Intelligent vehicle pre-start method based on user driving habits and environmental information

Abstract

This invention discloses a vehicle intelligent pre-start method based on user driving habits and environmental information. This invention relates to the field of vehicle self-starting technology and solves the problem of starting too early or too late due to insufficient integration with user driving habits, resulting in energy waste or user waiting. This invention determines the maximum energy consumption data through historical route data, calculates available energy consumption by combining it with the vehicle's remaining comprehensive energy consumption, and then verifies and starts the items to be implemented step by step according to the order of the items to be implemented and the energy consumption used, ensuring that the energy consumption during pre-start does not exceed the available energy consumption. This effectively solves problems such as range anxiety for pure electric vehicles and ineffective fuel consumption in gasoline vehicles. Through the design of "prohibiting starting when available energy consumption ≤ 0" and "stopping starting when cumulative energy consumption exceeds the limit," it avoids vehicle starting failures or subsequent energy shortages due to insufficient energy consumption, balancing the comfort of pre-start and the reliability of vehicle operation, and achieving the goal of "starting on demand, energy saving and high efficiency."

Description

Technical Field

[0001] This invention relates to the field of vehicle self-starting technology, specifically to a vehicle intelligent pre-starting method based on user driving habits and environmental information. Background Technology

[0002] With the rapid development of automotive intelligent technology, vehicle intelligent pre-start function has gradually become one of the core functions to enhance the user's driving experience. Its core purpose is to pre-start relevant vehicle components so that users can have a comfortable cabin environment and a ready-to-use vehicle system when they get in the car. However, existing vehicle intelligent pre-start technology still has many shortcomings, especially in terms of energy consumption control and the rationality of pre-start, making it difficult to meet the personalized needs of users and the adaptation requirements of actual driving scenarios.

[0003] Most existing pre-start technologies rely on fixed-time activation or simple historical data statistics, lacking a scientific energy consumption verification mechanism. This often results in problems such as blindly triggering startup items and unreasonable energy consumption control. Specifically, existing technologies typically do not consider the vehicle's remaining comprehensive energy consumption and the energy consumption requirements of subsequent driving routes, blindly activating all preset startup items. This can easily lead to increased range anxiety for pure electric vehicles, increased ineffective fuel consumption for gasoline vehicles, and even situations where excessive pre-start energy consumption leads to insufficient energy consumption for subsequent driving or startup failures. Even when some technologies attempt to control energy consumption, they fail to combine the user's historical driving route energy consumption data for accurate prediction, simply relying on remaining energy consumption for rough control, thus failing to achieve a dynamic balance between pre-start functionality and energy economy.

[0004] Meanwhile, existing pre-start technologies lack precision in starting timing and selection of start items. They either fail to adequately consider user habits when locking in the start time, leading to starts that are too early or too late, wasting energy or causing user wait times; or they fail to select start items based on high-frequency user habits, triggering invalid start items and further increasing energy consumption. Furthermore, some pre-start technology processes are not rigorously designed, lacking clear quantitative standards and logical loops, resulting in poor operability and difficulty in adapting to different users' driving patterns, leading to inconsistent user experiences.

[0005] In response to the technical pain points of the existing technologies, such as unreasonable energy consumption control, inaccurate selection of start-up timing and start-up items, and poor adaptability, there is an urgent need for a vehicle intelligent pre-start method that can combine user driving habits and environmental information to achieve precise, energy-saving, and personalized vehicle intelligent pre-start, so as to solve the shortcomings of the existing technologies and improve the level of vehicle intelligence and user driving experience. Summary of the Invention

