Driving intention recognition method and device, equipment and medium

Abstract

The invention discloses a driving intention recognition method and device, equipment and a medium. The driving intention recognition method is applied to the driving intention recognition system, and the driving intention recognition system comprises a pre-processing module, a reasoning module and a post-processing module. The driving intention recognition method comprises the following steps: acquiring original driving data of a vehicle through a pre-processing module, and performing data processing of a set mode on the original driving data to obtain a target driving feature; performing intention recognition on the target driving feature through the reasoning module to obtain an intention recognition result of the driver; and correcting the intention recognition result through the post-processing module to obtain a target intention recognition result. According to the technical scheme, through the optimized processing flow of the pre-processing module and the post-processing module, the driving key features can be rapidly and accurately extracted, redundant information is reduced, the accuracy of the model is improved, and the reliability of an intention recognition result is further improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and particularly to a driving intention recognition method, device, equipment and medium. Background Art

[0002] With the development of vehicle intelligence and autonomous driving technology, the interaction mode between vehicles and drivers has become increasingly complex. Among them, intention recognition, as one of the core technologies in intelligent vehicle systems, plays a crucial role.

[0003] Traditional intention recognition methods usually require long-term training and debugging, and often face problems such as complex data processing processes and inaccurate feature extraction, resulting in slow system response and poor user experience. Therefore, most existing intention recognition methods have problems such as insufficient accuracy, low processing efficiency, and too long development cycles, seriously affecting the performance of intelligent vehicle systems and user experience. Summary of the Invention

[0004] The present invention provides a driving intention recognition method, device, equipment and medium. By optimizing the processing flow of the preprocessing module and the postprocessing module, it can quickly and accurately extract key driving features, reduce redundant information, improve the accuracy of the model, and further enhance the reliability of the intention recognition result.

[0005] According to one aspect of the present invention, a driving intention recognition method is provided. The driving intention recognition method is applied to a driving intention recognition system, which includes a preprocessing module, an inference module, and a postprocessing module. The driving intention recognition method includes:

[0006] Obtain the original driving data of the vehicle through the preprocessing module, perform data processing on the original driving data in a set manner to obtain target driving features;

[0007] Perform intention recognition on the target driving features through the inference module to obtain the intention recognition result of the driver;

[0008] Correct the intention recognition result through the postprocessing module to obtain the target intention recognition result.

[0009] According to another aspect of the present invention, a driving intention recognition device is provided. The driving intention recognition method is configured in a driving intention recognition system, which includes a preprocessing module, an inference module, and a postprocessing module. The driving intention recognition method includes:

[0010] A preprocessing module, configured to obtain the original driving data of the vehicle, perform data processing on the original driving data in a set manner to obtain target driving features;

[0011] An inference module for performing intent recognition on the target driving features to obtain an intent recognition result of the driver;

[0012] A post-processing module for correcting the intent recognition result to obtain a target intent recognition result.

[0013] According to another aspect of the present invention, there is provided an electronic device, which includes:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the at least one processor is enabled to execute the driving intent recognition method according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the driving intent recognition method according to any embodiment of the present invention when executed.

[0018] In the technical solution of the embodiment of the present invention, the original driving data of the vehicle is obtained through the preprocessing module, and the original driving data is processed in a set manner to obtain target driving features; the inference module performs intent recognition on the target driving features to obtain an intent recognition result of the driver; the post-processing module corrects the intent recognition result to obtain a target intent recognition result. In this technical solution, through the optimized processing flow of the preprocessing module and the post-processing module, the driving key features can be quickly and accurately extracted, redundant information is reduced, the accuracy of the model is improved, and the reliability of the intent recognition result is further enhanced.

[0019] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0021] Figure 1It is a flowchart of a driving intention recognition method provided by Embodiment 1 of the present invention;

[0022] Figure 2 It is a flowchart of a driving intention recognition method provided by Embodiment 2 of the present invention;

[0023] Figure 3 It is a schematic structural diagram of a driving intention recognition system provided by Embodiment 3 of the present invention;

[0024] Figure 4 It is a schematic structural diagram of an electronic device provided by Embodiment 4 of the present invention. Detailed implementation manners

[0025] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0026] It should be noted that the terms "first", "second", and "target" in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device including a series of steps or units does not necessarily have to be limited to those clearly listed steps or units, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0027] Embodiment 1

