Method, device and storage medium for saving fuel consumption of hybrid electric vehicle

Abstract

The present disclosure relates to a method for saving fuel consumption of a hybrid vehicle, which is applied to a cloud server and includes: receiving a trip prediction request sent by the hybrid vehicle, extracting information of the user driving the vehicle from the request, and querying the historical trip records of the user according to the information; if the historical trip records of the user are queried, screening the historical trips that match the trip starting point of the user from the historical trip records of the user; if the historical trip records of the user are not queried, finding associated users of the user according to the big data of the vehicle network, obtaining the historical trip records of the associated users, and screening the historical trips that match the trip starting point of the user from the historical trip records of the associated users; sending a trip prediction response to the vehicle to assist the vehicle in optimizing the allocation of hybrid energy. The solution of the present disclosure provides trip prediction to the vehicle based on the big data of the vehicle network, thereby helping the user save fuel consumption of the vehicle when driving on familiar roads.

Description

Technical Field

[0001] Embodiments of the present application relate to the field of hybrid electric vehicles, and in particular, to a method, device, and storage medium for saving fuel consumption of hybrid electric vehicles. Background Art

[0002] The drive system of a hybrid electric vehicle is jointly composed of two or more single drive systems that can operate simultaneously, and the driving power of the vehicle is provided independently by a single drive system or jointly by multiple drive systems. Hybrid electric vehicles use internal combustion engines and electric motors as hybrid power sources. They have the advantages of good power performance, fast response, and long working hours of fuel engines, as well as the benefits of no pollution and low noise of electric motors, achieving the best match between the engine and the electric motor. Summary of the Invention

[0003] Embodiments of the present application provide a method for saving fuel consumption of hybrid electric vehicles, which is applied to a cloud server and includes:

[0004] Receiving a trip prediction request sent by a hybrid electric vehicle, extracting information of the user driving the vehicle from the trip prediction request, and querying the historical trip record of the user according to the information of the user; wherein, the information of the user includes: the identity information of the user and the trip start point information;

[0005] If the historical trip record of the user is queried, then screening the historical trips that match the trip start point of the user from the historical trip record of the user; if the historical trip record of the user is not queried, then finding the associated users of the user according to the big data of the vehicle networking, obtaining the historical trip records of the associated users, and screening the historical trips that match the trip start point of the user from the historical trip records of the associated users;

[0006] Sending a trip prediction response to the vehicle to assist the vehicle in optimizing the allocation of hybrid energy; wherein, the trajectory information of the screened historical trips is carried in the trip prediction response.

[0007] Embodiments of the present application provide a method for saving fuel consumption of hybrid electric vehicles, which is applied to a hybrid electric vehicle and includes:

[0008] When the user driving the hybrid electric vehicle does not turn on the navigation, sending a trip prediction request to the cloud server, and the trip prediction request carries the information of the user; receiving the trip prediction response sent by the cloud server, and obtaining the trajectory information of the historical trip from it; wherein, the information of the user includes: the identity information of the user and the trip start point information;

[0009] Use part or all of the trajectory of the historical trip as the trajectory of the predicted trip, and send a road condition query request to the navigation server, where the road condition query request carries the trajectory information of the predicted trip; receive the road condition query response sent by the navigation server, and obtain the road condition information of the predicted trip from it;

[0010] Optimize the allocation of hybrid energy according to the road condition information of the predicted trip.

[0011] An embodiment of the present application provides a device for saving fuel consumption of a hybrid vehicle, including: a memory and a processor, where the memory stores a computer program, and when the computer program is executed by the processor, the steps of the method for saving fuel consumption of the hybrid vehicle are implemented.

[0012] An embodiment of the present application provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the method for saving fuel consumption of the hybrid vehicle are implemented.