[0006] To address the shortcomings of existing technologies, this invention provides a vehicle intelligent pre-start method based on user driving habits and environmental information, which solves the problem of starting too early or too late due to insufficient integration with user driving habits, resulting in energy waste or user waiting.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a vehicle intelligent pre-start method based on user driving habits and environmental information, comprising the following steps: Step 1: From the user's associated historical vehicle usage data, identify the associated start times within the tracing period, and lock the clustering features of the start times within a preset time period. From this, identify the habit times associated with the corresponding user's vehicle usage habits. The specific method is as follows: Using the current moment as the baseline, determine a set of tracing cycles; Within the tracing period, determine the associated start time within the preset time period, identify the total number G of the corresponding preset time period within the tracing period, and sum the total number of start times associated with different preset time periods to obtain H. If H and G satisfy: H÷G≥80%, then the corresponding preset time period is recorded as a pending time period; otherwise, no calibration is performed. Based on the marked undetermined time periods, the multiple sets of start times associated with different undetermined time periods are sorted in chronological order to confirm the start time sequence. Then, time data segments are randomly selected from the start time sequence, and the density features associated with the time data segments are determined: the duration range F associated with the time data segments is identified, and the total number J of start times in the time data segments is determined. Using F ÷ J = M, the density feature M associated with the corresponding time data segments is confirmed. The density features associated with different time data segments in the start time sequence are determined in turn, and the maximum value is selected from the determined density features. The time data segment associated with the maximum value is recorded as the clustering data segment. The specific method for confirming habitual times is as follows: The start times of several groups associated within the clustered data segment are confirmed, and the minimum start time and the maximum start time are confirmed from them. Then, the intermediate time between the minimum start time and the maximum start time is locked, and the locked intermediate time is recorded as the custom time. Step 2: Based on the user's confirmed habit time, lock the auto-start time associated with the corresponding preset time period, then send an auto-start signal to the user's associated terminal, and receive the terminal instructions sent by the user. The specific method is as follows: Based on the confirmed habit time and the preset lead time, where the lead time is the preset time, the habit time is used as the reference, and a lead time is moved forward. The time corresponding to the end of the lead time is recorded as the start time, and the terminal command is the start command. Step 3: Based on the received terminal instructions, from the historical startup data of different startup items associated with the vehicle, record the startup items that have reached the target number of startups as pending implementation items, and simultaneously lock the energy consumption data associated with different pending implementation items. The specific method is as follows: Based on the received terminal instructions, the system confirms the historical startup items associated with the corresponding preset time period within the tracing period, identifies the number of startups associated with each historical startup item in different preset time periods from the historical startup data, and marks the number of startups associated with different historical startup items as C. k Where k represents different historical startup items, and the total number of items within the preset time period during the tracing period is denoted as G, and C is identified. k And whether G satisfies: C k If ÷G≥80%, the corresponding historical startup item will be marked as an item to be implemented; otherwise, no marking is required. The specific method for determining the energy consumption data corresponding to the items to be implemented is as follows: Based on the marked items to be implemented, identify the energy consumption data associated with the corresponding vehicle in the historical operation data associated with the items to be implemented within the traceability period, and confirm the total running time and total energy consumption associated with the items to be implemented within the traceability period. The formula is: Energy consumption data = total energy consumption ÷ total running time, to confirm the energy consumption data associated with the corresponding items to be implemented within the traceability period. Step 4: Based on the energy consumption parameters and start count associated with different implementation items, generate a selection sequence associated with each implementation item. Then, confirm the route data associated with the preset time period from historical vehicle usage data. Combine this with the current vehicle's remaining comprehensive energy consumption to confirm the available energy consumption. Finally, based on the available energy consumption, lock the start items within the selection sequence and initiate the start process. The specific method is as follows: Based on the number of times each implementation item is initiated, sort them in descending order of numerical value to generate several selection sequences associated with each implementation item. The driving route associated with the start time within the preset time period is identified from historical vehicle usage data. From the identified driving routes, the energy consumption data associated with different driving routes is identified. From the identified energy consumption data, the maximum energy consumption data is selected. Based on the current total energy consumption of the wheels, the available energy consumption is identified. Available energy consumption = total energy consumption - maximum energy consumption data. If available energy consumption ≤ 0, the item to be implemented is not allowed to start. The specific method for locking the start item from the candidate sequence is as follows: From the confirmed candidate sequence, select the first group of implementation items, determine the energy consumption associated with each implementation item, and mark the energy consumption data associated with the corresponding implementation item as N. i Where i represents different items to be implemented, and their energy consumption is N. i× Pre-set time: The pre-set time is a preset time. It identifies whether the energy consumption used exceeds the available energy consumption. If it does, the implementation item is not allowed to start. If it does not exceed the limit, the first group of implementation items is started, and the energy consumption of the second group of implementation items is confirmed simultaneously. The total energy consumption of the first and second groups of implementation items is also confirmed. If the total exceeds the available energy consumption, the second group of implementation items is not allowed to start. If it does not exceed the limit, the second group of implementation items is started, and the subsequent third group of implementation items is determined. This process continues until the total energy consumption associated with the subsequent implementation items exceeds the available energy consumption. If it does not exceed the limit, all determined implementation items are started.

