Vehicle data prediction method and device, equipment and storage medium

Abstract

The invention relates to a vehicle data prediction method and device, equipment and a storage medium. The method comprises the following steps: in response to a data prediction request initiated by a target vehicle, determining a data query index according to data attributes of to-be-predicted data indicated by the data prediction request and road section position information of a road section where the target vehicle is located, querying from a corresponding relationship according to the data query index to obtain target driving data, according to the target driving data and the data prediction request, a data prediction result of the to-be-predicted data is determined, and the corresponding relation is constructed according to the road section position information of the different reference road sections and the historical driving data. By adopting the method, the accuracy of data prediction can be improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, device, and storage medium for predicting vehicle data. Background Technology

[0002] With the continuous development of the field of vehicle driving, in order to make it easier for drivers to understand the future changes of vehicle data (such as energy consumption, road slope and atmospheric pressure), vehicle data prediction methods have emerged. Generally, vehicle prediction data for future periods can be predicted based on historical vehicle data.

[0003] However, due to the large volume of historical vehicle data and the wide range of driving scenarios it covers, directly using historical vehicle data for data prediction using the above method may result in a mismatch between the historical vehicle data and the prediction scenario, thereby reducing the accuracy of the data prediction. Summary of the Invention

[0004] Therefore, it is necessary to provide a vehicle data prediction method, apparatus, device, and storage medium that can improve the accuracy of data prediction in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a vehicle data prediction method, including:

[0006] In response to a data prediction request initiated by the target vehicle, a data query index is determined based on the data attributes of the data to be predicted indicated in the data prediction request and the road segment location information of the target vehicle.

[0007] Based on the data query index, the target driving data is obtained by querying the corresponding relationship; the corresponding relationship is constructed based on the road segment location information and historical driving data of different reference road segments.

[0008] Based on the target driving data and the data prediction request, determine the data prediction result for the data to be predicted.

[0009] In one embodiment, a data query index is determined based on the data attributes of the data to be predicted indicated in the data prediction request, and the road segment location information of the target vehicle, including:

[0010] Based on the road segment location information of the target vehicle, determine the road segment identification information; based on the data attributes of the data to be predicted indicated by the data prediction request, determine the impact of the target vehicle's driving status on the prediction of the data to be predicted, and based on the impact, determine the auxiliary index; based on the road segment identification information and the auxiliary index, determine the data query index.

[0011] In one embodiment, determining the auxiliary index based on the impact includes:

[0012] When the vehicle's driving status affects the prediction of the data to be predicted, an auxiliary index is determined based on the vehicle attribute information of the target vehicle and the object information of the driving object; when the vehicle's driving status does not affect the prediction of the data to be predicted, an auxiliary index is determined based on the initial index.

[0013] In one embodiment, the method further includes:

[0014] Acquire historical driving data of the reference vehicle at different sampling times during its journey along the reference driving path; wherein the reference driving path contains at least two adjacent reference road segments; determine the reference driving data for each reference road segment based on the historical driving data at the sampling time corresponding to each reference road segment; construct a first correspondence between the road segment location information and the reference driving data of different reference road segments, and / or construct a second correspondence between the vehicle attribute information of the reference vehicle, the object information of the driving object of the reference vehicle, and the road segment location information and the reference driving data of different reference road segments.

[0015] In one embodiment, the reference driving data includes road segment attribute information; based on the historical driving data at the sampling time corresponding to each reference road segment, the reference driving data for each reference road segment is determined, including:

[0016] For each reference road segment, if the reference road segment is not the first reference road segment in the reference driving path, the historical driving data of the corresponding sampling time of the reference road segment is processed based on the time difference between the sampling time of the reference road segment and the sampling time of the previous reference road segment to obtain the road segment attribute information; if the reference road segment is the first reference road segment in the reference driving path, the road segment attribute information is determined based on the historical driving data of the first sampling time and the historical driving data of the last sampling time of the reference road segment.

[0017] In one embodiment, based on the time difference between the collection time corresponding to the reference road segment and the collection time corresponding to the previous reference road segment, the historical driving data of the sampling time corresponding to the reference road segment is processed to obtain the road segment attribute information of the reference road segment, including:

[0018] The time difference value is determined by comparing the first sampling time of the reference road segment with the last sampling time of the previous reference road segment. If the time difference value is greater than the time threshold, the road segment attribute information is determined by comparing the historical driving data of the last sampling time of the reference road segment with the historical driving data of the last sampling time of the previous reference road segment. If the time difference value is less than or equal to the time threshold, the road segment attribute information is determined by comparing the historical driving data of the first and last sampling times of the reference road segment.

[0019] In one embodiment, a first correspondence is constructed between the road segment location information and reference driving data for different reference road segments, and / or, vehicle attribute information of the reference vehicle, object information of the driving object of the reference vehicle, and a second correspondence is constructed between the road segment location information and reference driving data for different reference road segments, including:

[0020] For each reference road segment, the reference driving data of the reference road segment is verified based on the standard driving data corresponding to the reference driving data of the reference road segment. If the verification is successful, the reference road segment is used as the target road segment. A first correspondence relationship between the road segment location information and the reference driving data of different target road segments is constructed, and / or, a second correspondence relationship between the vehicle attribute information of the reference vehicle, the object information of the driving object of the reference vehicle, and the road segment location information and the reference driving data of different target road segments is constructed.

[0021] Secondly, this application also provides a vehicle data prediction device, comprising:

[0022] The index determination module is used to respond to the data prediction request initiated by the target vehicle and determine the data query index based on the data attributes of the data to be predicted indicated in the data prediction request and the road segment location information of the target vehicle.

[0023] The data acquisition module is used to query the corresponding relationship based on the data query index to obtain the target driving data; wherein, the corresponding relationship is constructed based on the road segment location information and historical driving data of different reference road segments;

[0024] The data prediction module is used to determine the data prediction result for the data to be predicted based on the target driving data and the data prediction request.

[0025] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0026] In response to a data prediction request initiated by the target vehicle, a data query index is determined based on the data attributes of the data to be predicted indicated in the data prediction request and the road segment location information of the target vehicle.

[0027] Based on the data query index, the target driving data is obtained by querying the corresponding relationship; the corresponding relationship is constructed based on the road segment location information and historical driving data of different reference road segments.

[0028] Based on the target driving data and the data prediction request, determine the data prediction result for the data to be predicted.

[0029] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0030] In response to a data prediction request initiated by the target vehicle, a data query index is determined based on the data attributes of the data to be predicted indicated in the data prediction request and the road segment location information of the target vehicle.

