Vehicle data uploading method and device and computer equipment
By compressing and dimensionality reduction of vehicle data in the Internet of Vehicles, and generating data compression feature expressions, the problem of high traffic when uploading vehicle data is solved, achieving more efficient data upload and reducing costs.
Patent Information
- Application Number
- CN202411261415.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-10
- Publication Date
- 2024-12-06
AI Technical Summary
In the Internet of Vehicles, vehicle data is uploaded to consume higher traffic, affecting the upload speed and increasing costs.
By compressing and dimensionality reduction processing of the vehicle data to be uploaded, a data compression feature expression is generated, and a data upload request carrying compressed feature expression is sent to the Internet of Vehicles platform, so that the platform can obtain the target vehicle data after decompression. The method includes using an encoder and a decoder, using a convolutional layer and a pooling layer for data compression and decompression, combining an attention module for dimensionality reduction, and adjusting the convolution kernel weight and bias when the data error is greater than the threshold.
It effectively reduces the data size of vehicle data, improves upload efficiency, and reduces traffic costs.
Smart Images

Figure CN119094566A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of vehicle networking, and in particular to a method, device and computer equipment for uploading vehicle data. Background Art
[0002] The Internet of Vehicles (IoV) refers to a large-scale system network that connects cars with each other, cars with roadside infrastructure, cars with pedestrians, and cars with the Internet through information sensing devices, and realizes intelligent information exchange and communication between cars, cars with roads, cars with people, and cars with the cloud. The main purpose of the IoV is to improve traffic safety, efficiency, and environmental protection, and to realize intelligent traffic management, intelligent dynamic information services, and intelligent vehicle control through information interaction between vehicles and the outside world.
[0003] In order to maximize the relevant functions of the Internet of Vehicles, vehicles need to upload vehicle data (such as vehicle operation data, vehicle basic data, etc.) to the Internet of Vehicles platform, so that the Internet of Vehicles platform can provide relevant services to the vehicle based on the uploaded vehicle data, such as status analysis, real-time warning, etc.
[0004] Currently, when uploading vehicle data, a high amount of traffic is consumed, which not only affects the upload speed of vehicle data, but also requires a high traffic cost. Summary of the invention
[0005] Based on this, it is necessary to provide a vehicle data uploading method, device and computer equipment that can improve the efficiency of vehicle data uploading in response to the above technical problems.
[0006] In a first aspect, the present application provides a method for uploading vehicle data. The method comprises:
[0007] Compressing the vehicle data to be uploaded to obtain a first data compression feature expression of the vehicle data to be uploaded;
[0008] Performing dimensionality reduction processing on the first data compression feature expression to obtain a second data compression feature expression of the data to be uploaded;
[0009] A data upload request carrying a second data compression feature expression is sent to the Internet of Vehicles platform; wherein the data upload request is used to instruct the Internet of Vehicles platform to decompress the second data compression feature expression to obtain target vehicle data corresponding to the second data compression feature expression.
[0010] In one embodiment, the vehicle data to be uploaded is compressed to obtain a first data compression feature expression of the vehicle data to be uploaded, including:
[0011] Based on the encoder, the vehicle data to be uploaded is compressed to obtain a first data compression feature expression of the vehicle data to be uploaded; wherein the encoder includes at least one convolution layer and at least one pooling layer.
[0012] In one embodiment, based on an encoder, the vehicle data to be uploaded is compressed to obtain a first data compression feature expression of the vehicle data to be uploaded, including:
[0013] Based on the data collection cycle and data type, the vehicle data to be uploaded is grouped to obtain a data matrix of the data to be uploaded;
[0014] Based on the encoder, the data matrix is compressed to obtain a first data compression feature expression of the vehicle data to be uploaded.
[0015] In one embodiment, performing dimensionality reduction processing on the first data compression feature expression to obtain a second data compression feature expression of the data to be uploaded includes:
[0016] Based on the attention module, a weight matrix is added to the first compressed data feature expression to obtain a second data compressed feature expression of the data to be uploaded.