[0028] Figure 1 It is a flowchart of a driving intention recognition method provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation of recognizing the driver's intention during vehicle intelligent driving. This method can be executed by a driving intention recognition system, which can be implemented in the form of hardware and / or software, and can be configured in an electronic device with data processing capabilities. As Figure 1 shown, this method includes:

[0029] In this embodiment, the driving intention recognition method is applied to a driving intention recognition system, which includes a preprocessing module, an inference module, and a postprocessing module. The preprocessing module and the postprocessing module in this embodiment can be regarded as the preprocessing and postprocessing processes of the model. In the preprocessing module of this embodiment, accurate feature extraction can be performed on the input data in the automotive field. The main objective of this preprocessing module is to convert the original input data (such as the driver's voice commands or driving behavior data, etc.) into high-quality, structured feature vectors, so that the subsequent inference process is more efficient and accurate. In the inference module of this embodiment, a method combining deep learning and machine learning is adopted, and combined with the features extracted by the preprocessing module, the driver's intention is recognized and classified. The function of the postprocessing module in this embodiment is to perform intelligent optimization on the output result based on the intention recognition. The postprocessing module ensures the accuracy and practical applicability of the recognition result through further processing of the recognition result.

[0030] S110. Obtain the original driving data of the vehicle through the preprocessing module, perform data processing on the original driving data in a set manner, and obtain the target driving features.

[0031] Among them, the vehicle can be the vehicle of current intelligent driving. The original driving data can be regarded as the vehicle driving data obtained during the vehicle driving process. The original driving data can include the driver's behavior data and the vehicle driving state data. Specifically, in this embodiment, the driving intention recognition system can obtain the original driving data from the vehicle's sensors and the voice recognition module, such as the driver's voice commands, the vehicle driving state, and the driver's behavior data. The data processing in a set manner can include preprocessing operations on the features, feature extraction operations, and feature selection and data dimensionality reduction processing methods, etc., and the features can also be processed in a set manner according to actual needs. The target driving features can be regarded as the final driving features obtained after the data processing in a set manner.

[0032] In this embodiment, the driver's behavior data and the vehicle driving state data can be obtained from the vehicle's sensors and the voice recognition module of the vehicle of current intelligent driving through the preprocessing module, and data preprocessing operations, feature extraction operations, and feature selection and data dimensionality reduction processing methods, etc., are performed on the driver's behavior data and the vehicle driving state data to obtain the processed driving features, that is, the target driving features.

[0033] S120. Perform intention recognition on the target driving features through the inference module to obtain the driver's intention recognition result.

[0034] Among them, intention recognition can be regarded as an operation of recognizing the driver's intention based on the target driving characteristics. In this embodiment, the inference module may include an intention recognition model for recognizing the driver's driving intention. The intention recognition model in this embodiment may be a pre-trained neural network model. The intention recognition result may be the result of recognizing the driver's intention identified by the target driving characteristics. In this embodiment, intention recognition processing may be performed through the intention recognition model and the target driving characteristics in the inference module, so as to output the corresponding intention recognition result.

[0035] S130. Correct the intention recognition result through the post-processing module to obtain the target intention recognition result.

[0036] Among them, correction may be an operation of adjusting and optimizing the intention recognition result. The target intention recognition result may be the final intention recognition result obtained after adjusting or optimizing the intention recognition result. The intention recognition result in this embodiment may be one or more. In this embodiment, the intention recognition result may be adjusted and optimized based on information such as preset business rules included in the post-processing module, so as to obtain the target intention recognition result.

[0037] The technical solution of the embodiment of the present invention is to obtain the original driving data of the vehicle through the pre-processing module, perform data processing in a set manner on the original driving data to obtain the target driving characteristics; perform intention recognition on the target driving characteristics through the inference module to obtain the driver's intention recognition result; correct the intention recognition result through the post-processing module to obtain the target intention recognition result. This technical solution can quickly and accurately extract the key driving characteristics, reduce redundant information, improve the accuracy of the model, and further improve the reliability of the intention recognition result through the optimized processing flow of the pre-processing module and the post-processing module.

[0038] Embodiment 2

[0039] Figure 2 It is a flowchart of a driving intention recognition method provided according to Embodiment 2 of the present invention. This embodiment is optimized based on the above embodiment. Specifically, the data processing in the set manner includes preprocessing, feature extraction, and data dimensionality reduction processing; correspondingly, obtaining the original driving data of the vehicle through the pre-processing module, performing data processing in the set manner on the original driving data to obtain the target driving characteristics, including: obtaining the original driving data of the vehicle through the pre-processing module, performing preprocessing on the original driving data to obtain the preprocessed driving data; performing feature extraction on the preprocessed driving data to obtain the driving feature data; performing data dimensionality reduction processing on the driving feature data to obtain the target driving characteristics. As Figure 2 shown, the method includes:

[0040] In this embodiment, the driving intention recognition method is applied to a driving intention recognition system, which includes a preprocessing module, an inference module, and a postprocessing module.