[0013] In the method for saving fuel consumption of a hybrid vehicle provided by an embodiment of the present application, the cloud server receives a trip prediction request sent by the hybrid vehicle. If the historical trip record of the user is queried, the historical trips matching the trip start point of the user are filtered from the historical trip record of the user; if the historical trip record of the user is not queried, the associated users of the user are found according to the big data of the vehicle networking, the historical trip records of the associated users are obtained, and the historical trips matching the trip start point of the user are filtered from the historical trip records of the associated users; a trip prediction response is sent to the vehicle to assist the vehicle in optimizing the allocation of hybrid energy; wherein, the trip prediction response carries the trajectory information of the filtered historical trip. The above method for saving fuel consumption of a hybrid vehicle provides trip prediction for the vehicle based on the big data of the vehicle networking, thereby helping the user save the fuel consumption of the vehicle when driving on familiar roads.

[0014] In the method for saving fuel consumption of a hybrid vehicle provided by an embodiment of the present application, when the user driving the hybrid vehicle does not turn on the navigation, the hybrid vehicle sends a trip prediction request to the cloud server, and the trip prediction request carries the information of the user; receive the trip prediction response sent by the cloud server, and obtain the trajectory information of the historical trip from it; use part or all of the trajectory of the historical trip as the trajectory of the predicted trip, and send a road condition query request to the navigation server, where the road condition query request carries the trajectory information of the predicted trip; receive the road condition query response sent by the navigation server, and obtain the road condition information of the predicted trip from it; optimize the allocation of hybrid energy according to the road condition information of the predicted trip. The above method for saving fuel consumption of a hybrid vehicle helps the user save the fuel consumption of the vehicle when driving on familiar roads by means of the trip prediction provided by the cloud server.

[0015] Other aspects will be apparent upon reading and understanding the accompanying drawings and the detailed description. Description of the Drawings

[0016] The accompanying drawings are used to provide an understanding of the technical solutions of the present application and form a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solutions of the present application and do not constitute a limitation to the technical solutions of the present application.

[0017] Figure 1 Flowchart of a method for saving fuel consumption of a hybrid vehicle (on the side of the cloud server) for an embodiment of the present application;

[0018] Figure 2 Flowchart of a method for saving fuel consumption of a hybrid vehicle (on the side of the hybrid vehicle) for an embodiment of the present application;

[0019] Figure 3 Schematic diagram of a device for saving fuel consumption of a hybrid vehicle for an embodiment of the present application. Detailed Embodiments

[0020] The present application describes multiple embodiments, but the description is exemplary rather than restrictive, and it will be apparent to those of ordinary skill in the art that there can be more embodiments and implementation solutions within the scope of the embodiments described in the present application. Although many possible combinations of features are shown in the accompanying drawings and discussed in the detailed embodiments, many other combinations of the disclosed features are also possible. Unless specifically restricted, any feature or element of any embodiment can be combined with any other feature or element in any other embodiment, or can replace any other feature or element in any other embodiment.

[0021] The present application includes and contemplates combinations with features and elements known to those of ordinary skill in the art. The embodiments, features, and elements already disclosed in the present application can also be combined with any conventional features or elements to form a unique inventive solution defined by the appended claims. Any feature or element of any embodiment can also be combined with features or elements from other inventive solutions to form another unique inventive solution defined by the appended claims. Therefore, it should be understood that any feature shown and / or discussed in the present application can be implemented alone or in any suitable combination. Therefore, the embodiments are not subject to other limitations except those made according to the appended claims and their equivalents. In addition, various modifications and changes can be made within the scope of protection of the appended claims.

[0022] In addition, when describing exemplary embodiments, the specification may have presented methods and / or processes as a particular sequence of steps. However, to the extent that the method or process does not depend on a particular order of the steps described herein, the method or process should not be limited to the particular order of steps described. As will be understood by those of ordinary skill in the art, other sequences of steps are possible. Accordingly, the particular order of steps set forth in the specification should not be construed as a limitation on the appended claims. In addition, the claims directed to the method and / or process should not be limited to performing their steps in the order written, as those skilled in the art can readily understand that such orders may vary and still remain within the spirit and scope of the embodiments of the present application.

[0023] In most cases, users only turn on the navigation when going to unfamiliar destinations. For familiar routes passed by daily, they usually do not turn on the navigation. When the vehicle does not know the destination of the user's itinerary, it will not be able to optimize the allocation of hybrid energy according to the user's itinerary arrangement.

