Method for predicting position of vehicle, position prediction device, server, and storage medium
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ECOFLOW INC
- Filing Date
- 2023-01-29
- Publication Date
- 2026-06-26
AI Technical Summary
In cases where a vehicle loses contact, existing technologies struggle to quickly and accurately predict its exact location, resulting in low rescue efficiency.
By obtaining vehicle information sent by the missing vehicle before it went missing, including its location and destination, multiple routes were determined. Based on the route information of each route, the driving speed was predicted. Combined with the time interval between the current time and the time of disappearance, the current location of the vehicle was accurately determined.
This improves the accuracy of predicting the current location of missing vehicles, ensuring that rescue measures are targeted and efficient.
Smart Images
Figure CN116182885B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of information processing technology, and in particular to a vehicle location prediction method, a vehicle location prediction device, a vehicle management server, and a storage medium. Background Technology
[0002] In recent years, more and more people have enjoyed road trips, which have brought them a richer mobile lifestyle experience. However, road trips also carry many risks. Therefore, how to quickly and accurately predict the exact location of a vehicle when it loses contact, so as to quickly rescue missing persons, has become an urgent problem for relevant technical personnel to solve. Summary of the Invention
[0003] Based on this, this application provides a vehicle location prediction method, a vehicle location prediction device, a vehicle management server, and a storage medium, which can more accurately predict the vehicle's location.
[0004] In a first aspect, this application provides a vehicle location prediction method, applied to a vehicle management server, the method comprising:
[0005] Obtain vehicle information sent by the missing vehicle before it lost contact, the vehicle information including the first location of the missing vehicle when it sent the vehicle information and the time of loss of contact;
[0006] Obtain the destination of the missing vehicle;
[0007] Determine one or more routes based on the first location and the destination;
[0008] Based on the route information of each of the aforementioned routes, predict the driving speed corresponding to each of the aforementioned routes;
[0009] The current predicted location of the missing vehicle is determined based on the first location, each of the travel routes, the travel speed corresponding to each of the travel routes, and the first interval between the current time and the time of loss of contact.
[0010] Secondly, this application provides a vehicle location prediction device, applied to a vehicle management server, the device comprising:
[0011] The vehicle information acquisition module is used to acquire vehicle information sent by the missing vehicle before it lost contact. The vehicle information includes the first location of the missing vehicle when it sent the vehicle information and the time of loss of contact.
[0012] A destination acquisition module is used to acquire the destination of the missing vehicle.
[0013] A route determination module is used to determine one or more travel routes based on the first location and the destination;
[0014] The speed prediction module is used to predict the driving speed corresponding to each of the travel routes based on the route information of each travel route.
[0015] The location prediction module is used to determine the current predicted location of the missing vehicle based on the first location, each of the travel routes, the travel speed corresponding to each of the travel routes, and the first interval between the current time and the time of loss of contact.
[0016] Thirdly, this application provides a vehicle management server, which includes a processor and a memory, the memory being used to store a computer program; the processor being used to execute the computer program and, when executing the computer program, to implement the vehicle position prediction method as described above.
[0017] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the vehicle position prediction method described above.
[0018] This application embodiment obtains the first location, time of loss of contact, and destination sent by the missing vehicle before it lost contact; determines one or more routes based on the first location and destination; predicts the corresponding speed for each route based on the route information; when predicting the speed for each route, each route is predicted separately based on its corresponding route information, rather than using a uniform prediction method or a single route information as the basis for prediction, making the predicted speed more reasonable and closer to the actual speed for each route. Furthermore, based on the first location, each route, the corresponding speed for each route, and the first interval between the current time and the time of loss of contact, the current predicted location of the missing vehicle is determined, which is closer to the actual location reached by the vehicle, improving the accuracy of predicting the current location of the missing vehicle. Attached Figure Description
[0019] Figure 1 This is a schematic flowchart of a vehicle position prediction method provided in an embodiment of this application;
[0020] Figure 2 This is a flowchart illustrating a vehicle position prediction method provided in another embodiment of this application;
[0021] Figure 3 This is a flowchart illustrating a vehicle position prediction method provided in another embodiment of this application;
[0022] Figure 4 This is a flowchart illustrating a vehicle position prediction method provided in another embodiment of this application;
[0023] Figure 5 This is a flowchart illustrating a vehicle position prediction method provided in another embodiment of this application;
[0024] Figure 6 This is a flowchart illustrating a vehicle position prediction method provided in another embodiment of this application;
[0025] Figure 7 This is a flowchart illustrating a vehicle position prediction method provided in another embodiment of this application;
[0026] Figure 8 This is a schematic diagram of the driving path and position prediction in a vehicle position prediction method provided in an embodiment of this application;
[0027] Figure 9 This is a schematic diagram illustrating the prediction of a first parameter affecting driving speed in a vehicle position prediction method provided in an embodiment of this application;
[0028] Figure 10 This is a block diagram of a vehicle position prediction device provided in an embodiment of this application;
[0029] Figure 11 This is a block diagram of a vehicle management server provided in one embodiment of this application. Detailed Implementation
[0030] 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, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.