[0017] In one of the embodiments, the data upload request is specifically used to instruct the Internet of Vehicles platform to decompress the second data compression feature expression based on a decoder to obtain vehicle data corresponding to the second data compression feature expression.
[0018] In one embodiment, the method further comprises:
[0019] Based on the error function, determining the data error between the target vehicle data and the vehicle data to be uploaded;
[0020] When the data error is greater than the error threshold, the weights and biases of the convolution kernels in the convolution layer of the encoder are adjusted.
[0021] In a second aspect, the present application also provides a vehicle data uploading device. The device comprises:
[0022] A compression module, used for compressing the vehicle data to be uploaded to obtain a first data compression feature expression of the vehicle data to be uploaded;
[0023] A processing module, used for performing dimensionality reduction processing on the first data compression feature expression to obtain a second data compression feature expression of the data to be uploaded;
[0024] An upload module is used to send a data upload request carrying a second data compression feature expression to the Internet of Vehicles platform; wherein the data upload request is used to instruct the Internet of Vehicles platform to decompress the second data compression feature expression to obtain the target vehicle data corresponding to the second data compression feature expression.
[0025] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:
[0026] Compressing the vehicle data to be uploaded to obtain a first data compression feature expression of the vehicle data to be uploaded;
[0027] Performing dimensionality reduction processing on the first data compression feature expression to obtain a second data compression feature expression of the data to be uploaded;
[0028] A data upload request carrying a second data compression feature expression is sent to the Internet of Vehicles platform; wherein the data upload request is used to instruct the Internet of Vehicles platform to decompress the second data compression feature expression to obtain target vehicle data corresponding to the second data compression feature expression.
[0029] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:
[0030] Compressing the vehicle data to be uploaded to obtain a first data compression feature expression of the vehicle data to be uploaded;
[0031] Performing dimensionality reduction processing on the first data compression feature expression to obtain a second data compression feature expression of the data to be uploaded;
[0032] A data upload request carrying a second data compression feature expression is sent to the Internet of Vehicles platform; wherein the data upload request is used to instruct the Internet of Vehicles platform to decompress the second data compression feature expression to obtain target vehicle data corresponding to the second data compression feature expression.
[0033] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:
[0034] Compressing the vehicle data to be uploaded to obtain a first data compression feature expression of the vehicle data to be uploaded;
[0035] Performing dimensionality reduction processing on the first data compression feature expression to obtain a second data compression feature expression of the data to be uploaded;
[0036] A data upload request carrying a second data compression feature expression is sent to the Internet of Vehicles platform; wherein the data upload request is used to instruct the Internet of Vehicles platform to decompress the second data compression feature expression to obtain target vehicle data corresponding to the second data compression feature expression.
[0037] The above-mentioned vehicle data uploading method, device and computer equipment compress the vehicle data to be uploaded to obtain a first data compression feature expression of the vehicle data to be uploaded. Perform dimensionality reduction processing on the first data compression feature expression to obtain a second data compression feature expression of the data to be uploaded. Send a data upload request carrying the second data compression feature expression to the Internet of Vehicles platform; wherein the data upload request is used to instruct the Internet of Vehicles platform to decompress the second data compression feature expression to obtain the target vehicle data corresponding to the second data compression feature expression. When uploading the vehicle data to be uploaded, the present application compresses the vehicle data to be uploaded to obtain the first data compression feature expression, and further performs dimensionality reduction processing on the first data compression feature expression to obtain the second compression feature expression, which is then uploaded to the Internet of Vehicles platform, effectively reducing the data size of the vehicle data to be uploaded, which not only improves the upload efficiency of the vehicle data to be uploaded, but also reduces the traffic cost when uploading data. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] FIG1 is an application environment diagram of the vehicle data uploading method provided in this embodiment;
[0039] FIG2 is a schematic diagram of a flow chart of a first vehicle data uploading method provided in this embodiment;
[0040] Figure 3 A schematic diagram of a process for obtaining a first data compression feature expression provided in this embodiment;
