Energy management optimization method, device, equipment and storage medium

Abstract

The application provides an energy management optimization method and device, equipment and storage medium, relates to the technical field of hybrid vehicles, and the method comprises the following steps: when a hybrid vehicle is not started in navigation, it is determined that the owner is oil preference, a cloud server is triggered to determine a target travel route from historical repeated travel routes according to the current travel position and the current travel time of the hybrid vehicle, the oil saving amount corresponding to the historical repeated travel route is greater than the sum of the oil saving amounts of single routes obtained by splitting the historical repeated travel route into separate travel routes; the cloud server performs predicted energy management planning on the hybrid vehicle according to the target travel route, obtains a target battery power required by the target travel route, and sends the target battery power to the hybrid vehicle; and the hybrid vehicle performs a predicted energy management function according to the target battery power. The application can better exert the energy-saving potential of the powertrain of the hybrid vehicle and improve fuel efficiency.

Description

Technical Field

[0001] This application relates to the field of hybrid vehicle technology, and in particular to an energy management optimization method, apparatus, device and storage medium. Background Technology

[0002] With the development of new energy vehicle technology, the application of hybrid vehicles is becoming increasingly common. Hybrid vehicles, such as plug-in hybrid electric vehicles (PHEVs), have multiple energy sources. Under different driving conditions, it is necessary to rationally coordinate the energy supply and distribution of each power source to keep the engine and electric motor operating within their high-efficiency range and improve fuel economy.

[0003] Currently, the energy of hybrid vehicles is typically managed through predictive energy management systems. These systems plan energy consumption based on navigation and traffic information, generating electricity during the engine's high-efficiency range and using pure electricity during the engine's low-efficiency range to save fuel. However, when managing the energy of hybrid vehicles through predictive energy management, there are instances where the energy-saving potential of the hybrid powertrain cannot be fully realized. Summary of the Invention

[0004] This application provides an energy management optimization method, apparatus, device, and storage medium to address the problem that current methods for managing the energy of hybrid vehicles through predictive energy management functions fail to realize the energy-saving potential of the hybrid vehicle powertrain.

[0005] In a first aspect, this application provides an energy management optimization method applied to a cloud server, the energy management optimization method comprising:

[0006] Receive trigger command, which is issued by the hybrid vehicle when the owner's fuel preference is determined without turning on the navigation;

[0007] In response to the trigger command, based on the current travel location and current travel time of the hybrid vehicle, the target travel route is determined from the historical repeated travel routes. The historical repeated travel routes are similar travel routes with a travel probability greater than the travel threshold obtained by similar processing of the routes obtained by splicing the first and last of the historical travel routes within the preset time window according to the travel order. The fuel saving corresponding to the historical repeated travel routes is greater than the sum of the fuel saving of splitting the historical repeated travel routes into individual travel routes.

[0008] Based on the target travel route, predictive energy management planning is performed on the hybrid vehicle to obtain the target battery charge required for the target travel route;

[0009] Send a target battery charge to the hybrid vehicle so that the hybrid vehicle can perform predictive energy management functions based on the target battery charge.

[0010] Optionally, historical repeating routes are obtained through the following methods: acquiring vehicle historical travel route information within a preset time period; dividing the vehicle historical travel route information into preset time windows to obtain vehicle historical travel route information corresponding to multiple preset time windows; concatenating the vehicle historical travel routes corresponding to each preset time window according to the travel sequence to obtain multiple concatenated travel routes; based on preset rules, performing similarity processing on the multiple concatenated travel routes to obtain similar travel routes with a similarity greater than a first threshold, the preset rules including the length of the road segments of the concatenated travel routes, the time period of the road segment, the name of the road segment, and the average speed of the road segment; The probability of travel is defined as the ratio of a first quantity to a second quantity. The first quantity represents the number of similar travel routes, and the second quantity represents the number of spliced ​​travel routes within a preset time period. If the probability of travel is greater than or equal to a travel threshold, the similar travel routes are determined as initial repeated travel routes. The initial repeated travel routes are input into the fuel-saving simulation model corresponding to the predictive energy management function to obtain the first fuel saving amount. The initial repeated travel routes are then split into individual travel routes, which are input into the fuel-saving simulation model respectively to obtain the second fuel saving amount for each route. If the first fuel saving amount is greater than the sum of the second fuel saving amount, the initial repeated travel routes are determined as historical repeated travel routes.

[0011] Optionally, based on preset rules, multiple spliced ​​travel routes are subjected to similarity processing to obtain similar travel routes with a similarity greater than a first threshold. This includes: comparing the spliced ​​travel routes pairwise based on preset rules; for each segment contained in the two spliced ​​travel routes to be compared, if the difference in the length of the corresponding segment is less than a second threshold, the difference in the time period of the corresponding segment is less than a third threshold, the difference in the average speed of the corresponding segment is less than a fourth threshold, and the names of the corresponding segments are the same, then the similarity value of the corresponding segment is set to 1; determining a first sum, which represents the sum of the similarity values ​​corresponding to the spliced ​​travel routes; determining a second sum, which represents the sum of the number of segments contained in the spliced ​​travel routes; determining the similarity as the ratio of the first sum to the second sum; and comparing the similarity with the first threshold to obtain similar travel routes with a similarity greater than the first threshold.

[0012] Optionally, the energy management optimization method further includes: if the travel probability is less than the travel threshold, then determining that there are no historically repeated travel routes; changing the preset time window length, and re-executing the step of dividing the vehicle's historical travel route information into preset time windows to obtain the vehicle's historical travel route information corresponding to multiple preset time windows respectively.

[0013] Optionally, the energy management optimization method also includes: obtaining historical repeated travel routes according to a preset period.

[0014] Optionally, before dividing the vehicle's historical travel route information into a preset time window, the energy management optimization method further includes: aggregating the route information of the vehicle's historical travel routes into a single target information.

[0015] Optionally, based on the current travel location and current travel time of the hybrid vehicle, a target travel route is determined from historical repeated travel routes, including: comparing the current travel location and current travel time of the hybrid vehicle with the route information of historical repeated travel routes, and determining historical repeated travel routes that include the current travel location and whose time difference with the current travel time is less than a fifth threshold as the target travel route.

[0016] Optionally, the energy management optimization method further includes: if multiple historical repeated travel routes are obtained from historical repeated travel routes based on the current travel location and current travel time of the hybrid vehicle, then the historical repeated travel route with the highest travel probability among the multiple historical repeated travel routes is determined as the target travel route; if there are multiple historical repeated travel routes with the highest travel probability, then the historical repeated travel route with the highest travel probability and the greatest fuel saving is determined as the target travel route.

[0017] Optionally, after sending the target battery charge to the hybrid vehicle, the energy management optimization method further includes: if it is determined that the current travel location of the hybrid vehicle deviates from the target travel route, sending a message to the hybrid vehicle to terminate the execution of the predictive energy management function and reducing the travel probability corresponding to the target travel route.

[0018] Secondly, this application provides an energy management optimization method applied to hybrid vehicles, the energy management optimization method comprising:

[0019] Determine whether the owner of a hybrid vehicle prefers gasoline when navigation is not enabled.

[0020] If so, a trigger command is sent to the cloud server to obtain the target battery charge required for the travel route. The target battery charge is determined by the cloud server in response to the trigger command, based on the current travel location and current travel time of the hybrid vehicle, from historical repeated travel routes, and based on the target travel route, predictive energy management planning is performed on the hybrid vehicle. Historical repeated travel routes are similar travel routes with a travel probability greater than a travel threshold obtained by similar processing of routes obtained by splicing the first and last of historical travel routes within a preset time window according to the travel order based on preset rules. The fuel saving amount corresponding to the historical repeated travel route is greater than the sum of the fuel saving amounts of splitting the historical repeated travel route into individual travel routes.