[0031] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the scope of the application. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.
[0032] It should also be further understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.
[0033] In recent years, more and more people have enjoyed road trips, which have brought them a richer mobile lifestyle experience. However, road trips also carry many risks. Therefore, how to quickly and accurately predict the exact location of a vehicle when it loses contact, so as to quickly rescue missing persons, has become an urgent problem for relevant technical personnel to solve.
[0034] This application embodiment obtains the first location, time of loss of contact, and destination sent by the missing vehicle before it lost contact; determines one or more routes based on the first location and destination; predicts the corresponding speed for each route based on the route information; when predicting the speed for each route, each route is predicted separately based on its corresponding route information, rather than using a uniform prediction method or a single route information as the basis for prediction, making the predicted speed more reasonable and closer to the actual speed for each route. Furthermore, based on the first location, each route, the corresponding speed for each route, and the first interval between the current time and the time of loss of contact, the current predicted location of the missing vehicle is determined, which is closer to the actual location reached by the vehicle, improving the accuracy of predicting the current location of the missing vehicle.
[0035] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.
[0036] See Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of the vehicle location prediction method of this application, applied to a vehicle management server. The method includes steps S101 to S105.
[0037] Step S101: Obtain the vehicle information sent by the missing vehicle before it lost contact. The vehicle information includes the first location of the missing vehicle when it sent the vehicle information and the time of loss of contact.
[0038] In step S101, loss of connection may refer to the vehicle losing communication with the vehicle management server and / or the vehicle failing to arrive at the corresponding location within the specified time frame.
[0039] In all embodiments of this application, "missing vehicle" refers to any vehicle that has lost communication with the vehicle management server. Since vehicles can continuously send vehicle information to the vehicle management server at regular intervals during operation, that is, periodically send vehicle information to the vehicle management server, when a vehicle is not yet out of contact, it can continuously send vehicle information to the vehicle management server at regular intervals while traveling in an area with communication signals. Based on this, when the vehicle management server receives vehicle information from the previous time interval or period, if it does not receive vehicle information in the current time interval or period, it can determine that the vehicle is out of contact. Therefore, the vehicle information from the previous time interval or period can be considered as the vehicle information sent by the vehicle before it lost contact.
[0040] In this embodiment, the vehicle information may include the first location of the missing vehicle when it sent the vehicle information and the time of loss of contact. In other embodiments, the vehicle information may also include at least one of the following: road number, fuel level, driving speed, communication device battery level, and signal strength when the missing vehicle sent the vehicle information. The road number can determine which road the missing vehicle was traveling on, and the fuel level can determine how far the missing vehicle can travel, thus helping to determine the specific range of the missing vehicle's location.
[0041] After a missing vehicle loses communication with the vehicle management server, the vehicle information sent by the vehicle before it lost contact can be obtained to determine where the vehicle lost contact (i.e., the first location) and when the last vehicle information was sent (i.e., the time of loss of contact).
[0042] In some embodiments, after a missing vehicle loses communication with the vehicle management server, the server may first attempt to call the vehicle. If no response is received, the server will then retrieve vehicle information sent by the vehicle before it lost contact. The attempt to call the missing vehicle can be based on an emergency call (eCall) system, specifically by calling the vehicle's onboard terminal. Since vehicles are equipped with 2G, 3G, and 4G mobile communication devices, the vehicle management server can use an emergency call method to attempt to contact the missing vehicle after it has 2G cellular communication capabilities. In some examples, the vehicle management server may also use a user-registered phone number to attempt to contact the owner of the missing vehicle.
[0043] Step S102: Obtain the destination of the missing vehicle.
[0044] In practical applications, lost vehicles can plan their journeys in advance (including destination and route planning) and send the plans to the vehicle management server. Lost vehicles can also send their destination as vehicle information to the vehicle management server while in motion. For example, a user can determine their destination through the vehicle's navigation system, sending the destination information to the vehicle management server and requesting navigation; thus, the vehicle management server can obtain the destination.
[0045] In step S102, the vehicle management server can obtain the destination of the missing vehicle based on the received itinerary and / or vehicle information. Based on the destination of the missing vehicle, it can determine which road the missing vehicle is most likely to have taken, and then analyze the road conditions during the journey to the destination, and roughly analyze what caused the vehicle to go missing.
[0046] It should be noted that steps S101 and S102 can be performed simultaneously or in a specific order. For example, steps S101 and S102 can be performed simultaneously, or steps S101 can be performed first, followed by steps S102.