[0041] Figure 4 A schematic diagram of the principle of the data matrix corresponding to the data to be uploaded provided in this embodiment;
[0042] Figure 5 A schematic diagram of the principle of the vehicle data uploading method provided in this embodiment;
[0043] Figure 6 A schematic diagram of a flow chart of adjusting the weight and bias of a convolution kernel in a convolution layer of an encoder provided in this embodiment;
[0044] Figure 7 A schematic diagram of the flow of a second vehicle data uploading method provided in this embodiment;
[0045] Figure 8 A structural block diagram of a vehicle data uploading device provided in this embodiment;
[0046] FIG. 9 is a diagram showing the internal structure of a computer device provided in this embodiment. DETAILED DESCRIPTION
[0047] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0048] The vehicle data uploading method provided in the embodiment of the present application can be executed by the vehicle, specifically, it can be executed by a vehicle-mounted terminal configured on the vehicle or a controller on the vehicle. That is, the method can be applied to the application environment shown in Figure 1. Among them, the vehicle 102 compresses the vehicle data to be uploaded to obtain a first data compression feature expression of the vehicle data to be uploaded. And the first data compression feature expression is subjected to dimensionality reduction processing to obtain a second data compression feature expression of the data to be uploaded. The vehicle 102 uploads the second data compression feature expression to the Internet of Vehicles platform 104, so that the Internet of Vehicles platform 104 decompresses the second data compression feature expression to obtain the target vehicle data corresponding to the second data compression feature expression.
[0049] The Internet of Vehicles platform 104 may be implemented using an independent server or a server cluster consisting of multiple servers.
[0050] The vehicle in this application refers to a vehicle that has a need to upload vehicle data to be uploaded. This application does not limit the specific model and type of the vehicle.
[0051] In one embodiment, as shown in FIG2 , a vehicle data uploading method is provided, and the method is applied to the vehicle in FIG1 as an example for explanation, as shown in FIG2 , including the following steps:
[0052] S201, compressing the vehicle data to be uploaded to obtain a first data compression feature expression of the vehicle data to be uploaded.
[0053] Among them, the vehicle data to be uploaded refers to the vehicle data that needs to be uploaded to the Internet of Vehicles platform. For example, vehicle operation data, vehicle basic data, etc. In this application, the vehicle data to be uploaded mainly comes from the data collected by TBOX on the whole vehicle and other data obtained by the camera. The first data compression feature expression refers to the expression form of the vehicle data to be uploaded after the vehicle data to be uploaded is compressed.
[0054] As an optional implementation of the embodiment of the present application, a compression tool is used to compress the uploaded vehicle data to obtain a first data compression feature expression of the vehicle data to be uploaded. The compression tool can be a data compression software or a neural network model with data processing function.
[0055] S202: Perform dimensionality reduction processing on the first data compression feature expression to obtain a second data compression feature expression of the data to be uploaded.
[0056] The dimensionality reduction process refers to obtaining more representative vehicle data based on the refined processing of the data, thereby reducing the influence of invalid data on the refined compression features. The second data compression feature expression refers to the expression form of the first data compression feature expression obtained by performing dimensionality reduction processing on the first data compression feature expression.
[0057] Optionally, in this embodiment, based on the data processing module, the first compressed data feature expression is subjected to dimensionality reduction processing to obtain a second data compressed feature expression of the data to be uploaded. Exemplarily, based on the data processing module, the first compressed data feature expression is subjected to dimensionality reduction processing to obtain a second data compressed feature expression of the data to be uploaded.
[0058] S203, sending a data upload request carrying the second data compression feature expression to the Internet of Vehicles platform.
[0059] The data upload request is used to instruct the Internet of Vehicles platform to decompress the second data compression feature expression to obtain the target vehicle data corresponding to the second data compression feature expression. The data upload request is a request message for uploading data to the Internet of Vehicles platform.
[0060] As an optional implementation of the embodiment of the present application, the second data compression feature expression is uploaded to the Internet of Vehicles platform, and the Internet of Vehicles platform decompresses the second data compression feature expression based on a decompression tool to obtain the target vehicle data corresponding to the second data compression feature expression. The decompression tool can be a decompression software or a neural network model with data processing function.