[0008] This invention provides a vehicle intelligent pre-start method based on user driving habits and environmental information. Compared with existing technologies, it has the following advantages: By setting a reasonable 30-day traceability period, focusing on the preset time periods of users' high-frequency vehicle use, and locking the density characteristics of the start time through cluster analysis, the middle time of the cluster data segment corresponding to the maximum density is taken as the habit time. Combined with the preset pre-start time, the self-start time is determined. This not only avoids the mechanicalness of fixed-time pre-start, but also ensures the accuracy and stability of the habit time through the 80% percentage threshold screening. It effectively avoids the energy waste caused by starting too early and the user waiting problem caused by starting too late. It makes the vehicle pre-start completely fit the user's personalized driving habits and achieve the convenient experience of "ready as soon as you get in the car". By determining the maximum energy consumption data through historical route data and calculating the available energy consumption based on the vehicle's remaining comprehensive energy consumption, and then stepping through and starting the items to be implemented according to the order of the items to be implemented and the energy consumption (energy consumption parameter × pre-implementation time), it is ensured that the energy consumption during the pre-start process does not exceed the available energy consumption, effectively solving problems such as range anxiety of pure electric vehicles and ineffective fuel consumption of fuel vehicles. At the same time, through the design of "prohibiting starting when available energy consumption ≤ 0" and "stopping starting when cumulative energy consumption exceeds the limit", it avoids vehicle starting failure or subsequent energy shortage due to insufficient energy consumption, taking into account the comfort of pre-start and the reliability of vehicle driving, and achieving the goal of "starting on demand and energy saving and high efficiency". Attached Figure Description

[0009] Figure 1 This is a schematic diagram of the method flow of the present invention. Detailed Implementation

[0010] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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 are within the scope of protection of the present invention.

