A vehicle charging prediction method, device, equipment, medium and product

Abstract

The application discloses a vehicle charging prediction method and device, equipment, medium and product, and relates to the technical fields of automobile charging and artificial intelligence. The method comprises the following steps: obtaining target associated data of a target vehicle; the target associated data comprises at least one of target user portrait data, target vehicle portrait data, target real-time driving behavior data and historical behavior data in a vehicle data service platform to which the target vehicle belongs; based on key fields in a charging prompt word template, the target associated data is processed, and a target charging prompt word is generated according to a processing result; the key fields comprise at least one of a current residual power, a last charging mileage and a historical charging residual power median; and the target charging prompt word is input into a vehicle charging prediction model for processing, so that a target charging prediction result is obtained. Through the above technical scheme, the accuracy of vehicle charging prediction can be improved.

Description

Technical Field

[0001] This invention relates to the fields of vehicle charging and artificial intelligence technology, and in particular to a vehicle charging prediction method, device, equipment, medium, and product. Background Technology

[0002] With the growing popularity of global environmental protection and sustainable development concepts, the electric vehicle market has ushered in a period of rapid development.

[0003] However, as electric vehicles become increasingly popular, charging difficulties, user anxiety, decision fatigue, and fragmented services have become deep-seated pain points for electric vehicle users, mainly due to the following issues: First, insufficient data dimensionality and dynamism. Existing technologies generally rely on historical statistical features and static user attributes to build models, lacking the ability to capture dynamic scenarios in real time. For example, existing solutions only use statistics such as historical charging cycles and median remaining battery power, ignoring the impact of real-time data such as the user's current driving behavior (e.g., average speed, mileage) and weather conditions (temperature, rain, snow). This static modeling approach cannot adapt to the dynamic changes in charging demand, and existing models may misjudge due to the lack of access to real-time driving data. Second, weak generalization ability of prediction models. Existing prediction models generally suffer from insufficient modeling of nonlinear relationships. For example, time series decomposition methods struggle to capture the complex coupling relationship between charging demand and weather and user behavior, while long short-term memory network models are prone to errors when dealing with extreme values ​​(e.g., a surge in charging demand due to low winter temperatures). Traditional models rely on manual feature engineering and cannot autonomously discover hidden patterns in the data. Third, simplistic recommendation strategies. Existing technologies lack user segmentation and dynamic adjustment, resulting in low efficiency in supply and demand matching. Most strategies are based solely on general indicators such as distance and price, without considering users' historical preferences. For example, the dynamic Hough model sorts charging stations by passenger flow and price, but it cannot identify users' preferences for specific brands of charging stations, leading to insufficient personalization. Summary of the Invention

[0004] This invention provides a method, apparatus, device, medium, and product for predicting vehicle charging, in order to solve the problem of the inability to accurately predict vehicle charging.

[0005] According to one aspect of the present invention, a vehicle charging prediction method is provided, comprising: Obtain target-related data for the target vehicle; the target-related data includes at least one of the following: target user profile data, target vehicle profile data, target real-time driving behavior data, and historical behavior data from the vehicle data service platform to which the target vehicle belongs; Based on the key fields in the charging prompt word template, the target associated data is processed, and a target charging prompt word is generated according to the processing result; the key fields include at least one of the following: current remaining battery power, driving distance of the most recent charge, and median remaining battery power of historical charges; The target charging prompt is input into the vehicle charging prediction model for processing to obtain the target charging prediction result.

[0006] According to another aspect of the present invention, a vehicle charging prediction device is provided, comprising: The data acquisition module is used to acquire target-related data of the target vehicle; the target-related data includes at least one of the following: target user profile data, target vehicle profile data, target real-time driving behavior data, and historical behavior data from the vehicle data service platform to which the target vehicle belongs; The prompt word generation module is used to process the target associated data based on key fields in the charging prompt word template, and generate target charging prompt words according to the processing results; the key fields include at least one of the following: current remaining battery power, driving mileage during the most recent charge, and median remaining battery power during historical charges; The prediction result acquisition module is used to input the target charging prompt word into the vehicle charging prediction model for processing to obtain the target charging prediction result.

[0007] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the vehicle charging prediction method according to any embodiment of the present invention.

[0008] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the vehicle charging prediction method according to any embodiment of the present invention.

[0009] According to another aspect of the present invention, a computer program product is provided, comprising a computer program / instructions that, when executed by a processor, implement the vehicle charging prediction method as described in any embodiment of the present invention.