[0031] Based on the data query index, the target driving data is obtained by querying the corresponding relationship; the corresponding relationship is constructed based on the road segment location information and historical driving data of different reference road segments.

[0032] Based on the target driving data and the data prediction request, determine the data prediction result for the data to be predicted.

[0033] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0034] In response to a data prediction request initiated by the target vehicle, a data query index is determined based on the data attributes of the data to be predicted indicated in the data prediction request and the road segment location information of the target vehicle.

[0035] Based on the data query index, the target driving data is obtained by querying the corresponding relationship; the corresponding relationship is constructed based on the road segment location information and historical driving data of different reference road segments.

[0036] Based on the target driving data and the data prediction request, determine the data prediction result for the data to be predicted.

[0037] The aforementioned vehicle data prediction method, apparatus, equipment, and storage medium introduce a correspondence constructed based on road segment location information and historical driving data for different reference road segments. In response to a data prediction request initiated by a target vehicle, a data query index is determined based on the data attributes of the data to be predicted indicated in the data prediction request and the road segment location information of the target vehicle. The target driving data is then obtained by querying the correspondence according to the data query index. Subsequently, the data prediction result is determined based on the target driving data and the data prediction request. By combining the road segment location information and the data attributes of the data to be predicted to obtain the target driving data, the compatibility between the target driving data and the vehicle's location and the data to be predicted can be guaranteed, thus ensuring the reliability of subsequent data predictions and improving the accuracy of the data prediction results. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 This is a flowchart illustrating a vehicle data prediction method in one embodiment;

[0040] Figure 2 This is a schematic diagram illustrating the process of determining a data query index in one embodiment;

[0041] Figure 3 This is a flowchart illustrating the process of constructing the correspondence in one embodiment;

[0042] Figure 4 This is a flowchart illustrating the process of determining road segment attribute information in one embodiment;

[0043] Figure 5 A flowchart illustrating the process of constructing the correspondence in another embodiment;

[0044] Figure 6 This is a flowchart illustrating the vehicle data prediction method in another embodiment;

[0045] Figure 7 This is a structural block diagram of a vehicle data prediction device in one embodiment;

[0046] Figure 8 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0048] With the continuous development of the field of vehicle driving, in order to make it easier for drivers to understand the future changes of vehicle data (such as energy consumption, road slope and atmospheric pressure), vehicle data prediction methods have emerged. Generally, vehicle prediction data for future periods can be predicted based on historical vehicle data.

[0049] However, due to the large volume of historical vehicle data and the wide range of driving scenarios it covers, directly using historical vehicle data for data prediction using the above method may result in a mismatch between the historical vehicle data and the prediction scenario, thereby reducing the accuracy of the data prediction.

[0050] Based on this, in an exemplary embodiment, a vehicle data prediction method is provided. The method is illustrated using an application to a computer device as an example, where the computer device can be a server or a terminal with powerful computing capabilities, such as... Figure 1 As shown, the specific steps include:

[0051] S101, in response to the data prediction request initiated by the target vehicle, determines the data query index based on the data attributes of the data to be predicted indicated in the data prediction request and the road segment location information of the road segment where the target vehicle is located.

[0052] The target vehicle refers to an intelligent vehicle with data prediction needs. A data prediction request is a request to predict vehicle data for the target vehicle in the future. The data to be predicted is the vehicle data to be predicted, such as vehicle energy consumption, road gradient, and atmospheric pressure.

[0053] Data attributes, in essence, are the fundamental properties of data. They can be categorized into two types based on their impact on vehicle driving conditions: physical attributes and non-physical attributes. Physical attributes can include dimensions unaffected by vehicle driving conditions, such as atmospheric pressure, road slope, and temperature. Non-physical attributes, on the other hand, can include dimensions affected by vehicle driving conditions, such as vehicle energy consumption and vehicle speed.

[0054] A road segment refers to the individual road sections obtained after dividing a complete road based on predictive partitioning logic. Road segment location information refers to the location information of the vehicle within that road segment, which may include, but is not limited to, the latitude and longitude of the road segment. A data query index refers to the index fields used for data querying.

[0055] It's worth noting that a complete road can be divided into multiple adjacent segments based on preset road lengths and turning patterns. After segmenting, vehicle driving data within each segment can be stored as a unit. Correspondingly, during the data prediction phase, historical driving data of the vehicle's current road segment can be obtained for prediction, thus ensuring the matching of the acquired historical driving data with the vehicle's environment.

[0056] The driver inside the target vehicle can initiate a data prediction request through a display page associated with the in-vehicle terminal. For example, the driver can select the data to be predicted on the display page and click the "OK" button. At this point, the in-vehicle terminal can generate a data prediction request based on the data to be predicted.

[0057] In response to a data prediction request initiated by the target vehicle, the data identifier of the data to be predicted can be used to query the correspondence between the data identifiers and the attributes of each candidate data to obtain the data attributes of the data to be predicted.

[0058] The current location of the target vehicle can be determined based on the positioning device deployed inside the vehicle. Then, based on the current location, the road segment where the target vehicle is located can be determined. For example, when the target vehicle starts moving, the complete driving path can be divided into candidate road segments based on the standard road segment division record of the target vehicle's complete driving path. At this time, the candidate road segment containing the current vehicle location can be used as the road segment where the target vehicle is located at the current moment.

[0059] In one alternative implementation, after determining the data attributes of the data to be predicted and the road segment where the target vehicle is located, the data attributes and the road segment location information can be fused to obtain a data query index.

[0060] In another alternative implementation, the query information to be included in the data query index can be determined based on the data attributes of the data to be predicted; then, the query information to be included in the data query index and the road segment location information of the target vehicle are fused together to obtain the data query index.

[0061] S102, based on the data query index, query from the corresponding relationship to obtain the target driving data.

[0062] The correspondence is constructed based on the location information of different reference road segments and historical driving data. Furthermore, the correspondence can be a data pair consisting of a data query index and historical driving data. A reference road segment refers to any road segment a vehicle can travel on. Historical driving data refers to the driving data generated by different vehicles traveling on different road segments within a historical time period. Target driving data refers to the historical driving data that matches the data query index.

[0063] In one alternative implementation, a data query index can be used to query within the corresponding relationship, thereby retrieving the target driving data associated with the data query index. For example, a database of vehicle driving data can be constructed based on the corresponding relationship, and the data query index can be used to query within the database to obtain the target driving data.

[0064] S103, based on the target driving data and the data prediction request, determine the data prediction result for the data to be predicted.