[0047] Step S103: Determine one or more routes based on the first location and the destination.
[0048] In step S103, based on the first location and the destination, and in conjunction with the map, one or more possible routes from the first location to the destination can be determined.
[0049] Figure 8 A schematic diagram showing the driving path and location prediction is provided. Figure 8 In this scenario, assume the missing vehicle lost contact at point P1, and point P2 is its destination. That is, the location of point P1 is the last location sent by the missing vehicle to the vehicle management server. There are three possible routes from point P1 to point P2: route L1 (direction 1), route L2 (direction 2), and route L3 (direction 3).
[0050] In practical applications, when planning the route from point P1 to point P2, the first route L1, the second route L2, and the third route L3 are all the driving paths the vehicle takes from its initial position to its destination. Additionally, route L1 can be defaulted as the primary route, meaning the probability or weight of the missing vehicle traveling in direction 1 is set to the maximum probability or weight. The second route L2 and the third route L3 are then considered as alternative routes during the prediction process.
[0051] Step S104: Based on the route information of each route, predict the corresponding travel speed for each route.
[0052] In step S104, the route information can refer to information related to the travel route that affects the travel speed, including but not limited to: the road width of the travel route, the congestion situation of the travel route, and the traffic accident situation of the travel route. In some embodiments, the route information can be at least one of the road width of the travel route, the congestion situation of the travel route, and the traffic accident situation of the travel route.
[0053] In some embodiments, the route information for each travel route can be information obtained in real time by the vehicle management server. For example, the vehicle management server receives traffic data uploaded by vehicles traveling on each route in real time, and can then process the traffic data to obtain the route information for each travel route.
[0054] In some embodiments, route information of the travel route can also be included as part of vehicle information and sent to the vehicle management server continuously at certain time intervals along with the vehicle information.
[0055] Based on the route information of each route, the corresponding driving speed for each route is predicted. This makes the predicted driving speed for each route closer to the actual driving speed for each route, which helps to more accurately determine the current predicted location of the missing vehicle.
[0056] Step S105: Determine the current predicted location of the missing vehicle based on the first location, each travel route, the corresponding travel speed of each travel route, and the first interval between the current time and the time of loss of contact.
[0057] In step S105, the first position can be used as the starting position of each route. The travel time of the missing vehicle can be determined based on the first interval between the current time and the time of loss of contact. Based on the travel speed corresponding to each route and the first interval, the distance traveled by the missing vehicle can be roughly determined. Combined with the first position, the current predicted position of the missing vehicle on each route can be determined, and thus the current predicted position of the missing vehicle can be determined.
[0058] This application embodiment obtains the first location, time of loss of contact, and destination sent by the missing vehicle before it lost contact; determines one or more routes based on the first location and destination; predicts the corresponding speed for each route based on the route information; when predicting the speed for each route, each route is predicted separately based on its corresponding route information, rather than using a uniform prediction method or a single route information as the basis for prediction, making the predicted speed more reasonable and closer to the actual speed for each route. Furthermore, based on the first location, each route, the corresponding speed for each route, and the first interval between the current time and the time of loss of contact, the current predicted location of the missing vehicle is determined, which is closer to the actual location reached by the vehicle, improving the accuracy of predicting the current location of the missing vehicle.
[0059] In some embodiments, step S104, predicting the travel speed corresponding to each travel route based on the route information of each travel route, may include: sub-steps S1041, S1042, and S1043, such as... Figure 2 As shown.
[0060] Sub-step S1041: Determine the first parameter corresponding to each travel route based on the route information of each travel route.
[0061] In sub-step S1041, the first parameter is the speed-affecting parameter of the travel route, which is greater than 0 and less than 1. In specific implementation, the first parameter can be obtained based on the route information of each travel route, and the first parameter is different for different travel routes.
[0062] Sub-step S1042: Obtain the average speed of the missing vehicle.
[0063] In sub-step S1042, the average speed of the missing vehicle can refer to the average speed of the missing vehicle over a certain period of time before it went missing. Compared to using the speed of the missing vehicle before it went missing, using the average speed of the missing vehicle can reduce detection errors and random errors, and can more objectively represent the actual speed of the missing vehicle. For example, multiple speeds of multiple missing vehicles over a certain period of time before they went missing can be obtained, and the average of these multiple speeds is the average speed of the missing vehicle.
[0064] It should be noted that the execution order of sub-steps S1041 and S1042 is not important. Sub-steps S1041 can be executed first and then S1042, or they can be executed simultaneously.
[0065] Sub-step S1043: Calculate the product of the average driving speed and the first parameter corresponding to each route to obtain the driving speed corresponding to each route.
[0066] In sub-step S1043, the travel speed corresponding to each travel route is equal to the product of the average travel speed and the first parameter corresponding to each travel route.