[0041] S210. Obtain the original driving data of the vehicle through the preprocessing module, and perform preprocessing on the original driving data to obtain the preprocessed driving data.

[0042] Among them, the preprocessing may include data cleaning processing and standardization processing; among them, the data cleaning processing may include data cleaning and data denoising processing. In this embodiment, the original driving data of the vehicle can be obtained through the preprocessing module, and then data cleaning processing and data denoising processing are performed on the original driving data, so as to remove irrelevant information, and the driving data after data cleaning processing and data denoising processing is subjected to standardization processing to obtain the preprocessed driving data. In this embodiment, through the standardization processing, it can be ensured that the data is under the same dimension, which is convenient for subsequent data processing operations.

[0043] In this embodiment, optionally, performing preprocessing on the original driving data to obtain the preprocessed driving data includes: performing data cleaning processing on the original driving data to obtain the cleaned driving data; performing standardization processing on the cleaned driving data to obtain the preprocessed driving data.

[0044] Among them, the data cleaning processing includes processing such as removing duplicate records, filling in missing values, and correcting error data. The cleaned driving data can be considered as the driving data obtained through processing such as removing duplicate records, filling in missing values, and correcting error data. The standardization processing can be considered as performing a preset standard format processing operation on the cleaned driving data.

[0045] In this embodiment, the original driving data can be processed such as removing duplicate records, filling in missing values, and correcting error data to obtain the cleaned driving data, and then the format of the cleaned driving data is converted into a preset standard data format, so as to obtain the preprocessed driving data.

[0046] In this embodiment, through such a setting, preprocessing operations can be performed on the original driving data, so that the driving data can maintain a consistent data format, which helps to eliminate the scale difference between different features and makes it easier to learn and understand the data during subsequent model processing.

[0047] S220. Extract features from the preprocessed driving data to obtain driving feature data.

[0048] Among them, feature extraction can be the extraction and processing of key vehicle feature data from the preprocessed driving data. In this embodiment, feature extraction can be performed through a feature extraction model or other machine learning methods. Driving feature data can be considered as the feature data obtained by extracting key features from the preprocessed driving data.

[0049] In this embodiment, key features can be extracted from the preprocessed driving data through specific automotive domain knowledge. For example, for driving voice data, spectral features of the audio or feature data such as speech patterns are extracted; for driving behavior data, driving habits of the driver or movement trajectories of the vehicle are extracted.

[0050] S230. Perform data dimensionality reduction processing on the driving feature data to obtain the target driving features.

[0051] Among them, data dimensionality reduction processing can be considered as an operation to reduce the data dimension of the driving feature data. The target driving features can be considered as the feature data obtained after data dimensionality reduction processing. In this embodiment, a dimensionality reduction algorithm can be set to perform data dimensionality reduction processing on the driving feature data to obtain the processed target driving features.

[0052] In this embodiment, optionally, performing data dimensionality reduction processing on the driving feature data to obtain the target driving features includes: performing feature selection on the driving feature data through a set feature selection algorithm to obtain the selected driving features; performing dimensionality reduction processing on the selected driving features through a data dimensionality reduction algorithm to obtain the target driving features.

[0053] Among them, the set feature selection algorithm can be an algorithm used to select features. The set feature selection algorithm in this embodiment can be any algorithm that can select features, and this embodiment does not limit it. In this embodiment, the required feature types can be preset. For example, some feature scenarios can be preset, or the features to be recognized can be selected according to some personal information characteristics, so as to select the driving features that meet the preset feature types according to the feature selection algorithm. The data dimensionality reduction algorithm can be an algorithm that reduces the data dimension. Exemplarily, the data dimensionality reduction algorithm in this embodiment can be the principal component analysis (PCA) algorithm, or the linear discriminant analysis (LDA) algorithm, etc. The data dimensionality reduction algorithm in this embodiment can be any algorithm that can perform data dimensionality reduction, and this embodiment does not limit it.