[0065] The so-called data prediction result refers to the specific numerical value of the data to be predicted in the future period.

[0066] In one alternative implementation, the target driving data can be processed according to the data prediction requirements contained in the data prediction request to obtain the data prediction result for the data to be predicted. For example, the target driving data and the data prediction request can be input into a trained prediction model, which performs feature extraction processing on the target driving data and outputs the data prediction result based on the extracted data features and the data prediction request.

[0067] In another alternative implementation, when the data prediction request is to predict the vehicle driving data of the current road segment, the target driving data can be directly used as the data prediction result of the data to be predicted.

[0068] Once the data prediction results are determined, they can be displayed on the in-vehicle terminal's associated display page, prompting the driver to perform corresponding driving operations based on the data prediction results.

[0069] The aforementioned vehicle data prediction method introduces a correspondence constructed based on the location information of different reference road segments and historical driving data. In response to a data prediction request initiated by a target vehicle, a data query index is determined based on the data attributes of the data to be predicted indicated in the data prediction request and the location information of the road segment where the target vehicle is located. The target driving data is then obtained by querying the correspondence using this index. Finally, based on the target driving data and the data prediction request, the data prediction result for the data to be predicted is determined. By combining the location information of the road segment and the data attributes of the data to be predicted to obtain the target driving data, the method ensures the compatibility between the target driving data and the vehicle's location and the data to be predicted, thereby guaranteeing the reliability of subsequent data predictions and improving the accuracy of the prediction results.

[0070] Based on the above embodiments, this application provides an optional method for determining the data query index, such as... Figure 2 As shown, the specific steps include:

[0071] S201, determine the road segment signage information based on the road segment location information of the target vehicle.

[0072] The location information of a road segment may include, but is not limited to, the latitude and longitude of the starting point and the ending point of the road segment. Road segment identification information refers to the identification information used to distinguish each road segment.

[0073] In one optional implementation, the latitude and longitude of the starting point and the ending point of the road segment can be determined based on the road segment location information of the target vehicle. Then, road segment identification information is determined based on the latitude and longitude of the starting and ending points. It is worth noting that, to ensure the reliability of road segment identification, different road segments with completely identical starting and ending points will not be created during road segment division.

[0074] For example, an initial identifier field can be generated based on the latitude and longitude of the starting and ending points of the road segment, following the string rule [start latitude, start longitude, end latitude, end longitude]. Then, the initial identifier field can be encoded (e.g., UTF-8 encoding) to obtain a byte array, and a hash calculation can be performed on the byte array to obtain a 32-byte hash array. Finally, a numeric type (e.g., long type) return value can be read from the first 8 bytes of the hash array to obtain the road segment identifier information. Since the return value of the numeric type is within the range of 19 digits, the road segment identifier information can be 19 digits long. Furthermore, since latitude and longitude can have positive and negative values, the sign can be retained in the road segment identifier information.

[0075] Understandably, the reason why the initial identifier field obtained by concatenating latitude and longitude was not directly used as the road segment identifier information is because the initial identifier field is too long in bytes, and latitude and longitude information is sensitive geographical location information. If plaintext latitude and longitude are used to index road segments directly, it will cause information security problems. Therefore, by using the above road segment ID generation rules to desensitize the latitude and longitude information of road segments, user information security and privacy can be protected.

[0076] S202, based on the data attributes of the data to be predicted indicated by the data prediction request, determine the impact of the target vehicle's driving status on the prediction of the data to be predicted, and determine the auxiliary index based on the impact.

[0077] The vehicle driving status refers to the vehicle's driving status at the current moment, which may include, but is not limited to, the vehicle's driving status under different external environments and under different driving habits. The auxiliary index refers to auxiliary fields used for indexing, excluding road segment identification information.

[0078] In one optional embodiment, the data attributes of the data to be predicted indicated by the data prediction request can be analyzed to determine the impact of the target vehicle's driving state on the predicted data. For example, the impact of different vehicle driving states on vehicle data under each data attribute can be pre-analyzed based on historical driving experience. Then, an attribute correspondence between each data attribute and its impact can be constructed based on the analysis results. Correspondingly, the data attributes of the data to be predicted can be used as indexes to query the attribute correspondence, thereby obtaining the impact of the target vehicle's driving state on the predicted data.

[0079] After determining the impact, other vehicle information besides road segment identification information can be identified when generating the data query index. Then, the other vehicle information is processed to obtain the auxiliary index.

[0080] S203, based on road segment identification information and auxiliary indexes, determines the data query index.

[0081] In one optional embodiment, the road segment identification information can be standardized first. For example, the positive and negative identifiers in the road segment identification information can be processed. For instance, if the road segment identification information is positive, the positive identifier can be removed and a "1" can be added before it; if the road segment identification information is negative, the negative identifier can be removed and a "0" can be added before it. Then, the standardized road segment identification information and the auxiliary index are concatenated to obtain the data query index.

[0082] Alternatively, the standardized road segment identification information and auxiliary index can be mapped to the corresponding positions in the index template to obtain the data query index.

[0083] In this embodiment of the application, a data query index is generated by combining road segment identification information and an auxiliary index determined based on the impact of vehicle driving status on the data to be predicted, which can ensure the comprehensiveness and accuracy of the data query index.

[0084] Based on the above embodiments, this application provides an optional method for determining auxiliary indexes. Specifically, when the vehicle driving state affects the prediction of the data to be predicted, the auxiliary index is determined based on the vehicle attribute information of the target vehicle and the object information of the driving object; when the vehicle driving state does not affect the prediction of the data to be predicted, the auxiliary index is determined based on the initial index.

[0085] Among these, vehicle attribute information refers to the inherent attributes of a vehicle, which may include, but is not limited to, vehicle model information; object information refers to the driving habit information of the driving object, such as a user profile of the driving object; and the initial index refers to the unprocessed initial fields, which may also be empty fields.

[0086] In one alternative implementation, if it is determined that the influence is that the vehicle's driving status affects the prediction of the data to be predicted, the vehicle attribute information of the target vehicle can be obtained directly, and the object information of the driving object can be obtained through the information collection device deployed in the target vehicle.

[0087] Next, the vehicle attribute information and object information can be processed separately to obtain auxiliary indexes. For example, feature extraction can be performed on the vehicle attribute information and object information separately, and the resulting attribute features and object features can be used as auxiliary indexes. Furthermore, after determining the auxiliary indexes, road segment identification information can be concatenated with the auxiliary indexes to obtain a data query index.