[0067] For example, if the first parameters corresponding to the travel routes L1, L2, and L3 are α1, α2, and α3 respectively, and the average speed of the lost vehicle is V, then the predicted travel speeds corresponding to the travel routes L1, L2, and L3 are α1*V, α2*V, and α3*V respectively.
[0068] This application embodiment determines a first parameter affecting driving speed for each travel route based on the route information, and calculates the product of the average driving speed and the first parameter for each travel route to obtain the driving speed for each travel route. In this way, the driving speed for each travel route is closer to the actual driving speed for that route, and more consistent with reality.
[0069] In some embodiments, the travel route includes one or more road segments. Sub-step S1041, which determines the first parameter corresponding to each travel route based on the route information of each travel route, may further include sub-steps S10411 and S10412, such as... Figure 3 As shown.
[0070] Sub-step S10411: Determine the first sub-parameter corresponding to each road segment based on the road segment information of each road segment in the travel route.
[0071] In sub-step S10411, the travel route is divided into one or more segments, each with corresponding segment information, based on which the first sub-parameter corresponding to each segment is determined. Subdividing the travel route into multiple segments and determining the first sub-parameter corresponding to each segment allows for a more precise determination of the first sub-parameter affecting the travel speed for each segment.
[0072] Sub-step S10412: Calculate the average value of the first sub-parameter corresponding to all road segments in each travel route, and use it as the first parameter corresponding to each travel route.
[0073] In sub-step S10412, the average value of the first sub-parameters corresponding to all road segments in each travel route is used as the first parameter corresponding to each travel route, which can obtain the first parameter affecting the travel speed of each travel route that is more in line with the actual situation.
[0074] by Figure 8The diagram illustrating the driving path and location prediction is shown below. Assume the travel route L1 is divided into two segments L11 and L12, and the first sub-parameters corresponding to segments L11 and L12 are α and α, respectively. L11 α L12 Then the first parameter α1 corresponding to the travel route L1 satisfies: α1=(α L11 +α L12 ) / 2.
[0075] For example: in Figure 8 The route L2 is divided into two segments L21 and L22, and the first sub-parameters corresponding to the two segments L21 and L22 are α and L22, respectively. L21 α L22 Then the first parameter α2 corresponding to the travel route L2 satisfies: α2=(α L21 +α L22 ) / 2.
[0076] For example: in Figure 8 The route L3 is divided into three segments L31, L32, and L33. The first sub-parameters corresponding to the three segments L31, L32, and L33 are α, ... L31 α L32 α L33 Then the first parameter α3 corresponding to the travel route L3 is (α L31 +α L32 +α L33 ) / 3.
[0077] In this embodiment, the travel route is subdivided into multiple segments, and a first sub-parameter corresponding to each segment is determined. Then, the average value of one or more first sub-parameters in each travel route is used as the first parameter corresponding to each travel route. In this way, the first parameter affecting the travel speed is more accurate.
[0078] It should be noted that, in other embodiments, the maximum or minimum value among the multiple first sub-parameters in each travel route can also be used as the first parameter corresponding to each travel route.
[0079] In some embodiments, step S105, determining the current predicted location of the missing vehicle based on the first location, each travel route, the travel speed corresponding to each travel route, and the first interval between the current time and the time of loss of contact, may include sub-steps S105A1 and S105A2, such as... Figure 4 As shown.
[0080] Sub-step S105A1: Obtain the duration adjustment parameter, and determine the second interval duration based on the first interval duration and the duration adjustment parameter; the second interval duration is less than the first interval duration.
[0081] In sub-step S105A1, the duration adjustment parameter is the adjustment parameter for the first interval duration, which is greater than 0 and less than 1. The duration adjustment parameter can be predicted based on one or more duration adjustment influencing factors, including but not limited to: weather information, road condition information of the travel route, and itinerary information. The missing vehicle can include the duration adjustment influencing factors as part of its vehicle information, sending it continuously to the vehicle management server at certain time intervals. In practice, the missing vehicle may have lost contact before the current time. Therefore, by adjusting the first interval duration between the current time and the time of loss of contact using the duration adjustment parameter, the adjusted second interval duration is less than the first interval duration, making the second interval duration closer to the actual time interval of loss of contact. In some embodiments, the product of the first interval duration and the duration adjustment parameter is used as the second interval duration.
[0082] Sub-step S105A2: Determine the current predicted location of the missing vehicle based on the first location, each travel route, the corresponding travel speed of each travel route, and the second interval duration.
[0083] In sub-step S105A2, the adjusted second interval duration is used to replace the first interval duration. Combined with the first position, each travel route, and the corresponding travel speed of each travel route, the current predicted position of the missing vehicle is determined, which can improve the prediction accuracy of the current predicted position of the missing vehicle.