[0061] The above-mentioned vehicle data uploading method compresses the vehicle data to be uploaded to obtain a first data compression feature expression of the vehicle data to be uploaded. The first data compression feature expression is subjected to dimensionality reduction processing to obtain a second data compression feature expression of the data to be uploaded. A data upload request carrying the second data compression feature expression is sent to the Internet of Vehicles platform; wherein the data upload request is used to instruct the Internet of Vehicles platform to decompress the second data compression feature expression to obtain the target vehicle data corresponding to the second data compression feature expression. When uploading the vehicle data to be uploaded, the present application compresses the vehicle data to be uploaded to obtain a first data compression feature expression, and further performs dimensionality reduction processing on the first data compression feature expression to obtain a second compression feature expression, which is then uploaded to the Internet of Vehicles platform, effectively reducing the data size of the vehicle data to be uploaded, which not only improves the upload efficiency of the vehicle data to be uploaded, but also reduces the traffic cost when uploading data.
[0062] In one embodiment, in order to more efficiently compress the uploaded vehicle data and improve the data upload efficiency, Figure 3As shown, an optional implementation of S201 includes:
[0063] S301, compressing the vehicle data to be uploaded based on an encoder to obtain a first data compression feature expression of the vehicle data to be uploaded.
[0064] The encoder includes at least one convolution layer and at least one pooling layer. The encoder converts the input sequence into a fixed-length context vector, which is mainly used to compress the uploaded data.
[0065] An optional implementation of this embodiment is to group the vehicle data to be uploaded based on the data collection cycle and data type to obtain a data matrix of the data to be uploaded. Based on the encoder, the data matrix is compressed to obtain a first data compression feature expression of the vehicle data to be uploaded. Figure 4 As shown, based on the data collection cycle and data type, the vehicle data to be uploaded is grouped to obtain a data matrix of the data to be uploaded. The specific implementation method is to group the vehicle data to be uploaded by time period. Construct a data matrix in the format of M×T×N. Where M represents a certain type of data, T represents a period, and M×T represents all data of a certain type of data within the T period. N represents a matrix with a size of N M×T. On this basis, based on the encoder, the data matrix is compressed to obtain the first data compression feature expression of the vehicle data to be uploaded. An optional implementation method is to input the data matrix in the format of M×T×N into the encoder, and the encoder outputs the first data compression feature expression based on the internal convolution layer and pooling layer. For example, .
[0066] On the basis of the above embodiment, an optional implementation method of performing dimensionality reduction processing on the first data compression feature expression to obtain the second data compression feature expression of the data to be uploaded is as follows: Figure 5 As shown, based on the attention module, a weight matrix is added to the first compressed data feature expression to obtain a second data compressed feature expression of the data to be uploaded. Specifically, the attention module will output the weight matrix , and the first compressed data feature expression Perform pixel-level multiplication to reduce the dimension of the first compressed data feature expression to obtain a refined output , which is the second data compression feature expression. Among them, the attention module has a convolution kernel of size 1×1.
[0067] On the basis of the above embodiment, a data upload request carrying a second data compression feature expression is sent to the Internet of Vehicles platform; wherein the data upload request is used to instruct the Internet of Vehicles platform to decompress the second data compression feature expression to obtain the target vehicle data corresponding to the second data compression feature expression. An optional implementation method is to send a data upload request carrying a second data compression feature expression to the Internet of Vehicles platform; wherein the data upload request is specifically used to instruct the Internet of Vehicles platform to decompress the second data compression feature expression based on a decoder to obtain the vehicle data corresponding to the second data compression feature expression. Please refer to the above Figure 5 The decoder in this implementation is a component corresponding to the encoder, and the decoder includes at least one convolutional layer and at least one pooling layer.