[0010] This invention, in its embodiments, acquires target-related data for a target vehicle. This target-related data includes at least one of the following: target user profile data, target vehicle profile data, target real-time driving behavior data, and historical behavior data from the vehicle data service platform to which the target vehicle belongs. Based on key fields in a charging prompt word template, the target-related data is processed, and a target charging prompt word is generated according to the processing result. The key fields include at least one of the following: current remaining battery power, mileage driven during the most recent charge, and median remaining battery power during historical charges. The target charging prompt word is then input into a vehicle charging prediction model for processing to obtain a target charging prediction result. Therefore, by using a vehicle charging prediction model to predict the target charging result based on multiple dimensions of data associated with the target vehicle, the target charging prediction result can be accurately predicted, optimizing the user's charging experience.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a flowchart of a vehicle charging prediction method provided in Embodiment 1 of the present invention; Figure 2 This is a flowchart of another vehicle charging prediction method provided in Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of the structure of a vehicle charging prediction device provided in Embodiment 3 of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device that implements the vehicle charging prediction method of Embodiment 4 of the present invention. Detailed Implementation

[0014] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0015] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0016] Furthermore, it should be noted that the information collected in the technical solution of this invention is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of related data all comply with the relevant laws, regulations and standards of relevant countries and regions, necessary confidentiality measures have been taken, and public order and good morals are not violated. Corresponding operation entry points are provided for users to choose to authorize or refuse.

[0017] Figure 1 This is a flowchart of a vehicle charging prediction method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations requiring vehicle charging prediction. The method can be executed by a vehicle charging prediction device, which can be implemented in hardware and / or software. This device can be configured in an electronic device with corresponding data processing capabilities, such as a server. Figure 1 As shown, the method includes: S110. Obtain target-related data of the target vehicle; the target-related data includes at least one of the following: target user profile data, target vehicle profile data, target real-time driving behavior data, and historical behavior data from the vehicle data service platform to which the target vehicle belongs.

[0018] The target vehicle is the vehicle to be predicted for charging. Target-related data is data associated with the target vehicle. Target user profile data is the attribute information corresponding to the target user. This data may include the target user's behavioral preferences, driving habits, usage needs, and risk attributes. The target user is the owner of the target vehicle. Target vehicle profile data is data used to characterize the inherent attributes and usage characteristics of the target vehicle. This includes the target vehicle brand, the type of power battery (e.g., ternary lithium battery / lithium iron phosphate battery), and the number of days since purchase. Target real-time driving behavior data is data collected in real-time from the target vehicle reflecting the driver's actual operating behavior. This data includes the target vehicle's current speed and current total mileage. Historical behavior data from the vehicle data service platform to which the target vehicle belongs is vehicle behavior data stored within a historical time period on the platform.

[0019] Specifically, acquiring target-related data for a target vehicle can be achieved by legally obtaining authorized target user profile data and target vehicle profile data through in-vehicle terminals or mobile terminals; real-time driving behavior data of the target vehicle can be obtained through vehicle sensors; and a data query request can be initiated to the vehicle data service platform to which the target vehicle belongs. Based on user authorization, vehicle binding relationship, and permission verification, historical behavior data can be read from the database of the vehicle data service platform. Thus, by collecting or querying at least one of the following methods—in-vehicle terminals, mobile terminals, vehicle sensors, and vehicle data service platforms—target user profile data, target vehicle profile data, real-time driving behavior data, and historical behavior data can be obtained. By collecting data from multiple dimensions, including user attributes, vehicle attributes, real-time driving status, and historical driving behavior, accurate characterization and comprehensive evaluation of driving behavior and vehicle status can be achieved, avoiding the bias and misjudgment caused by a single data source, and providing reliable data support for vehicle charging prediction.

[0020] S120. Based on the key fields in the charging prompt word template, process the target associated data and generate the target charging prompt word according to the processing result; the key fields include at least one of the current remaining power, the driving mileage of the most recent charging and the median of the remaining power during historical charging.

[0021] The charging prompt template is a text framework used to generate charging prompts. The template includes at least one key field: Target charging prompt is the charging prompt corresponding to the target vehicle; Current remaining battery power is the remaining battery power of the vehicle at the current moment; Last charging mileage is the cumulative mileage traveled by the vehicle from the most recent charging event to the current moment; Median remaining battery power during at least one historical charging event is the median remaining battery power for the vehicle.

[0022] Specifically, based on the preset key fields in the charging prompt word template, which include at least one of the following: current remaining battery level, mileage during the most recent charge, and median remaining battery level during historical charges, target-related data for the target vehicle is extracted and processed. This processed target-related data is then populated into the charging prompt word template to generate a target charging prompt word suitable for the current charging prediction scenario. This allows for the generation of more accurate charging reminders that better match the current vehicle usage status by combining multi-dimensional data such as the vehicle's current remaining battery level, mileage, and historical charging behavior.

[0023] S130. Input the target charging prompt word into the vehicle charging prediction model for processing to obtain the target charging prediction result.

[0024] The vehicle charging prediction model is a pre-trained model used for predicting vehicle charging speeds. The target charging prediction result is the charging prediction result for the target vehicle. The charging prediction result includes whether or not to charge.

[0025] Specifically, the target charging prompt is input into a trained vehicle charging prediction model to obtain the target charging prediction result. This model predicts the charging behavior of the target vehicle based on multi-dimensional historical and real-time data, enabling accurate prediction of vehicle charging needs. Personalized charging reminders can be pushed to users at appropriate times, effectively preventing trip interruptions due to forgotten charging or insufficient battery power. It also helps optimize battery usage strategies, extend battery life, and improve user experience and vehicle reliability.