[0011] Please see Figure 1 This application provides a vehicle intelligent pre-start method based on user driving habits and environmental information, including the following steps: Step 1: From the historical vehicle usage data associated with the user, identify the start time associated within the traceability period, and lock the clustering features of the start time within a preset time period, thereby locking the habit time associated with the user's vehicle usage habits. The specific method for locking the clustering features at the start time within the preset time period is as follows: Using the current time as the baseline, a set of traceability periods is determined, with the traceability period set to 30 days. Within the traceability period, determine the associated start time within a preset time period. The preset time period is determined in advance by the operator based on experience, generally corresponding to the time period from 6:00 AM to 10:00 AM or from 4:00 PM to 8:00 PM. Identify the total number G of the corresponding preset time period within the traceability period. Summate the total number of start times associated with different preset time periods to obtain H. If H and G satisfy: H ÷ G ≥ 80%, then the corresponding preset time period is recorded as a pending time period; otherwise, no marking is performed. Based on the marked pending time periods, the multiple sets of start times associated with different pending time periods are sorted in chronological order to confirm the start time sequence. Then, time data segments are randomly selected from the start time sequence, and the density features associated with the time data segments are determined: the duration range F associated with the time data segments is identified, and the total number J of start times within the time data segments is determined. Using F ÷ J = M, the density feature M associated with the corresponding time data segments is confirmed. The density features associated with different time data segments within the start time sequence are determined sequentially, and the maximum value is selected from several groups of determined density features. The time data segment associated with the maximum value is recorded as the cluster data segment. Specifically, within the historically associated traceability period, there are corresponding preset time periods. Then, cluster analysis is performed on the start times associated with the preset time periods, and the corresponding maximum density is confirmed from the real-time confirmed cluster features. That is, the corresponding time segment where the start times are most clustered is identified, and the corresponding habit time is locked from it, so that it can conform to the user's usage habits when starting automatically in the future. The specific method for confirming habitual times is as follows: The start times of several groups associated within the clustered data segment are confirmed, and the minimum start time and the maximum start time are confirmed from them. Then, the intermediate time between the minimum start time and the maximum start time is locked, and the locked intermediate time is recorded as the custom time. Based on the established habit time, the subsequent automatic start time is then locked to facilitate adaptive start processing of the vehicle. Step 2: Based on the user's confirmed habit time, lock the auto-start time associated with the corresponding preset time period, send an auto-start signal to the user terminal associated with the user, and receive the terminal instructions sent by the user. The specific method for locking at startup is as follows: Based on the confirmed habit time and the preset lead time, where the lead time is the preset time, generally 10 minutes, the system moves forward one lead time from the habit time as the baseline. The time corresponding to the end of the lead time is recorded as the start time, and the start time is located before the habit time. The time difference between the start time and the habit time is the lead time, and the terminal command is the start command, which is confirmed by the corresponding user. Step 3: Based on the received terminal instructions, record the corresponding start items that have reached the target number of starts from the historical start data of different start items associated with the vehicle as items to be implemented, and simultaneously lock the energy consumption parameters associated with different items to be implemented. The specific method for locking the implementation item is as follows: Based on the received terminal command (i.e., the startup command confirmed by the user), the historical startup items associated with the corresponding preset time period are confirmed within the tracing period. The number of startups associated with the historical startup items in different preset time periods is identified from the historical startup data, and the number of startups associated with different historical startup items is marked as C. k Where k represents different historical startup items, and the total number of items within the preset time period during the tracing period is denoted as G, and C is identified. k And whether G satisfies: C k If ÷G≥80%, the corresponding historical startup item will be marked as an item to be implemented; otherwise, no marking is required. Based on the marked items to be implemented, identify the energy consumption data associated with the corresponding vehicle in the historical operation data associated with the items to be implemented within the traceability period, and confirm the total running time and total energy consumption associated with the items to be implemented within the traceability period. The formula is: Energy consumption data = total energy consumption ÷ total running time, to confirm the energy consumption data associated with the corresponding items to be implemented within the traceability period. Specifically, when the terminal command is the determined start command, the historical start items and historical start data associated with the vehicle are locked according to the corresponding start command. From the locked historical start data, the number of historical starts and historical energy consumption associated with different historical start items are identified. Start items with a high number of historical starts are recorded as corresponding items to be implemented. The corresponding items to be implemented belong to the user's habit items in each driving process. Based on the confirmed habit items and the corresponding energy consumption data, the energy consumption parameters associated with the corresponding habit items can be effectively confirmed, which facilitates subsequent feature verification and locks the start items associated with the vehicle during the self-starting process. Step 4: Based on the energy consumption parameters and number of starts associated with different implementation items, generate a selection sequence associated with different implementation items. Then, confirm the route data associated with the preset time period from historical vehicle usage data. Combine the current vehicle's remaining comprehensive energy consumption to confirm the available energy consumption. Based on the available energy consumption, lock the start item in the selection sequence and perform the start process. The specific method for confirming available energy consumption is as follows: Based on the number of times each implementation item is initiated, sort them in descending order of numerical value to generate several selection sequences associated with each implementation item. The driving route associated with the start time within the preset time period is identified from historical vehicle usage data. From the identified driving routes, the energy consumption data associated with different driving routes is identified. From the identified energy consumption data, the maximum energy consumption data is selected. Based on the current total energy consumption of the wheels, the available energy consumption is identified. Available energy consumption = total energy consumption - maximum energy consumption data. If available energy consumption ≤ 0, the item to be implemented is not allowed to start. From the confirmed candidate sequence, select the first group of implementation items, determine the energy consumption associated with each implementation item, and mark the energy consumption data associated with the corresponding implementation item as N. i Where i represents different items to be implemented, and their energy consumption is N. i × Pre-set time: The pre-set time is a preset time, usually 10 minutes. It identifies whether the energy consumption exceeds the available energy consumption. If it does, the item to be implemented is not allowed to start. If it does not exceed the limit, the first group of items to be implemented is started, and the energy consumption of the second group of items to be implemented is confirmed at the same time. The total energy consumption of the first and second groups of items to be implemented is also confirmed. If the total exceeds the available energy consumption, the second group of items to be implemented is not allowed to start. If it does not exceed the limit, the second group of items to be implemented is started, and the subsequent third group of items to be implemented is determined. This process continues until the total energy consumption associated with the subsequent items to be implemented exceeds the available energy consumption. If it does not exceed the limit, all determined items to be implemented are started. Specifically, the maximum energy consumption data is determined by historical route data, and the available energy consumption is calculated by combining the vehicle's remaining comprehensive energy consumption. Then, based on the order of the items to be implemented and the energy consumption (energy consumption parameter × pre-implementation time), the items to be implemented are checked and started step by step to ensure that the energy consumption during the pre-start process does not exceed the available energy consumption. This effectively solves problems such as range anxiety of pure electric vehicles and ineffective fuel consumption of fuel vehicles. At the same time, through the design of "prohibiting starting when available energy consumption ≤ 0" and "stopping starting when cumulative energy consumption exceeds the limit", the vehicle starting failure or subsequent driving energy shortage caused by insufficient energy consumption is avoided. It takes into account the comfort of pre-start and the reliability of vehicle driving, and achieves the goal of "starting on demand and energy saving and high efficiency".

