Intelligent traffic interaction system based on virtual reality

Abstract

The invention relates to the technical field of vehicle information interaction systems, in particular to an intelligent traffic interaction system based on virtual reality, and the system comprises an information collection module which is used for collecting real-time traffic information and real-time user voice information; the voice interaction module is used for performing voice analysis on real-time user voice information and performing voice synthesis on system output information; the traffic decision analysis module is used for carrying out route planning on a target planning route according to the real-time traffic information, the user preference information and a target location, and the traffic decision interaction module is used for carrying out information regulation and control on a system output information voice synthesis process according to a route planning result and the user preference information. According to the invention, through the real-time traffic information and the real-time user voice information, in combination with intelligent voice interaction and traffic decision analysis, the target planning route is optimized and adjusted at the same time, and accurate planning of the target planning route is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle information interaction systems, and in particular to an intelligent transportation interaction system based on virtual reality. Background Art

[0002] At present, when traffic congestion has become a common problem in urban travel, the real-time traffic conditions are constantly changing. The planned route provided by this system can avoid traffic jam sections for users according to the real-time congestion conditions of the road. This system can obtain new route information without affecting driving safety, greatly reducing the possibility of accidents caused by operating navigation equipment. Route planning enables hands and eyes to focus on driving. For visually impaired people or those who are not familiar with the operation of electronic devices, the route planning method of this system is more friendly and convenient.

[0003] Chinese Patent Publication No.: CN105070041B discloses an information interaction method based on an intelligent transportation interaction system, including the following steps: (1) presetting interaction information using binary coding; (2) the sending end selects the set interaction information, determines whether the same interaction information has been received. If so, the interaction information is not sent. If not, the interaction information is transmitted; (3) the receiving end receives and analyzes the interaction information, and determines whether the receiving end meets the receiving conditions included in the control information. If so, it enters step (4), otherwise the interaction information is ignored; (4) determines whether the receiving end has received the same interaction information. If so, the interaction information is ignored, otherwise the interaction information is displayed and an alarm is issued. This solution is difficult to obtain the current road traffic conditions in real time through voice interaction, and it is impossible to plan a route suitable for the user's preferences according to the user's actual driving state. Summary of the Invention

[0004] Therefore, the present invention provides an intelligent transportation interaction system based on virtual reality to overcome the problems in the prior art, such as the poor traffic interaction efficiency and low adaptability of the planned route of the intelligent cockpit driving system, due to the inability to perform information fusion analysis on warning interaction information and user driving behavior, and the inability to obtain the current road traffic conditions in real time through voice interaction and plan a route suitable for the user's preferences according to the user's actual driving state.

[0005] To achieve the above object, the present invention provides an intelligent transportation interaction system based on virtual reality, including:

[0006] An information collection module for collecting real-time traffic information and real-time user voice information;

[0007] A voice interaction module, which is used to perform voice parsing on the real-time user voice information, is also used to perform voice synthesis on the system output information, is also used to perform voice interaction standard judgment on the voice parsing result and the voice synthesis result, and corrects the voice parsing result and the system output information according to the voice interaction standard judgment result;

[0008] A traffic decision analysis module, which is used to match a target location according to the voice parsing result, is also used to output a driving behavior feature type according to the real-time traffic information, is also used to optimize the driving behavior feature type output process according to the user preference information, and is also used to plan a target planned route according to the driving behavior feature type optimization result and the target location;

[0009] A traffic decision interaction module, which is used to regulate the information in the voice synthesis process of the system output information according to the route planning result and the user preference information.

[0010] Further, in the voice interaction module, the real-time user voice information is parsed by a voice parsing method, and the voice parsing method includes:

[0011] Step A01, training a convolutional neural network model according to a preset user voice data set, outputting a convolutional neural network model that meets the preset correct rate as a user voice text recognition model, and recognizing the real-time user voice information according to the user voice text recognition model to obtain actual user voice text type information;

[0012] Step A02, performing semantic understanding on the actual user voice text type information by a natural language processing method.

[0013] Further, in the voice interaction module, the system output information is synthesized by a voice synthesis method, and the voice synthesis method includes:

[0014] Step BO1, extracting features from the system output information according to a signal processing algorithm to obtain system output feature information;

[0015] Step BO2, determining the voice synthesis type of the voice synthesis engine according to the system output feature information, determining the voice synthesis target of the voice synthesis engine according to the voice synthesis requirement scheme, and performing voice synthesis on the system output feature information according to the voice synthesis type and the voice synthesis target to obtain a voice synthesis result.