[0026] Optionally, the training method for the vehicle charging prediction model is as follows: Obtain sample association data for the sample vehicles; the sample association data includes at least one of the following: sample user profile data, sample vehicle profile data, sample real-time driving behavior data, and historical behavior data from the vehicle data service platform to which the sample vehicle belongs; process the sample association data based on key fields in the charging prompt word template, and generate sample charging prompt words based on the processing results; input the sample charging prompt words into the automotive industry large model to generate predicted charging results; wherein, the automotive industry large model is obtained by incrementally pre-training the initial large model using automotive industry knowledge corpus; fine-tune the automotive industry large model based on the predicted charging results and the actual charging results labeled on the sample vehicles to obtain the vehicle charging prediction model.

[0027] The sample vehicles are used to train the vehicle charging prediction model. Sample association data is data associated with the sample vehicles. Sample user profile data is the attribute information corresponding to the sample users. This data may include the sample users' behavioral preferences, driving habits, usage needs, and risk attributes. The sample users are the owners of the sample vehicles. Sample vehicle profile data is data used to characterize the inherent attributes and usage characteristics of the sample vehicles. This data includes the sample vehicle brand, the type of power battery (e.g., ternary lithium battery / lithium iron phosphate battery), and the number of days since purchase. Sample real-time driving behavior data is data collected in real-time from the sample vehicles reflecting the actual operating behavior of the drivers. Historical behavior data from the vehicle data service platform to which the sample vehicles belong is vehicle behavior data stored within a historical time period on the platform. Sample charging prompts are the charging prompts corresponding to the sample vehicles. The automotive industry big model is a large language model obtained by fine-tuning the initial big model using automotive industry knowledge corpus. The automotive industry big model is a large model with professional understanding of the automotive field. The automotive industry knowledge corpus is a structured dataset containing automotive-related professional knowledge, technical specifications, business logic, and scenario data. The predicted charging results are the charging predictions for sample vehicles. The initial large-scale model is a general-purpose large language model with basic language understanding and generation capabilities.

[0028] Specifically, at least one sample vehicle's associated data is acquired. This associated data includes at least one of the following: sample user profile data, sample vehicle profile data, sample real-time driving behavior data, and historical behavior data from the vehicle data service platform to which the sample vehicle belongs. Based on key fields in the charging prompt word template, the associated data is processed, and sample charging prompt words are generated according to the processing results. These sample charging prompt words are then input into a large automotive industry model to generate predicted charging results. The large automotive industry model is obtained by incrementally pre-training an initial large model using automotive industry knowledge corpus. Based on the predicted charging results and the actual charging results labeled on the sample vehicles, the large automotive industry model is fine-tuned and trained. The optimization objective is to "accurately output 'charging or not charging' prediction results based on the input multi-dimensional associated data," learning the mapping relationship between the associated data and the predicted charging results to obtain the trained vehicle charging prediction model. By relying on the finely tuned and optimized vehicle charging prediction model, it is possible to capture real-time changes in user behavior and environment, accurately mine the inherent correlation of multi-dimensional data such as vehicle driving, battery level, and charging habits, and ensure that the predicted charging results are consistent with actual vehicle use scenarios and user usage patterns, thereby generating accurate and demand-appropriate charging prediction results.

[0029] This invention, in its embodiments, acquires target-related data for a target vehicle. This target-related data includes at least one of the following: target user profile data, target vehicle profile data, target real-time driving behavior data, and historical behavior data from the vehicle data service platform to which the target vehicle belongs. Based on key fields in a charging prompt word template, the target-related data is processed, and a target charging prompt word is generated according to the processing result. The key fields include at least one of the following: current remaining battery power, mileage driven during the most recent charge, and median remaining battery power during historical charges. The target charging prompt word is then input into a vehicle charging prediction model for processing to obtain a target charging prediction result. Therefore, by using a vehicle charging prediction model to predict the target charging result based on multiple dimensions of data associated with the target vehicle, the target charging prediction result can be accurately predicted, optimizing the user's charging experience.

[0030] Figure 2 This is a flowchart of another vehicle charging prediction method provided in Embodiment 2 of the present invention. Based on the above embodiments, this embodiment optimizes the process of "processing target-related data based on key fields in the charging prompt word template and generating target charging prompt words based on the processing results," providing an optional implementation scheme. For example... Figure 2 As shown, the method includes: S210. Obtain target-related data of the target vehicle; the target-related data includes at least one of the following: target user profile data, target vehicle profile data, target real-time driving behavior data, and historical behavior data from the vehicle data service platform to which the target vehicle belongs.

[0031] S220. Extract the current remaining battery power from the target vehicle profile data.

[0032] Specifically, the target vehicle profile data is analyzed and features are extracted to obtain the current remaining power battery information of the target vehicle, i.e., the current remaining power is extracted.

[0033] S230. Based on historical behavior data in the vehicle data service platform to which the target vehicle belongs, obtain at least one charging event; the at least one charging event includes the most recent charging event.