[0088] It is worth noting that the target driving data obtained at this time can include historical driving data generated by other vehicles similar to the target vehicle, as well as historical driving data generated by other vehicles driven by objects with the same driving habits as the target vehicle's current driver.

[0089] Furthermore, to ensure the rationality of the target driving data, environmental information about the driving environment can be incorporated. That is, based on vehicle attribute information and object information, environmental information is combined to generate an auxiliary index.

[0090] In another alternative implementation, if the vehicle's driving status does not affect the prediction of the data to be predicted, it proves that only the road segment identification information affects the data query process. In this case, an auxiliary index can be determined directly based on the initial index. For example, an empty field can be used as an auxiliary index; that is, the data query index can be determined directly based on the road segment identification information.

[0091] In this embodiment of the application, by combining the vehicle attribute information of the target vehicle, the object information of the driving object, and the initial index, an auxiliary index is determined, which can ensure the adaptability between the auxiliary index and the prediction requirements, thereby ensuring the reliability of the data query index determination.

[0092] Based on the above embodiments, this application provides an optional method for constructing correspondences. For example... Figure 3 As shown, the specific steps include:

[0093] S301, acquire historical driving data of the reference vehicle at different sampling times during its journey on the reference driving path.

[0094] The "reference vehicle" refers to any intelligent vehicle with information collection capabilities. The "reference driving path" refers to any path that the vehicle can travel on, and further, the reference driving path includes at least two adjacent reference road segments. The "sampling time" refers to the moment when vehicle driving data is collected.

[0095] In one alternative implementation, the reference driving path can first be divided into adjacent reference road segments according to road segmentation logic. Then, historical driving data at different sampling times can be collected by information collection devices deployed in the reference vehicles as they travel on the reference driving path.

[0096] For example, vehicle energy consumption at different sampling times can be collected using devices such as a battery management system or fuel flow sensor deployed in a reference vehicle; vehicle speed at different sampling times can be collected using a vehicle speed sensor; atmospheric pressure at different sampling times can be collected using an atmospheric pressure sensor; and road gradient at different sampling times can be collected using a combination of a global satellite navigation system and an inertial measurement unit.

[0097] S302, based on the historical driving data of the sampling time corresponding to each reference road segment, determine the reference driving data for each reference road segment.

[0098] The so-called reference driving data refers to the historical driving data within the reference road segment.

[0099] In one alternative implementation, for each reference road segment, the travel time during which the reference vehicle traveled through the reference road segment can be determined; then, the historical travel data at each sampling time included in the travel time segment is used as the reference travel data for that reference road segment.

[0100] For example, while the reference vehicle is traveling along the reference route, the vehicle's driving data can be collected in real time and associated with and stored along with the road segment identification information of the reference road segment where the reference vehicle is located. After the journey is completed, the reference driving data for each reference road segment can be obtained.

[0101] It is worth noting that, to ensure the rationality of driving data segmentation, two optional methods for information storage are provided. One optional method is that when a set of points with consecutive and identical road segment identifiers encounters its first distinct road segment identifier, the historical driving data associated with the previous set of points with consecutive and identical road segment identifiers is used as the reference driving data for a reference road segment. For example, if the road segment identifiers continuously uploaded by the reference vehicle are AAAAABB, then the historical driving data associated with consecutive and identical AAAAA identifiers is the reference driving data for reference road segment A.

[0102] If a reference road segment cannot end because it is the last reference road segment in a reference driving route, or because the signal cannot be uploaded for an extended period due to network or other reasons. Therefore, another method is to consider a set of consecutive and identical road segment identifiers as a complete reference road segment if the reporting time of the last point in the set exceeds a time threshold (e.g., ten minutes) without any new point reports. In this case, the historical driving data associated with the point set is the reference driving data for the reference road segment. For example, if a reference vehicle continuously uploads road segment identifiers as "CCCCC", and no signal is reported after ten minutes following the fifth "C", then the five consecutive identical "C" road segment identifiers represent all points with the road segment identifier "C". The historical driving data associated with "CCCCC" can be considered the reference driving data for reference road segment C.

[0103] S303, construct a first correspondence between the road segment location information and reference driving data of different reference road segments, and / or, construct the vehicle attribute information of the reference vehicle, the object information of the driving object of the reference vehicle, and a second correspondence between the road segment location information and reference driving data of different reference road segments.

[0104] The so-called first correspondence is the data correspondence constructed when vehicle driving data is not affected by vehicle driving status. Furthermore, the first correspondence is constructed based on the road segment location information and reference driving data.

[0105] In one optional implementation, when the various types of vehicle driving data in the reference driving data are not affected by the vehicle driving status, for each reference road segment, a data query index for the reference road segment can be determined based on the road segment location information; then, a first correspondence between the data query index and the reference driving data within the reference road segment is constructed.

[0106] The so-called second correspondence is the data correspondence constructed when vehicle driving data is affected by vehicle driving status. Furthermore, the second correspondence is constructed based on the vehicle attribute information of the reference vehicle, the object information of the reference vehicle's driving object, the road segment location information of the reference road segment, and the reference driving data.

[0107] In another optional implementation, when all types of vehicle driving data in the reference driving data are affected by the vehicle driving status, for each reference road segment, a data query index can be constructed based on the vehicle attribute information, object information, and road segment location information of the reference vehicle; then, a second correspondence between the data query index and the reference driving data within that reference road segment can be constructed.

[0108] In another optional implementation, when the reference driving data includes both driving data affected by the vehicle's driving state and driving data unaffected by the vehicle's driving state, the above-mentioned correspondence construction method can be used to simultaneously construct a first correspondence between the road segment location information of different reference road segments and the reference driving data, and construct a second correspondence between the vehicle attribute information of the reference vehicle, the object information of the driving object of the reference vehicle, and the road segment location information of different reference road segments and the reference driving data.

[0109] It is understandable that the correspondence when querying data in response to a data prediction request initiated by a target vehicle includes a first correspondence and / or a second correspondence. Therefore, when the data to be predicted is not affected by the vehicle's driving status, a data query can be performed in the first correspondence based solely on the data query index determined by the road segment location information; or, when the data to be predicted is affected by the vehicle's driving status, a data query can be performed in the second correspondence based on the data query index determined by the vehicle attribute information, object information, and road segment location information; or, when the data to be predicted contains both data types unaffected by the vehicle's driving status and data types affected by the vehicle's driving status, a query can be performed simultaneously in both the first and second correspondences.

