Vehicle positioning data processing method, electronic device and storage medium

Abstract

The present disclosure relates to a vehicle positioning data processing method, electronic device and storage medium, the method comprising: pre-processing target positioning data to obtain positioning data to be classified; inputting the positioning data to be classified into a trained first classification model to obtain a first reference label of the positioning data to be classified; inputting the positioning data to be classified into a trained second classification model to obtain a second reference label of the positioning data to be classified; the first classification model and the second classification model are different models; determining a storage strategy for the target positioning data according to the first reference label and the second reference label, and storing and processing the target positioning data according to the storage strategy. The purpose of screening positioning data is achieved, thereby reducing storage pressure.

Description

Technical Field

[0001] The present disclosure relates to the field of autonomous driving technology, and in particular to a vehicle positioning data processing method, electronic device, and storage medium. Background Art

[0002] In recent years, with the rapid development of driverless technology, driverless vehicles have been widely used in various scenarios. Positioning data is crucial to the driving quality of driverless vehicles. Through in-depth analysis of the positioning data generated during the driving process of the vehicle, various problems of the vehicle can be discovered and diagnosed in a timely manner.

[0003] Autonomous vehicles will continuously generate a large amount of positioning data during continuous driving, which poses unprecedented challenges to data processing and storage. These positioning data are crucial for vehicle performance analysis and fault diagnosis.

[0004] However, due to the huge amount of data, how to effectively classify and store massive positioning data, focus on and store valuable data, and reduce the pressure on the database has become an urgent problem to be solved. Summary of the invention

[0005] In order to solve the above technical problems or at least partially solve the above technical problems, the embodiments of the present disclosure provide a vehicle positioning data processing method, an electronic device and a storage medium, which achieve the purpose of screening a large amount of positioning data, thereby reducing storage pressure.

[0006] In a first aspect, an embodiment of the present disclosure provides a vehicle positioning data processing method, the method comprising:

[0007] Preprocess the target positioning data to obtain positioning data to be classified;

[0008] Inputting the positioning data to be classified into a trained first classification model to obtain a first reference label of the positioning data to be classified;

[0009] Inputting the positioning data to be classified into a trained second classification model to obtain a second reference label of the positioning data to be classified; the first classification model and the second classification model are different models;

[0010] Determining a storage strategy for the target positioning data according to the first reference tag and the second reference tag;

[0011] The target positioning data is stored and processed according to the storage strategy.

[0012] Further, the determining a storage strategy for the target positioning data according to the first reference tag and the second reference tag includes:

[0013] In response to determining, according to the first reference tag and the second reference tag, that the importance of the target positioning data does not meet a first set requirement, determining that the storage strategy is to delete the target positioning data;

[0014] In response to determining, according to the first reference tag and the second reference tag, that the importance of the target positioning data reaches a first set requirement, determining the storage strategy to store the target positioning data.

[0015] Further, the determining a storage strategy for the target positioning data according to the first reference tag and the second reference tag includes:

[0016] In response to determining that the importance of the target positioning data meets a first set requirement according to the first reference label and the second reference label, inputting the positioning data to be classified into a trained third classification model to obtain a third reference label of the positioning data to be classified, wherein the third classification model is different from the first classification model and different from the second classification model;

[0017] A storage strategy for the target positioning data is determined according to the third reference tag and the second reference tag.

[0018] Further, the determining a storage strategy for the target positioning data according to the third reference tag and the second reference tag includes:

[0019] In response to determining, according to the third reference tag and the second reference tag, that the importance of the target positioning data does not meet a second set requirement, determining that the storage strategy is to compress and store the target positioning data;

[0020] In response to determining, according to the third reference tag and the second reference tag, that the importance of the target positioning data reaches a second set requirement, determining the storage strategy to perform extended storage on the target positioning data.

[0021] Furthermore, it also includes:

[0022] Obtain historical positioning data reported by vehicles;

[0023] In response to the existence of an access record for the historical positioning data, setting a first tag for the historical positioning data;

[0024] In response to the historical positioning data having no access record, setting a second tag for the historical positioning data;

[0025] The untrained first classification model is trained by using a first training data set to obtain the trained first classification model, wherein the first training data set includes historical positioning data set with the first label and historical positioning data set with the second label.