[0084] In some embodiments, sub-step S1051, obtaining the duration adjustment parameter, may include sub-steps S105A11 and S105A12, such as... Figure 5 As shown.
[0085] Sub-step S105A11: Obtain the weather information corresponding to the first location at the time of loss of contact.
[0086] In sub-step S105A11, the duration adjustment influencing factor is obtained as weather information, which is the weather information corresponding to the time and first location of the missing vehicle. The missing vehicle can include the weather information as part of the vehicle information and send it to the vehicle management server continuously at certain time intervals along with the vehicle information.
[0087] Sub-step S105A12: Determine the duration adjustment parameters based on weather information.
[0088] In sub-step S105A12, the duration adjustment parameter is determined based on weather information. Generally, when the weather is good, the duration adjustment parameter will be closer to 1, and when the weather is bad (e.g., heavy rain, fog, sandstorms, etc.), the duration adjustment parameter will be closer to 0.
[0089] In some embodiments, in addition to weather information, the duration adjustment influencing factors also include other duration adjustment influencing factors. In this case, a duration adjustment sub-parameter can be determined based on each duration adjustment influencing factor, and the final duration adjustment parameter can be the average value of multiple duration adjustment sub-parameters.
[0090] In some embodiments, the vehicle information also includes fuel level information. In this case, step S105 involves determining the first location, each travel route, the corresponding travel speed for each route, and the first interval between the current time and the time of loss of contact. Figure 6 As shown, determining the current predicted location of the missing vehicle may also include: sub-steps S105B1, S105B2, and S105B3.
[0091] Sub-step S105B1: Determine the vehicle's drivable range based on the first position and fuel level information.
[0092] In sub-step S105B1, since the vehicle information also includes fuel level information, the distance the vehicle can travel can be determined based on the fuel level information. Therefore, the vehicle's drivable range can be determined based on the first position and the fuel level information.
[0093] Sub-step S105B2: Based on the first position, each travel route, the corresponding travel speed of each travel route, and the first interval between the current time and the time of loss of contact, determine the candidate predicted position corresponding to each travel route.
[0094] In sub-step S105B2, the first position can be used as the starting point of each route. Based on the driving speed corresponding to each route and the first interval duration, the distance traveled by the missing vehicle can be roughly determined. Combined with the first position, the candidate predicted positions of the missing vehicle on each route can be determined.
[0095] Sub-step S105B3: Determine the current predicted location of the missing vehicle based on the candidate predicted locations and drivable ranges corresponding to each travel route. The current predicted location of the missing vehicle is within the drivable range.
[0096] In sub-step S105B3, based on the drivable range, candidate predicted positions for each route that are outside the drivable range can be excluded, thereby determining the current predicted position of the missing vehicle.
[0097] In some embodiments, when a candidate predicted location corresponding to a certain route exceeds the drivable range, the intersection of the drivable range and the route can be determined as the candidate predicted location corresponding to that route. Then, the candidate predicted locations corresponding to each route can be determined as the current predicted location of the missing vehicle. The number of such current predicted locations can be one or more.
[0098] like Figure 7 As shown, in some embodiments, the vehicle position prediction method further includes steps S106, S107, and S108.
[0099] Step S106: Obtain vehicle missing information. Vehicle missing information includes multiple regions and the accident type corresponding to each region.
[0100] In step S106, the vehicle loss file can be a pre-established file that records multiple areas where accidents have occurred and the types of accidents that occurred in each area.
[0101] Step S107: Based on the current predicted location and the vehicle loss record, determine the predicted area where the missing vehicle is located and the accident type corresponding to the predicted area.
[0102] In step S107, since the vehicle missing records contain multiple regions and the types of accidents that occur in each region, the predicted region where the missing vehicle is located and the corresponding accident type can be determined based on the current predicted location and the vehicle missing records.
[0103] Step S108: Determine the target rescue plan corresponding to the accident type in the predicted area, and execute the target rescue plan.
[0104] In step S108, after determining the accident type corresponding to the predicted area, the corresponding target rescue plan can be determined and executed. This improves the targeting and efficiency of the rescue.
[0105] The following is combined Figure 8 This paper uses the example of a motorhome losing contact during operation to illustrate the prediction of its travel path and the location of a rescue operation.
[0106] Before the RV starts its journey from location P0 to destination P2, the RV (or its onboard terminal) sends vehicle information, including the starting point P0, starting time, route plan, road number, fuel level, and destination P2, to the vehicle management server. During the journey, the RV periodically feeds back vehicle information to the vehicle management server, which may include the current road number, current location, weather conditions, traffic congestion, speed, fuel level, communication device battery level, and signal strength.