[0110] In this embodiment of the application, by constructing a correspondence between two different situations, the reliability of historical driving data processing can be guaranteed, thereby ensuring the accuracy of subsequent target driving data acquisition.

[0111] Understandably, in practical applications, since road segments are spliced ​​together, when determining the road segment attribute information of a reference road segment, if only the driving data in a single road segment is considered, the difference between the vehicle driving data of two adjacent points in adjacent road segments may be missed (e.g., the difference between the vehicle driving data of the last point in the previous road segment and the vehicle driving data of the first point in the current road segment).

[0112] Based on this, and building upon the above embodiments, this application provides an optional method for determining reference driving data. Specifically, for each reference road segment, if the reference road segment is not the first reference road segment in the reference driving path, the historical driving data of the sampling time corresponding to the reference road segment is processed based on the time difference between the sampling time corresponding to the reference road segment and the sampling time corresponding to the previous reference road segment to obtain the road segment attribute information; if the reference road segment is the first reference road segment in the reference driving path, the road segment attribute information is determined based on the historical driving data of the first sampling time and the historical driving data of the last sampling time corresponding to the reference road segment.

[0113] The time difference value refers to the difference between the collection times. The reference driving data includes road segment attribute information. Road segment attribute information refers to relevant information that characterizes the changing attributes of vehicles traveling within a road segment. The first collection time is the first sampling time among all sampling times corresponding to the reference road segment, and the last collection time is the last sampling time among all sampling times corresponding to the reference road segment.

[0114] In one optional implementation, for each reference road segment, if the reference road segment is not the first reference road segment in the reference driving path, the time difference value between the collection time corresponding to the reference road segment and the collection time corresponding to the previous reference road segment can be calculated. Then, based on the magnitude of the time difference value, the historical driving data corresponding to the sampling time of the reference road segment is processed to obtain the road segment attribute information of the reference road segment.

[0115] For example, when the time difference is small, the road segment attribute information of the reference road segment can be determined solely based on the historical driving data at the corresponding sampling time. When the time difference is large, it is necessary to combine the historical driving data at the corresponding sampling time of the previous reference road segment to determine the road segment attribute information.

[0116] In another alternative implementation, for each reference road segment, if the reference road segment is the first reference road segment in the reference driving path, the road segment attribute information of the reference road segment can be determined based on the data difference between the historical driving data at the first collection time and the historical driving data at the last collection time in the sampling time corresponding to the reference road segment.

[0117] For example, for each data dimension, the difference between the historical driving data of that data dimension at the last collection time and the historical driving data of that data dimension at the first collection time can be used as the road segment attribute information of the reference road segment in the data dimension.

[0118] For example, the energy consumption difference between the relative energy consumption at the end of the data collection period and the relative energy consumption at the first data collection period in reference road segment D can be used as the energy consumption attribute data of reference road segment D. In reference road segment D, the height difference between the relative height at the end of the data collection period and the relative height at the first data collection period can be calculated first, followed by the mileage difference between the relative mileage at the end of the data collection period and the relative mileage at the first data collection period. The ratio of the height difference to the mileage difference can then be used as the slope attribute data of reference road segment D.

[0119] For example, for each data dimension, the average of the historical driving data of that data dimension at the last collection time and the historical driving data of that data dimension at the first collection time can be used as the road segment attribute information of the reference road segment in the data dimension.

[0120] For example, the average speed between the vehicle speed at the last collection time and the vehicle speed at the first collection time in reference road segment D can be used as the speed attribute data of reference road segment D.

[0121] In this embodiment of the application, by selecting different methods to determine the road segment attribute information based on the location of the reference road segment, the rationality of the determination of the reference driving data can be guaranteed.

[0122] Based on the above embodiments, this application provides an optional method for determining road segment attribute information, such as... Figure 4 As shown, it specifically includes the following:

[0123] S401. Determine the time difference value based on the first sampling time in the sampling time corresponding to the reference road segment and the last sampling time in the sampling time corresponding to the previous reference road segment.

[0124] The so-called previous reference road segment is the previous reference road segment adjacent to the reference time in the direction of vehicle driving.

[0125] In one optional implementation, the difference between the first sampling time of the reference road segment and the last sampling time of the previous reference road segment can be used as the time difference value. Alternatively, after determining the difference between the first sampling time of the reference road segment and the last sampling time of the previous reference road segment, a preset time adjustment coefficient can be used to process the difference to obtain the time difference value.

[0126] S402, determine whether the time difference value is greater than the time threshold. If yes, execute S403; otherwise, execute S404.

[0127] The time threshold is used to measure the magnitude of the time difference. It can be determined based on the historical experience of those skilled in the art or on a large amount of time data. This application does not impose any restrictions on this. For example, the time threshold can be 2 seconds.

[0128] In one alternative implementation, the time difference value can be compared with a time threshold. If the time difference value is greater than the time threshold, step S403 is executed; if the time difference value is less than or equal to the time threshold, step S404 is executed.

[0129] S403. Based on the historical driving data of the last collection time in the sampling time corresponding to the reference road segment and the historical driving data of the last collection time in the sampling time corresponding to the previous reference road segment, determine the road segment attribute information of the reference road segment.

[0130] In one alternative implementation, when the time difference value is greater than a time threshold, it indicates that the missed historical driving data from the last collection time of the previous reference road segment will affect the road segment attribute information of the reference road segment. Therefore, it is necessary to determine the road segment attribute information of the reference road segment based on the historical driving data from the last collection time of the corresponding reference road segment and the historical driving data from the last collection time of the corresponding previous reference road segment.

[0131] For example, for each data dimension, the difference between the historical driving data of that data dimension at the last collection time in the reference road segment and the historical driving data of that data dimension at the last collection time in the previous reference road segment can be used as the road segment attribute information of the reference road segment in the data dimension.

[0132] S404. Based on the historical driving data of the first and last sampling times of the reference road segment, determine the road segment attribute information.

[0133] In one alternative implementation, when the time difference value is greater than a time threshold, it proves that the historical driving data from the last collection time in the previous reference road segment, which was missed, will not affect the road segment attribute information of the reference road segment. Therefore, the road segment attribute information of the reference road segment can be determined directly based on the data difference between the historical driving data from the first collection time and the historical driving data from the last collection time in the sampling time corresponding to the reference road segment.

[0134] In this embodiment of the application, by combining the magnitude of the time difference value, the road segment attribute information of the reference road segment is determined, which can ensure the rationality of the determination of the road segment attribute information.