[0054] In this embodiment, the set feature selection algorithm can be used to perform feature selection on the driving feature data, so as to retain the features that best represent the driver's intention as the selected driving features, and then use a data dimensionality reduction algorithm (such as PCA) to perform dimensionality reduction processing on the selected driving features to obtain the final target driving features.

[0055] In this embodiment, through such a setting, by processing the driving data with a feature selection algorithm and a data dimensionality reduction algorithm, the required key feature types can be retained, the data dimension can also be reduced, and the computational complexity can be reduced.

[0056] S240. Perform intention recognition on the target driving feature through an inference module to obtain the driver's intention recognition result.

[0057] In this embodiment, optionally, perform intention recognition on the driving feature vector through an inference module to obtain the driver's intention recognition result, including: obtaining the intention recognition model in the inference module; inputting the target driving feature into the intention recognition model to obtain the driver's intention recognition result.

[0058] Among them, the intention recognition model can be a pre-trained deep neural network model. The intention recognition model in this embodiment can be a Long Short-Term Memory (LSTM) model or a Transformer model. The intention recognition result can be a result such as navigation, window control, or volume adjustment.

[0059] In this embodiment, the intention recognition model included can be obtained through the inference module, and then the target driving feature is input into the intention recognition model. After the intention recognition model performs an intention recognition operation on the target driving feature, the driver's intention recognition result is obtained.

[0060] Furthermore, in the training stage of the intention recognition model, the initial intention recognition model can be trained using the extracted feature vector samples, and trained with a large amount of labeled data to learn the driver's behavior pattern, so as to obtain the final target intention model that meets the requirements.

[0061] In this embodiment, through such a setting, by combining deep learning and machine learning methods, and combining the features extracted by the preprocessing module, the driver's intention is recognized, improving the accuracy and reliability of intention recognition.

[0062] Furthermore, in this embodiment, the intention recognition result can also be classified. In this embodiment, it can be classified according to the intention recognition task or according to the scenario where the intention recognition is located, and can also be classified according to other situations, which can be set according to actual needs. Exemplarily, the classification based on the intention recognition task can include driving behavior recognition, in-vehicle interaction intention, and driving assistance systems, etc. The classification based on the scenario where the intention recognition is located can include urban road driving, highway driving, parking lot operation, and driving in bad weather, etc. In this embodiment, the corresponding type classification operation can be performed on the recognized intention recognition result according to the pre-set intention recognition category.

[0063] S250. The intention recognition result is corrected by the post - processing module to obtain the target intention recognition result.

[0064] In this embodiment, optionally, correcting the intention recognition result by the post - processing module to obtain the target intention recognition result includes: obtaining the set business rules in the post - processing module; correcting the intention recognition result according to the set business rules to obtain the target intention recognition result.

[0065] Among them, the set business rules can be pre - set business rules. In this embodiment, the business rules can be set according to the specific business scenarios preset for intention recognition and can be set according to actual needs. Exemplarily, in this embodiment, the business rules can be pre - set according to content such as driver experience and road traffic rules. For example, when driving on a highway, a driver usually does not have the intention of making a sharp turn; when the red light is on, a driver usually has the intention of stopping, etc. When the intention recognition result does not conform to the set business rules, the intention recognition result can be corrected according to the set business rules to obtain the target intention recognition result.

[0066] In this embodiment, the set business rules stored in the post - processing module can be obtained, and the intention recognition result is corrected according to the set business rules and context information to obtain the target intention recognition result. Exemplarily, if the driver says "turn down the volume", but the speech recognition misrecognizes it as "turn up the volume", the post - processing module can automatically correct it in combination with context information (such as the current volume level), so that the final target intention recognition result is "turn down the volume".

[0067] In this embodiment, through such a setting, the intention recognition result can be corrected and optimized based on the pre - set business rules, so as to obtain the final intention recognition result, further improving the accuracy of intention recognition.

[0068] In this embodiment, optionally, it further includes: when there are multiple intention recognition results, obtaining the priorities corresponding to the multiple intention recognition results; screening the multiple intention recognition results according to the priorities corresponding to the multiple intention recognition results to obtain the target intention recognition result.

[0069] Among them, the priority can be the corresponding priority obtained by scoring the intention recognition result according to the pre - set scoring coefficient. There may be one or more intention recognition results in this embodiment. When there are multiple intention recognition results, the priorities corresponding to the intention recognition results can be determined. The priority in this embodiment can be a pre - set scoring coefficient for the intention recognition result, and the corresponding priority is determined according to the scoring coefficient of the intention recognition result.