[0107] When the vehicle management server receives the last location P1 sent by the RV, it predicts the RV's travel path and rescue range based on the current time and all vehicle information during the journey. The vehicle management server uses the time when it last received the location P1 (i.e., the first location) sent by the RV as the time of loss of contact, and the time when it performs RV location prediction and rescue is the current time. The difference between the current time and the time of loss of contact is the first interval duration Δt1. All vehicle information during the journey is used to predict the travel speed V. The location before loss of contact is P1. Therefore, the current predicted location P of the RV after loss of contact can be determined according to the following formula:
[0108] Predicted location P predicting = Position before loss of contact P1 + (Predicted speed V * First interval duration △t1).
[0109] As an example, with Figure 8 Taking the first route L1, the second route L21-L22, and the third route L31-L33 as examples, the above formula can also be transformed into the following system of equations:
[0110]
[0111] Where V1 is the predicted speed of the first travel route L1, and P predicting1 V1 represents the predicted position of the RV on the first travel route L1; V2 represents the predicted speed on the second travel route L21-L22; P represents the predicted speed of the RV. predicting2 V3 represents the predicted position of the RV on the second route L21-L22; V3 represents the predicted speed on the third route L31-L33; P represents the predicted speed of the RV on the third route L31-L33. predicting3 V represents the predicted position of the RV on the third travel route L31-L33; R represents the RV's drivable range based on its fuel level prediction. 平均 The average speed of the RV can be calculated based on the speed and time data from the RV's travel data before it lost contact.
[0112] α is the primary parameter affecting driving speed corresponding to the travel route. It can be calculated based on factors such as road width, traffic congestion, and the presence of accidents. Different travel routes have different α values. Specifically, each travel route is divided into N parts, resulting in N α values. ii , N α i Summing and then averaging, see Formula 2 below:
[0113] Where 0 < α < 1.
[0114] by Figure 9 The first travel route L1 shown is divided into L11 and L12 with PX as the boundary.
[0115] For example, if L11 is a free-flowing road segment and L12 is a congested road segment, then α corresponds to L11. L11 α greater than L12 L12 Substituting into Formula 2 above, we get α L11 With α L12 Summing and averaging yields the first parameter α1 that affects the travel speed corresponding to the first travel route L1.
[0116] For example, if L11 is a narrow road section and L12 is a wide road section, then α corresponds to L11. L11 α less than L12 L12 Substituting into Formula 2 above, we get α L11 With α L12 Summing and averaging yields the first parameter α1 that affects the travel speed corresponding to the first travel route L1.
[0117] The first travel route L1 is divided into L11 and L12, so N is 2. Combining this with equation set 1, the travel speed V1 corresponding to the first travel route L1 can be predicted. Similarly, the first parameters α1 and α2, which affect the travel speed of the second travel route L2 and the third travel route L3, as well as the travel speeds V2 and V3, can be predicted in the same way.
[0118] In other embodiments, in order to improve the prediction accuracy of the current predicted location P of the RV after losing contact, a duration adjustment parameter β is introduced, where β is related to the first interval duration Δt1 in Formula 1 and Equation 1 above.
[0119] Specifically, it can be expressed using the following formula three:
[0120] The second interval duration Δt2 = βΔt1, where the first interval duration Δt1 = (t current -t missing )
[0121] Among them, t current tmissing is the current time, and tmissing is the time of loss of contact. β is a duration adjustment parameter for weather information, road condition information of the travel route, and / or itinerary information, which can be calculated using the following formula:
[0122] Where 0 < β < 1, and M is the number of duration-modifying influencing factors.
[0123] In some embodiments, if the duration adjustment factor only includes weather information and road condition information of the travel route, then M = 2. If the weather conditions are good, the β corresponding to the weather information is closer to 1, and vice versa. Similarly, if the road conditions are good, the β corresponding to the road condition information of the travel route is closer to 1, and vice versa.
[0124] In some embodiments, if the duration adjustment factors include weather information, road condition information of the route, and trip arrangement information, then M = 3. It should be noted that trip arrangement information refers to whether there are any driving tasks scheduled within the first interval from the time of loss of contact to the current time.
[0125] For example, if the time of loss of contact is 3:00 AM and the current time is 4:30 AM, then the first interval is 90 minutes. Within these 90 minutes, the traveler may be partially or entirely in motion, or partially or entirely out of motion. Therefore, by combining the travel schedule information, the corresponding β value is determined.
[0126] Taking a 90-minute period with 65 minutes of travel time as an example, the β value corresponding to the itinerary information can be 65 / 90≈0.72. Based on the above example, assuming the β value corresponding to weather information is 0.82, the β value corresponding to road condition information is 0.89, and the β value corresponding to itinerary information is 0.72, then using Formula 4 above, we can calculate β = (0.82 + 0.89 + 0.72) / 3 = 0.81. Accordingly, substituting into Formula 3 above, we can obtain: the predicted second interval duration Δt2 = βΔt1, which is equivalent to Δt2 = 0.81 * 90 minutes = 72.9 minutes.