[0135] To ensure the validity of historical driving data in the correspondence, based on the above embodiments, this application provides an optional method for constructing the correspondence, such as... Figure 5 As shown, it specifically includes the following:

[0136] S501: For each reference road segment, the reference driving data of the reference road segment is verified based on the standard driving data corresponding to the reference driving data of the reference road segment, and if the verification is successful, the reference road segment is used as the target road segment.

[0137] The so-called standard driving data refers to the range of driving data when the vehicle is in standard driving conditions. The so-called target road segment refers to the road segment that has been verified and passed by the reference driving data.

[0138] For each reference road segment, the reference driving data can be validated for reasonableness based on the corresponding standard driving data. Once the reasonableness validation of the reference road segment is passed, it can be used as the target road segment.

[0139] For example, the data attribute information of each data dimension in the reference road segment can be compared with the standard attribute range of the corresponding data dimension. When the data attribute information of each data dimension is within the standard attribute range, the reference road segment is taken as the target road segment.

[0140] For example, regarding vehicle speed, when the vehicle speed on the reference road section is between 0 km / h and 200 km / h, the reasonableness check of the vehicle speed is passed. Here, 0 km / h-200 km / h is the reasonable driving speed range determined by those skilled in the art.

[0141] Regarding the actual road segment length, it can be verified by comparing the actual length of the reference road segment with the standard planned length. For example, if the difference between the actual road segment length and the standard planned length is less than a difference threshold, the reasonableness verification of the actual road segment length is considered passed. The difference threshold is determined based on the average vehicle speed within the reference road segment and the standard planned length. For example, the difference threshold = average vehicle speed * 3 + standard planned length / 30. Parameters 3 and 30 are optimal calculation parameters determined by those skilled in the art.

[0142] Regarding the slope, the rationality verification of the road slope is passed when the road slope of the reference section is between [-30°, 30°]. Among them, [-30°, 30°] is the reasonable slope range determined by those skilled in the art.

[0143] Regarding vehicle energy consumption, if the actual length of the reference road segment is less than or equal to 100 meters, then check whether the energy consumption of the reference road segment is less than or equal to 0.15 kWh; if the actual length of the reference road segment is greater than 100 meters, then check whether the energy consumption per unit kilometer of the reference road segment is less than 1.5 kWh.

[0144] S502, construct a first correspondence between the road segment location information and reference driving data for different target road segments, and / or, construct the vehicle attribute information of the reference vehicle, the object information of the driving object of the reference vehicle, and a second correspondence between the road segment location information and reference driving data for different target road segments.

[0145] After identifying the target road segment, the above steps can be followed. Under the condition that the various types of vehicle driving data in the reference driving data are not affected by the vehicle driving status, for each target road segment, the data query index of the target road segment can be determined based on the road segment location information. Then, the first correspondence between the data query index and the reference driving data within the target road segment is constructed.

[0146] Given that all types of vehicle driving data in the reference driving data are affected by vehicle driving status, for each target road segment, a data query index can be constructed based on the vehicle attribute information, object information, and road segment location information of the reference vehicle; then, a second correspondence can be constructed between the data query index and the reference driving data within the target road segment.

[0147] When the reference driving data includes both driving data affected by the vehicle's driving status and driving data unaffected by the vehicle's driving status, the above-mentioned correspondence construction method can be used as a reference to construct a first correspondence between the road segment location information of different target road segments and the reference driving data, and to construct a second correspondence between the vehicle attribute information of the reference vehicle, the object information of the driving object of the reference vehicle, and the road segment location information of different target road segments and the reference driving data.

[0148] In this embodiment of the application, by verifying the rationality of the data in the reference road segment, the corresponding relationship that can be constructed is more reasonable, thereby ensuring the accuracy of the subsequent data prediction results.

[0149] Furthermore, based on the above embodiments, this application provides a presentation format for the correspondence. Specifically, the first correspondence can be presented in the form of Table 1 below, where Table 1 is a single-dimensional data storage table. Single-dimensional data indicates that the data query index only contains the dimension of road segment location information.

[0150] Table 1 Single-Dimensional Data Storage Table

[0151]

[0152] It is worth noting that, when constructing the correspondence, to avoid artificially creating data hotspots, the road segment ID (i.e., data identification information) can first be hashed (e.g., using Message-Digest Algorithm 5 (MD5)) when generating the data query index. Then, the first four characters of the hash result are used as the starting field of the index and concatenated with the standardized data identification information to obtain the data query index for the target road segment.

[0153] Furthermore, driving data such as road segment mileage, road segment elevation level, road segment slope, road segment atmospheric pressure, and road segment temperature, which are not affected by the vehicle's driving status, can be filled into the data storage table to obtain the first correspondence under the target road segment.

[0154] The second correspondence can be presented in the form of Tables 2 and 3 below, where Table 2 is the multi-dimensional data storage table 1; and Table 3 is the multi-dimensional data storage table 2. Multi-dimensional data indicates that the data query index contains multiple data dimensions.

[0155] Table 2 Multi-dimensional data storage Table 1

[0156]

[0157] Table 3 Multi-dimensional data storage Table 2

[0158]

[0159] It is worth noting that the data query index in Table 2 is constructed based on actual object information and actual vehicle attribute information; while the data query index in Table 3 is constructed based on the object type of the actual object information and the attribute type of the actual vehicle attribute information. Furthermore, weather data affecting vehicle operation, such as temperature and humidity, can be appended to the index to achieve fast and accurate data retrieval.

[0160] Furthermore, driving data such as road segment energy consumption, road segment single-dimensional tonnage energy consumption, and road segment speed, which are affected by vehicle driving conditions, can be populated into the data storage table from the reference driving data to obtain the second correspondence under the target road segment. The vehicle driving data in the column combinations in Tables 2 and 3 are consistent.

[0161] It is worth noting that the reason for constructing two second correspondences that differ only in the data query index is that, when performing subsequent data queries, if the actual vehicle attribute information and actual object information associated with the data prediction request cannot be found, the attribute type and object type can be further queried, thereby ensuring the reliability of data acquisition.

[0162] To ensure data richness, each target road segment's mapping relationship can be associated with multiple sets of data, each set representing driving data for that target road segment along different travel routes. For example, a data version number of 10 indicates that the mapping relationship contains 10 driving data entries. Since the number of driving data entries is constant, when the number of data entries for a target road segment exceeds a certain threshold, it is necessary to perform a deletion and insertion process on each driving data entry; that is, delete driving data entries acquired more recently and retain those acquired earlier. Furthermore, since the same mapping relationship contains multiple driving data entries, in actual processing, the average value of all data entries can be used as the target driving data.