[0012] Some of the data in the above formulas are numerical calculations with dimensions removed, and the contents not described in detail in this specification are all prior art known to those skilled in the art.

[0013] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. A vehicle intelligent pre-start method based on user driving habits and environmental information, characterized in that, Includes the following steps: Step 1: From the historical vehicle usage data associated with the user, identify the start time associated within the traceability period, and lock the clustering features of the start time within a preset time period, thereby locking the habit time associated with the user's vehicle usage habits. Step 2: Based on the user's confirmed habit time, lock the auto-start time associated with the corresponding preset time period, send an auto-start signal to the user terminal associated with the user, and receive the terminal instructions sent by the user. Step 3: Based on the received terminal instructions, record the corresponding start items that have reached the target number of starts from the historical start data of different start items associated with the vehicle as items to be implemented, and simultaneously lock the energy consumption data associated with different items to be implemented. Step 4: Based on the energy consumption parameters and number of starts associated with different implementation items, generate a selection sequence associated with different implementation items. Then, confirm the route data associated with the preset time period from historical vehicle usage data. Combine the current vehicle's remaining comprehensive energy consumption to confirm the available energy consumption. Based on the available energy consumption, lock the start item in the selection sequence and start it.

2. The intelligent vehicle pre-start method based on user driving habits and environmental information according to claim 1, characterized in that, In step one, the specific method for locking the clustering features at the start time within the preset time period is as follows: Using the current moment as the baseline, determine a set of tracing cycles; Within the tracing period, determine the associated start time within the preset time period, identify the total number G of the corresponding preset time period within the tracing period, and sum the total number of start times associated with different preset time periods to obtain H. If H and G satisfy: H÷G≥80%, then the corresponding preset time period is recorded as a pending time period; otherwise, no calibration is performed. Based on the marked undetermined time periods, the multiple sets of start times associated with different undetermined time periods are sorted in chronological order to confirm the start time sequence. Then, time data segments are randomly selected from the start time sequence, and the density features associated with the time data segments are determined: the duration range F associated with the time data segments is identified, and the total number J of start times in the time data segments is determined. Using F ÷ J = M, the density feature M associated with the corresponding time data segments is confirmed. The density features associated with different time data segments in the start time sequence are determined in turn, and the maximum value is selected from the determined density features. The time data segment associated with the maximum value is recorded as the clustering data segment.

