L4-level automatic driving and platform communication method based on public network condition

Abstract

The invention relates to an L4-level automatic driving and platform communication method based on a public network condition, and the method comprises the steps: M1, enabling an automatic driving vehicle to run on a road, and obtaining the data information of the operation state of the vehicle in real time; m2, based on the data information of the running state of the vehicle, performing feature extraction on the data of the running state of the vehicle by adopting a feature extraction algorithm of vehicle data based on a word bag model, and constructing a feature matrix of the vehicle running state data to obtain data information of the feature matrix of the vehicle running state data; and M3, based on the data information of the characteristic matrix of the vehicle operation state data, constructing a platform data rapid access model based on a BP neural network, and encrypting the operation state data of the vehicle to obtain the processed data information of the vehicle operation state. According to the invention, the efficiency of data processing and analysis is improved, and the persistent and low-energy-consumption communication between the autonomous vehicle and the platform is ensured.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a communication method between an L4 level autonomous driving and a platform based on a public network. Background Art

[0002] In the prior art, a Chinese patent (application number: 202411320385.X, publication number: CN 118843111A) discloses a vehicle network communication method, system, device and storage medium, including: an initialization module, which is used to issue certificates to the unmanned mining card and the cloud control platform respectively through a pre-built cryptographic service platform; an authentication request message acquisition module, which is used to encrypt and sign through the vehicle-side OBU of the unmanned mining card and the certificate information of the cloud control platform using the national secret algorithm to obtain an identity authentication request message; an authentication message acquisition module, which is used to perform vehicle verification and target session key generation through the cloud control platform and based on the certificate information corresponding to the unmanned mining card and the identity authentication request message to obtain an authentication message; a key negotiation completion module, which is used to decrypt and platform verify through the vehicle-side OBU and the authentication message to obtain a target session key; a business communication module, which is used to perform business communication through the vehicle-side OBU, the target session key and the cloud control platform. However, the communication between the vehicle and the control terminal in this solution is based on the OBU device communicating data according to the full vehicle data under the provisions of the communication protocol. For situations where the business data structure is complex and the data volume is large, long-term communication consumes a lot of energy. It cannot meet the requirements of long-term status communication with the control terminal when the vehicle is offline and dormant, or the main energy module cannot be used for charging. Summary of the invention

[0003] In view of the above deficiencies in the prior art, the present invention provides a communication method between L4 level autonomous driving and a platform based on public network conditions, which not only improves the efficiency of data processing and analysis, but also ensures persistent and low-energy communication between the autonomous driving vehicle and the platform.

[0004] In order to achieve the above-mentioned purpose and other related purposes, the technical solution provided by the present invention is as follows:

[0005] A method for communicating between an L4 level autonomous driving and a platform based on a public network, the method comprising:

[0006] M1. The autonomous driving vehicle is driving on the road and real-time data information on the vehicle's operating status is obtained;

[0007] M2. Based on the data information of the running state of the vehicle, a feature extraction algorithm of vehicle data based on a bag-of-words model is used to extract features from the data of the running state of the vehicle, and a feature matrix of the vehicle running state data is constructed to obtain data information of the feature matrix of the vehicle running state data;

[0008] M3. Based on the data information of the characteristic matrix of the vehicle operation status data, a platform data rapid access model based on a BP neural network is constructed to encrypt the vehicle operation status data to obtain the processed vehicle operation status data information;

[0009] M4. Based on the processed data information of the vehicle operation status, establish a data access evaluation function F between the vehicle and the platform, evaluate the data access between the vehicle and the platform, and obtain data information of the evaluation value of the data access between the vehicle and the platform.

[0010] Furthermore, the method further comprises:

[0011] M5. Based on the data information of the evaluation value of the data access between the vehicle and the platform, a preset threshold is set. If the evaluation value of the data access between the vehicle and the platform is less than the preset threshold, the requirement is not met, and the process returns to step M3. If the evaluation value of the data access between the vehicle and the platform is greater than the preset threshold, the requirement is met, and the data communication between the autonomous driving and the platform is completed.

[0012] Furthermore, the evaluation function F of the data access between the vehicle and the platform is:

[0013]

[0014] Among them, x is the data information of the processed vehicle operation status, α1, α2 and α3 are the data access evaluation factors between the vehicle and the platform, and f is the penalty function of the processed vehicle operation status.