[0021] Predictive energy management functions are performed based on the target battery level.

[0022] Optionally, determining whether the vehicle owner has a fuel preference includes: determining the vehicle owner's fuel preference setting operation in response to the vehicle owner's fuel preference setting operation on the hybrid vehicle's infotainment system; or, determining the vehicle owner's fuel preference if the ratio of the historical number of times the hybrid vehicle has been refueled to the historical number of times it has been charged is greater than a ratio threshold; or, determining the vehicle owner's fuel preference if the mileage of the hybrid vehicle in pure electric mode is less than the mileage in fuel mode within a historical period, as obtained from the cloud server.

[0023] Optionally, after performing the predictive energy management function based on the target battery level, the energy management optimization method further includes: receiving a message from the cloud server to terminate the execution of the predictive energy management function; and terminating the execution of the predictive energy management function.

[0024] Thirdly, this application provides an energy management optimization device applied to a cloud server, the energy management optimization device comprising:

[0025] The receiving module is used to receive trigger commands, which are issued by the hybrid vehicle when the driver determines the fuel preference without turning on the navigation.

[0026] The determination module is used to respond to the trigger command and determine the target travel route from the historical repeated travel routes based on the current travel location and current travel time of the hybrid vehicle. The historical repeated travel routes are similar travel routes with a travel probability greater than the travel threshold obtained by similar processing of the routes obtained by splicing the first and last historical travel routes within the preset time window according to the travel order. The fuel saving corresponding to the historical repeated travel routes is greater than the sum of the fuel saving of splitting the historical repeated travel routes into individual travel routes.

[0027] The processing module is used to perform predictive energy management planning for the hybrid vehicle based on the target travel route, and to obtain the target battery charge required for the target travel route.

[0028] The sending module is used to send the target battery charge to the hybrid vehicle so that the hybrid vehicle can perform predictive energy management functions based on the target battery charge.

[0029] Optionally, the energy management optimization device further includes an acquisition module for obtaining historical recurring travel routes through the following methods: acquiring vehicle historical travel route information within a preset time period; dividing the vehicle historical travel route information into multiple preset time windows to obtain vehicle historical travel route information corresponding to each preset time window; splicing the vehicle historical travel routes corresponding to each preset time window according to the travel order to obtain multiple spliced ​​travel routes; and performing similarity processing on the multiple spliced ​​travel routes based on preset rules to obtain similar travel routes with a similarity greater than a first threshold. The preset rules include the length of the road segments of the spliced ​​travel routes, the time period of the road segments, the name of the road segments, and... The average speed of the road segment; the probability of travel is determined as the ratio of a first quantity to a second quantity, where the first quantity represents the number of similar travel routes and the second quantity represents the number of spliced ​​travel routes within a preset time period; if the probability of travel is greater than or equal to a travel threshold, the similar travel route is determined as the initial repeated travel route; the initial repeated travel route is input into the fuel-saving simulation model corresponding to the predictive energy management function to obtain the first fuel saving amount; and the initial repeated travel route is split into individual travel routes, which are then input into the fuel-saving simulation model to obtain the second fuel saving amount corresponding to each route; if the first fuel saving amount is greater than the sum of the second fuel saving amount, the initial repeated travel route is determined as the historical repeated travel route.

[0030] Optionally, when the acquisition module performs similarity processing on multiple spliced ​​travel routes based on preset rules to obtain similar travel routes with a similarity greater than a first threshold, it specifically performs the following: Based on preset rules, it compares the spliced ​​travel routes pairwise; for each segment contained in the two spliced ​​travel routes to be compared, if the difference in the length of the corresponding segment is less than a second threshold, the difference in the time period of the corresponding segment is less than a third threshold, the difference in the average speed of the corresponding segment is less than a fourth threshold, and the names of the corresponding segments are the same, then the similarity value of the corresponding segment is set to 1; a first sum is determined, which represents the sum of the similarity values ​​corresponding to the spliced ​​travel routes; a second sum is determined, which represents the sum of the number of segments contained in the spliced ​​travel routes; the similarity is determined as the ratio of the first sum to the second sum; the similarity is compared with the first threshold to obtain similar travel routes with a similarity greater than the first threshold.

[0031] Optionally, the acquisition module is also used to: if the travel probability is less than the travel threshold, determine that there are no historically repeated travel routes; change the preset time window length, and re-execute the steps of dividing the vehicle's historical travel route information into preset time windows to obtain the vehicle's historical travel route information corresponding to multiple preset time windows respectively.

[0032] Optionally, the acquisition module is also used to: obtain historical repeated travel routes according to a preset period.

[0033] Optionally, the acquisition module is also used to: aggregate the route information of the vehicle's historical travel routes into a single target information before dividing the vehicle's historical travel route information into a preset time window.

[0034] Optionally, the determining module is specifically used to: compare the current travel location and current travel time of the hybrid vehicle with the route information of historical repeated travel routes, and determine the historical repeated travel routes that include the current travel location and whose time difference with the current travel time is less than the fifth threshold as the target travel route.

[0035] Optionally, the determining module is also used to: if multiple historical repeated travel routes are obtained from historical repeated travel routes based on the current travel location and current travel time of the hybrid vehicle, then determine the historical repeated travel route with the highest travel probability among the multiple historical repeated travel routes as the target travel route; if there are multiple historical repeated travel routes with the highest travel probability, then determine the historical repeated travel route with the highest travel probability and the greatest fuel saving as the target travel route.

[0036] Optionally, the sending module is also configured to: after sending the target battery charge to the hybrid vehicle, if it is determined that the current travel location of the hybrid vehicle deviates from the target travel route, send a message to the hybrid vehicle to terminate the execution of the predictive energy management function and reduce the travel probability corresponding to the target travel route.

[0037] Fourthly, this application provides an energy management optimization method applied to a hybrid vehicle, the energy management optimization device comprising:

[0038] The determination module is used to determine whether the owner has a fuel preference when the navigation of a hybrid vehicle is not turned on;

[0039] The sending module is used to send a trigger command to the cloud server if the condition is met, in order to obtain the target battery charge required for the travel route. The target battery charge is obtained by the cloud server responding to the trigger command, determining the target travel route from historical repeated travel routes based on the current travel location and current travel time of the hybrid vehicle, and performing predictive energy management planning for the hybrid vehicle based on the target travel route. The historical repeated travel routes are similar travel routes with a travel probability greater than the travel threshold obtained by similar processing of the routes obtained by splicing the historical travel routes within a preset time window according to the travel order. The fuel saving amount corresponding to the historical repeated travel routes is greater than the sum of the fuel saving amounts of splitting the historical repeated travel routes into individual travel routes.

[0040] The execution module is used to perform predictive energy management functions based on the target battery level.

[0041] Optionally, the determining module is specifically used to: determine the owner's fuel preference in response to the owner's fuel preference setting operation on the vehicle's infotainment system; or, determine the owner's fuel preference if the ratio of the historical number of times the hybrid vehicle has been refueled to the historical number of times it has been charged is greater than a ratio threshold; or, determine the owner's fuel preference if the mileage of the hybrid vehicle in pure electric mode is less than the mileage in fuel mode within a historical period, as obtained from the cloud server.

[0042] Optionally, the execution module is also configured to: after performing the predictive energy management function based on the target battery level, receive a message from the cloud server to terminate the execution of the predictive energy management function; and terminate the execution of the predictive energy management function.

[0043] Fifthly, this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0044] The memory stores the instructions that the computer executes;

[0045] The processor executes computer execution instructions stored in memory to implement the energy management optimization method as described in the first or second aspect of this application.