[0024] As Figure 1 shown, an embodiment of the present application provides a method for saving fuel consumption of a hybrid vehicle, which is applied to a cloud server and includes:

[0025] Step S10: Receive a trip prediction request sent by the hybrid vehicle, extract information of the user driving the vehicle from the trip prediction request, and query the historical trip record of the user according to the user's information; wherein, the user's information includes: the user's identity information and the trip start point information;

[0026] Step S20: If the historical trip record of the user is queried, then screen the historical trips that match the trip start point of the user from the historical trip record of the user; if the historical trip record of the user is not queried, then find the associated users of the user according to the big data of the vehicle network, obtain the historical trip records of the associated users, and screen the historical trips that match the trip start point of the user from the historical trip records of the associated users;

[0027] Step S30: Send a trip prediction response to the vehicle to assist the vehicle in optimizing the allocation of hybrid energy; wherein, the trajectory information of the screened historical trips is carried in the trip prediction response.

[0028] The method for saving the fuel consumption of a hybrid vehicle provided by the above embodiments. The cloud server receives a trip prediction request sent by the hybrid vehicle, extracts the information of the user driving the vehicle from the trip prediction request, and queries the historical trip records of the user according to the user's information. Among them, the user's information includes: the user's identity information and the trip starting point information. If the historical trip records of the user are queried, then the historical trips matching the user's trip starting point are filtered out from the historical trip records of the user. If the historical trip records of the user are not queried, then the associated users of the user are found according to the big data of the vehicle network, the historical trip records of the associated users are obtained, and the historical trips matching the user's trip starting point are filtered out from the historical trip records of the associated users. A trip prediction response is sent to the vehicle to assist the vehicle in optimizing the allocation of hybrid energy. Among them, the trajectory information of the filtered historical trips is carried in the trip prediction response. The above method for saving the fuel consumption of a hybrid vehicle provides trip prediction to the vehicle based on the big data of the vehicle network, thereby helping the user save the fuel consumption of the vehicle when driving on familiar roads.

[0029] In some exemplary embodiments, the user driving the hybrid vehicle is a registered user of the cloud server.

[0030] In some exemplary embodiments, the user's identity information includes at least one of the following information: the account number and password of the registered user.

[0031] In some exemplary embodiments, the method further includes:

[0032] Receiving a registration request sent by the hybrid vehicle, and saving the personal information of the user driving the hybrid vehicle and the information of the vehicle submitted during the registration process.

[0033] In some exemplary embodiments, the user's personal information includes at least one of the following information: age, gender, work unit, home address, marital status, and children status. In other embodiments, the user's personal information may also include other information.

[0034] In some exemplary embodiments, the vehicle's information includes at least one of the following information: the brand and model of the vehicle, the license plate number, and the price range where the vehicle is located. In other embodiments, the vehicle's information may also include other information.

[0035] In some exemplary embodiments, the filtering out of the historical trips matching the user's trip starting point from the historical trip records of the user includes:

[0036] Find historical trips that meet the following screening criteria from the user's historical trip records, and use the screened historical trips as the historical trips that match the user's trip starting point;

[0037] Among them, the screening criteria include the following conditions:

[0038] The time interval between the starting time of the historical trip and the current time is less than the first time threshold;

[0039] The day of the week of the historical trip is the same as the day of the week of the current time;

[0040] The distance between the starting position of the historical trip and the user's trip starting position is less than the first distance threshold.

[0041] For example, historical trip 1 is from 8:00 to 8:40 in the morning on Monday (last Monday), from Community A to Workplace B; historical trip 2 is from 8:00 to 8:30 in the morning on Tuesday (last Tuesday), from Community A to Hospital C; the starting point of the user's trip is Community A, and the current time is 7:55 in the morning, Monday. Assuming that the first time threshold is 15 minutes, historical trip 1 can be used as the historical trip that matches the user's trip starting point.

[0042] In some exemplary embodiments, the method further includes:

[0043] If a request to share a historical trip sent by a hybrid vehicle is received, obtain the trajectory information and time information of the historical trip of the user driving the hybrid vehicle from the request and save them.

