maintenance time interval of the target part includes: Based on the vehicle maintenance manual and historical maintenance information, a second predicted maintenance interval is determined for each of the target parts; Based on the first predicted maintenance time interval and the second predicted maintenance interval, the maintenance time interval for each target part is obtained.

4. The method according to claim 3, characterized in that, The process of obtaining the maintenance time interval for each target part based on the first and second predicted maintenance time intervals includes: Obtain the earliest and latest dates in the first and second predicted maintenance time intervals for the target part, and determine the part maintenance time interval based on the earliest and latest dates.

5. The method according to claim 2, characterized in that, The step of inputting the target part's status information, historical maintenance information, and predicted vehicle environment data into the first prediction model to obtain the first predicted maintenance time interval for the target part includes: Based on historical vehicle operation data, the vehicle's user profile, and seasonal information, predictive vehicle environmental data is determined; the predictive vehicle environmental data includes at least one of air quality information, temperature information, and humidity information within a preset time period. The target part's status information, historical maintenance information, and predicted vehicle environment data are input into the first prediction model to obtain the first predicted maintenance time interval for the target part.

6. The method according to claim 2, characterized in that, The step of inputting the target part's status information, historical maintenance information, and predicted vehicle operation data into the second prediction model to obtain the first predicted maintenance time interval for the target part includes: Based on historical vehicle operation data, user profiles of the vehicle, and seasonal information, predicted vehicle operation data is obtained; the predicted vehicle operation data includes at least one of the working duration of the target part within a preset time period and the average working intensity of the target part. The target part's status information, historical maintenance information, and predicted vehicle operation data are input into the second prediction model to obtain the first predicted maintenance time interval for the target part.

7. The method according to claim 1, characterized in that, The step of inputting the target part status information and historical maintenance information of the target part into the corresponding prediction model to obtain the part maintenance time interval of the target part includes: Input the target part status information and historical maintenance information of the target part into the corresponding prediction model to obtain the first predicted maintenance time interval and the optimal part maintenance date of the target part; Based on the user profile of the vehicle, determine the vehicle tag; based on the vehicle tag, determine the key target parts of the vehicle; Based on the earliest date of the first predicted maintenance time interval and the optimal part maintenance date, the part maintenance time interval of the key target part is determined.

8. The method according to claim 1, characterized in that, The step involves inputting the maintenance time interval of each target part into the maintenance model to obtain a set of vehicle maintenance reminder times, including: Based on the clustering algorithm and the preset number of reminders, all the maintenance time intervals of the parts are clustered to obtain the first reminder time cluster, and the number of the first reminder time cluster is the preset number of reminders; The reminder date is obtained based on the earliest date in the first reminder time cluster; Based on each of the aforementioned reminder dates, the set of vehicle maintenance reminder times is obtained.

9. The method according to claim 8, characterized in that, Based on the set of vehicle maintenance reminder times, reminder information is output, including: If the reminder date in the vehicle maintenance reminder time set is reached, output the target part maintenance content and the corresponding part maintenance time interval corresponding to the first reminder time cluster.

10. A vehicle maintenance reminder system, characterized in that, The system includes: Data acquisition module: Acquires vehicle data, which includes at least target part status information and historical maintenance information; the target part status information is the status information of the parts of the vehicle that require maintenance. The parts maintenance time interval module inputs the target part status information and historical maintenance information of the target part into the corresponding prediction model based on the attribute tags of the target part to obtain the parts maintenance time interval of the target part; the prediction model corresponds to the attribute tags. The reminder information module inputs the maintenance time interval of each target part into the maintenance model to obtain a set of vehicle maintenance reminder times; The sending module outputs reminder information based on the set of vehicle maintenance reminder times.

11. A vehicle, characterized in that, The vehicles include: Memory, used to store executable program code; A processor for calling and running the executable program code from the memory, causing the vehicle to perform the method as claimed in any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, It stores instructions that, when executed by one or more processors, cause the processors to perform the method as described in any one of claims 1 to 9.

Images