[0034] A charging event refers to a record of the charging process from the start to the end of charging. The most recent charging event is the charging event that occurred before and is closest to the current time.

[0035] Specifically, based on the historical behavior data in the vehicle data service platform to which the target vehicle belongs, the historical charging record corresponding to the target vehicle is obtained. The historical charging record includes at least one charging event, and the most recent charging event is obtained from the historical charging record.

[0036] S240. Obtain the historical cumulative total mileage corresponding to the most recent charging event, obtain the current cumulative total mileage from the target real-time driving behavior data, and take the difference between the current cumulative total mileage and the historical cumulative total mileage as the driving mileage of the most recent charging event.

[0037] The historical cumulative total mileage is the total mileage driven by the vehicle at the time of the most recent charging event. The current cumulative total mileage is the total mileage driven by the vehicle at the current moment.

[0038] Specifically, by obtaining the historical cumulative total mileage corresponding to the most recent charging event, the current cumulative total mileage is obtained from the target's real-time driving behavior data, and the difference between the current cumulative total mileage and the historical cumulative total mileage is taken as the mileage driven during the most recent charging. This can provide a reliable data foundation for predicting charging behavior based on the recent usage intensity of the target vehicle after the most recent charging.

[0039] S250. Obtain the historical remaining charge corresponding to at least one charging event, and determine the median of the historical remaining charge as the median of the historical remaining charge.

[0040] Specifically, to obtain the historical remaining battery level corresponding to at least one charging event, the historical remaining battery levels can be arranged in ascending or descending order to obtain a historical remaining battery level sequence. The median of the historical remaining battery level is then obtained based on the median of this sequence. By determining the median of the historical remaining battery level, the interference of extreme data (such as excessively low or high historical remaining battery levels) on the overall charging habit assessment can be effectively avoided. Compared to the average value, it more stably reflects the charging habits of the target user, which is beneficial for subsequent charging demand prediction and charging reminder generation based on the median of the historical remaining battery level. This makes the charging prediction results more consistent with the user's daily driving patterns, improving the rationality and accuracy of charging reminders.

[0041] S260. Based on the current remaining battery level, the mileage driven during the most recent charge, and the median remaining battery level during historical charges, fill in the charging prompt word template to obtain the target charging prompt word.

[0042] Specifically, the key fields in the charging prompt word template include at least one of the following: current remaining battery level, mileage driven during the most recent charge, and median remaining battery level during historical charges. The corresponding fields in the charging prompt word template are filled in based on the current remaining battery level, mileage driven during the most recent charge, and median remaining battery level during historical charges to obtain the target charging prompt word.

[0043] S270. Input the target charging prompt word into the vehicle charging prediction model for processing to obtain the target charging prediction result.

[0044] Optionally, based on the key fields in the charging prompt template, the target associated data is processed, and the target charging prompt is generated based on the processing results, including: Optionally, based on historical behavior data from the vehicle data service platform to which the target vehicle belongs, at least one charging event is obtained, including: obtaining historical behavior data of the target vehicle from the vehicle data service platform to which the target vehicle belongs, and determining whether there is at least one charging event of the target vehicle in the historical behavior data; if there is no charging event in the historical behavior data of the target vehicle, then extracting target user attribute information from the target user profile data, and extracting the target vehicle brand from the target vehicle profile data; based on the target user attribute information and the target vehicle brand, filtering similar users matching the target user from the vehicle data service platform, and determining at least one charging event of the similar users.

[0045] Similar users are those who are similar to the target users.

[0046] Specifically, the system retrieves historical behavior data of the target vehicle from the vehicle data service platform to which the target vehicle belongs, and determines whether there is at least one charging event for the target vehicle in the historical behavior data. If there is no charging event in the historical behavior data of the target vehicle, the system extracts target user attribute information from the target user profile data and target vehicle brand from the target vehicle profile data. Based on the target user attribute information and target vehicle brand, the system filters similar users matching the target user from the vehicle data service platform and determines at least one charging event for the similar user. If there is a charging event in the historical behavior data of the target vehicle, the system retrieves at least one charging event for the target vehicle from the vehicle data service platform. Therefore, when the historical behavior data of the target vehicle contains at least one charging event, this event is directly retrieved from the vehicle data service platform. When the historical behavior data of the target vehicle does not contain at least one charging event, similar users are selected from the vehicle data service platform based on the target user attribute information and the target vehicle brand, and the charging events of these similar users are determined. This fully utilizes the historical behavior data of massive users to conduct horizontal comparisons of the target user's charging habits and supplement group characteristics, effectively solving the problem of insufficient historical behavior data for a single user. By combining user attributes and vehicle brand to select similar users, the accuracy and rationality of charging prediction results are improved, and the system's generalization ability is enhanced.