[0044] If the user driving the hybrid vehicle shares a historical trip, the cloud server saves the trajectory information and time information of the historical trip in the cloud, which is convenient for providing a reference for the user's future trip prediction. If the user driving the hybrid vehicle does not share a historical trip, the cloud server does not have any historical trip records of this user, and when making a trip prediction for this user, it can only rely on the big data system to use the historical trip records of other users as the prediction basis.

[0045] In some exemplary embodiments, finding the associated users of the user according to the big data of the vehicle network includes:

[0046] Take the user who sends the trip prediction request as the target user, and take the registered users who have shared historical trips on the cloud server as the reference users;

[0047] Establish the feature vectors of multiple reference users, and set corresponding weights for each feature in the feature vectors; where any one feature is a factor for measuring the similarity between the reference user and the target user;

[0048] For any reference user, determine the numerical value of each feature in the feature vector of the reference user, accumulate the product of the numerical values of all features and the weights corresponding to the features to obtain an accumulated sum, and use the product of the accumulated sum and the confidence level of the reference user as the association score of the reference user;

[0049] Take the M reference users with the highest association scores as the associated users of the target user.

[0050] In some exemplary embodiments, the features in the feature vector may include at least one of the following: whether the work units of the reference user and the target user are the same, whether the home addresses of the reference user and the target user are close, whether the ages of the reference user and the target user are close, whether the genders of the reference user and the target user are the same, whether the marital statuses of the reference user and the target user are the same, and whether the child statuses of the reference user and the target user are the same. For example, when the feature is whether the work units of the reference user and the target user are the same, if the work units of the reference user and the target user are the same, the value of this feature is 1, and if the work units of the reference user and the target user are different, the value of this feature is 0.

[0051] In other embodiments, the features in the feature vector may also be other factors for measuring the similarity between the reference user and the target user.

[0052] In some exemplary embodiments, the initial values of the confidence levels of all reference users are the same.

[0053] In some exemplary embodiments, obtain the historical travel records of the associated users, and screen the historical travels that match the travel starting point of the user from the historical travel records of the associated users, including:

[0054] For the M associated users, obtain the historical travel records of the M associated users;

[0055] For any associated user, find the historical travels that meet the following screening conditions from the historical travel records of the associated user, and use the screened historical travels as the historical travels that match the travel starting point of the target user;

[0056] Count the end positions of the historical travels of the M associated users, accumulate the association scores of the associated users with the same end position, and use the end position with the highest association score as the end position of the predicted travel;

[0057] Among them, the screening conditions include the following conditions:

[0058] The time interval between the starting time of the historical travel and the current time is less than the first time threshold;

[0059] The day of the week of the historical itinerary is the same as the day of the week of the current time;

[0060] The distance between the starting position of the historical itinerary and the starting position of the target user's itinerary is less than a first distance threshold.

[0061] In some exemplary embodiments, the method further includes:

[0062] Receiving a prediction result notification sent by a hybrid vehicle, and obtaining a judgment result on whether the predicted itinerary is accurate from it; if the predicted itinerary is accurate and the prediction is made based on the historical itinerary of an associated user, then increase the confidence level of the associated user whose end position of the historical itinerary in the associated users is the same as the end position of the predicted itinerary by a preset value.

[0063] By comparing the result of the previous predicted itinerary with the actual itinerary, the confidence level of the associated user can be continuously updated, so that the confidence level of the associated user with the same itinerary as the target user continuously increases, thereby increasing the accuracy of the predicted itinerary.

[0064] As Figure 2 shown, an embodiment of the present application provides a method for saving the fuel consumption of a hybrid vehicle, which is applied to a hybrid vehicle and includes:

[0065] Step S10, when the user driving the hybrid vehicle does not turn on the navigation, send a trip prediction request to the cloud server, and the trip prediction request carries the user's information; receive the trip prediction response sent by the cloud server, and obtain the trajectory information of the historical itinerary from it; wherein, the user's information includes: the user's identity information and the itinerary starting point information;

[0066] Step S20, use part or all of the trajectory of the historical itinerary as the trajectory of the predicted itinerary, send a road condition query request to the navigation server, and the road condition query request carries the trajectory information of the predicted itinerary; receive the road condition query response sent by the navigation server, and obtain the road condition information of the predicted itinerary from it;

[0067] Step S30, perform optimized allocation of hybrid energy according to the road condition information of the predicted itinerary.