[0046] In a sixth aspect, this application provides a computer-readable storage medium storing computer program instructions, which, when executed, implement the energy management optimization method as described in the first or second aspect of this application.

[0047] In a seventh aspect, this application provides a computer program product, including a computer program that, when executed, implements the energy management optimization method as described in the first or second aspect of this application.

[0048] The energy management optimization method, apparatus, equipment, and storage medium provided in this application determine whether the owner of a hybrid vehicle prefers fuel consumption when navigation is not activated. If so, the hybrid vehicle sends a trigger command to a cloud server to obtain the target battery charge required for the travel route. The cloud server responds to the trigger command and, based on the hybrid vehicle's current location and travel time, determines the target travel route from historical repeated travel routes. These historical repeated travel routes are obtained by similarity processing of routes obtained by concatenating historical travel routes within a preset time window according to travel order, based on preset rules. The probability of such similarity is greater than a travel threshold, and the fuel savings corresponding to these historical repeated travel routes are greater than the sum of the fuel savings from splitting them into individual travel routes. The cloud server performs predictive energy management planning for the hybrid vehicle based on the target travel route to obtain the target battery charge required for the target travel route. The cloud server sends the target battery charge to the hybrid vehicle, and upon receiving the target battery charge, the hybrid vehicle executes the predictive energy management function accordingly. This application determines the target travel route from historical repeated travel routes based on the current travel location and time of the hybrid vehicle, and uses this information for predictive energy management planning of the hybrid vehicle. Historical repeated travel routes are highly regular and more energy-efficient travel routes pieced together from multiple trips. This avoids the problem of limited energy saving in predictive energy management when a single travel route fails to achieve the transition from low-efficiency engine energy consumption to high-efficiency engine energy consumption due to the engine not generating electricity in its high-efficiency range at the beginning. Based on accurately predicting the target battery charge required for the hybrid vehicle's travel route, this application ensures that the hybrid vehicle generates electricity in advance in the engine's high-efficiency range, thereby allowing it to use pure electricity in the engine's low-efficiency range, better utilizing the energy-saving potential of the hybrid vehicle's powertrain, and improving the overall fuel efficiency of the entire journey. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This is a schematic diagram illustrating an application scenario provided in one embodiment of this application;

[0051] Figure 2 A schematic diagram of signaling interaction for an energy management optimization method provided in an embodiment of this application;

[0052] Figure 3A flowchart illustrating a method for obtaining historical repeating travel routes according to an embodiment of this application;

[0053] Figure 4 This is a schematic diagram of the structure of an energy management optimization device provided in an embodiment of this application;

[0054] Figure 5 A schematic diagram of the structure of an energy management optimization device provided in another embodiment of this application;

[0055] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0057] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation portals are provided for users to choose to authorize or refuse.

[0058] The application of hybrid vehicles is becoming increasingly common. Hybrid electric vehicles (PHEVs), for example, can collect information such as traffic conditions, vehicle speed, slope, traffic lights, and distance to other vehicles along the route. Through predictive energy management, they can optimize the battery consumption curve for reaching the destination, thus optimizing engine operation to run more within the fuel-efficient range, achieving fuel savings and emission reductions. Predictive energy management essentially involves predicting when the engine will experience low efficiency during the journey, generating electricity in advance during the engine's high efficiency range, and using the pre-prepared battery power during the low efficiency range for pure electric drive, thereby improving overall fuel efficiency throughout the journey.

[0059] However, not all hybrid vehicles have the opportunity to adjust their power generation range for energy savings on every trip. At the very least, they need to be able to charge at high speeds before they can discharge at low speeds. While the predictive energy management function of hybrid vehicles may maximize energy savings on a single trip, in the overall cycle of driving, there are still many periods before traffic congestion where high-speed charging is not possible, causing the engine to operate in an unefficient range and lose some thermal efficiency. For example, if a hybrid vehicle's battery is low at the start, and the subsequent mileage consists of long stretches of low-speed road, there is no opportunity to generate electricity in advance, even with traffic information. In practical applications, a high-speed charging opportunity is often required before pure electric driving can be used, preventing the powertrain from reaching its full energy-saving potential.

[0060] In related technologies, global optimization strategies can be used, such as driving equivalent factor learning methods, model predictive control (MPC) methods, various vehicle speed prediction algorithms, stochastic dynamic programming methods, and reinforcement learning methods. However, these optimization strategies typically require the hybrid vehicle's controller or cloud server to have extremely high computing power and a very long learning time on the vehicle side, and the actual driving range they can handle is also very limited, making practical application difficult. Additionally, there are schemes that analyze a user's habitual routes for a single trip to optimize predictive energy management for that trip. However, if the route for a single trip does not have the engine's high-efficiency operating range, or if the high-efficiency operating range is after the low-efficiency operating range, the goal of fuel saving cannot be achieved.

[0061] To address the aforementioned issues, this application provides an energy management optimization method, apparatus, device, and storage medium. Based on the historical patterns of driver travel, it identifies highly regular travel routes across different time spans. Multiple consecutive travel routes are merged into a single trip. The method analyzes whether the fuel savings of the merged trip, using predictive energy management assumptions, are greater than the total fuel savings of a single trip. If it is more energy-efficient, it indicates that predictive energy management, which considers multiple trips as a single trip, can address situations where high-speed charging is not possible before congestion, achieving higher energy-saving effects. Therefore, for each trip, it is determined whether the driver is traveling on a historically recurring route that is more energy-efficient and pieced together from multiple highly regular trips. If so, predictive energy management is applied to the corresponding travel segments along the route to ensure that the hybrid vehicle generates electricity in advance during the engine's high-efficiency range, allowing the vehicle to use pure electricity during the engine's low-efficiency range. This maximizes the energy-saving potential of the hybrid powertrain and improves the overall fuel efficiency of the entire trip.

[0062] The following section provides examples illustrating the application scenarios of the solution provided in this application.

[0063] Figure 1 This is a schematic diagram illustrating an application scenario provided by an embodiment of this application. For example... Figure 1 As shown, in this application scenario, the hybrid vehicle 101, without navigation activated, determines the driver's fuel consumption preference and obtains the target battery charge corresponding to the travel route from the cloud server 102. Based on the target battery charge, the hybrid vehicle 101 performs predictive energy management.

[0064] It should be noted that, Figure 1 This is merely a schematic diagram illustrating one application scenario provided by an embodiment of this application. This embodiment does not necessarily represent... Figure 1 The included equipment is not limited, nor is it restricted. Figure 1 The positional relationships between the devices are defined.

[0065] The technical solution of this application will now be described in detail through specific embodiments. It should be noted that the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0066] Figure 2 This is a signaling interaction diagram of an energy management optimization method provided in an embodiment of this application, wherein a hybrid vehicle is communicatively connected to a cloud server. Figure 2 As shown, the method in this application embodiment includes:

[0067] S201. For hybrid vehicles, determine whether the owner prefers gasoline when navigation is not activated.

[0068] In this embodiment, after the hybrid vehicle is powered on, if navigation is activated, the predictive energy management function is executed normally according to the navigation. Upon reaching the destination, the predictive energy management function is deactivated. However, if navigation is not activated, the energy management optimization method provided in this embodiment optimizes the predictive energy management function of the hybrid vehicle. First, it determines whether the vehicle owner has a fuel preference. If the owner prefers fuel, the energy management optimization method provided in this embodiment can improve the overall fuel efficiency of the entire trip.