[0026] Furthermore, it also includes:

[0027] Dividing the plurality of historical positioning data with the first tag and the reference positioning data group into two categories by using a clustering algorithm;

[0028] Setting a third label for the historical positioning data in the first category, and setting a fourth label for the historical positioning data in the second category;

[0029] The untrained second classification model is trained by using a second training data set to obtain the trained second classification model, wherein the second training data set includes historical positioning data set with the third label, historical positioning data set with the fourth label, and historical positioning data set with the second label.

[0030] Furthermore, the plurality of historical positioning data set with the first tag and the reference positioning data group are divided into two categories by a clustering algorithm, including:

[0031] Performing a first clustering on the plurality of historical positioning data provided with the first tag by a clustering algorithm to obtain a first clustering cluster and a second clustering cluster;

[0032] Determine a first number of positioning data in the first cluster that is identical to that in the reference positioning data set, and determine a second number of positioning data in the second cluster that is identical to that in the reference positioning data set;

[0033] determining the larger of the first amount and the second amount as a target amount;

[0034] Determine the clusters corresponding to the target number as target clusters, wherein the clusters corresponding to the first number are the first clusters, and the clusters corresponding to the second number are the second clusters; determine the centers of the positioning data in the target clusters that are the same as those in the reference positioning data group as the cluster centers of the first category, and determine the center of another cluster except the target cluster as the cluster center of the second category;

[0035] According to the cluster center of the first category and the cluster center of the second category, the plurality of historical positioning data provided with the first tag are clustered for the second time to obtain the positioning data of the first category and the positioning data of the second category.

[0036] Furthermore, it also includes:

[0037] The untrained third classification model is trained by using a third training data set to obtain a trained third classification model, wherein the third training data set includes historical positioning data set with the third label and historical positioning data set with the fourth label.

[0038] In a second aspect, the embodiment of the present disclosure further provides a vehicle positioning data processing device, the device comprising:

[0039] A preprocessing module is used to preprocess the target positioning data to obtain positioning data to be classified;

[0040] A first classification module, used for inputting the positioning data to be classified into a trained first classification model to obtain a first reference label of the positioning data to be classified;

[0041] A second classification module is used to input the positioning data to be classified into a trained second classification model to obtain a second reference label of the positioning data to be classified; the first classification model and the second classification model are different models;

[0042] a storage strategy determining module, configured to determine a storage strategy for the target positioning data according to the first reference tag and the second reference tag;

[0043] A processing module is used to store and process the target positioning data according to the storage strategy.

[0044] In a third aspect, an embodiment of the present disclosure further provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the vehicle positioning data processing method as described above.

[0045] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the vehicle positioning data processing method as described above.

[0046] A vehicle positioning data processing method provided by an embodiment of the present disclosure comprises the following steps: first, preprocessing target positioning data to obtain positioning data to be classified; the purpose of preprocessing the target positioning data is to facilitate the subsequent first classification model and the second classification model to effectively identify the characteristics of the target positioning data, and then classify the target positioning data, which is beneficial to improving the classification accuracy and efficiency; then, the preprocessed positioning data to be classified are respectively input into the first classification model and the second classification model to obtain a first reference label of the positioning data to be classified and a second reference label of the positioning data to be classified; the purpose of inputting the preprocessed positioning data to be classified into two different classification models is to improve the classification accuracy and classification reliability; the storage strategy of the target positioning data is determined by referring to the reference labels (including the first reference label and the second reference label) output by different classification models (including the first classification model and the second classification model), so that the determined storage strategy can be more accurate and reliable, and then the target positioning data is reasonably stored and processed, and the target positioning data is reasonably screened, thereby reducing the storage pressure. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0048] Figure 1 The process of a vehicle positioning data processing method in the embodiment of the present disclosure is as follows Figure 1 ;

[0049] Figure 2 The process of a vehicle positioning data processing method in the embodiment of the present disclosure is as follows Figure 2 ;

[0050] Figure 3 It is a structural schematic diagram of a vehicle positioning data processing device in an embodiment of the present disclosure;

[0051] Figure 4 It is a structural schematic diagram of an electronic device in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0052] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0053] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0054] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0055] Figure 1 FIG. 1 is a flow chart of a vehicle positioning data processing method in an embodiment of the present disclosure. The method can be executed by a vehicle positioning data processing device, which can be implemented in software and / or hardware, and can be configured in an electronic device. Figure 1 As shown, the method may specifically include the following steps:

[0056] S110: pre-process the target positioning data to obtain positioning data to be classified.