[0068] The method for saving the fuel consumption of a hybrid vehicle provided by the above embodiments, when the user driving the hybrid vehicle does not turn on the navigation, the hybrid vehicle sends a trip prediction request to the cloud server, and the user's information is carried in the trip prediction request; receives the trip prediction response sent by the cloud server, and obtains the trajectory information of the historical trip from it; wherein, the user's information includes: the user's identity information and the trip starting point information; uses part or all of the trajectory of the historical trip as the trajectory of the predicted trip, and sends a road condition query request to the navigation server, and the trajectory information of the predicted trip is carried in the road condition query request; receives the road condition query response sent by the navigation server, and obtains the road condition information of the predicted trip from it; performs optimized allocation of hybrid energy according to the road condition information of the predicted trip. The method for saving the fuel consumption of a hybrid vehicle helps the user save the fuel consumption of the vehicle when driving on familiar roads by means of the trip prediction provided by the cloud server.

[0069] In some exemplary embodiments, the trajectory information of the historical trip includes at least one of the following information: the starting position of the historical trip and the ending position of the historical trip.

[0070] In some exemplary embodiments, the trajectory information of the predicted trip includes at least one of the following information: the starting position of the predicted trip and the ending position of the predicted trip.

[0071] In some exemplary embodiments, the user driving the hybrid vehicle is a registered user of the cloud server.

[0072] In some exemplary embodiments, the user's identity information includes at least one of the following information: the account number and password of the registered user.

[0073] In some exemplary embodiments, the method further includes:

[0074] Sends a registration request to the cloud server, and submits the personal information of the user driving the hybrid vehicle and the information of the vehicle during the registration process.

[0075] In some exemplary embodiments, the user's personal information includes at least one of the following information: age, gender, work unit, home address, marital status, and children status. In other embodiments, the user's personal information may also include other information.

[0076] In some exemplary embodiments, the information of the vehicle includes at least one of the following information: the brand and model of the vehicle, the license plate number, and the price range where the vehicle is located. In other embodiments, the information of the vehicle may also include other information.

[0077] In some exemplary embodiments, using some or all of the trajectory of the historical trip as the trajectory of the predicted trip includes:

[0078] Determining a predicted distance based on the capacity and aging state of the battery;

[0079] Intercepting some or all of the trajectory from the historical trip as the trajectory of the predicted trip according to the predicted distance. For example, the larger the battery capacity, the farther the predicted distance can be set. The lighter the degree of battery aging, the farther the predicted distance can be set.

[0080] In some exemplary embodiments, the road condition information of the predicted trip includes at least one of the following information: the total number of road segments divided by the predicted trip, the number of kilometers of each road segment, and the average vehicle speed of each road segment.

[0081] In some exemplary embodiments, optimizing the allocation of hybrid energy according to the road condition information of the predicted trip includes:

[0082] Configuring the engine to provide power on road segments where the average vehicle speed is higher than a first threshold; configuring the battery and the motor to provide power on road segments where the average vehicle speed is lower than a second threshold; wherein the second threshold is less than the first threshold.

[0083] In some exemplary embodiments, the state of the energy storage element can be adjusted according to the distribution of smooth and congested road segments of the entire trip to achieve further fuel savings. For example, congested road segments are suitable for pure electric driving with the battery and the motor to avoid the inefficient area of the engine working, thereby saving fuel consumption. On the smooth road segments before entering the congested road segments, the engine can be made to work in advance and the battery can be charged to ensure that the battery has enough power for use in the congested road segments.

[0084] In some exemplary embodiments, the method further includes:

[0085] At the end of the trip, if it is detected that the user driving the hybrid vehicle submits a request to share the historical trip, then send a request to share the historical trip to the cloud server, carrying the trajectory information and time information of the historical trip therein.

[0086] In some exemplary embodiments, the method further includes:

[0087] At the end of the trip, determine whether the predicted trip is accurate according to the comparison result between the trajectory of the actual trip and the trajectory of the predicted trip, and send a prediction result notification to the cloud server, carrying the judgment result of whether the predicted trip is accurate therein.