[0068] In this embodiment, based on the data collection cycle and data type, the vehicle data to be uploaded is grouped to obtain a data matrix of the data to be uploaded. Based on the encoder, the data matrix is compressed to obtain a first data compression feature expression of the vehicle data to be uploaded. Based on the attention module, a weight matrix is added to the first compressed data feature expression to obtain a second data compression feature expression of the data to be uploaded. The second data compression feature expression is uploaded to the Internet of Vehicles platform, so that the Internet of Vehicles platform, based on the decoder, decompresses the second data compression feature expression to obtain the vehicle data corresponding to the second data compression feature expression, thereby achieving efficient uploading of the vehicle data to be uploaded and reducing the cost of traffic usage. In the embodiment, the vehicle and the Internet of Vehicles platform adopt a data processing model with a jump-layer architecture, that is, an encoder is configured on the vehicle side and a decoder is configured on the Internet of Vehicles platform, which increases the robustness and compatibility of the model.
[0069] In one embodiment, if Figure 6 As shown, an optional implementation method for uploading vehicle data includes:
[0070] S601, determining a data error between target vehicle data and vehicle data to be uploaded based on an error function.
[0071] The error function refers to a function used to determine the error between the target vehicle data and the vehicle data to be uploaded. The data error refers to the error value between the target vehicle data and the vehicle data to be uploaded.
[0072] Optionally, in this embodiment, the data error between the target vehicle data and the vehicle data to be uploaded may be determined by the following formula (1):
[0073] (1)
[0074] Where L represents the data error; y n Indicates the vehicle data to be uploaded; y n’ Represents target vehicle data.
[0075] S602: When the data error is greater than the error threshold, adjust the weight and bias of the convolution kernel in the convolution layer of the encoder.
[0076] Optionally, in this embodiment, when the data error is greater than the error threshold, the data error is input to the agent, and the agent adjusts the weight and bias of the convolution kernel in the convolution layer of the encoder based on the data error. The agent can be, but is not limited to, constructed by a neural network model.
[0077] In this embodiment, the data error between the target vehicle data and the vehicle data to be uploaded is determined based on the error function. When the data error is greater than the error threshold, the weight and bias of the convolution kernel in the convolution layer of the encoder are adjusted. Based on the feedback adjustment mechanism in this embodiment, when the upload result is not as expected, the weight and bias of the convolution kernel in the convolution layer of the encoder can be adjusted, thereby realizing closed-loop intelligent control of vehicle data upload.
[0078] In one embodiment, if Figure 7 As shown, an optional implementation of the vehicle data uploading method is:
[0079] S701, grouping the vehicle data to be uploaded based on the data collection cycle and data type to obtain a data matrix of the data to be uploaded.
[0080] S702: Based on the encoder, the data matrix is compressed to obtain a first data compression feature expression of the vehicle data to be uploaded. The encoder includes at least one convolution layer and at least one pooling layer.
[0081] S703: Based on the attention module, a weight matrix is added to the first compressed data feature expression to obtain a second data compression feature expression of the data to be uploaded.
[0082] S704, sending a data upload request carrying the second data compression feature expression to the Internet of Vehicles platform, the data upload request is used to instruct the Internet of Vehicles platform to decompress the second data compression feature expression based on a decoder to obtain vehicle data corresponding to the second data compression feature expression. The decoder includes at least one convolution layer and at least one pooling layer.
[0083] S705 , determining a data error between the target vehicle data and the vehicle data to be uploaded based on the error function.
[0084] S706: When the data error is greater than the error threshold, adjust the weight and bias of the convolution kernel in the convolution layer of the encoder.
[0085] In this embodiment, the vehicle data to be uploaded is compressed to obtain a first data compression feature expression of the vehicle data to be uploaded. The first data compression feature expression is subjected to dimensionality reduction processing to obtain a second data compression feature expression of the data to be uploaded. The second data compression feature expression is uploaded to the Internet of Vehicles platform so that the Internet of Vehicles platform decompresses the second data compression feature expression to obtain the target vehicle data corresponding to the second data compression feature expression. When uploading the vehicle data to be uploaded, the present application compresses the vehicle data to be uploaded to obtain a first data compression feature expression, and further performs dimensionality reduction processing on the first data compression feature expression to obtain a second compression feature expression, which is then uploaded to the Internet of Vehicles platform, effectively reducing the data size of the vehicle data to be uploaded, which not only improves the upload efficiency of the vehicle data to be uploaded, but also reduces the traffic cost when uploading data.