3. The intelligent vehicle pre-start method based on user driving habits and environmental information according to claim 2, characterized in that, In step one, the specific method for confirming the habitual time is as follows: The start times of several groups associated within the clustered data segment are confirmed, and the minimum start time and the maximum start time are confirmed from them. Then, the intermediate time between the minimum start time and the maximum start time is locked, and the locked intermediate time is recorded as the custom time.

4. The intelligent vehicle pre-start method based on user driving habits and environmental information according to claim 1, characterized in that, In step two, the specific method for locking the auto-start time is as follows: Based on the confirmed habitual time and the preset lead time, where the lead time is the preset duration, the system moves forward by one lead time based on the habitual time. The time corresponding to the end of the lead time is recorded as the auto-start time, and the terminal command is the start command.

5. The intelligent vehicle pre-start method based on user driving habits and environmental information according to claim 1, characterized in that, In step three, the specific method for locking the item to be implemented is as follows: Based on the received terminal instructions, the system confirms the historical startup items associated with the corresponding preset time period within the tracing period, identifies the number of startups associated with each historical startup item in different preset time periods from the historical startup data, and marks the number of startups associated with different historical startup items as C. k Where k represents different historical startup items, and the total number of items within the preset time period during the tracing period is denoted as G, and C is identified. k And whether G satisfies: C k If ÷G≥80%, the corresponding historical startup item will be marked as an item to be implemented; otherwise, no marking is required.

6. The intelligent vehicle pre-start method based on user driving habits and environmental information according to claim 5, characterized in that, In step three, the specific method for determining the energy consumption data corresponding to the item to be implemented is as follows: Based on the marked items to be implemented, identify the energy consumption data associated with the corresponding vehicle in the historical operation data associated with the items to be implemented within the traceability period, and confirm the total running time and total energy consumption associated with the items to be implemented within the traceability period. The formula is: Energy consumption data = Total energy consumption ÷ Total running time, to confirm the energy consumption data associated with the corresponding items to be implemented within the traceability period.

7. The intelligent vehicle pre-start method based on user driving habits and environmental information according to claim 1, characterized in that, In step four, the specific method for confirming available energy consumption is as follows: Based on the number of times each implementation item is initiated, sort them in descending order of numerical value to generate several selection sequences associated with each implementation item. The driving route associated with the start time within the preset time period is identified from historical vehicle usage data. From the identified driving routes, the energy consumption data associated with different driving routes is identified. From the identified energy consumption data, the maximum energy consumption data is selected. Based on the current total energy consumption of the wheels, the available energy consumption is identified. Available energy consumption = total energy consumption - maximum energy consumption data. If available energy consumption ≤ 0, the item to be implemented is not allowed to start.

8. The intelligent vehicle pre-start method based on user driving habits and environmental information according to claim 7, characterized in that, In step four, the specific method for locking the start item from the sequence to be selected is as follows: From the confirmed candidate sequence, select the first group of implementation items, determine the energy consumption associated with each implementation item, and mark the energy consumption data associated with the corresponding implementation item as N. i Where i represents different items to be implemented, and their energy consumption is N. i × Pre-set time: The pre-set time is a preset time. It identifies whether the energy consumption used exceeds the available energy consumption. If it does, the implementation item is not allowed to start. If it does not exceed the limit, the first group of implementation items is started, and the energy consumption of the second group of implementation items is confirmed simultaneously. The total energy consumption of the first and second groups of implementation items is also confirmed. If the total exceeds the available energy consumption, the second group of implementation items is not allowed to start. If it does not exceed the limit, the second group of implementation items is started, and the subsequent third group of implementation items is determined. This process continues until the total energy consumption associated with the subsequent implementation items exceeds the available energy consumption. If it does not exceed the limit, all determined implementation items are started.

Images