[0069] Optionally, determining whether a hybrid vehicle owner has a preference for gasoline can include: determining that the owner has a preference for gasoline in response to the owner's gasoline preference setting operation on the hybrid vehicle's infotainment system; or, determining that the owner has a preference for gasoline if the ratio of the historical number of times the hybrid vehicle has refueled to the historical number of times it has charged is greater than a ratio threshold; or, determining that the owner has a preference for gasoline if the mileage of the hybrid vehicle in pure electric mode is less than the mileage in gasoline mode within a historical period, as obtained from the cloud server.

[0070] For example, vehicle owners can set their fuel preference on the in-vehicle infotainment system of a hybrid vehicle to determine their fuel preference. Alternatively, the hybrid vehicle can determine the owner's fuel preference based on the ratio of historical refueling to historical charging times obtained from a cloud server. For instance, if the owner refueled 20 times and charged once in the past month, their fuel preference can be determined. Alternatively, the hybrid vehicle can determine the owner's fuel preference based on the mileage of the hybrid vehicle in pure electric mode and the mileage in fuel mode over the past month, obtained from a cloud server.

[0071] S202. If it is determined that the vehicle owner has a preference for gasoline, the hybrid vehicle sends a trigger command to the cloud server to obtain the target battery charge required for the travel route.

[0072] Accordingly, the cloud server receives the trigger command.

[0073] In this step, after determining the owner's fuel preference, the hybrid vehicle sends a trigger command to the cloud server to obtain the target battery charge required for the travel route, and the cloud server receives the trigger command accordingly.

[0074] S203. The cloud server responds to the trigger command and determines the target travel route from the historical repeated travel routes based on the current travel location and current travel time of the hybrid vehicle. The historical repeated travel routes are similar travel routes with a travel probability greater than the travel threshold obtained by similar processing of the routes obtained by splicing the first and last historical travel routes within the preset time window according to the travel order. The fuel saving corresponding to the historical repeated travel routes is greater than the sum of the fuel saving of splitting the historical repeated travel routes into individual travel routes.

[0075] In this step, historical repeated travel routes can be understood as high-probability travel routes. These routes are obtained by concatenating historical travel routes within a preset time window according to travel order, based on preset rules, and then performing similarity processing on these routes. The probability of these routes exceeding a travel threshold is considered similar. The fuel savings of a driver completing a historical repeated travel route in one go are greater than the sum of the fuel savings of driving each individual route within that historical repeated travel route separately. For example, the cloud server can obtain historical repeated travel routes according to a preset period. For details on how to obtain these routes, please refer to subsequent embodiments; they will not be repeated here. After receiving the trigger command, the cloud server can determine the target travel route from the historical repeated travel routes based on the current travel location and time of the hybrid vehicle. The target travel route is the route most similar to the hybrid vehicle's travel route.

[0076] Optionally, the cloud server determines the target travel route from historical repeated travel routes based on the current travel location and current travel time of the hybrid vehicle. This may include: comparing the current travel location and current travel time of the hybrid vehicle with the route information of historical repeated travel routes, and determining historical repeated travel routes that include the current travel location and whose time difference with the current travel time is less than a fifth threshold as the target travel route.

[0077] This embodiment is used to find the route most similar to the travel route of a hybrid vehicle in historical repeated travel routes. The target travel route can be determined by comparing whether the historical repeated travel routes contain travel times with a time difference of less than a fifth threshold with the current travel time of the hybrid vehicle, and whether they contain the current travel location.

[0078] Optionally, the energy management optimization method provided in this application embodiment may further include: if multiple historical repeated travel routes are obtained from historical repeated travel routes based on the current travel location and current travel time of the hybrid vehicle, then the historical repeated travel route with the highest travel probability among the multiple historical repeated travel routes is determined as the target travel route; if there are multiple historical repeated travel routes with the highest travel probability, then the historical repeated travel route with the highest travel probability and the greatest fuel saving is determined as the target travel route.

[0079] For example, if multiple historical repeating routes are obtained from historical repeating routes based on the current travel location and current travel time of the hybrid vehicle, the travel probabilities corresponding to each of the multiple historical repeating routes are first compared, thereby determining the historical repeating route with the highest travel probability as the target travel route. If there are multiple historical repeating routes with the highest travel probability, the fuel savings corresponding to each of the historical repeating routes with the highest travel probability can be further compared, thereby determining the historical repeating route with the greatest fuel savings as the target travel route.

[0080] Optionally, if the target travel route is not found from the historical repeated travel routes based on the current travel location and current travel time of the hybrid vehicle, a message is sent to the hybrid vehicle to terminate the execution of the predictive energy management function, so that the hybrid vehicle terminates the execution of the predictive energy management function.

[0081] S204. The cloud server performs predictive energy management planning for the hybrid vehicle based on the target travel route, and obtains the target battery charge required for the target travel route.

[0082] In this step, after determining the target travel route, the cloud server can perform predictive energy management planning for the hybrid vehicle based on the route. It then selects the corresponding time and road segments within the target route to control the predictive energy management parameters for the current trip, thus obtaining the target battery charge required for the route. This target battery charge is the amount of battery power required for the hybrid vehicle's journey. It can be understood that predictive energy management planning based on the target travel route ensures that the hybrid vehicle generates electricity in advance during the engine's high-efficiency range, allowing it to operate in pure electric mode during the engine's low-efficiency range, thereby maximizing the energy-saving potential of the hybrid powertrain and achieving fuel savings. For example, assuming the target travel route includes two trips (i.e., two separate routes), and the second trip begins in a congested area, because the hybrid vehicle generates and stores energy in advance during the first trip based on the target battery charge required for the route, it can operate in pure electric mode during the congested section, thus saving fuel.

[0083] S205, the cloud server sends the target battery charge to the hybrid vehicle.

[0084] Accordingly, the hybrid vehicle receives the target battery charge.

[0085] In this step, after obtaining the target battery charge required for the target travel route, the cloud server sends the target battery charge to the hybrid vehicle, and the hybrid vehicle receives the target battery charge accordingly.

[0086] S206. Hybrid vehicles perform predictive energy management functions based on the target battery charge level.

[0087] In this step, after receiving the target battery charge, the hybrid vehicle can execute predictive energy management based on the target battery charge required for the travel route. For example, during the journey, the hybrid vehicle compares its actual battery charge with the target battery charge to determine whether to generate electricity in advance during the engine's high-efficiency range, facilitating the use of pure electric power during the engine's low-efficiency range. The predictive energy management function ends once the hybrid vehicle reaches its destination.

[0088] The energy management optimization method provided in this application involves determining whether the owner of a hybrid vehicle prefers fuel consumption when navigation is not activated. If so, the hybrid vehicle sends a trigger command to a cloud server to obtain the target battery charge required for the travel route. The cloud server responds to the trigger command and, based on the hybrid vehicle's current location and travel time, determines the target travel route from historical repeated travel routes. These historical repeated travel routes are obtained by performing similarity processing on routes obtained by concatenating historical travel routes within a preset time window according to travel order, based on preset rules. The probability of such similar travel routes is greater than a travel threshold, and the fuel savings corresponding to these historical repeated travel routes are greater than the sum of the fuel savings from splitting them into individual travel routes. The cloud server performs predictive energy management planning for the hybrid vehicle based on the target travel route to obtain the target battery charge required for the target travel route. The cloud server sends the target battery charge to the hybrid vehicle, and upon receiving the target battery charge, the hybrid vehicle executes the predictive energy management function accordingly. Because this application embodiment determines the target travel route from historical repeated travel routes based on the current travel location and current travel time of the hybrid vehicle, it is used for predictive energy management planning of the hybrid vehicle. Historical repeated travel routes are highly regular multiple travel routes that are more energy-efficient. This avoids the problem that a single travel route cannot achieve the conversion from low-efficiency engine energy consumption to high-efficiency engine energy consumption area due to the engine not generating electricity in the high-efficiency range at the beginning, thus limiting the energy saving of predictive energy management. Based on accurately predicting the target battery charge required for the hybrid vehicle's travel route, it can ensure that the hybrid vehicle generates electricity in the high-efficiency range of the engine in advance, so that it can use pure electricity in the low-efficiency range of the engine, better exert the energy-saving potential of the hybrid vehicle powertrain, and improve the overall fuel efficiency of the entire journey.