[0057] The target positioning data specifically includes but is not limited to: timestamp (used to indicate the collection time of the target positioning data), location information (such as GPS coordinates), vehicle speed, driving direction and other multi-dimensional information.

[0058] The preprocessing of the target positioning data specifically includes: eliminating missing values ​​or outliers, and normalizing all feature data (such as timestamp, location information, vehicle speed, etc.) to between [0, 1], so that the subsequent first classification model and the second classification model can effectively identify the characteristics of the target positioning data, and then classify the target positioning data, which is conducive to improving classification accuracy and efficiency.

[0059] S120: Input the positioning data to be classified into a trained first classification model to obtain a first reference label of the positioning data to be classified.

[0060] S130, inputting the positioning data to be classified into a trained second classification model to obtain a second reference label of the positioning data to be classified; the first classification model and the second classification model are different models.

[0061] S140, determining a storage strategy for the target positioning data according to the first reference tag and the second reference tag;

[0062] S150: performing storage processing on the target positioning data according to the storage strategy.

[0063] For ease of description and understanding, the first reference tag may be X or Y. If the first reference tag is X, it means that the target positioning data has not been used, or the target positioning data has not been needed. In other words, it means that the target positioning data is not important. If the first reference tag is Y, it means that the target positioning data has been used, or the target positioning data has been needed. In other words, it means that the target positioning data is important.

[0064] The second reference tag can specifically be X, Y1 or Y2. If the second reference tag is X, it means that the target positioning data has not been used, or the target positioning data has not been needed. In other words, it means that the target positioning data is not important. If the second reference tag is Y1, it means that the target positioning data has been used but the number of times it has been used is less than a certain value (the value can be flexibly adjusted), or the target positioning data has been used but has not been applied to an important scene (the important scene can be set manually). In short, if the second reference tag is Y1, it means that the target positioning data is important, but the importance is average. If the second reference tag is Y2, it means that the target positioning data has been used but the number of times it has been used is greater than a certain value (the value can be flexibly adjusted), or the target positioning data has not only been used but also applied to an important scene (the important scene can be set manually, such as a problem analysis scene, i.e., related to BUG analysis). In short, if the second reference tag is Y2, it means that the target positioning data is important and has a high degree of importance.

[0065] In some implementations, determining a storage strategy for the target positioning data according to the first reference tag and the second reference tag includes:

[0066] In response to determining that the importance of the target positioning data does not meet the first set requirement according to the first reference tag and the second reference tag, the storage strategy is determined to delete the target positioning data. Exemplarily, if the first reference tag is X and the second reference tag is X or Y1, it is determined that the importance of the target positioning data does not meet the first set requirement, which means that the target positioning data is not important. Therefore, the target positioning data is not stored but deleted, thereby achieving the purpose of screening the target positioning data according to its importance and reducing the pressure of data storage. That is, when the first reference tag indicates that the target positioning data has not been used and the second reference tag indicates that the target positioning data has not been used, it is determined that the importance of the target positioning data does not meet the first set requirement; or, when the first reference tag indicates that the target positioning data has not been used and the second reference tag indicates that the target positioning data has been used, it is determined that the importance of the target positioning data does not meet the first set requirement.

[0067] In response to determining that the importance of the target positioning data meets the first set requirement according to the first reference tag and the second reference tag, the storage strategy is determined to store the target positioning data. Exemplarily, if the first reference tag is Y, regardless of whether the second reference tag is X, Y1 or Y2, it is determined that the importance of the target positioning data meets the first set requirement, which means that the target positioning data is important, so the target positioning data is stored to prevent the accidental deletion of important data and the subsequent data analysis from being affected. If the first reference tag is X, but the second reference tag is Y2, it is determined that the importance of the target positioning data meets the first set requirement, which means that the target positioning data is important, so the target positioning data is stored to prevent the accidental deletion of important data and the subsequent data analysis from being affected. That is, when the first reference tag indicates that the target positioning data has been used, it is determined that the importance of the target positioning data meets the first set requirement; or, when the first reference tag indicates that the target positioning data has not been used, and the second reference tag indicates that the target positioning data has been used and analyzed in the application scenario, it is determined that the importance of the target positioning data meets the first set requirement.