[0047] Optionally, the target real-time driving behavior data includes the vehicle's remaining mileage; the historical behavior data in the vehicle data service platform to which the target vehicle belongs includes the target user's target historical charging records; correspondingly, after obtaining the target charging prediction result, the method further includes: when the target charging prediction result is charging and a charging request from the target user is detected, obtaining the status information of at least one candidate charging pile within the target vehicle's driving range; based on the vehicle's remaining mileage and status information, determining at least one available charging pile from at least one candidate charging pile; based on the target historical charging records, obtaining the historical frequency of at least one historical charging pile, and matching the available charging pile with the historical charging pile, obtaining the charging frequency of the available charging pile based on the historical frequency; and determining the target charging pile based on the charging frequency and a frequency threshold.

[0048] Among these, "Remaining Range" refers to the theoretical mileage the target vehicle can continue driving with its current remaining battery power. "Target Historical Charging Records" are the charging records generated by the target vehicle within a historical time period. "Candidate Charging Stations" are charging stations selected based on the target vehicle's driving range. "Status Information" characterizes the charging station's status, including real-time status and estimated idle time; real-time status includes "busy" or "idle." "Available Charging Stations" are charging stations that are currently usable. "Historical Charging Stations" are charging stations used in the target vehicle's historical charging records. "Historical Frequency" is the charging frequency of historical charging stations. Charging frequency is the number of times a charging station has been used for charging.

[0049] Specifically, when the target charging prediction result is charging and a charging request from the target user is detected, the status information of at least one candidate charging pile within the target vehicle's driving range is obtained; based on the vehicle's remaining driving range, the real-time status of the candidate charging piles, and the expected idle time, at least one candidate charging pile is filtered to obtain at least one available charging pile that is within the range and is currently idle or expected to become available quickly; based on the target's historical charging records, the historical frequency of at least one historical charging pile is obtained, and the available charging piles are matched with the historical charging piles. Based on the historical frequency, the charging frequency of the available charging piles is obtained; based on the charging frequency and frequency threshold, the target charging pile is determined. By combining the vehicle's remaining driving range, the real-time busy / idle status of candidate charging stations, and the estimated idle time to filter available charging stations, it can ensure that the identified available charging stations are within the driving range and have actual charging conditions, avoiding charging failures due to charging station busyness or unavailability. At the same time, by determining target charging stations based on the charging frequency and frequency threshold of available charging stations, it can make full use of users' historical charging habits, prioritizing charging stations with high usage frequency and high reliability, further improving the accuracy and practicality of charging station recommendations, and enhancing user charging efficiency and driving experience.

[0050] Optionally, the target charging pile is determined based on the charging frequency and frequency threshold, including: if at least one charging frequency is less than the frequency threshold, then target user attribute information and target vehicle brand are extracted from target user profile data and target vehicle profile data; based on the target user attribute information and target vehicle brand, similar users matching the target user are screened from the vehicle data service platform, and similar historical charging records of similar users are determined; the charging frequency of at least one charging pile to be screened is obtained from at least one similar historical charging record, and based on the available charging piles, at least one charging pile to be screened is screened to obtain at least one recommended charging pile, and the recommended charging pile with the highest charging frequency is determined as the target charging pile.

[0051] Among them, similar historical charging records are the historical charging records of similar users. The charging piles to be filtered are the charging piles that have been used in similar historical charging records.

[0052] Specifically, if at least one charging frequency is less than a frequency threshold, target user attribute information is extracted from the target user profile data, and the target vehicle brand is extracted from the target vehicle profile data. Based on the target user attribute information and the target vehicle brand, similar users matching the target user are screened from the vehicle data service platform, and similar historical charging records of similar users are determined. The charging frequency of at least one charging pile to be screened is obtained from at least one similar historical charging record, and based on the available charging piles, at least one charging pile to be screened is screened to obtain at least one recommended charging pile. The recommended charging pile with the highest charging frequency is determined as the target charging pile. Thus, when the charging frequency of available charging piles is all below the frequency threshold, supplementing recommendations by introducing historical charging records of similar users can effectively solve the problem of recommendation failure caused by insufficient historical charging data of users and low preference for available charging piles. Combining user attribute information and vehicle brand to screen similar users, a second screening is performed based on the range of available charging piles to ensure that recommended charging piles meet the range attainment and usability conditions, and the recommended charging pile with the highest charging frequency is selected as the target charging pile, further improving the rationality and accuracy of target charging pile selection, ensuring that users can complete charging smoothly, and improving the overall charging experience.

[0053] Optionally, the target charging pile is determined based on the charging frequency and frequency threshold, including: if at least one charging frequency is greater than or equal to the frequency threshold, then the available charging pile with the highest charging frequency is determined as the target charging pile.

[0054] Specifically, if at least one charging frequency is greater than or equal to the frequency threshold, it indicates that there is an available charging station with sufficient range and that the user frequently visits. In this case, the available charging station with the highest charging frequency is identified as the target charging station.

[0055] Optionally, the target-related data may also include target environment data.

[0056] The target environmental data includes the current weather conditions (such as sunny or rainy) and temperature of the environment in which the target vehicle is located. By incorporating the target environmental data into the target-related data, the charging prediction process can fully incorporate the influence of real-time environmental factors, effectively improving the accuracy and rationality of charging demand judgment and charging pile selection, and enhancing the adaptability of the technical solution to different environmental scenarios.