[0086] Based on the same inventive concept, the embodiment of the present application also provides a vehicle data upload device for implementing the vehicle data upload method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiment of a vehicle data upload device provided below can refer to the limitations of the vehicle data upload method above, and will not be repeated here.
[0087] In one embodiment, if Figure 8 As shown, a vehicle data uploading device 1 is provided, comprising:
[0088] A compression module 10, used for compressing the vehicle data to be uploaded to obtain a first data compression feature expression of the vehicle data to be uploaded;
[0089] A processing module 20 is used to perform dimensionality reduction processing on the first data compression feature expression to obtain a second data compression feature expression of the data to be uploaded;
[0090] The upload module 30 is used to send a data upload request carrying the second data compression feature expression to the Internet of Vehicles platform; wherein the data upload request is used to instruct the Internet of Vehicles platform to decompress the second data compression feature expression to obtain the target vehicle data corresponding to the second data compression feature expression.
[0091] In one embodiment, the Figure 8 The compression module 10 is also specifically used for:
[0092] Based on the encoder, the vehicle data to be uploaded is compressed to obtain a first data compression feature expression of the vehicle data to be uploaded; wherein the encoder includes at least one convolution layer and at least one pooling layer.
[0093] In one embodiment, the Figure 8The compression module 1 is also specifically used for:
[0094] Based on the data collection cycle and data type, the vehicle data to be uploaded is grouped to obtain a data matrix of the data to be uploaded;
[0095] Based on the encoder, the data matrix is compressed to obtain a first data compression feature expression of the vehicle data to be uploaded.
[0096] In one embodiment, the Figure 8 The processing module 20 is also specifically used for:
[0097] Based on the attention module, a weight matrix is added to the first compressed data feature expression to obtain a second data compressed feature expression of the data to be uploaded.
[0098] In one embodiment, the Figure 8 The upload module 30 is also specifically used for:
[0099] The data upload request is specifically used to instruct the Internet of Vehicles platform so that the Internet of Vehicles platform, based on a decoder, decompresses the second data compression feature expression to obtain vehicle data corresponding to the second data compression feature expression.
[0100] In one embodiment, the Figure 8 A vehicle data uploading device 1, further comprising:
[0101] A determination module, used to determine a data error between the target vehicle data and the vehicle data to be uploaded based on an error function;
[0102] The adjustment module is used to adjust the weight and bias of the convolution kernel in the convolution layer of the encoder when the data error is greater than the error threshold.
[0103] Each module in the above-mentioned vehicle data uploading device can be implemented in whole or in part by software, hardware or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.
[0104] In one embodiment, a computer device is provided, and its internal structure diagram can be shown in Figure 9. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a vehicle data uploading method is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.
[0105] Those skilled in the art will understand that the structure shown in FIG. 9 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.
[0106] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:
[0107] Compressing the vehicle data to be uploaded to obtain a first data compression feature expression of the vehicle data to be uploaded;
[0108] Performing dimensionality reduction processing on the first data compression feature expression to obtain a second data compression feature expression of the data to be uploaded;
[0109] A data upload request carrying a second data compression feature expression is sent to the Internet of Vehicles platform; wherein the data upload request is used to instruct the Internet of Vehicles platform to decompress the second data compression feature expression to obtain target vehicle data corresponding to the second data compression feature expression.
[0110] In one embodiment, when the processor executes the computer program, the following steps are further implemented: compressing the vehicle data to be uploaded to obtain a first data compression feature expression of the vehicle data to be uploaded, including:
[0111] Based on the encoder, the vehicle data to be uploaded is compressed to obtain a first data compression feature expression of the vehicle data to be uploaded; wherein the encoder includes at least one convolution layer and at least one pooling layer.