[0127] Accordingly, the above system of equations can be transformed into the following system of equations:
[0128]
[0129] Regardless of whether the current predicted location P of the RV is obtained by using either Equation 1 or Equation 2, the final prediction can be made using the road evaluation function, from which the most likely route and current predicted location are selected.
[0130] For example, the road evaluation function F(G: destination 60%, R: road congestion 40%), and then from P... predicting1 P predicting2 P predicting3 The current predicted position P of the target is determined in the middle.
[0131] F(G,R)=μ(X·G(Dist,T)+Y·R(V 平均 ,T))
[0132] G(Dist,T) represents the correlation function between the distance Dist from each route to the destination and the time T for each route to reach the destination. In G(Dist,T), the route with the shortest distance Dist and the shortest time T to reach the destination have the highest weight. X is the driving safety factor for each route; the wider the road, the higher the safety factor.
[0133] R(V 平均 T) represents the average speed V along each route. 平均 The correlation function of the time T for reaching the destination along each route. In R(V 平均 In (T), the V of the travel route 平均 The larger the value, the greater the weight; the shortest travel time T to the destination is the highest weight. Y is the congestion coefficient for each travel route; the longer the congestion lasts under the same conditions, the lower the Y value. μ is the travel coefficient for each travel route; the more times a travel route is selected, the larger the value of μ.
[0134] By using the above methods, the current predicted location of missing vehicles can be determined more accurately, which facilitates the provision of rescue routes and scope references for accidents involving missing vehicles and can improve the efficiency of outdoor rescue for missing vehicles.
[0135] See Figure 10 , Figure 10 This is a block diagram of an embodiment of the vehicle location prediction device of this application, applied to a vehicle management server. The device 10 includes: a vehicle information acquisition module 101, a destination acquisition module 102, a route determination module 103, a speed prediction module 104, and a location prediction module 105. It should be noted that the functions of each module in the vehicle location prediction device of this embodiment correspond to the relevant steps in the above-described method. For detailed explanations of the relevant content, please refer to the above-described method section, which will not be repeated here.
[0136] The vehicle information acquisition module 101 is used to acquire vehicle information sent by the missing vehicle before it lost contact. The vehicle information includes the first location of the missing vehicle when it sent the vehicle information and the time of loss of contact.
[0137] The destination acquisition module 102 is used to acquire the destination of the missing vehicle.
[0138] The route determination module 103 is used to determine one or more travel routes based on the first location and the destination.
[0139] The speed prediction module 104 is used to predict the driving speed corresponding to each travel route based on the route information of each travel route.
[0140] The location prediction module 105 is used to determine the current predicted location of the missing vehicle based on the first location, each travel route, the corresponding travel speed of each travel route, and the first interval between the current time and the time of loss of contact.
[0141] This application embodiment obtains the first location, time of loss of contact, and destination sent by the missing vehicle before it lost contact; determines one or more routes based on the first location and destination; predicts the corresponding speed for each route based on the route information; when predicting the speed for each route, each route is predicted separately based on its corresponding route information, rather than using a uniform prediction method or a single route information as the basis for prediction, making the predicted speed more reasonable and closer to the actual speed for each route. Furthermore, based on the first location, each route, the corresponding speed for each route, and the first interval between the current time and the time of loss of contact, the current predicted location of the missing vehicle is determined, which is closer to the actual location reached by the vehicle, improving the accuracy of predicting the current location of the missing vehicle.
[0142] See Figure 11 , Figure 11 This is a block diagram of an embodiment of the vehicle management server of this application. It should be noted that the vehicle management server of this application embodiment can implement the above-described vehicle location prediction method. For a detailed description of the relevant content, please refer to the above-described method section, which will not be repeated here.
[0143] The vehicle management server 20 includes a processor 201 and a memory 202. The memory 202 stores computer programs; the processor 201 executes the computer programs and, when executing the computer programs, implements the vehicle position prediction method described above. The memory 202 is connected to the processor 201 via a bus.
[0144] The processor 201 can be a microcontroller unit, a central processing unit, or a digital signal processor, etc. The memory 202 can be a flash chip, a read-only memory, a disk, an optical disk, a USB flash drive, or a portable hard drive, etc.
[0145] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the vehicle position prediction method described above.
[0146] The computer-readable storage medium can be an internal storage unit of the vehicle's location prediction device or vehicle management server, such as a hard disk or memory. Alternatively, it can be an external storage device of the vehicle's location prediction device or vehicle management server, such as a pluggable hard disk, smart memory card, secure digital card, flash memory card, etc.
[0147] It should be understood that the terminology used in this application specification is for the purpose of describing particular embodiments only and is not intended to limit the application.
[0148] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.