[0068] By comprehensively considering the classification results of the first classification model and the second classification model on the target positioning data, the importance of the target positioning data is determined, which is beneficial to improving the accuracy and reliability of determining the importance of the target positioning data, and further laying the foundation for determining a reasonable storage strategy, so as to achieve the purpose of not causing important positioning data to be deleted, but also screening the positioning data and reducing storage pressure.

[0069] In some implementations, determining a storage strategy for the target positioning data according to the first reference tag and the second reference tag includes:

[0070] In response to determining that the importance of the target positioning data meets a first set requirement according to the first reference label and the second reference label, the positioning data to be classified is input into a trained third classification model to obtain a third reference label for the positioning data to be classified, and the third classification model is different from the first classification model and the second classification model; and a storage strategy for the target positioning data is determined according to the third reference label and the second reference label.

[0071] That is, when the importance of the target positioning data is determined to meet the first set requirement through the first reference label and the second reference label, the positioning data to be classified is further input into the trained third classification model to obtain the third reference label of the positioning data to be classified, and finally the storage strategy of the target positioning data is determined according to the third reference label and the second reference label, which further improves the classification accuracy and makes the formulation of the storage strategy more accurate and reliable. Specifically, if the first reference label is Y, regardless of whether the second reference label is X, Y1 or Y2, it is determined that the importance of the target positioning data meets the first set requirement; or, if the first reference label is X, but the second reference label is Y2, it is determined that the importance of the target positioning data meets the first set requirement. That is, when the target positioning data is determined to be used data through the first classification model, it is determined that the importance of the target positioning data meets the first set requirement. Or, when the target positioning data is determined to be unused data through the first classification model, but the target positioning data is determined to be not only used data but also analyzed in important scenes through the second classification model, at this time, it is also considered that the importance of the target positioning data meets the first set requirement. By comprehensively considering the classification results of different classification models, it is helpful to improve the classification accuracy.

[0072] According to the above content, when the importance of the target positioning data reaches the first set requirement, there is a situation where the classification result of the first classification model is inconsistent with the classification result of the second classification model (for example, the target positioning data is determined by the first classification model to be unused data, but the target positioning data is determined by the second classification model to be not only used data, but also analyzed in important scenarios; or, the target positioning data is determined by the first classification model to be used data, but the target positioning data is determined by the second classification model to be unused data). Therefore, in order to further determine whether the classification result of the first classification model is reliable or the classification result of the second classification model is reliable, this embodiment inputs the positioning data to be classified into a trained third classification model to obtain a third reference label for the positioning data to be classified, and determines the final result by referring to the classification result of the third classification model, thereby achieving the purpose of improving the classification accuracy, and then improving the rationality of the data storage strategy, so that the target positioning data is reasonably processed, that is, when the target positioning data is not important, it is deleted, when the target positioning data has a certain importance, it is compressed and stored, and when the target positioning data is more important, it is stored as original data, that is, it is not compressed and the original data is directly stored. The purpose of screening and storing target positioning data according to its importance is achieved, which not only avoids accidental deletion of important data, but also achieves the screening purpose and reduces storage pressure.

[0073] Among them, the third reference label can specifically be Y1 or Y2. It can be seen that the first reference label output by the first classification model is X or Y, the second reference label output by the second classification model is X, Y1 or Y2, and the third reference label output by the third classification model is Y1 or Y2, that is, the first reference label output by the first classification model and the second reference label output by the second classification model intersect, and the second reference label output by the second classification model and the third reference label output by the third classification model intersect. Through such a setting, and taking into account the reference labels output by each classification model, the importance of the target positioning data is determined, the accuracy of determining the importance of the target positioning data is improved, and the storage strategy formulated for the target positioning data is more reasonable.

[0074] In some implementations, determining a storage strategy for the target positioning data according to the third reference tag and the second reference tag includes:

[0075] In response to determining that the importance of the target positioning data does not meet the second set requirement according to the third reference tag and the second reference tag, the storage strategy is determined to compress and store the target positioning data. Exemplarily, if the third reference tag is Y1 and the second reference tag is X or Y1, it is determined that the importance of the target positioning data does not meet the second set requirement, which means that the target positioning data has a certain importance. Therefore, the target positioning data is not deleted, but compressed and stored to reduce the storage space occupied. That is, when the third reference tag indicates that the target positioning data has been used, and the second reference tag indicates that the target positioning data has not been used, it is determined that the importance of the target positioning data does not meet the second set requirement; or, when the third reference tag indicates that the target positioning data has been used, and the second reference tag also indicates that the target positioning data has been used, it is determined that the importance of the target positioning data does not meet the second set requirement.