[0112] In one embodiment, when the processor executes the computer program, the following steps are further implemented: based on the encoder, compressing the vehicle data to be uploaded to obtain a first data compression feature expression of the vehicle data to be uploaded, including:
[0113] Based on the data collection cycle and data type, the vehicle data to be uploaded is grouped to obtain a data matrix of the data to be uploaded;
[0114] Based on the encoder, the data matrix is compressed to obtain a first data compression feature expression of the vehicle data to be uploaded.
[0115] In one embodiment, when the processor executes the computer program, the following steps are further implemented: performing dimensionality reduction processing on the first data compression feature expression to obtain a second data compression feature expression of the data to be uploaded, including:
[0116] Based on the attention module, a weight matrix is added to the first compressed data feature expression to obtain a second data compressed feature expression of the data to be uploaded.
[0117] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0118] The data upload request is specifically used to instruct the Internet of Vehicles platform to decompress the second data compression feature expression based on a decoder to obtain vehicle data corresponding to the second data compression feature expression.
[0119] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0120] Based on the error function, determining the data error between the target vehicle data and the vehicle data to be uploaded;
[0121] When the data error is greater than the error threshold, the weights and biases of the convolution kernels in the convolution layer of the encoder are adjusted.
[0122] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:
[0123] Compressing the vehicle data to be uploaded to obtain a first data compression feature expression of the vehicle data to be uploaded;
[0124] Performing dimensionality reduction processing on the first data compression feature expression to obtain a second data compression feature expression of the data to be uploaded;
[0125] A data upload request carrying a second data compression feature expression is sent to the Internet of Vehicles platform; wherein the data upload request is used to instruct the Internet of Vehicles platform to decompress the second data compression feature expression to obtain target vehicle data corresponding to the second data compression feature expression.
[0126] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: compressing the vehicle data to be uploaded to obtain a first data compression feature expression of the vehicle data to be uploaded, including:
[0127] Based on the encoder, the vehicle data to be uploaded is compressed to obtain a first data compression feature expression of the vehicle data to be uploaded; wherein the encoder includes at least one convolution layer and at least one pooling layer.
[0128] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: based on the encoder, compressing the vehicle data to be uploaded to obtain a first data compression feature expression of the vehicle data to be uploaded, including:
[0129] Based on the data collection cycle and data type, the vehicle data to be uploaded is grouped to obtain a data matrix of the data to be uploaded;
[0130] Based on the encoder, the data matrix is compressed to obtain a first data compression feature expression of the vehicle data to be uploaded.
[0131] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: performing dimensionality reduction processing on the first data compression feature expression to obtain a second data compression feature expression of the data to be uploaded, including:
[0132] Based on the attention module, a weight matrix is added to the first compressed data feature expression to obtain a second data compressed feature expression of the data to be uploaded.
[0133] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0134] The data upload request is specifically used to instruct the Internet of Vehicles platform to decompress the second data compression feature expression based on a decoder to obtain vehicle data corresponding to the second data compression feature expression.
[0135] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0136] Based on the error function, determining the data error between the target vehicle data and the vehicle data to be uploaded;
[0137] When the data error is greater than the error threshold, the weights and biases of the convolution kernels in the convolution layer of the encoder are adjusted.
[0138] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:
[0139] Compressing the vehicle data to be uploaded to obtain a first data compression feature expression of the vehicle data to be uploaded;
[0140] Performing dimensionality reduction processing on the first data compression feature expression to obtain a second data compression feature expression of the data to be uploaded;
[0141] A data upload request carrying a second data compression feature expression is sent to the Internet of Vehicles platform; wherein the data upload request is used to instruct the Internet of Vehicles platform to decompress the second data compression feature expression to obtain target vehicle data corresponding to the second data compression feature expression.
[0142] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: compressing the vehicle data to be uploaded to obtain a first data compression feature expression of the vehicle data to be uploaded, including:
[0143] Based on the encoder, the vehicle data to be uploaded is compressed to obtain a first data compression feature expression of the vehicle data to be uploaded; wherein the encoder includes at least one convolution layer and at least one pooling layer.