[0070] In this embodiment, for the multiple intention recognition results identified, the post-processing module determines the priority or confidence level corresponding to each intention recognition result according to a preset scoring coefficient, and then screens the multiple intention recognition results according to the priority or confidence level corresponding to each intention recognition result to obtain the target intention recognition result, so as to ensure that the output result meets the actual requirements. When screening the multiple intention recognition results according to the priority corresponding to each intention recognition result in this embodiment, the results can be sorted from high to low according to each priority level, and the one with the highest priority can be considered as the optimal intention recognition result, that is, the target intention recognition result.

[0071] In this embodiment, through such a setting, it is possible to screen according to the priorities of multiple intention recognition results, determine the target intention recognition result, thereby optimizing the recognition result and improving the accuracy of intention recognition.

[0072] In this embodiment, the pre-processing module can convert messy input data into structured and efficient feature vectors, providing accurate input for the subsequent reasoning process; the reasoning module uses a method combining deep learning and machine learning, and combines the features extracted by the pre-processing module to recognize the driver's intention; the post-processing module intelligently optimizes the output result based on the intention recognition; through further processing of the recognition result, the accuracy and practical applicability of the recognition result are ensured. Through the optimized pre-processing process in this embodiment, key features can be quickly and accurately extracted from the voice and behavior data in the automotive field, reducing redundant information and improving the accuracy of the model; and through the intelligent post-processing module, the recognition result can be further optimized, making the output result more in line with the actual requirements, further improving the reliability and application effect of the intention recognition system. Moreover, through the optimization of the pre- and post-processing, the development cycle of the intention recognition system can be significantly shortened, enabling developers to complete the construction and iteration of the system more quickly, thereby accelerating the promotion and popularization of applications in the intelligent automotive field, helping enterprises to respond more quickly to user needs in a highly competitive market, and enhancing market competitiveness. This embodiment solves the problems of low efficiency, poor accuracy, and long development cycle in traditional methods through the pre- and post-processing processes of intention recognition in the automotive field, and can quickly and efficiently process the intention recognition tasks in the automotive field, and significantly improve the recognition accuracy and system response speed.

[0073] In the technical solution of the embodiment of the present invention, the preprocessing module obtains the original driving data of the vehicle, preprocesses the original driving data to obtain the preprocessed driving data; extracts features from the preprocessed driving data to obtain driving feature data; performs data dimensionality reduction processing on the driving feature data to obtain the target driving feature; the inference module performs intention recognition on the target driving feature to obtain the intention recognition result of the driver; the postprocessing module corrects the intention recognition result to obtain the target intention recognition result. In this technical solution, by optimizing the processing flow of the preprocessing module and the postprocessing module, the key driving features can be extracted quickly and accurately, redundant information is reduced, the accuracy of the model is improved, and the reliability of the intention recognition result is further enhanced.

[0074] Embodiment III

[0075] Figure 3 is a schematic structural diagram of a driving intention recognition system provided according to Embodiment III of the present invention. As Figure 3 shown, the system includes:

[0076] A preprocessing module 310, configured to obtain the original driving data of the vehicle, perform data processing in a set manner on the original driving data to obtain a target driving feature;

[0077] An inference module 320, configured to perform intention recognition on the target driving feature to obtain the intention recognition result of the driver;

[0078] A postprocessing module 330, configured to correct the intention recognition result to obtain a target intention recognition result.

[0079] Optionally, the data processing in the set manner includes preprocessing, feature extraction, and data dimensionality reduction processing;

[0080] Correspondingly, the preprocessing module 310 includes:

[0081] A preprocessing unit, configured to obtain the original driving data of the vehicle through the preprocessing module, preprocess the original driving data to obtain the preprocessed driving data;

[0082] A feature extraction unit, configured to extract features from the preprocessed driving data to obtain driving feature data;

[0083] A dimensionality reduction processing unit, configured to perform data dimensionality reduction processing on the driving feature data to obtain a target driving feature.

[0084] Optionally, the dimensionality reduction processing unit is specifically configured to:

[0085] Perform feature selection on the driving feature data through a set feature selection algorithm to obtain the selected driving features;

[0086] The selected driving features are dimensionally reduced through a data dimensionality reduction algorithm to obtain target driving features.

[0087] Optionally, the preprocessing unit is specifically configured to:

[0088] Perform data cleaning on the original driving data to obtain the cleaned driving data;

[0089] Perform standardization on the cleaned driving data to obtain the preprocessed driving data.