[0089] Based on the above embodiments, optionally, after the cloud server sends the target battery charge to the hybrid vehicle, if it determines that the current travel location of the hybrid vehicle deviates from the target travel route, it sends a message to the hybrid vehicle to terminate the execution of the predictive energy management function and reduces the travel probability corresponding to the target travel route; accordingly, the hybrid vehicle receives the message sent by the cloud server to terminate the execution of the predictive energy management function; and terminates the execution of the predictive energy management function.

[0090] For example, the cloud server can determine whether the hybrid vehicle's current travel location deviates from the target travel route based on its Global Positioning System (GPS) location. If it is determined that the hybrid vehicle's current travel location deviates from the target travel route, the cloud server sends a message to the hybrid vehicle to terminate the predictive energy management function, thereby causing the hybrid vehicle to terminate the predictive energy management function and reduce the travel probability corresponding to the target travel route. For example, assuming the travel probability corresponding to the target travel route is... The probability of travel corresponding to the reduced target travel route is then: For details on how to obtain the travel probability, please refer to the following implementation examples.

[0091] Based on the above embodiments, Figure 3 A flowchart illustrating a method for obtaining historical repeating travel routes according to an embodiment of this application, applied to a cloud server. For example... Figure 3 As shown, the method in this application embodiment may include:

[0092] S301. Obtain vehicle historical travel route information within a preset time period.

[0093] For example, if the preset time period is, say, the most recent three months, then the vehicle's historical travel route information within the most recent three months is obtained. It can be understood that this embodiment of the application is only executed to obtain the vehicle owner's historical recurring travel routes for car owners with specific fuel consumption preferences.

[0094] S302. Aggregate the route information of the vehicle's historical travel routes into a single target information.

[0095] In this step, the navigation system of the hybrid vehicle can determine the road segments included in each vehicle's historical travel route. Information for each road segment includes its starting and ending points, length, average speed, and time period. This information can be aggregated into a single target record, which can then be stored in a database.

[0096] S303. Divide the vehicle's historical travel route information into preset time windows to obtain the vehicle's historical travel route information corresponding to multiple preset time windows.

[0097] For example, preset time windows can be set to half a day, one day, three days, or one week. Different preset time windows can be used to divide historical travel route information, allowing for the aggregation and identification of historically repeated travel routes that achieve maximum energy savings. Assuming a preset duration of the past month and a preset time window of half a day, then historical travel route information corresponding to 60 half-days can be obtained.

[0098] S304. The historical travel routes of vehicles corresponding to each preset time window are spliced ​​together in the order of travel to obtain multiple spliced ​​travel routes.

[0099] For example, assuming a preset time window corresponds to 3 historical travel routes of vehicles, the three historical travel routes are spliced ​​together according to their travel order to obtain a spliced ​​travel route. Since the spliced ​​travel route is composed of multiple travel routes, the destination of the previous trip and the departure point of the next trip are the same location, and there are multiple departures and arrivals on the entire spliced ​​travel route.

[0100] S305. Based on preset rules, perform similarity processing on multiple spliced ​​travel routes to obtain similar travel routes with a similarity greater than a first threshold. The preset rules include the length of the spliced ​​travel route segments, the time period in which the segments are located, the name of the segments, and the average speed of the segments.

[0101] In this step, after obtaining multiple spliced ​​travel routes, similarity processing can be performed on the multiple spliced ​​travel routes based on preset rules to obtain the similarity corresponding to the similar travel routes, and then obtain similar travel routes with similarity greater than the first threshold.

[0102] Further, optionally, based on preset rules, performing similarity processing on multiple spliced ​​travel routes to obtain similar travel routes with a similarity greater than a first threshold may include: comparing the spliced ​​travel routes pairwise based on preset rules; for each segment contained in the two spliced ​​travel routes to be compared, if the difference in the length of the corresponding segments is less than a second threshold, the difference in the time period of the corresponding segments is less than a third threshold, the difference in the average speed of the corresponding segments is less than a fourth threshold, and the names of the corresponding segments are the same, then the similarity value of the corresponding segments is set to 1; determining a first sum, which is used to represent the sum of the similarity values ​​corresponding to the spliced ​​travel routes; determining a second sum, which is used to represent the sum of the number of segments contained in the spliced ​​travel routes; determining the similarity as the ratio of the first sum to the second sum; comparing the similarity with the first threshold to obtain similar travel routes with a similarity greater than the first threshold.

[0103] For example, when determining whether two spliced ​​travel routes are similar, for each segment contained in the two spliced ​​travel routes, the length of the corresponding segment, the time period of the corresponding segment, the name of the corresponding segment, and the average speed of the corresponding segment can be compared sequentially. When a corresponding segment is determined to be similar, its similarity value is set to 1, thus obtaining the sum of the similarity values ​​for each spliced ​​travel route. Assuming that both spliced ​​travel routes contain 80 segments, after comparing each segment contained in the two spliced ​​travel routes, if 79 segments are similar, then the sum of the similarity values ​​for the two spliced ​​travel routes is 79. Therefore, the similarity can be obtained as follows: By comparing the similarity with a first threshold, similar travel routes with a similarity greater than the first threshold can be obtained.

[0104] S306. Determine the travel probability as the ratio of a first quantity to a second quantity. The first quantity is used to represent the number of similar travel routes, and the second quantity is used to represent the number of spliced ​​travel routes within a preset time period.

[0105] For example, assuming the preset duration is the most recent month and the preset time window is half a day, 60 stitched travel routes can be obtained. Assuming that 40 of these 60 stitched travel routes are similar, a first ratio can be determined between the first number of similar travel routes and the second number of stitched travel routes within the preset duration. This is the probability of travel.

[0106] S307. If the probability of travel is greater than or equal to the travel threshold, then similar travel routes are determined as initial repeated travel routes.

[0107] In this step, after obtaining the travel probabilities corresponding to similar travel routes, the travel probabilities are compared with a travel threshold. Similar travel routes with a travel probability greater than or equal to the threshold are identified as initial repeating travel routes. These initial repeating travel routes indicate a high degree of consistency in user travel patterns within a preset time window. It can be understood that by determining similar travel routes as initial repeating travel routes based on travel probabilities, route stitching can be used to achieve globally optimal predictive energy management for the stitched routes when the probability is extremely high. Using travel probabilities to predict future driver travel habits can solve the problem of global energy management optimization not knowing how drivers will travel in the future.

[0108] Optionally, if the probability of travel is less than the travel threshold, it is determined that there are no historically repeated travel routes; the preset time window length can be changed, and step S303 can be executed again.

[0109] This embodiment attempts to find all possible ways to combine global energy-saving routes by changing the preset time window length. If the preset time window length reaches its maximum, for example, a maximum of one week, then changing the preset time window length stops.

[0110] S308. Input the initial repetitive travel route into the fuel-saving simulation model corresponding to the predictive energy management function to obtain the first fuel saving amount; and split the initial repetitive travel route into individual travel routes, input them into the fuel-saving simulation model respectively, and obtain the second fuel saving amount corresponding to the individual routes.