[0088] Such as Figure 3As shown in the figure, an embodiment of the present disclosure provides a device for saving the fuel consumption of a hybrid vehicle, including: a memory and a processor, where the memory stores a computer program, and when the computer program is executed by the processor, the steps of the above method for saving the fuel consumption of a hybrid vehicle are implemented.

[0089] An embodiment of the present disclosure provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the above method for saving the fuel consumption of a hybrid vehicle are implemented.

[0090] Those of ordinary skill in the art can understand that all or some of the steps in the above-disclosed methods, and the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, and appropriate combinations thereof. In the hardware implementation, the division of the functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be executed by several physical components in cooperation. Some or all of the components may be implemented as software executed by a processor, such as a digital signal processor or a microprocessor, or may be implemented as hardware, or may be implemented as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include a computer storage medium (or non-transitory medium) and a communication medium (or transitory medium). As is well known to those of ordinary skill in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data. Computer storage media include but are not limited to RAM, ROM, EEPROM, flash memory, or other memory technologies, CD-ROM, digital versatile disc (DVD), or other optical disc storage, magnetic cassette, tape, magnetic disk storage, or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, as is well known to those of ordinary skill in the art, a communication medium typically includes computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and can include any information delivery medium.

Claims

1. A method for saving fuel consumption of a hybrid vehicle, applied to a cloud server, comprising: Receiving a trip prediction request sent by a hybrid vehicle when the user does not turn on the navigation, extracting information of the user driving the vehicle from the trip prediction request, and querying the user's historical trip records according to the user's information; wherein, the user's information includes: the user's identity information and trip starting point information; If the user's historical trip records are queried, then screening the historical trips matching the user's trip starting point from the user's historical trip records; if the user's historical trip records are not queried, then finding the associated users of the user according to the big data of the vehicle networking, obtaining the historical trip records of the associated users, and screening the historical trips matching the user's trip starting point from the historical trip records of the associated users; Sending a trip prediction response to the vehicle to assist the vehicle in optimizing the allocation of hybrid energy; wherein, the trajectory information of the screened historical trip is carried in the trip prediction response; Receiving a prediction result notification sent by the hybrid vehicle, and obtaining a judgment result on whether the predicted trip is accurate from it; if the predicted trip is accurate and the prediction is made according to the historical trip of the associated user, then increasing the confidence of the associated user whose end position of the historical trip is the same as the end position of the predicted trip by a preset value; Wherein, finding the associated users of the user according to the big data of the vehicle networking includes: Taking the user who sends the trip prediction request as the target user, and taking the registered users who have shared historical trips on the cloud server as the reference users; Establishing feature vectors of multiple reference users, and setting corresponding weights for each feature in the feature vectors; wherein, any one feature is a factor for measuring the similarity between the reference user and the target user; For any one reference user, determining the value of each feature in the feature vector of the reference user, accumulating the product of the values of all features and the weights corresponding to the features to obtain an accumulated sum, and taking the product of the accumulated sum and the confidence of the reference user as the association score of the reference user; Taking the M reference users with the highest association scores as the associated users of the target user.

2. The method according to claim 1, wherein: The screening of the historical trips matching the user's trip starting point from the user's historical trip records includes: Searching for historical trips that meet the following screening conditions from the user's historical trip records, and taking the screened historical trips as the historical trips matching the user's trip starting point; Wherein, the screening conditions include the following conditions: The time interval between the starting time of the historical trip and the current time is less than the first time threshold; The day of the week of the historical trip is the same as the day of the week of the current time; The distance between the starting position of the historical trip and the user's trip starting point is less than the first distance threshold.

3. The method according to claim 1, wherein: Obtaining the historical trip records of the associated users, and screening the historical trips matching the user's trip starting point from the historical trip records of the associated users, including: For M associated users, obtain the historical trip records of the M associated users; For any one of the associated users, find the historical trips that meet the following screening conditions from the historical trip records of the associated user, and use the screened historical trips as the historical trips that match the starting point of the target user's trip; Count the end positions of the historical trips of the M associated users, accumulate the association scores of the associated users with the same end position, and use the end position with the highest association score as the end position of the predicted trip; Among them, the screening conditions include the following conditions: The time interval between the starting time of the historical trip and the current time is less than the first time threshold; The day of the week of the historical trip is the same as the day of the week of the current time; The distance between the starting position of the historical trip and the starting position of the target user's trip is less than the first distance threshold.