[0057] Optionally, the fields in the charging prompt template may also include: user attribute information, vehicle brand, power battery type, number of days since purchase, speed of the last charge, median historical charging mileage, historical charging cycle, current weather conditions and temperature, etc.

[0058] Among these, the most recent charging speed is the average vehicle speed from the most recent charging event to the present. The median historical charging mileage is the median mileage traveled between two consecutive historical charging events. The historical charging cycle is the number of days between two consecutive historical charging events.

[0059] Specifically, in addition to key fields, the charging prompt template can also include fields such as: user attribute information, vehicle brand, battery type, number of days since purchase, speed at the last charge, median historical charging mileage, historical charging cycle, current weather conditions, and temperature. For example, the charging prompt template structure could be: "User attribute information includes {X}, driving {vehicle brand} vehicle, battery type is {battery type}, purchased {X} days ago, current remaining battery level {X}%; speed at the last charge {X} km / h, mileage at the last charge {X} km; median historical remaining battery level {X}%, median historical charging mileage {X} km, historical charging cycle {X} days; current weather conditions {X}, temperature {X}℃. Please predict whether the user intends to charge, actual charging result: {charge or not charge}", where X represents the field value to be filled. This allows for a comprehensive depiction of charging scenario characteristics from multiple dimensions, including vehicle hardware attributes, usage time, driving behavior, historical charging patterns, and real-time environment. This results in more comprehensive and realistic charging prompts, effectively improving the accuracy of charging predictions.

[0060] Optionally, after obtaining the target charging station, the method also includes: visually displaying the target charging station on the central control screen of the target vehicle.

[0061] The central control screen is the in-vehicle display terminal.

[0062] Specifically, after obtaining the target charging station, the charging information of the target charging station is displayed visually on the central control screen of the target vehicle. The charging information includes the type of charging station (such as fast charging or slow charging), estimated driving time, real-time status and distance, etc., so as to realize the real-time presentation and intuitive interaction of charging-related information on the vehicle terminal, making it convenient for users to confirm and navigate.

[0063] In this embodiment of the invention, when there is no charging event for the target vehicle in its historical behavior data, similar users are selected from the vehicle data service platform based on the target user attribute information and the target vehicle brand. The charging events of these similar users are then determined, effectively solving the problem of insufficient historical behavior data for a single user. Combining user attributes and vehicle brand for similar user selection improves the accuracy and rationality of charging prediction results and enhances the system's generalization ability. By combining the vehicle's remaining mileage, the real-time busy / idle status of candidate charging stations, and the estimated idle time to select available charging stations, it ensures that available charging stations are within the vehicle's range and have practical charging conditions, avoiding charging failures due to charging station busyness or inaccessibility. Furthermore, based on available charging stations... The system determines target charging stations based on charging frequency and frequency thresholds, prioritizing those with high usage frequency and reliability to improve the accuracy and practicality of charging station recommendations. When the charging frequency of available charging stations is below the frequency threshold, supplementary recommendations are made by incorporating historical charging records from similar users. This effectively addresses recommendation failures caused by insufficient historical charging data from users and low preference for available charging stations. Furthermore, by combining user attribute information and vehicle brand to filter similar users, a secondary filtering process is performed based on the range of available charging stations. This ensures that recommended charging stations meet the range attainment and usability requirements, and the recommended charging station with the highest charging frequency is selected as the target charging station. This further enhances the rationality and accuracy of target charging station selection, ensuring users can complete charging smoothly and improving the overall charging experience.

[0064] Figure 3 This is a schematic diagram of a vehicle charging prediction device provided in Embodiment 3 of the present invention. This embodiment is applicable to situations requiring vehicle charging prediction. The device can be implemented in hardware and / or software and can be configured in an electronic device with corresponding data processing capabilities, such as a server. Figure 3 As shown, the device includes: The data acquisition module 310 is used to acquire target-related data of the target vehicle; the target-related data includes at least one of the following: target user profile data, target vehicle profile data, target real-time driving behavior data, and historical behavior data from the vehicle data service platform to which the target vehicle belongs. The prompt word generation module 320 is used to process the target associated data based on the key fields in the charging prompt word template, and generate the target charging prompt word according to the processing result; the key fields include at least one of the following: current remaining power, driving distance of the most recent charge, and median remaining power of historical charges; The prediction result acquisition module 330 is used to input the target charging prompt word into the vehicle charging prediction model for processing, and obtain the target charging prediction result.

[0065] This invention, in its embodiments, acquires target-related data for a target vehicle. This target-related data includes at least one of the following: target user profile data, target vehicle profile data, target real-time driving behavior data, and historical behavior data from the vehicle data service platform to which the target vehicle belongs. Based on key fields in a charging prompt word template, the target-related data is processed, and a target charging prompt word is generated according to the processing result. The key fields include at least one of the following: current remaining battery power, mileage driven during the most recent charge, and median remaining battery power during historical charges. The target charging prompt word is then input into a vehicle charging prediction model for processing to obtain a target charging prediction result. Therefore, by using a vehicle charging prediction model to predict the target charging result based on multiple dimensions of data associated with the target vehicle, the target charging prediction result can be accurately predicted, optimizing the user's charging experience.