[0111] In this step, the fuel-saving simulation model corresponding to the predictive energy management function is pre-deployed on the segment server and used to calculate the fuel savings of the travel route. The initial repetitive travel route, assumed to be completed by the driver in one trip, is input into the fuel-saving simulation model corresponding to the predictive energy management function to obtain the first fuel savings. The initial repetitive travel route is then broken down into individual routes taken by the driver individually, and each route is input into the fuel-saving simulation model to obtain the second fuel savings corresponding to each individual route.

[0112] S309. If the fuel quantity in the first section is greater than the sum of the fuel quantities in the second section, then the initial repeated travel route is determined to be the historical repeated travel route.

[0113] In this step, after obtaining the first and second fuel gauge readings, the sum of the second fuel gauge readings is calculated. The first fuel gauge reading is then compared to the sum of the second fuel gauge readings. If the first fuel gauge reading is greater than the sum of the second fuel gauge readings, the initial repeated trip route is identified as a historical repeated trip route, and the first fuel gauge reading is recorded. For example, the historical repeated trip routes and their corresponding first fuel gauge readings are stored in a database. The historical repeated trip routes obtained through this step are high-probability trip routes and can save fuel.

[0114] Optionally, if the fuel quantity in the first segment is less than or equal to the sum of the fuel quantities in the second segment, it is determined that there are no historically repeated travel routes; the preset time window length can be changed, and step S303 can be executed again.

[0115] Optionally, historical repeating travel routes can be obtained according to a preset period.

[0116] For example, if the preset cycle is every Saturday, then every Saturday the cloud server processes the driver's travel patterns based on the historical information of the Telematic Service Provider (TSP), that is, it executes the above steps S303 to S309 according to the preset cycle to obtain historical repeated travel routes.

[0117] The method for obtaining historical repeating travel routes provided in this application embodiment acquires historical travel route information of vehicles within a preset time period, aggregates the route information of historical travel routes of vehicles into a single target information; divides the historical travel route information of vehicles into preset time windows to obtain historical travel route information of vehicles corresponding to multiple preset time windows respectively; splices the historical travel routes of vehicles corresponding to each preset time window according to the travel order to obtain multiple spliced ​​travel routes; and performs similarity processing on the multiple spliced ​​travel routes based on preset rules to obtain similar travel routes with a similarity greater than a first threshold. The preset rules include the length of the road segments of the spliced ​​travel routes, the time period of the road segments, and the road segments' similarity to a first threshold. The system calculates the route name and average speed of the road segment; determines the travel probability as the ratio of a first quantity to a second quantity, where the first quantity represents the number of similar travel routes and the second quantity represents the number of spliced ​​travel routes within a preset time period; if the travel probability is greater than or equal to a travel threshold, the similar travel route is identified as the initial repeated travel route; the initial repeated travel route is input into the fuel-saving simulation model corresponding to the predictive energy management function to obtain the first fuel saving amount; and the initial repeated travel route is split into individual travel routes, which are then input into the fuel-saving simulation model to obtain the second fuel saving amount corresponding to each route; if the first fuel saving amount is greater than the sum of the second fuel saving amount, the initial repeated travel route is identified as a historical repeated travel route. Since the embodiments of this application obtain historical recurring travel routes with a travel probability greater than or equal to the travel threshold and a fuel saving amount greater than the sum of the fuel saving amounts corresponding to the individual travel routes split into separate travel routes based on the spliced ​​travel routes corresponding to the spliced ​​travel routes, when the historical recurring travel routes are used for predictive energy management planning of hybrid vehicles, the target battery charge required for the travel routes of hybrid vehicles can be accurately predicted. This allows the hybrid vehicles to better utilize the energy-saving potential of the hybrid vehicle powertrain and improve the overall fuel efficiency of the entire journey when performing predictive energy management functions based on the target battery charge.

[0118] In summary, the technical solution provided in this application has at least the following advantages:

[0119] (1) Compared with the existing global optimization algorithm, the amount of computation required is very small. It only needs to merge and find the most frequently repeated travel routes, and compare the fuel saving of the merged repeated travel routes with the sum of the fuel saving of each individual route to determine the reasonable length of the optimal global optimization time window and the aggregated historical repeated travel routes. This achieves the best global energy saving under the condition that the historical repeated travel routes are roughly fixed, and the car owner benefits the most.

[0120] (2) Using historical repeated travel routes, due to the large amount of data, the prediction of vehicle speed is more accurate than that of navigation single data, and the fuel-saving effect of predictive energy management is better than that of single travel.

[0121] (3) This application can optimize the segmentation of different preset time window lengths and the data of different number of trips to aggregate and find the aggregated historical repeated trip routes that can achieve the maximum fuel saving.

[0122] (4) This application does not require that the aggregated travel routes are completely consistent. It only requires that the travel routes are extremely high in terms of time series and recurrence probability, making it easier to determine commuting routes such as those to and from get off work.

[0123] (5) The fuel-saving simulation model used in this application is deployed on a cloud server, which has higher accuracy than the traditional table lookup method and can be iteratively updated at any time according to actual usage.

[0124] The following are embodiments of the apparatus described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method described in this application.

[0125] Figure 4 This is a schematic diagram of the structure of an energy management optimization device provided in one embodiment of this application, applied to a cloud server. For example... Figure 4 As shown, the energy management optimization device 400 of this application embodiment includes: a receiving module 401, a determining module 402, a processing module 403, and a transmitting module 404. Wherein:

[0126] The receiving module 401 is used to receive a trigger command, which is issued by the hybrid vehicle when the driver determines the fuel preference without turning on the navigation.

[0127] The determination module 402 is used to respond to the trigger command and determine the target travel route from the historical repeated travel routes based on the current travel location and current travel time of the hybrid vehicle. The historical repeated travel routes are similar travel routes with a travel probability greater than the travel threshold obtained by similar processing of the routes obtained by splicing the first and last historical travel routes within the preset time window according to the travel order based on preset rules. The fuel saving corresponding to the historical repeated travel routes is greater than the sum of the fuel saving of splitting the historical repeated travel routes into individual travel routes.

[0128] The processing module 403 is used to perform predictive energy management planning for the hybrid vehicle based on the target travel route, and to obtain the target battery charge required for the target travel route.

[0129] The sending module 404 is used to send the target battery charge to the hybrid vehicle so that the hybrid vehicle can perform predictive energy management functions based on the target battery charge.

[0130] In some embodiments, the energy management optimization device 400 may further include an acquisition module 405, configured to obtain historical repeating travel routes by: acquiring vehicle historical travel route information within a preset time period; dividing the vehicle historical travel route information into multiple preset time windows to obtain vehicle historical travel route information corresponding to each preset time window; splicing the vehicle historical travel routes corresponding to each preset time window together according to the travel order to obtain multiple spliced ​​travel routes; and performing similarity processing on the multiple spliced ​​travel routes based on preset rules to obtain similar travel routes with a similarity greater than a first threshold, wherein the preset rules include the length of the road segment of the spliced ​​travel route, the time period of the road segment, and the road segment... The system identifies the name of the route and the average speed of the road segment; determines the travel probability as the ratio of a first quantity to a second quantity, where the first quantity represents the number of similar travel routes and the second quantity represents the number of spliced ​​travel routes within a preset time period; if the travel probability is greater than or equal to a travel threshold, the similar travel route is identified as the initial repeated travel route; the initial repeated travel route is input into the fuel-saving simulation model corresponding to the predictive energy management function to obtain the first fuel saving amount; and the initial repeated travel route is split into individual travel routes, which are then input into the fuel-saving simulation model to obtain the second fuel saving amount corresponding to each route; if the first fuel saving amount is greater than the sum of the second fuel saving amount, the initial repeated travel route is identified as a historical repeated travel route.