[0015] Furthermore, the penalty function f of the processed vehicle running state is,

[0016]

[0017] Among them, x is the data information of the vehicle operating status after processing.

[0018] Furthermore, in step M2, the feature extraction of the vehicle running status data using a vehicle data feature extraction algorithm based on a bag-of-words model includes:

[0019] M21. Based on the data information of the vehicle's operating status, a dictionary function Q of the vehicle's operating status data is established,

[0020]

[0021] Wherein, y is the data information of the running state of the vehicle, β1, β2 and β3 are dictionary forming factors of the running state data of the vehicle, and the data of the running state of the vehicle is lexicographically formed to obtain the data information of the dictionary of the running state of the vehicle;

[0022] M22. Based on the data information of the dictionary of the vehicle's operating status, a vectorized function W of the vehicle's operating status is established,

[0023]

[0024] Wherein, z is the data information of the dictionary of the running state of the vehicle, δ1, δ2 and δ3 are the vectorization factors of the running state of the vehicle, and the dictionary of the running state of the vehicle is vectorized to obtain the data information of the vectorization matrix of the running state of the vehicle;

[0025] M23. Based on the data information of the vectorized matrix of the vehicle running state, a feature extraction function R of the vehicle running state data is established,

[0026]

[0027] Among them, r is the data information of the vectorized matrix of the vehicle's operating status, γ1, γ2 and γ3 are the feature extraction factors of the vehicle's operating status, feature extraction is performed on the data of the vehicle's operating status, and a feature matrix of the vehicle's operating status data is constructed to obtain the data information of the feature matrix of the vehicle's operating status data.

[0028] Furthermore, the feature extraction factors γ1, γ2 and γ3 of the vehicle running state are:

[0029] Among them, r is the data information of the vectorized matrix of the vehicle's operating status.

[0030] Furthermore, in step M3, the construction of a platform data rapid access model based on a BP neural network and encryption processing of the vehicle's operating status data include:

[0031] M31. Input the data information of the characteristic matrix of the vehicle running status data into the platform data rapid access model for training and learning, initialize the model encryption parameters, and obtain the data information of the initialized model encryption parameters;

[0032] M32. Input the data information of the initialized model encryption parameters into the BP neural network for optimization, and establish the optimization function S of the BP neural network.

[0033]

[0034] Among them, q is the data information of the model encryption parameters after initialization, η1, η2 and η3 are the optimization factors of the BP neural network, and the model encryption parameters are optimized to obtain the data information of the optimized model encryption parameters;

[0035] M33. Based on the data information of the optimized model encryption parameters, establish a model encryption function G,

[0036]

[0037] Among them, g is the data information of the optimized model encryption parameters, λ1, λ2 and λ3 are the weight coefficients of the model, and the vehicle operation status data is encrypted to obtain the processed vehicle operation status data information.

[0038] Furthermore, the constraint function H of the weight coefficients λ1, λ2 and λ3 of the model is,

[0039] The value range of the constraint function H is (0,1).

[0040] In order to achieve the above-mentioned purpose and other related purposes, the present invention also provides a communication system between L4 level autonomous driving and a platform based on a public network, including a computer device, which is programmed or configured to execute any one of the steps of the communication method between L4 level autonomous driving and a platform based on a public network.

[0041] In order to achieve the above-mentioned purpose and other related purposes, the present invention also provides a computer-readable storage medium, which stores a computer program programmed or configured to execute any one of the methods for communicating between L4-level autonomous driving and a platform based on public network conditions.

[0042] The present invention has the following positive effects:

[0043] 1. The present invention extracts features from the vehicle's operating status data by using a feature extraction algorithm for vehicle data based on a bag-of-words model, constructs a feature matrix of the vehicle's operating status data, and combines this with a platform data rapid access model based on a BP neural network to encrypt the vehicle's operating status data. This not only enables the vehicle's status to be monitored for a long time when the vehicle is offline / dormant, and enables remote command operations to improve automation efficiency, but also improves the efficiency of data processing and analysis.