[0066] Optionally, the prompt word generation module 320 includes: The current remaining battery power extraction unit is used to extract the current remaining battery power from the target vehicle profile data; The charging event determination unit is used to determine at least one charging event based on historical behavior data in the vehicle data service platform to which the target vehicle belongs; the at least one charging event includes the most recent charging event. The most recent charging mileage determination unit is used to obtain the historical cumulative total mileage corresponding to the most recent charging event, obtain the current cumulative total mileage from the target real-time driving behavior data, and take the difference between the current cumulative total mileage and the historical cumulative total mileage as the most recent charging mileage. The historical charging remaining power median determination unit is used to obtain the historical charging remaining power corresponding to at least one charging event, and determine the median of the historical charging remaining power as the historical charging remaining power median. The target charging prompt word determination unit is used to fill the charging prompt word template with the current remaining power, the driving distance of the most recent charge, and the median of the remaining power during historical charges to obtain the target charging prompt word.

[0067] Optionally, the charging event determination unit includes: The event judgment subunit is used to obtain the historical behavior data of the target vehicle from the vehicle data service platform to which the target vehicle belongs, and to determine whether there is at least one charging event of the target vehicle in the historical behavior data of the target vehicle. The first data extraction subunit is used to extract target user attribute information from the target user profile data and target vehicle brand from the target vehicle profile data if there is no charging event in the historical behavior data of the target vehicle. The similar event determination subunit is used to filter similar users matching the target user from the vehicle data service platform based on the target user attribute information and the target vehicle brand, and to determine at least one charging event of the similar user.

[0068] Optionally, the training method for the vehicle charging prediction model is as follows: Obtain sample association data for the sample vehicles; the sample association data includes at least one of the following: sample user profile data, sample vehicle profile data, sample real-time driving behavior data, and historical behavior data from the vehicle data service platform to which the sample vehicle belongs; process the sample association data based on key fields in the charging prompt word template, and generate sample charging prompt words based on the processing results; input the sample charging prompt words into the automotive industry large model to generate predicted charging results; wherein, the automotive industry large model is obtained by incrementally pre-training the initial large model using automotive industry knowledge corpus; fine-tune the automotive industry large model based on the predicted charging results and the actual charging results labeled on the sample vehicles to obtain the vehicle charging prediction model.

[0069] Optionally, the target's real-time driving behavior data includes the vehicle's remaining mileage; the target vehicle's historical behavior data in the vehicle data service platform includes the target user's target historical charging records. Accordingly, the device also includes: a target charging station determination module, comprising: The status information determination unit is used to obtain the status information of at least one candidate charging pile within the driving range of the target vehicle when the target charging prediction result is charging and a charging request from the target user is detected. The available charging pile determination unit is used to determine at least one available charging pile from at least one candidate charging pile based on the vehicle's remaining driving range and status information. The charging frequency determination unit is used to obtain the historical frequency of at least one historical charging pile based on the target historical charging record, and to match the available charging piles with the historical charging piles, and to obtain the charging frequency of the available charging piles based on the historical frequency. The target charging station determination unit is used to determine the target charging station based on the charging frequency and frequency threshold.

[0070] Optionally, the target charging station determination unit includes: The second data extraction subunit is used to extract target user attribute information and target vehicle brand from target user profile data and target vehicle profile data if at least one charging frequency is less than the frequency threshold. The similar charging record determination subunit is used to filter similar users matching the target user from the vehicle data service platform based on the target user attribute information and the target vehicle brand, and to determine the similar historical charging records of similar users. The target charging pile determination subunit is used to obtain the charging frequency of at least one charging pile to be screened from at least one similar historical charging record, and to screen at least one charging pile to be screened based on available charging piles to obtain at least one recommended charging pile, and to determine the recommended charging pile with the highest charging frequency as the target charging pile.

[0071] The vehicle charging prediction device provided in this embodiment of the invention can execute the vehicle charging prediction method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0072] According to embodiments of the present invention, the present invention also provides an electronic device, a readable storage medium, and a computer program product.

[0073] Figure 4 A schematic diagram of an electronic device 10 that can be used to implement Embodiment 4 of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0074] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0075] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0076] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as vehicle charging prediction methods.

[0077] In some embodiments, the vehicle charging prediction method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the vehicle charging prediction method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the vehicle charging prediction method by any other suitable means (e.g., by means of firmware).

[0078] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0079] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0080] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0081] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0082] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0083] A computing system can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product within the cloud computing service system to address the shortcomings of traditional physical hosts and virtual private servers, such as high management difficulty and weak business scalability.