[0090] Optionally, the inference module 320 is specifically configured to:

[0091] Obtain the intention recognition model in the inference module;

[0092] Input the target driving features into the intention recognition model to obtain the driver's intention recognition result.

[0093] Optionally, the post-processing module 330 is specifically configured to:

[0094] Obtain the set business rules in the post-processing module;

[0095] Correct the intention recognition result according to the set business rules to obtain the target intention recognition result.

[0096] Optionally, the post-processing module of the system further includes: a screening unit, configured to, when there are multiple intention recognition results, obtain the priorities corresponding to the multiple intention recognition results; screen the multiple intention recognition results according to the priorities corresponding to the multiple intention recognition results to obtain the target intention recognition result.

[0097] A driving intention recognition system provided by an embodiment of the present invention can execute a driving intention recognition method provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method.

[0098] Embodiment IV

[0099] Figure 4 It is a schematic structural diagram of an electronic device provided according to Embodiment IV of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device (such as a helmet, glasses, a watch, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0100] AsFigure 4 As shown in Figure 4 , the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. Among them, the memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0101] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0102] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the driving intention recognition method.

[0103] In some embodiments, the driving intention recognition method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the driving intention recognition method described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the driving intention recognition method in any other appropriate way (e.g., by means of firmware).

[0104] The various embodiments of the systems and techniques described above in this specification can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.

[0105] The computer programs for implementing the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs can be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0106] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0107] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0108] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0109] The computing system can include a client and a server. The client and the server are generally far from each other and usually interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0110] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0111] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A driving intention recognition method, characterized in that: The driving intention recognition method is applied to a driving intention recognition system, which includes a pre-processing module, a reasoning module and a post-processing module; The driving intention recognition method comprises: Acquiring original driving data of the vehicle through the pre-processing module, performing data processing in a set manner on the original driving data to obtain target driving characteristics; Performing intention recognition on the target driving feature through the inference module to obtain a driver's intention recognition result; The intention recognition result is corrected by the post-processing module to obtain a target intention recognition result.

2. The method according to claim 1, characterized in that The data processing of the setting method includes preprocessing, feature extraction and data dimension reduction processing; Accordingly, the original driving data of the vehicle is obtained through the pre-processing module, and the original driving data is processed in a set manner to obtain the target driving characteristics, including: Acquiring original driving data of the vehicle through the pre-processing module, pre-processing the original driving data to obtain pre-processed driving data; Extracting features from the preprocessed driving data to obtain driving feature data; The driving characteristic data is subjected to data dimension reduction processing to obtain target driving characteristics.

3. The method according to claim 2, characterized in that Performing data dimension reduction processing on the driving characteristic data to obtain target driving characteristics includes: Performing feature selection on the driving feature data by setting a feature selection algorithm to obtain selected driving features; The selected driving features are subjected to dimensionality reduction processing by a data dimensionality reduction algorithm to obtain target driving features.

4. The method according to claim 2, characterized in that: Preprocessing the original driving data to obtain preprocessed driving data includes: Performing data cleaning on the original driving data to obtain cleaned driving data; The cleaned driving data is standardized to obtain pre-processed driving data.

5. The method according to claim 1, characterized in that: The driving feature vector is subjected to intention recognition by the inference module to obtain a driver's intention recognition result, including: Obtaining an intent recognition model in the reasoning module; The target driving feature is input into the intention recognition model to obtain the driver's intention recognition result.

6. The method according to claim 1, characterized in that The intention recognition result is corrected by the post-processing module to obtain a target intention recognition result, including: Obtaining the set business rules in the post-processing module; The intention recognition result is modified according to the set business rules to obtain a target intention recognition result.

7. The method according to claim 1, characterized in that Also includes: When there are multiple intent recognition results, obtain the priorities corresponding to the multiple intent recognition results; The multiple intention recognition results are screened according to the priorities corresponding to the multiple intention recognition results to obtain a target intention recognition result.

8. A driving intention recognition system, characterized in that: include: A pre-processing module, used to obtain original driving data of the vehicle, perform data processing in a set manner on the original driving data, and obtain target driving characteristics; An inference module, used to perform intention recognition on the target driving feature to obtain a driver's intention recognition result; The post-processing module is used to correct the intention recognition result to obtain the target intention recognition result.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the driving intention recognition method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the driving intention recognition method according to any one of claims 1 to 7 when executed.

Images