[0044] 2. The present invention evaluates the data access between the vehicle and the platform by establishing a data access evaluation function F between the vehicle and the platform, which can not only ensure the quality and efficiency of the data entering the vehicle and the platform, but also ensure the persistent and low-energy communication between the autonomous driving vehicle and the platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0046] Figure 2It is a flow chart of a feature extraction algorithm of vehicle data based on the bag-of-words model of the present invention;

[0047] Figure 3 The figure is a flow chart of constructing a platform data rapid access model based on BP neural network according to the present invention. DETAILED DESCRIPTION

[0048] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0049] Example 1: Figure 1 As shown, a method for communicating between an L4 level autonomous driving and a platform based on a public network, the method comprising:

[0050] M1. The autonomous driving vehicle is driving on the road and real-time data information on the vehicle's operating status is obtained;

[0051] M2. Based on the data information of the running state of the vehicle, a feature extraction algorithm of vehicle data based on a bag-of-words model is used to extract features from the data of the running state of the vehicle, and a feature matrix of the vehicle running state data is constructed to obtain data information of the feature matrix of the vehicle running state data;

[0052] M3. Based on the data information of the characteristic matrix of the vehicle operation status data, a platform data rapid access model based on a BP neural network is constructed to encrypt the vehicle operation status data to obtain the processed vehicle operation status data information;

[0053] M4. Based on the processed data information of the vehicle operation status, establish a data access evaluation function F between the vehicle and the platform, evaluate the data access between the vehicle and the platform, and obtain data information of the evaluation value of the data access between the vehicle and the platform.

[0054] In this embodiment, the method further includes:

[0055] M5. Based on the data information of the evaluation value of the data access between the vehicle and the platform, a preset threshold is set. If the evaluation value of the data access between the vehicle and the platform is less than the preset threshold, the requirement is not met, and the process returns to step M3. If the evaluation value of the data access between the vehicle and the platform is greater than the preset threshold, the requirement is met, and the data communication between the autonomous driving and the platform is completed.

[0056] In this embodiment, the evaluation function F of the data access between the vehicle and the platform is:

[0057]

[0058] Among them, x is the data information of the processed vehicle operation status, α1, α2 and α3 are the data access evaluation factors between the vehicle and the platform, and f is the penalty function of the processed vehicle operation status.

[0059] In this embodiment, the penalty function f of the processed vehicle running state is,

[0060]

[0061] Among them, x is the data information of the vehicle operating status after processing.

[0062] In this embodiment, if Figure 2 As shown, in step M2, the feature extraction of vehicle running status data using a vehicle data feature extraction algorithm based on a bag-of-words model includes:

[0063] M21. Based on the data information of the vehicle's operating status, a dictionary function Q of the vehicle's operating status data is established,

[0064]

[0065] Wherein, y is the data information of the running state of the vehicle, β1, β2 and β3 are dictionary forming factors of the running state data of the vehicle, and the data of the running state of the vehicle is lexicographically formed to obtain the data information of the dictionary of the running state of the vehicle;

[0066] M22. Based on the data information of the dictionary of the vehicle's operating status, a vectorized function W of the vehicle's operating status is established,

[0067]

[0068] Wherein, z is the data information of the dictionary of the running state of the vehicle, δ1, δ2 and δ3 are the vectorization factors of the running state of the vehicle, and the dictionary of the running state of the vehicle is vectorized to obtain the data information of the vectorization matrix of the running state of the vehicle;

[0069] M23. Based on the data information of the vectorized matrix of the vehicle running state, a feature extraction function R of the vehicle running state data is established,

[0070]

[0071] Among them, r is the data information of the vectorized matrix of the vehicle's operating status, γ1, γ2 and γ3 are the feature extraction factors of the vehicle's operating status, feature extraction is performed on the data of the vehicle's operating status, and a feature matrix of the vehicle's operating status data is constructed to obtain the data information of the feature matrix of the vehicle's operating status data.

[0072] In this embodiment, the feature extraction factors γ1, γ2 and γ3 of the vehicle running state are:

[0073]

[0074] Among them, r is the data information of the vectorized matrix of the vehicle's operating status.

[0075] Example 2: Based on the communication method between L4 level autonomous driving and the platform under public network conditions in Example 1, the present invention is further illustrated and described below.