[0076] In response to determining that the importance of the target positioning data meets the second set requirement according to the third reference tag and the second reference tag, the storage strategy is determined to perform extended storage of the target positioning data. If the third reference tag is Y1 and the second reference tag is Y2, it is determined that the importance of the target positioning data meets the second set requirement; and if the third reference tag is Y2, regardless of whether the second reference tag is X, Y1 or Y2, it is determined that the importance of the target positioning data meets the second set requirement. When the importance of the target positioning data meets the second set requirement, it means that the importance of the target positioning data is high. Therefore, when storing the target positioning data, it is not compressed to prevent data loss, but the target positioning data is extended to be stored, that is, the target positioning data itself is directly stored to ensure that during data analysis, key information will not be ignored or lost due to the storage strategy, thereby improving the accuracy and completeness of data analysis. That is, when the third reference tag indicates that the target positioning data has been used, and the second reference tag indicates that the target positioning data has been used and analyzed, it is determined that the importance of the target positioning data meets the second set requirement; or, when the third reference tag indicates that the target positioning data has been used and analyzed, it is determined that the importance of the target positioning data meets the second set requirement.

[0077] In some embodiments, the vehicle positioning data processing method further includes: acquiring historical positioning data reported by the vehicle; in response to the existence of an access record for the historical positioning data, setting a first tag for the historical positioning data (for example, setting tag Y to indicate that the historical positioning data has been used); in response to the absence of an access record for the historical positioning data, setting a second tag for the historical positioning data (for example, setting tag X to indicate that the historical positioning data has not been used).

[0078] The untrained first classification model is trained by using a first training data set to obtain the trained first classification model, wherein the first training data set includes historical positioning data set with the first label and historical positioning data set with the second label.

[0079] Furthermore, it also includes:

[0080] According to the plurality of historical positioning data set with the first label and the reference positioning data group, the plurality of historical positioning data are divided into two categories by a clustering algorithm; a third label is set for the historical positioning data in the first category (for example, label Y1 is set, indicating that the historical positioning data has been used but has not been analyzed in an important scene), and a fourth label is set for the historical positioning data in the second category (for example, label Y2 is set, indicating that the historical positioning data has been used and analyzed in an important scene). The positioning data in the reference positioning data group are all data that have been used and analyzed in an important scene.

[0081] The untrained second classification model is trained by using a second training data set to obtain the trained second classification model, wherein the second training data set includes historical positioning data set with the third label, historical positioning data set with the fourth label, and historical positioning data set with the second label.

[0082] Specifically, the plurality of historical positioning data set with the first tag and the reference positioning data group are divided into two categories by a clustering algorithm, including:

[0083] By means of a clustering algorithm, the plurality of historical positioning data provided with the first label are clustered for the first time to obtain a first clustering cluster and a second clustering cluster; a first number of positioning data in the first clustering cluster that is identical to that in the reference positioning data group is determined, and a second number of positioning data in the second clustering cluster that is identical to that in the reference positioning data group is determined; the larger of the first number and the second number is determined as a target number; a clustering cluster corresponding to the target number is determined as a target clustering cluster, wherein the clustering cluster corresponding to the first number is the first clustering cluster, and the clustering cluster corresponding to the second number is the second clustering cluster; (i.e., a target clustering cluster having more identical positioning data with the reference positioning data group is determined from the first clustering cluster and the second clustering cluster). The center of each positioning data in the target cluster that is the same as that in the reference positioning data group is determined as the cluster center of the first category, and the center of another cluster other than the target cluster is determined as the cluster center of the second category; according to the cluster center of the first category and the cluster center of the second category, the plurality of historical positioning data set with the first label are clustered for the second time to obtain the positioning data of the first category and the positioning data of the second category. For example, if 100 positioning data in the first cluster overlap with the positioning data in the reference positioning data group, and 60 positioning data in the second cluster overlap with the positioning data in the reference positioning data group, then the first cluster is the target cluster that has more identical positioning data with the reference positioning data group. At this time, the center of the 100 positioning data is determined as the cluster center of the first category, and the center of the second cluster is determined as the cluster center of the second category. After the cluster centers are determined, the second clustering is performed, and the positioning data classified into the cluster center of the first category is the positioning data of the first category, and the positioning data classified into the cluster center of the second category is the positioning data of the second category. A third label is set for the historical positioning data in the first category, and a fourth label is set for the historical positioning data in the second category, so as to obtain high-precision sample data for training the classification model.