[0131] Optionally, when the acquisition module 405 performs similarity processing on multiple spliced ​​travel routes based on preset rules to obtain similar travel routes with a similarity greater than a first threshold, it can specifically be used to: compare the spliced ​​travel routes pairwise based on preset rules; for each segment contained in the two spliced ​​travel routes to be compared, if the difference in the length of the corresponding segment is less than a second threshold, the difference in the time period of the corresponding segment is less than a third threshold, the difference in the average speed of the corresponding segment is less than a fourth threshold, and the names of the corresponding segments are the same, then the similarity value of the corresponding segment is set to 1; determine a first sum, which is used to represent the sum of the similarity values ​​corresponding to the spliced ​​travel routes; determine a second sum, which is used to represent the sum of the number of segments contained in the spliced ​​travel routes; determine the similarity as the ratio of the first sum to the second sum; compare the similarity with the first threshold to obtain similar travel routes with a similarity greater than the first threshold.

[0132] Optionally, the acquisition module 405 can also be used to: if the travel probability is less than the travel threshold, determine that there are no historically repeated travel routes; change the preset time window length, and re-execute the steps of dividing the vehicle's historical travel route information into preset time windows to obtain the vehicle's historical travel route information corresponding to multiple preset time windows respectively.

[0133] Optionally, the acquisition module 405 can also be used to: obtain historical repeated travel routes according to a preset period.

[0134] Optionally, the acquisition module 405 can also be used to aggregate the route information of the vehicle's historical travel routes into a single target information before dividing the vehicle's historical travel route information into a preset time window.

[0135] In some embodiments, the determining module 402 may be specifically used to: compare the current travel location and current travel time of the hybrid vehicle with the route information of historical repeated travel routes, and determine the historical repeated travel routes that include the current travel location and whose time difference with the current travel time is less than a fifth threshold as the target travel route.

[0136] Optionally, the determining module 402 can also be used to: if multiple historical repeated travel routes are obtained from historical repeated travel routes based on the current travel location and current travel time of the hybrid vehicle, then determine the historical repeated travel route with the highest travel probability among the multiple historical repeated travel routes as the target travel route; if there are multiple historical repeated travel routes with the highest travel probability, then determine the historical repeated travel route with the highest travel probability and the greatest fuel saving as the target travel route.

[0137] Optionally, the sending module 404 can also be used to: after sending the target battery charge to the hybrid vehicle, if it is determined that the current travel location of the hybrid vehicle deviates from the target travel route, send a message to the hybrid vehicle to terminate the execution of the predictive energy management function and reduce the travel probability corresponding to the target travel route.

[0138] The apparatus in this application embodiment can be used to execute the cloud server solution in any of the above method embodiments. Its implementation principle and technical effect are similar, and will not be repeated here.

[0139] Figure 5 This is a schematic diagram of an energy management optimization device provided in another embodiment of this application, applied to a hybrid vehicle. Figure 5 As shown, the energy management optimization device 500 of this application embodiment includes: a determining module 501, a sending module 502, and an execution module 503. Wherein:

[0140] The determination module 501 is used to determine whether the owner has a preference for fuel consumption when the navigation of the hybrid vehicle is not turned on.

[0141] The sending module 502 is used to send a trigger command to the cloud server if the condition is met, in order to obtain the target battery charge required for the travel route. The target battery charge is obtained by the cloud server responding to the trigger command, determining the target travel route from historical repeated travel routes based on the current travel location and current travel time of the hybrid vehicle, and performing predictive energy management planning for the hybrid vehicle based on the target travel route. The historical repeated travel routes are similar travel routes with a travel probability greater than the travel threshold obtained by similar processing of the routes obtained by splicing the historical travel routes within a preset time window according to the travel order. The fuel saving amount corresponding to the historical repeated travel routes is greater than the sum of the fuel saving amounts of splitting the historical repeated travel routes into individual travel routes.

[0142] The execution module 503 is used to perform predictive energy management functions based on the target battery charge level.

[0143] In some embodiments, the determining module 501 may be specifically used to: determine the owner's fuel preference in response to the owner's fuel preference setting operation on the vehicle's infotainment system; or, determine the owner's fuel preference if the ratio of the number of times the hybrid vehicle has historically refueled to the number of times it has historically charged is greater than a ratio threshold; or, determine the owner's fuel preference if the mileage of the hybrid vehicle in pure electric mode within a historical period is less than the mileage in fuel mode.

[0144] Optionally, the execution module 503 can also be used to: after performing the predictive energy management function according to the target battery level, receive a message from the cloud server to terminate the execution of the predictive energy management function; and terminate the execution of the predictive energy management function.

[0145] The apparatus of this application embodiment can be used to execute the hybrid vehicle scheme in any of the above method embodiments. Its implementation principle and technical effect are similar, and will not be repeated here.

[0146] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 6 As shown, the electronic device 600 may include at least one processor 601 and a memory 602.

[0147] The memory 602 is used to store programs. Specifically, the program may include program code, which includes computer-executable instructions.

[0148] The memory 602 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage device.

[0149] The processor 601 executes computer execution instructions stored in the memory 602 to implement the energy management optimization method described in the foregoing method embodiments. The processor 601 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application. Specifically, when implementing the energy management optimization method described in the foregoing method embodiments, the electronic device may be, for example, a server or other electronic device with processing capabilities. When implementing the energy management optimization method described in the foregoing method embodiments, the electronic device may be, for example, an electronic control unit in a vehicle.

[0150] Optionally, the electronic device 600 may also include a communication interface 603. In specific implementations, if the communication interface 603, memory 602, and processor 601 are implemented independently, they can be interconnected via a bus to complete communication. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc., but this does not imply that there is only one bus or one type of bus.

[0151] Optionally, in a specific implementation, if the communication interface 603, memory 602, and processor 601 are integrated on a single chip, then the communication interface 603, memory 602, and processor 601 can communicate through an internal interface.

[0152] This application also provides a computer-readable storage medium storing computer program instructions, which, when executed by a processor, implement the above-mentioned energy management optimization method.

[0153] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described energy management optimization method.

[0154] The aforementioned computer-readable storage medium can be implemented from any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0155] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an application-specific integrated circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in an energy management optimization device.

[0156] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0157] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. An energy management optimization method, characterized in that, The energy management optimization method, applied to cloud servers, includes: Receive a trigger command, which is issued by the hybrid vehicle when the driver determines the owner's fuel preference without activating navigation; In response to the trigger command, based on the current travel location and current travel time of the hybrid vehicle, a target travel route is determined from historical repeated travel routes. The historical repeated travel routes are similar travel routes with a travel probability greater than a travel threshold obtained by performing similarity processing on spliced ​​routes based on preset rules. The spliced ​​route is a route obtained by splicing multiple historical travel routes within a preset time window according to the travel order. The fuel saving amount corresponding to the historical repeated travel route is greater than the sum of the fuel saving amounts of splitting the historical repeated travel route into individual travel routes. Based on the target travel route, predictive energy management planning is performed on the hybrid vehicle to obtain the target battery charge required for the target travel route; The target battery charge is sent to the hybrid vehicle so that the hybrid vehicle performs predictive energy management functions based on the target battery charge.