[0163] Furthermore, by adopting the above data storage structure, if we want to expand the data types on any road segment in the future, we can directly expand the group horizontally without affecting the storage of old data, thereby realizing the dynamic expansion of data storage.

[0164] Based on the above embodiments, to ensure efficient data acquisition, a one-dimensional historical database storing the first correspondence can be constructed, as well as a multi-dimensional historical database storing the second correspondence. Furthermore, a corresponding one-dimensional historical data cache can be configured for the one-dimensional historical database, and a corresponding multi-dimensional historical data cache can be configured for the multi-dimensional historical database.

[0165] When performing data queries, you can first determine whether to query a single-dimensional or multi-dimensional historical database based on the data attributes of the data to be predicted. After locating the database to be queried, you can first query the target driving data in the corresponding cache of the database; if it is not found, then query the corresponding database. The corresponding relationships in the cache can be updated in real time based on data popularity.

[0166] In addition, it is necessary to regularly clear the data in the cache (for example, if the expiration time is one week, regularly clear the data stored in the cache one week ago).

[0167] Figure 6 This is a flowchart illustrating a vehicle data prediction method in another embodiment. Based on the above embodiments, this embodiment provides an optional example of a vehicle data prediction method. (Combined with...) Figure 6 The specific implementation process is as follows:

[0168] S601, acquire historical driving data of the reference vehicle at different sampling times during its journey on the reference driving path.

[0169] The reference driving route includes at least two adjacent reference road segments.

[0170] S602, based on the historical driving data of the sampling time corresponding to each reference road segment, determine the reference driving data for each reference road segment.

[0171] Optionally, for each reference road segment, if the reference road segment is not the first reference road segment in the reference driving path, the time difference value is determined based on the first collection time in the sampling time corresponding to the reference road segment and the last collection time in the sampling time corresponding to the previous reference road segment; if the time difference value is greater than the time threshold, the road segment attribute information of the reference road segment is determined based on the historical driving data of the last collection time in the sampling time corresponding to the reference road segment and the historical driving data of the last collection time in the sampling time corresponding to the previous reference road segment; if the time difference value is less than or equal to the time threshold, the road segment attribute information of the reference road segment is determined based on the historical driving data of the first collection time and the historical driving data of the last collection time in the sampling time corresponding to the reference road segment.

[0172] When the reference road segment is the first reference road segment in the reference driving route, the road segment attribute information of the reference road segment is determined based on the historical driving data of the first and last sampling times in the sampling time corresponding to the reference road segment.

[0173] S603: For each reference road segment, the reference driving data of the reference road segment is verified based on the standard driving data corresponding to the reference driving data of the reference road segment, and if the verification is successful, the reference road segment is used as the target road segment.

[0174] S604, construct a first correspondence between the road segment location information and reference driving data for different target road segments, and / or, construct the vehicle attribute information of the reference vehicle, the object information of the driving object of the reference vehicle, and a second correspondence between the road segment location information and reference driving data for different target road segments.

[0175] S605, in response to a data prediction request initiated by the target vehicle, determines the road segment identification information based on the road segment location information of the target vehicle.

[0176] S606, based on the data attributes of the data to be predicted indicated by the data prediction request, determine the impact of the target vehicle's driving status on the prediction of the data to be predicted, and determine the auxiliary index based on the impact.

[0177] Optionally, if the vehicle's driving status affects the prediction of the data to be predicted, an auxiliary index is determined based on the vehicle attribute information of the target vehicle and the object information of the driving object; if the vehicle's driving status does not affect the prediction of the data to be predicted, an auxiliary index is determined based on the initial index.

[0178] S607: Based on the road segment identification information and auxiliary index, determine the data query index, and based on the data query index, query from the first correspondence and / or the second correspondence to obtain the target driving data.

[0179] S608 determines the data prediction result for the data to be predicted based on the target driving data and the data prediction request.

[0180] The specific processes of S601-S608 described above can be found in the description of the above method embodiments. Their implementation principles and technical effects are similar, and will not be repeated here.

[0181] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0182] Based on the same inventive concept, this application also provides a vehicle data prediction device for implementing the vehicle data prediction method described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more vehicle data prediction device embodiments provided below can be found in the limitations of the vehicle data prediction method described above, and will not be repeated here.

[0183] In one exemplary embodiment, such as Figure 7 As shown, a vehicle data prediction device 1 is provided, comprising: an index determination module 10, a data acquisition module 20, and a data prediction module 30, wherein:

[0184] The index determination module 10 is used to respond to a data prediction request initiated by the target vehicle and determine the data query index based on the data attributes of the data to be predicted indicated by the data prediction request and the road segment location information of the road segment where the target vehicle is located.

[0185] The data acquisition module 20 is used to query the corresponding relationship based on the data query index to obtain the target driving data; wherein, the corresponding relationship is constructed based on the road segment location information and historical driving data of different reference road segments;

[0186] The data prediction module 30 is used to determine the data prediction result of the data to be predicted based on the target driving data and the data prediction request.

[0187] In one exemplary embodiment, the index determination module 10 is specifically used for:

[0188] Based on the road segment location information of the target vehicle, determine the road segment identification information; based on the data attributes of the data to be predicted indicated by the data prediction request, determine the impact of the target vehicle's driving status on the prediction of the data to be predicted, and based on the impact, determine the auxiliary index; based on the road segment identification information and the auxiliary index, determine the data query index.

[0189] In one exemplary embodiment, the index determination module 10 is further configured to:

[0190] When the vehicle's driving status affects the prediction of the data to be predicted, an auxiliary index is determined based on the vehicle attribute information of the target vehicle and the object information of the driving object; when the vehicle's driving status does not affect the prediction of the data to be predicted, an auxiliary index is determined based on the initial index.

[0191] In an exemplary embodiment, the vehicle data prediction device 1 further includes a construction module, wherein the construction module is specifically used for:

[0192] Acquire historical driving data of the reference vehicle at different sampling times during its journey along the reference driving path; wherein the reference driving path contains at least two adjacent reference road segments; determine the reference driving data for each reference road segment based on the historical driving data at the sampling time corresponding to each reference road segment; construct a first correspondence between the road segment location information and the reference driving data of different reference road segments, and / or construct a second correspondence between the vehicle attribute information of the reference vehicle, the object information of the driving object of the reference vehicle, and the road segment location information and the reference driving data of different reference road segments.