[0084] Furthermore, an untrained third classification model is trained by a third training data set to obtain a trained third classification model, wherein the third training data set includes historical positioning data set with the third label and historical positioning data set with the fourth label.

[0085] Among them, the first classification model, the second classification model and the third classification model are all support vector machine models, and the kernel function can adopt the radial basis function (RBF kernel) to take into account both linear and nonlinear data distribution.

[0086] Based on the above embodiments, Figure 2 The flowchart of a vehicle positioning data processing method shown is as follows:

[0087] S210: Input the preprocessed positioning data into an X / Y classification model to obtain a first output result.

[0088] The first output result is X or Y.

[0089] S220 , input the preprocessed positioning data into the X / Y1 / Y2 classification model to obtain a second output result.

[0090] The second output result is X, Y1 or Y2.

[0091] S230. If the first output result is X and the second output result is X; or, the first output result is X and the second output result is Y1, execute S240; otherwise, execute S250.

[0092] S240: Delete the positioning data.

[0093] S250 , input the preprocessed positioning data into the Y1 / Y2 classification model to obtain a third output result.

[0094] The third output result is Y1 or Y2.

[0095] S260. If the third output result is Y1 and the second output result is X; or, the third output result is Y1 and the second output result is Y1, execute S270; otherwise, execute S280.

[0096] S270: compress and store the positioning data.

[0097] S280: Expand and store the positioning data.

[0098] That is, the positioning data itself is stored without compression.

[0099] Figure 3 FIG. 1 is a schematic diagram of the structure of a vehicle positioning data processing device in an embodiment of the present disclosure. Figure 3As shown: the device includes: a preprocessing module 310, used to preprocess the target positioning data to obtain the positioning data to be classified; a first classification module 320, used to input the positioning data to be classified into a trained first classification model to obtain a first reference label of the positioning data to be classified; a second classification module 330, used to input the positioning data to be classified into a trained second classification model to obtain a second reference label of the positioning data to be classified; the first classification model and the second classification model are different models; a storage strategy determination module 340, used to determine the storage strategy of the target positioning data according to the first reference label and the second reference label; a processing module 350, used to store and process the target positioning data according to the storage strategy.

[0100] The vehicle positioning data processing device provided in the embodiment of the present disclosure can execute the steps in the vehicle positioning data processing method provided in the method embodiment of the present disclosure, and the execution steps and beneficial effects are no longer repeated here.

[0101] Figure 4 Schematic diagram of the structure of an electronic device in the embodiment of the present disclosure. Figure 4 , which shows a structural schematic diagram of an electronic device 500 suitable for implementing the embodiments of the present disclosure. Figure 4 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0102] like Figure 4 As shown, the electronic device 500 may include a processing device 501, a ROM 502, a RAM 503, a bus 504, an input / output (I / O) interface 505, an input device 506, an output device 507, a storage device 508, and a communication device 509. The processing device (e.g., a central processing unit, a graphics processor, etc.) 501 can perform various appropriate actions and processes to implement the method of the embodiment described in the present disclosure according to the program stored in the read-only memory (ROM) 502 or the program loaded from the storage device 508 to the random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other through the bus 504. The input / output (I / O) interface 505 is also connected to the bus 504.

[0103] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart, thereby implementing the vehicle positioning data processing method as described above. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0104] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0105] The computer-readable medium may be included in the electronic device; or it may exist independently without being assembled into the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: pre-processes the target positioning data to obtain the positioning data to be classified; inputs the positioning data to be classified into a trained first classification model to obtain the first reference label of the positioning data to be classified; inputs the positioning data to be classified into a trained second classification model to obtain the second reference label of the positioning data to be classified; the first classification model and the second classification model are different models; determines the storage strategy of the target positioning data according to the first reference label and the second reference label, and performs storage processing on the target positioning data according to the storage strategy.