[0149] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and such modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
Claims
1. A method for predicting the location of a vehicle, characterized in that, Applied to a vehicle management server, the method includes: Obtain vehicle information sent by the missing vehicle before it lost contact, the vehicle information including the first location of the missing vehicle when it sent the vehicle information and the time of loss of contact; Obtain the destination of the missing vehicle; Multiple travel routes are determined based on the first location and the destination; Based on the route information of each of the aforementioned routes, predict the driving speed corresponding to each of the aforementioned routes; Based on the first location, each of the stated travel routes, the corresponding travel speeds for each of the stated travel routes, and the first interval between the current time and the time of loss of contact, the current predicted location of the missing vehicle is determined, including: Obtain the duration adjustment parameter, and determine the second interval duration based on the first interval duration and the duration adjustment parameter; the second interval duration is less than the first interval duration; the duration adjustment parameter is greater than 0 and less than 1; the duration adjustment parameter is determined based on one or more of the weather information, road condition information of the driving route, and itinerary arrangement information; The current predicted location of the missing vehicle is determined based on the first location, each of the travel routes, the travel speed corresponding to each of the travel routes, and the second interval duration.
2. The method according to claim 1, characterized in that, The step of predicting the travel speed corresponding to each of the travel routes based on the route information of each of the travel routes includes: Based on the route information of each of the aforementioned routes, determine the first parameter corresponding to each of the aforementioned routes; Obtain the average speed of the missing vehicle; The average driving speed is calculated by multiplying it by the first parameter corresponding to each of the travel routes to obtain the driving speed corresponding to each of the travel routes.
3. The method according to claim 2, characterized in that, The travel route includes one or more road segments, and the route information includes road segment information for each of the road segments; The step of determining the first parameter corresponding to each of the travel routes based on the route information of each travel route includes: Based on the road segment information of each road segment in the travel route, determine the first sub-parameter corresponding to each road segment; Calculate the average value of the first sub-parameter corresponding to all the road segments in each of the travel routes, and use it as the first parameter corresponding to each of the travel routes.
4. The method according to claim 1, characterized in that, The acquisition of duration adjustment parameters includes: Obtain the weather information corresponding to the first location at the time of loss of contact; The duration adjustment parameters are determined based on the weather information.
5. The method according to claim 1, characterized in that, The vehicle information also includes fuel level information. Determining the current predicted location of the missing vehicle based on the first location, each of the travel routes, the corresponding travel speed for each travel route, and the first interval between the current time and the time of loss of contact includes: Based on the first location and the fuel level information, the driving range of the vehicle is determined; Based on the first location, each of the travel routes, the travel speed corresponding to each of the travel routes, and the first interval between the current time and the time of loss of contact, the candidate predicted location corresponding to each of the travel routes is determined; Based on the candidate predicted locations corresponding to each of the travel routes and the drivable range, the current predicted location of the missing vehicle is determined, and the current predicted location of the missing vehicle is within the drivable range.
6. The method according to claim 1, characterized in that, The method further includes: Obtain vehicle out-of-connection records, which include multiple regions and the accident type corresponding to each region; Based on the current predicted location and the vehicle loss record, the predicted area where the missing vehicle is located and the accident type corresponding to the predicted area are determined; Determine the target rescue plan corresponding to the accident type in the predicted area, and execute the target rescue plan.
7. A vehicle position prediction device, characterized in that, The device, applied to a vehicle management server, includes: The vehicle information acquisition module is used to acquire vehicle information sent by the missing vehicle before it lost contact. The vehicle information includes the first location of the missing vehicle when it sent the vehicle information and the time of loss of contact. A destination acquisition module is used to acquire the destination of the missing vehicle. The route determination module is used to determine multiple travel routes based on the first location and the destination; The speed prediction module is used to predict the driving speed corresponding to each of the travel routes based on the route information of each travel route. A location prediction module is used to determine the current predicted location of the missing vehicle based on the first location, each of the travel routes, the travel speed corresponding to each of the travel routes, and the first interval between the current time and the time of loss of contact, including: Obtain the duration adjustment parameter, and determine the second interval duration based on the first interval duration and the duration adjustment parameter; the second interval duration is less than the first interval duration; the duration adjustment parameter is greater than 0 and less than 1; the duration adjustment parameter is determined based on one or more of the weather information, road condition information of the driving route, and itinerary arrangement information; The current predicted location of the missing vehicle is determined based on the first location, each of the travel routes, the travel speed corresponding to each of the travel routes, and the second interval duration.
8. A vehicle management server, characterized in that, The vehicle management server includes a processor and a memory, the memory being used to store a computer program; the processor is used to execute the computer program and, when executing the computer program, to implement the vehicle position prediction method as described in any one of claims 1-6.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the vehicle position prediction method as described in any one of claims 1-6.