4. The method according to claim 1, wherein: The method further includes: Receiving a registration request sent by a hybrid vehicle, and saving the personal information of the user driving the hybrid vehicle and the information of the vehicle submitted during the registration process.

5. The method according to claim 1, wherein: The method further includes: If a request for sharing historical trips sent by a hybrid vehicle is received, obtain the trajectory information and time information of the historical trips of the user driving the hybrid vehicle from the request and save them.

6. A method for saving fuel consumption of a hybrid vehicle, applied to a hybrid vehicle, including: When the user driving the hybrid vehicle does not turn on the navigation, send a trip prediction request to the cloud server, and the trip prediction request carries the user's information; Receive the trip prediction response sent by the cloud server, and obtain the trajectory information of the historical trip therefrom; wherein, the user's information includes: the user's identity information and trip starting point information; Use part or all of the trajectory of the historical trip as the trajectory of the predicted trip, send a road condition query request to the navigation server, and the road condition query request carries the trajectory information of the predicted trip; receive the road condition query response sent by the navigation server, and obtain the road condition information of the predicted trip therefrom; Optimize the allocation of hybrid energy according to the road condition information of the predicted trip; At the end of the trip, determine whether the predicted trip is accurate according to the comparison result between the trajectory of the actual trip and the trajectory of the predicted trip, and send a prediction result notification to the cloud server, which carries the judgment result of whether the predicted trip is accurate. When the judgment result is that the predicted trip is accurate, if the prediction is made by the cloud server based on the historical trips of the associated users, the cloud server will increase the confidence level of the associated users among the associated users whose end positions of the historical trips are the same as the end position of the predicted trip by a preset value; Among them, the associated users are found by the cloud server according to the big data of the vehicle network for the user; Finding the associated users of the user according to the big data of the vehicle network includes: Regarding the user who sends the trip prediction request as the target user, and regarding the registered users who have shared historical trips on the cloud server as the reference users; Establish feature vectors of multiple reference users, and set corresponding weights for each feature in the feature vectors; wherein, any one feature is a factor for measuring the similarity between a reference user and a target user. For any one reference user, determine the value of each feature in the feature vector of the reference user, accumulate the product of the values of all features and the weights corresponding to the features to obtain an accumulated sum, and use the product of the accumulated sum and the confidence level of the reference user as the association score of the reference user. Take the M reference users with the highest association scores as the associated users of the target user.

7. The method according to claim 6, wherein: The step of using part or all of the trajectory of the historical trip as the trajectory of the predicted trip includes: Determine the predicted distance according to the capacity and aging state of the battery. Intercept part or all of the trajectory of the historical trip as the trajectory of the predicted trip according to the predicted distance.

8. The method according to claim 6, wherein: The road condition information of the predicted trip includes at least one of the following information: the total number of road segments divided by the predicted trip, the number of kilometers of each road segment, and the average vehicle speed of each road segment.

9. The method according to claim 8, wherein: Optimally allocate hybrid energy according to the road condition information of the predicted trip, including: Configure the engine to provide power on road segments where the average vehicle speed is higher than the first threshold; configure the battery and the motor to provide power on road segments where the average vehicle speed is lower than the second threshold; wherein, the second threshold is less than the first threshold.

10. The method according to claim 6, wherein: The method further includes: At the end of the trip, if it is detected that the user driving the hybrid vehicle submits a request to share the historical trip, send a request to share the historical trip to the cloud server, carrying the trajectory information and time information of the historical trip therein.

11. A device for saving fuel consumption of a hybrid vehicle, comprising: A memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, the steps of the method for saving fuel consumption of a hybrid vehicle according to any one of claims 1-5 or 6-10 above are implemented.

12. A computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the method for saving fuel consumption of a hybrid vehicle according to any one of claims 1-5 or 6-10 above are implemented.

Images