[0106] Optionally, when the above one or more programs are executed by the electronic device, the electronic device may also execute other steps described in the above embodiments.

[0107] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0108] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

Claims

1. A vehicle positioning data processing method, characterized in that: The method comprises: Preprocess the target positioning data to obtain positioning data to be classified; Inputting the positioning data to be classified into a trained first classification model to obtain a first reference label of the positioning data to be classified; Inputting the positioning data to be classified into a trained second classification model to obtain a second reference label of the positioning data to be classified; the first classification model and the second classification model are different models; Determining a storage strategy for the target positioning data according to the first reference tag and the second reference tag; The target positioning data is stored and processed according to the storage strategy.

2. The method according to claim 1, characterized in that: The step of determining a storage strategy for the target positioning data according to the first reference tag and the second reference tag includes: In response to determining, according to the first reference tag and the second reference tag, that the importance of the target positioning data does not meet a first set requirement, determining that the storage strategy is to delete the target positioning data; In response to determining, according to the first reference tag and the second reference tag, that the importance of the target positioning data reaches a first set requirement, determining the storage strategy to store the target positioning data.

3. The method according to claim 1, characterized in that The step of determining a storage strategy for the target positioning data according to the first reference tag and the second reference tag includes: In response to determining that the importance of the target positioning data meets a first set requirement according to the first reference label and the second reference label, inputting the positioning data to be classified into a trained third classification model to obtain a third reference label of the positioning data to be classified, wherein the third classification model is different from the first classification model and different from the second classification model; A storage strategy for the target positioning data is determined according to the third reference tag and the second reference tag.

4. The method according to claim 3, characterized in that: The step of determining a storage strategy for the target positioning data according to the third reference tag and the second reference tag includes: In response to determining, according to the third reference tag and the second reference tag, that the importance of the target positioning data does not meet a second set requirement, determining that the storage strategy is to compress and store the target positioning data; In response to determining, according to the third reference tag and the second reference tag, that the importance of the target positioning data reaches a second set requirement, determining the storage strategy to perform extended storage on the target positioning data.

5. The method according to claim 1, characterized in that: Also includes: Obtain historical positioning data reported by vehicles; In response to the existence of an access record for the historical positioning data, setting a first tag for the historical positioning data; In response to the historical positioning data having no access record, setting a second tag for the historical positioning data; The untrained first classification model is trained by using a first training data set to obtain the trained first classification model, wherein the first training data set includes historical positioning data set with the first label and historical positioning data set with the second label.

6. The method according to claim 5, characterized in that Also includes: Dividing the plurality of historical positioning data with the first tag and the reference positioning data group into two categories by using a clustering algorithm; Setting a third label for the historical positioning data in the first category, and setting a fourth label for the historical positioning data in the second category; The untrained second classification model is trained by using a second training data set to obtain the trained second classification model, wherein the second training data set includes historical positioning data set with the third label, historical positioning data set with the fourth label, and historical positioning data set with the second label.

7. The method according to claim 6, characterized in that The method further comprises dividing the plurality of historical positioning data with the first tag and the reference positioning data group into two categories by using a clustering algorithm, including: Performing a first clustering on the plurality of historical positioning data provided with the first tag by a clustering algorithm to obtain a first clustering cluster and a second clustering cluster; Determine a first number of positioning data in the first cluster that is identical to that in the reference positioning data set, and determine a second number of positioning data in the second cluster that is identical to that in the reference positioning data set; determining the larger of the first amount and the second amount as a target amount; Determining the clusters corresponding to the target number as target clusters, wherein the clusters corresponding to the first number are the first clusters, and the clusters corresponding to the second number are the second clusters; Determine the center of each positioning data in the target cluster that is the same as that in the reference positioning data group as the cluster center of the first category, and determine the center of another cluster except the target cluster as the cluster center of the second category; According to the cluster center of the first category and the cluster center of the second category, the plurality of historical positioning data provided with the first tag are clustered for the second time to obtain the positioning data of the first category and the positioning data of the second category.

8. The method according to claim 6, characterized in that Also includes: The untrained third classification model is trained by using a third training data set to obtain a trained third classification model, wherein the third training data set includes historical positioning data set with the third label and historical positioning data set with the fourth label.

9. An electronic device, characterized in that: The electronic device comprises: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images