[0084] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0085] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for predicting vehicle charging, characterized in that, The method includes: Obtain target-related data for the target vehicle; the target-related data includes at least one of the following: target user profile data, target vehicle profile data, target real-time driving behavior data, and historical behavior data from the vehicle data service platform to which the target vehicle belongs; Based on the key fields in the charging prompt word template, the target associated data is processed, and a target charging prompt word is generated according to the processing result; the key fields include at least one of the following: current remaining battery power, driving distance of the most recent charge, and median remaining battery power of historical charges; The target charging prompt is input into the vehicle charging prediction model for processing to obtain the target charging prediction result.

2. The method according to claim 1, characterized in that, The process of processing the target associated data based on key fields in the charging prompt word template and generating target charging prompt words based on the processing results includes: Extract the current remaining battery power from the target vehicle profile data; Based on historical behavior data in the vehicle data service platform to which the target vehicle belongs, at least one charging event is obtained; the at least one charging event includes the most recent charging event. Obtain the historical cumulative total mileage corresponding to the most recent charging event, obtain the current cumulative total mileage from the target real-time driving behavior data, and take the difference between the current cumulative total mileage and the historical cumulative total mileage as the driving mileage of the most recent charging event; Obtain the historical remaining charge corresponding to the at least one charging event, and determine the median of the historical remaining charge as the median of the historical remaining charge; The target charging prompt word is obtained by filling the charging prompt word template with the current remaining battery power, the driving distance of the most recent charge, and the median remaining battery power of historical charges.

3. The method according to claim 2, characterized in that, The process of obtaining at least one charging event based on historical behavior data from the vehicle data service platform to which the target vehicle belongs includes: Obtain historical behavior data of the target vehicle from the vehicle data service platform to which the target vehicle belongs, and determine whether there is at least one charging event of the target vehicle in the historical behavior data of the target vehicle; If there are no charging events in the historical behavior data of the target vehicle, then the target user attribute information is extracted from the target user profile data, and the target vehicle brand is extracted from the target vehicle profile data. Based on the target user attribute information and the target vehicle brand, similar users matching the target user are filtered from the vehicle data service platform, and at least one charging event of the similar user is determined.

4. The method according to claim 1, characterized in that, The training method for the vehicle charging prediction model is as follows: Obtain sample association data for the sample vehicles; the sample association data includes at least one of the following: sample user profile data, sample vehicle profile data, sample real-time driving behavior data, and historical behavior data from the vehicle data service platform to which the sample vehicles belong; Based on the key fields in the charging prompt word template, the sample associated data is processed, and sample charging prompt words are generated according to the processing results. The sample charging prompt words are then input into the automotive industry big model to generate predicted charging results. The automotive industry big model is obtained by incrementally pre-training the initial big model using automotive industry knowledge corpus. Based on the predicted charging results and the actual charging results labeled on the sample vehicles, the large-scale automotive industry model is fine-tuned and trained to obtain a vehicle charging prediction model.

5. The method according to claim 1, characterized in that, The target's real-time driving behavior data includes the vehicle's remaining mileage; the target vehicle's historical behavior data in the vehicle data service platform includes the target user's target historical charging records. Accordingly, after obtaining the target charging prediction result, the method further includes: When the target charging prediction result is charging, and a charging request from the target user is detected, the status information of at least one candidate charging pile within the driving range of the target vehicle is obtained. Based on the vehicle's remaining mileage and the status information, at least one available charging station is determined from the at least one candidate charging station. Based on the target historical charging records, the historical frequency of at least one historical charging pile is obtained, and the available charging pile is matched with the historical charging pile. Based on the historical frequency, the charging frequency of the available charging pile is obtained. The target charging station is determined based on the charging frequency and frequency threshold.

6. The method according to claim 5, characterized in that, The step of determining the target charging pile based on the charging frequency and frequency threshold includes: If at least one charging frequency is less than the frequency threshold, then target user attribute information and target vehicle brand are extracted from the target user profile data and the target vehicle profile data. Based on the target user attribute information and the target vehicle brand, similar users matching the target user are filtered from the vehicle data service platform, and similar historical charging records of the similar users are determined. The charging frequency of at least one charging pile to be screened is obtained from the at least one similar historical charging record. Based on the available charging piles, the at least one charging pile to be screened is screened to obtain at least one recommended charging pile. The recommended charging pile with the highest charging frequency is determined as the target charging pile.

7. A vehicle charging prediction device, characterized in that, The device includes: The data acquisition module is used to acquire target-related data of the target vehicle; the target-related data includes at least one of the following: target user profile data, target vehicle profile data, target real-time driving behavior data, and historical behavior data from the vehicle data service platform to which the target vehicle belongs; The prompt word generation module is used to process the target associated data based on key fields in the charging prompt word template, and generate target charging prompt words according to the processing results; the key fields include at least one of the following: current remaining battery power, driving mileage during the most recent charge, and median remaining battery power during historical charges; The prediction result acquisition module is used to input the target charging prompt word into the vehicle charging prediction model for processing to obtain the target charging prediction result.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the vehicle charging prediction method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the vehicle charging prediction method according to any one of claims 1-6.

10. A computer program product comprising a computer program that, when executed by a processor, implements the vehicle charging prediction method according to any one of claims 1-6.

Images