[0076] like Figure 1 As shown, a method for communicating between an L4 level autonomous driving and a platform based on a public network, the method comprising:

[0077] M1. The autonomous driving vehicle is driving on the road and real-time data information on the vehicle's operating status is obtained;

[0078] M2. Based on the data information of the running state of the vehicle, a feature extraction algorithm of vehicle data based on a bag-of-words model is used to extract features from the data of the running state of the vehicle, and a feature matrix of the vehicle running state data is constructed to obtain data information of the feature matrix of the vehicle running state data;

[0079] M3. Based on the data information of the characteristic matrix of the vehicle operation status data, a platform data rapid access model based on a BP neural network is constructed to encrypt the vehicle operation status data to obtain the processed vehicle operation status data information;

[0080] M4. Based on the processed data information of the vehicle operation status, establish a data access evaluation function F between the vehicle and the platform, evaluate the data access between the vehicle and the platform, and obtain data information of the evaluation value of the data access between the vehicle and the platform.

[0081] In this embodiment, if Figure 3 As shown, in step M3, the construction of a platform data rapid access model based on a BP neural network and encryption processing of the vehicle's operating status data include:

[0082] M31. Input the data information of the characteristic matrix of the vehicle running status data into the platform data rapid access model for training and learning, initialize the model encryption parameters, and obtain the data information of the initialized model encryption parameters;

[0083] M32. Input the data information of the initialized model encryption parameters into the BP neural network for optimization, and establish the optimization function S of the BP neural network.

[0084]

[0085] Among them, q is the data information of the model encryption parameters after initialization, η1, η2 and η3 are the optimization factors of the BP neural network, and the model encryption parameters are optimized to obtain the data information of the optimized model encryption parameters;

[0086] M33. Based on the data information of the optimized model encryption parameters, establish a model encryption function G,

[0087]

[0088] Among them, g is the data information of the optimized model encryption parameters, λ1, λ2 and λ3 are the weight coefficients of the model, and the vehicle operation status data is encrypted to obtain the processed vehicle operation status data information.

[0089] In this embodiment, the constraint function H of the weight coefficients λ1, λ2 and λ3 of the model is,

[0090]

[0091] The value range of the constraint function H is (0,1).

[0092] In this embodiment, the present invention provides a communication system between L4 level autonomous driving and a platform based on a public network, including a computer device, which is programmed or configured to execute any one of the steps of the communication method between L4 level autonomous driving and a platform based on a public network.

[0093] In this embodiment, the vehicle side includes a backup energy module, a 5G communication module, a power control system, an automatic driving system, etc.; the network side includes a 4G / 5G base station, optical fiber, etc.; the data management platform includes a server, a gateway, a data middle platform, a scheduling platform, etc.

[0094] In this embodiment, the present invention provides a computer-readable storage medium, which stores a computer program programmed or configured to execute any one of the methods for communicating between L4-level autonomous driving and a platform based on a public network.

[0095] Any reference to memory, storage, database or other media used in the embodiments provided in the present application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM).

[0096] In summary, the present invention not only improves the efficiency of data processing and analysis, but also ensures persistent and low-energy communication between the autonomous driving vehicle and the platform.

[0097] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A communication method between L4 level autonomous driving and a platform based on a public network, characterized in that: The method comprises: M1. The autonomous driving vehicle is driving on the road and real-time data information on the vehicle's operating status is obtained; M2. Based on the data information of the running state of the vehicle, a feature extraction algorithm of vehicle data based on a bag-of-words model is used to extract features from the data of the running state of the vehicle, and a feature matrix of the vehicle running state data is constructed to obtain data information of the feature matrix of the vehicle running state data; M3. Based on the data information of the characteristic matrix of the vehicle operation status data, a platform data rapid access model based on a BP neural network is constructed to encrypt the vehicle operation status data to obtain the processed vehicle operation status data information; M4. Based on the processed data information of the vehicle operation status, establish a data access evaluation function F between the vehicle and the platform, evaluate the data access between the vehicle and the platform, and obtain data information of the evaluation value of the data access between the vehicle and the platform.