2. The energy management optimization method according to claim 1, characterized in that, The historical repeat travel routes were obtained through the following methods: Obtain vehicle historical travel route information within a preset time period; The vehicle's historical travel route information is divided into preset time windows to obtain vehicle historical travel route information corresponding to multiple preset time windows respectively. The historical travel routes of vehicles corresponding to each preset time window are spliced ​​together in the order of travel to obtain multiple spliced ​​travel routes. Based on the preset rules, the multiple spliced ​​travel routes are processed to obtain similar travel routes with a similarity greater than a first threshold. The preset rules include the length of the road segment of the spliced ​​travel route, the time period of the road segment, the name of the road segment, and the average speed of the road segment. The probability of travel is determined as the ratio of a first quantity to a second quantity, where the first quantity represents the number of similar travel routes and the second quantity represents the number of spliced ​​travel routes within the preset time period. If the travel probability is greater than or equal to the travel threshold, then the similar travel routes are determined to be initial repeated travel routes; The initial repeated travel route is input into the fuel-saving simulation model corresponding to the predictive energy management function to obtain the first fuel saving amount; And the initial repeated travel route is split into individual travel routes, which are then input into the fuel-saving simulation model to obtain the second fuel saving amount corresponding to each individual route; If the fuel consumption of the first segment is greater than the sum of the fuel consumption of the second segment, then the initial repeated travel route is determined to be the historical repeated travel route.

3. The energy management optimization method according to claim 2, characterized in that, The step of performing similarity processing on the multiple spliced ​​travel routes based on the preset rules to obtain similar travel routes with a similarity greater than a first threshold includes: Based on the preset rules, the spliced ​​travel routes are compared pairwise; For each segment of the two spliced ​​travel routes to be compared, if the difference in the length of the corresponding segment is less than the second threshold, the difference in the time period of the corresponding segment is less than the third threshold, the difference in the average speed of the corresponding segment is less than the fourth threshold, and the names of the corresponding segments are the same, then the similarity value of the corresponding segment is set to 1. A first sum is determined, which is used to characterize the sum of similarity values ​​corresponding to the spliced ​​travel routes; Determine the second sum, which is used to characterize the sum of the number of road segments contained in the spliced ​​travel route; The similarity is determined as the ratio of the first sum to the second sum; The similarity is compared with the first threshold to obtain similar travel routes whose similarity is greater than the first threshold.

4. The energy management optimization method according to claim 2, characterized in that, Also includes: If the probability of travel is less than the travel threshold, then it is determined that there are no historically repeated travel routes. Change the preset time window length and re-execute the step of dividing the vehicle's historical travel route information into preset time windows to obtain the vehicle's historical travel route information corresponding to multiple preset time windows.

5. The energy management optimization method according to claim 2, characterized in that, Also includes: The historical repeated travel routes are obtained according to a preset period.

6. The energy management optimization method according to claim 2, characterized in that, Before dividing the vehicle's historical travel route information into preset time windows, the method further includes: The route information of the vehicle's historical travel routes is aggregated into a single target information.

7. The energy management optimization method according to claim 2, characterized in that, The step of determining the target travel route from historical repeated travel routes based on the current travel location and current travel time of the hybrid vehicle includes: The current travel location and current travel time of the hybrid vehicle are compared with the route information of the historical repeated travel routes, and the historical repeated travel routes that include the current travel location and whose time difference with the current travel time is less than a fifth threshold are determined as the target travel route.

8. The energy management optimization method according to claim 7, characterized in that, Also includes: If multiple historical repeating routes are obtained from the historical repeating routes based on the current travel location and current travel time of the hybrid vehicle, then the historical repeating route with the highest travel probability among the multiple historical repeating routes is determined as the target travel route. If there are multiple historically repeated travel routes with the highest travel probability, then the historically repeated travel route with the highest travel probability and the greatest fuel saving is determined as the target travel route.

9. The energy management optimization method according to any one of claims 1 to 8, characterized in that, After sending the target battery charge to the hybrid vehicle, the method further includes: If it is determined that the current travel location of the hybrid vehicle deviates from the target travel route, a message is sent to the hybrid vehicle to terminate the execution of the predictive energy management function and reduce the travel probability corresponding to the target travel route.

10. An energy management optimization method, characterized in that, The energy management optimization method, applied to hybrid vehicles, includes: In the case that the navigation is not turned on in the hybrid vehicle, determine whether the owner has a preference for gasoline; If so, a trigger command is sent to the cloud server to obtain the target battery charge required for the travel route. The target battery charge is obtained by the cloud server responding to the trigger command, determining the target travel route from historical repeated travel routes based on the current travel location and current travel time of the hybrid vehicle, and performing predictive energy management planning for the hybrid vehicle based on the target travel route. The historical repeated travel routes are similar travel routes with a travel probability greater than a travel threshold obtained by performing similarity processing on spliced ​​routes based on preset rules. The spliced ​​route is a route obtained by splicing multiple historical travel routes within a preset time window according to the travel order. The fuel saving corresponding to the historical repeated travel route is greater than the sum of the fuel saving of splitting the historical repeated travel route into individual travel routes. Based on the target battery level, perform predictive energy management functions.

11. The energy management optimization method according to claim 10, characterized in that, Determining whether a car owner has a particular fuel preference includes: In response to the vehicle owner's operation of setting fuel preference on the vehicle's infotainment system, the vehicle owner's fuel preference is determined; Alternatively, if the ratio of the number of times the hybrid vehicle has been refueled to the number of times it has been charged in history, obtained from the cloud server, is greater than a ratio threshold, then the owner's fuel preference is determined. Alternatively, if the mileage of the hybrid vehicle in pure electric mode over a historical period, obtained from the cloud server, is less than the mileage in fuel mode, then the owner is determined to have a fuel preference.

12. The energy management optimization method according to claim 10 or 11, characterized in that, After performing predictive energy management based on the target battery charge, the method further includes: Receive a message from the cloud server to terminate the execution of the predictive energy management function; The predictive energy management function is terminated.

13. An energy management optimization device, characterized in that, The energy management optimization device, applied to cloud servers, includes: A receiving module is used to receive a trigger command, which is issued by the hybrid vehicle when the driver determines the driver's fuel preference without activating navigation; The determination module is used to respond to the trigger command and determine the target travel route from historical repeated travel routes based on the current travel location and current travel time of the hybrid vehicle. The historical repeated travel routes are similar travel routes with a travel probability greater than a travel threshold obtained by performing similarity processing on spliced ​​routes based on preset rules. The spliced ​​route is a route obtained by splicing multiple historical travel routes within a preset time window according to the travel order. The fuel saving amount corresponding to the historical repeated travel route is greater than the sum of the fuel saving amounts of splitting the historical repeated travel route into individual travel routes. The processing module is used to perform predictive energy management planning for the hybrid vehicle based on the target travel route, and to obtain the target battery charge required for the target travel route. The transmitting module is used to transmit the target battery charge to the hybrid vehicle so that the hybrid vehicle can perform predictive energy management functions based on the target battery charge.

14. An energy management optimization device, characterized in that, The energy management optimization device, applied to hybrid vehicles, includes: The determination module is used to determine whether the owner has a fuel preference when the navigation of the hybrid vehicle is not turned on. The sending module is configured to send a trigger command to the cloud server if the condition is met, to obtain the target battery charge required for the travel route. The target battery charge is determined by the cloud server in response to the trigger command, based on the current travel location and time of the hybrid vehicle, from historical repeated travel routes. Based on the target travel route, predictive energy management planning is performed on the hybrid vehicle. The historical repeated travel routes are similar travel routes with a travel probability greater than a travel threshold, obtained by performing similarity processing on spliced ​​routes according to preset rules. The spliced ​​route is obtained by splicing multiple historical travel routes within a preset time window according to the travel order. The fuel savings corresponding to the historical repeated travel routes are greater than the sum of the fuel savings from splitting the historical repeated travel routes into individual travel routes. The execution module is used to perform predictive energy management functions based on the target battery charge level.

15. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the energy management optimization method as described in any one of claims 1 to 12.

16. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions, which, when executed, implement the energy management optimization method as described in any one of claims 1 to 12.

Images