[0193] In one exemplary embodiment, the building module is further configured to:

[0194] For each reference road segment, if the reference road segment is not the first reference road segment in the reference driving path, the historical driving data of the corresponding sampling time of the reference road segment is processed based on the time difference between the sampling time of the reference road segment and the sampling time of the previous reference road segment to obtain the road segment attribute information; if the reference road segment is the first reference road segment in the reference driving path, the road segment attribute information is determined based on the historical driving data of the first sampling time and the historical driving data of the last sampling time of the reference road segment.

[0195] In one exemplary embodiment, the building module is further configured to:

[0196] The time difference value is determined by comparing the first sampling time of the reference road segment with the last sampling time of the previous reference road segment. If the time difference value is greater than the time threshold, the road segment attribute information is determined by comparing the historical driving data of the last sampling time of the reference road segment with the historical driving data of the last sampling time of the previous reference road segment. If the time difference value is less than or equal to the time threshold, the road segment attribute information is determined by comparing the historical driving data of the first and last sampling times of the reference road segment.

[0197] In one exemplary embodiment, the building module is further configured to:

[0198] For each reference road segment, the reference driving data of the reference road segment is verified based on the standard driving data corresponding to the reference driving data of the reference road segment. If the verification is successful, the reference road segment is used as the target road segment. A first correspondence relationship between the road segment location information and the reference driving data of different target road segments is constructed, and / or, a second correspondence relationship between the vehicle attribute information of the reference vehicle, the object information of the driving object of the reference vehicle, and the road segment location information and the reference driving data of different target road segments is constructed.

[0199] Each module in the aforementioned vehicle data prediction device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0200] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 8As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a vehicle data prediction method. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0201] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0202] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0203] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0204] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0205] It should be noted that the data involved in this application (including but not limited to vehicle driving data) is all data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0206] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0207] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0208] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A vehicle data prediction method, characterized in that, The method includes: In response to a data prediction request initiated by a target vehicle, a data query index is determined based on the data attributes of the data to be predicted indicated in the data prediction request and the road segment location information of the road segment where the target vehicle is located. Based on the data query index, the target driving data is obtained by querying the corresponding relationship; wherein, the corresponding relationship is constructed based on the road segment location information and historical driving data of different reference road segments; Based on the target driving data and the data prediction request, determine the data prediction result for the data to be predicted.

2. The method according to claim 1, characterized in that, The step of determining the data query index based on the data attributes of the data to be predicted indicated by the data prediction request and the road segment location information of the target vehicle includes: Based on the road segment location information of the target vehicle, determine the road segment identification information; Based on the data attributes of the data to be predicted indicated by the data prediction request, determine the impact of the vehicle driving status of the target vehicle on the prediction of the data to be predicted, and determine the auxiliary index based on the impact. The data query index is determined based on the road segment identification information and the auxiliary index.

3. The method according to claim 2, characterized in that, The determination of the auxiliary index based on the aforementioned impact includes: In the case where the influence situation is that the vehicle's driving state affects the prediction of the data to be predicted, an auxiliary index is determined based on the vehicle attribute information of the target vehicle and the object information of the driving object. If the vehicle's driving state does not affect the prediction of the data to be predicted, an auxiliary index is determined based on the initial index.

4. The method according to any one of claims 1-3, characterized in that, The method further includes: Acquire historical driving data of the reference vehicle at different sampling times during its journey along the reference driving path; wherein the reference driving path contains at least two adjacent reference road segments; Based on the historical driving data at the sampling time corresponding to each reference road segment, the reference driving data for each reference road segment is determined. Construct a first correspondence between the location information of different reference road segments and the reference driving data, and / or construct the vehicle attribute information of the reference vehicle, the object information of the driving object of the reference vehicle, and a second correspondence between the location information of different reference road segments and the reference driving data.

5. The method according to claim 4, characterized in that, The reference driving data includes road segment attribute information; The step of determining the reference driving data for each reference road segment based on the historical driving data at the sampling time corresponding to each reference road segment includes: For each reference road segment, if the reference road segment is not the first reference road segment in the reference driving path, the historical driving data of the sampling time corresponding to the reference road segment is processed according to the time difference value between the sampling time corresponding to the reference road segment and the sampling time corresponding to the previous reference road segment to obtain the road segment attribute information of the reference road segment. When the reference road segment is the first reference road segment in the reference driving path, the road segment attribute information of the reference road segment is determined based on the historical driving data of the first collection time and the historical driving data of the last collection time in the sampling time corresponding to the reference road segment.

6. The method according to claim 5, characterized in that, The step involves processing the historical driving data corresponding to the sampling time of the reference road segment based on the time difference between the sampling time corresponding to the reference road segment and the sampling time corresponding to the previous reference road segment, to obtain the road segment attribute information of the reference road segment, including: The time difference value is determined based on the first sampling time in the sampling time corresponding to the reference road segment and the last sampling time in the sampling time corresponding to the previous reference road segment; If the time difference value is greater than the time threshold, the road segment attribute information of the reference road segment is determined based on the historical driving data of the last collection time in the sampling time corresponding to the reference road segment and the historical driving data of the last collection time in the sampling time corresponding to the previous reference road segment. If the time difference value is less than or equal to the time threshold, the road segment attribute information of the reference road segment is determined based on the historical driving data of the first and last sampling times in the sampling time corresponding to the reference road segment.

7. The method according to claim 4, characterized in that, The construction of a first correspondence between the road segment location information and reference driving data for different reference road segments, and / or the construction of the vehicle attribute information of the reference vehicle, the object information of the driving object of the reference vehicle, and a second correspondence between the road segment location information and reference driving data for different reference road segments, includes: For each reference road segment, the reference driving data of the reference road segment is verified based on the standard driving data corresponding to the reference driving data of the reference road segment, and if the verification passes, the reference road segment is taken as the target road segment. Construct a first correspondence between the location information of different target road segments and the reference driving data, and / or construct the vehicle attribute information of the reference vehicle, the object information of the driving object of the reference vehicle, and a second correspondence between the location information of different target road segments and the reference driving data.

8. A vehicle data prediction device, characterized in that, The device includes: The index determination module is used to respond to a data prediction request initiated by a target vehicle and determine a data query index based on the data attributes of the data to be predicted indicated by the data prediction request and the road segment location information of the road segment where the target vehicle is located. The data acquisition module is used to query the corresponding relationship based on the data query index to obtain the target driving data; wherein the corresponding relationship is constructed based on the road segment location information and historical driving data of different reference road segments; The data prediction module is used to determine the data prediction result for the data to be predicted based on the target driving data and the data prediction request.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images