[0144] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: based on the encoder, compressing the vehicle data to be uploaded to obtain a first data compression feature expression of the vehicle data to be uploaded, including:
[0145] Based on the data collection cycle and data type, the vehicle data to be uploaded is grouped to obtain a data matrix of the data to be uploaded;
[0146] Based on the encoder, the data matrix is compressed to obtain a first data compression feature expression of the vehicle data to be uploaded.
[0147] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: performing dimensionality reduction processing on the first data compression feature expression to obtain a second data compression feature expression of the data to be uploaded, including:
[0148] Based on the attention module, a weight matrix is added to the first compressed data feature expression to obtain a second data compressed feature expression of the data to be uploaded.
[0149] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: the data upload request is specifically used to instruct the Internet of Vehicles platform so that the Internet of Vehicles platform, based on a decoder, decompresses the second data compression feature expression to obtain vehicle data corresponding to the second data compression feature expression.
[0150] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0151] Based on the error function, determining the data error between the target vehicle data and the vehicle data to be uploaded;
[0152] When the data error is greater than the error threshold, the weights and biases of the convolution kernels in the convolution layer of the encoder are adjusted.
[0153] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile 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), magnetoresistive 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. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.
[0154] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, 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 specification.
[0155] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A vehicle data uploading method, characterized in that: The method comprises: Compressing the vehicle data to be uploaded to obtain a first data compression feature expression of the vehicle data to be uploaded; Performing dimensionality reduction processing on the first data compression feature expression to obtain a second data compression feature expression of the data to be uploaded; A data upload request carrying the second data compression feature expression is sent to the Internet of Vehicles platform; wherein the data upload request is used to instruct the Internet of Vehicles platform to decompress the second data compression feature expression to obtain the target vehicle data corresponding to the second data compression feature expression.
2. The method according to claim 1, characterized in that The compressing the vehicle data to be uploaded to obtain a first data compression feature expression of the vehicle data to be uploaded includes: Based on the encoder, the vehicle data to be uploaded is compressed to obtain a first data compression feature expression of the vehicle data to be uploaded; wherein the encoder includes at least one convolution layer and at least one pooling layer.
3. The method according to claim 2, characterized in that The step of compressing the vehicle data to be uploaded based on the encoder to obtain a first data compression feature expression of the vehicle data to be uploaded includes: Based on the data collection cycle and data type, the vehicle data to be uploaded are grouped to obtain a data matrix of the data to be uploaded; Based on the encoder, the data matrix is compressed to obtain a first data compression feature expression of the vehicle data to be uploaded.
4. The method according to claim 2, characterized in that: The performing dimensionality reduction processing on the first data compression feature expression to obtain a second data compression feature expression of the data to be uploaded includes: Based on the attention module, a weight matrix is added to the first compressed data feature expression to obtain a second data compression feature expression of the data to be uploaded.
5. The method according to claim 3, characterized in that: The data upload request is specifically used to instruct the Internet of Vehicles platform to decompress the second data compression feature expression based on a decoder to obtain vehicle data corresponding to the second data compression feature expression.
6. The method according to claim 2, characterized in that The method further comprises: Based on the error function, determining the data error between the target vehicle data and the vehicle data to be uploaded; When the data error is greater than the error threshold, the weight and bias of the convolution kernel in the convolution layer of the encoder are adjusted.
7. A vehicle data uploading device, characterized in that: The device comprises: A compression module, used for compressing the vehicle data to be uploaded to obtain a first data compression feature expression of the vehicle data to be uploaded; A processing module, configured to perform dimensionality reduction processing on the first data compression feature expression to obtain a second data compression feature expression of the data to be uploaded; An upload module is used to send a data upload request carrying the second data compression feature expression to the Internet of Vehicles platform; wherein the data upload request is used to instruct the Internet of Vehicles platform to decompress the second data compression feature expression to obtain the target vehicle data corresponding to the second data compression feature expression.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the vehicle data uploading method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the vehicle data uploading method according to any one of claims 1 to 6 are implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the vehicle data uploading method described in any one of claims 1 to 6 are implemented.