2. The method for communicating between an L4-level autonomous driving system and a platform based on a public network according to claim 1, characterized in that: The method further comprises: M5. Based on the data information of the evaluation value of the data access between the vehicle and the platform, a preset threshold is set. If the evaluation value of the data access between the vehicle and the platform is less than the preset threshold, the requirement is not met, and the process returns to step M3. If the evaluation value of the data access between the vehicle and the platform is greater than the preset threshold, the requirement is met, and the data communication between the autonomous driving and the platform is completed.

3. The method for communicating between an L4-level autonomous driving system and a platform based on a public network according to claim 1, characterized in that: The evaluation function F of the data access between the vehicle and the platform, Among them, x is the data information of the processed vehicle operation status, α1, α2 and α3 are the data access evaluation factors between the vehicle and the platform, and f is the penalty function of the processed vehicle operation status.

4. The method for communicating between an L4-level autonomous driving system and a platform based on a public network according to claim 3, characterized in that: The penalty function f of the vehicle running state after the processing is, Among them, x is the data information of the vehicle operating status after processing.

5. The method for communicating between an L4-level autonomous driving system and a platform based on a public network according to claim 1, characterized in that: In step M2, the feature extraction of vehicle running status data using a vehicle data feature extraction algorithm based on a bag-of-words model includes: M21. Based on the data information of the vehicle's operating status, a dictionary function Q of the vehicle's operating status data is established, Wherein, y is the data information of the running state of the vehicle, β1, β2 and β3 are dictionary forming factors of the running state data of the vehicle, and the data of the running state of the vehicle is lexicographically formed to obtain the data information of the dictionary of the running state of the vehicle; M22. Based on the data information of the dictionary of the vehicle's operating status, a vectorized function W of the vehicle's operating status is established, Wherein, z is the data information of the dictionary of the running state of the vehicle, δ1, δ2 and δ3 are the vectorization factors of the running state of the vehicle, and the dictionary of the running state of the vehicle is vectorized to obtain the data information of the vectorization matrix of the running state of the vehicle; M23. Based on the data information of the vectorized matrix of the vehicle running state, a feature extraction function R of the vehicle running state data is established, Among them, r is the data information of the vectorized matrix of the vehicle's operating status, γ1, γ2 and γ3 are the feature extraction factors of the vehicle's operating status, feature extraction is performed on the data of the vehicle's operating status, and a feature matrix of the vehicle's operating status data is constructed to obtain the data information of the feature matrix of the vehicle's operating status data.

6. The method for communicating between an L4-level autonomous driving system and a platform based on a public network according to claim 5, characterized in that: The feature extraction factors γ1, γ2 and γ3 of the vehicle running state are: Among them, r is the data information of the vectorized matrix of the vehicle's operating status.

7. The method for communicating between an L4-level autonomous driving system and a platform based on a public network according to claim 1, characterized in that: In step M3, the construction of a platform data rapid access model based on a BP neural network and encryption processing of the vehicle's operating status data include: M31. Input the data information of the characteristic matrix of the vehicle running status data into the platform data rapid access model for training and learning, initialize the model encryption parameters, and obtain the data information of the initialized model encryption parameters; M32. Input the data information of the initialized model encryption parameters into the BP neural network for optimization, and establish the optimization function S of the BP neural network. Among them, q is the data information of the model encryption parameters after initialization, η1, η2 and η3 are the optimization factors of the BP neural network, and the model encryption parameters are optimized to obtain the data information of the optimized model encryption parameters; M33. Based on the data information of the optimized model encryption parameters, establish a model encryption function G, Among them, g is the data information of the optimized model encryption parameters, λ1, λ2 and λ3 are the weight coefficients of the model, and the vehicle operation status data is encrypted to obtain the processed vehicle operation status data information.

8. The method for communicating between an L4 autonomous driving system and a platform based on a public network according to claim 7, characterized in that: The constraint function H of the weight coefficients λ1, λ2 and λ3 of the model is, The value range of the constraint function H is (0,1).

9. A communication system between an L4 autonomous driving system and a platform based on a public network, comprising a computer device, characterized in that: The computer device is programmed or configured to execute the steps of the method for communicating between an L4 level autonomous driving and a platform based on a public network as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program that is programmed or configured to execute the method for communicating between an L4-level autonomous driving and a platform based on a public network as described in any one of claims 1 to 8.

Images