[0016] Further, the voice interaction module calculates the semantic understanding matching rate x1 according to the vector of the semantic understanding standard and the vector of the semantic understanding result and sets Represents a vector and the vector dot product of, Represents a vector magnitude of, Represents a vector magnitude of, the voice interaction module compares the semantic understanding matching rate x1 with the preset semantic understanding matching rate x0, judges the semantic understanding situation according to the comparison result, and corrects the semantic understanding result according to the judgment result, where:

[0017] When x1≥x0, the voice interaction module determines that the semantic understanding situation meets the standard, and the voice interaction module does not correct the semantic understanding result;

[0018] When x1<x0, the voice interaction module determines that the semantic understanding situation does not meet the standard, the voice interaction module corrects the semantic understanding result, and adjusts the error information of the semantic understanding result according to the default information of the semantic understanding standard;

[0019] The voice interaction module is based on the vector of the speech synthesis standard and the vector of the speech synthesis result calculates the speech synthesis matching rate y1, sets Represents a vector and the vector dot product of, Represents a vector magnitude of, Represents a vector magnitude of, the voice interaction module compares the speech synthesis matching rate y1 with the preset speech synthesis matching rate y0, judges the speech synthesis situation according to the comparison result, and corrects the system output information according to the judgment result, where:

[0020] When y1≥y0, the voice interaction module determines that the speech synthesis situation meets the standard, and the voice interaction module does not correct the system output information;

[0021] When y1<y0, the voice interaction module determines that the speech synthesis situation does not meet the standard, the voice interaction module corrects the system output information, and adjusts the error information of the system output information according to the correction method in the speech synthesis standard.

[0022] Further, the traffic decision analysis module determines the target location text information Te based on the location information obtained by matching in the location database according to the voice parsing result, and calculates the target location matching degree S1 according to the target location text information Te. It is set that S1 = max(Sim(Te, DB_i)), where DB_i represents the i-th record in the location database, Sim(Te, DB_i) represents the matching degree between the target location text information Te and the i-th record DB_i in the location database, and max(Sim(Te, DB_i)) represents the maximum value of the matching degree between the target location text information Te and the i-th record DB_i in the location database;

[0023] The traffic decision analysis module compares the target location matching degree S1 with the preset target location matching degree S0, and matches the target location according to the comparison result, where:

[0024] When S1 ≥ S0, the traffic decision analysis module determines the positioning information of the corresponding record of the target location matching degree S1 in the location database as the target location;

[0025] When S1 < S0, the traffic decision analysis module recalculates the target location matching degree S1 until S1 ≥ S0.

[0026] Further, the traffic decision analysis module calculates the driving behavior index R1 according to the user's steering wheel operation parameter A, user's pedal operation parameter B, user's vehicle acceleration C, user's vehicle trajectory parameter D, and user's line-of-sight focus parameter E. It is set that R1 = 0.25×A + 0.1×B + 0.3×C + 0.25×D + 0.1×E;

[0027] The traffic decision analysis module compares the driving behavior index R1 with the preset driving behavior index R0, and outputs the driving behavior characteristic type according to the comparison result, where:

[0028] When R1 > R0, the traffic decision analysis module outputs the driving behavior characteristic type as aggressive;

[0029] When R1 = R0, the traffic decision analysis module outputs the driving behavior characteristic type as steady;

[0030] When R1 < R0, the traffic decision analysis module outputs the driving behavior characteristic type as cautious.

[0031] Further, the traffic decision analysis module obtains the number of times K1 of user driving behavior queries according to the user preference information, compares the number of times K1 of user driving behavior queries with the preset number of times K0 of user driving behavior queries, optimizes and judges the output process of the driving behavior feature type according to the comparison result, and optimizes the driving behavior feature type output process according to the judgment result, where:

[0032] When K1 ≥ K0, the traffic decision analysis module determines not to optimize the output process of the driving behavior feature type;

[0033] When K1 < K0, the traffic decision analysis module determines to optimize the output process of the driving behavior feature type, and sets the driving behavior analysis optimization parameter β to adjust the driving behavior index R1, and sets e is the base of the natural logarithm, the adjusted driving behavior index is R2, and it is set that R2 = β × R1.

[0034] Further, when the traffic decision analysis module plans the target planned route according to the optimized result of the driving behavior feature type and the target location, it matches the target location with each driving behavior feature type in the optimized result of the driving behavior feature type to obtain the location information corresponding to each driving behavior feature type, and obtains the corresponding arrival time T1 according to the location information, and calculates the path recommendation index L1 according to the arrival time T1, the traffic congestion degree J1 and the meteorological condition index q1, and sets Wherein, represents the weight coefficient for adjusting the traffic congestion degree J1, represents the weight coefficient for adjusting the meteorological condition index q1, represents the weight coefficient for adjusting the arrival time T1, and it is set that J1 = a × q1, a represents the coefficient for adjusting the meteorological condition index q1, and 0 < a < 1;

[0035] When the traffic decision analysis module plans the target planned route according to the optimized result of the driving behavior feature type and the target location, it also compares the path recommendation index L1 with the preset path recommendation index L0, judges the line type of the target planned route according to the comparison result, and outputs according to the judgment result, where:

[0036] When L1 > L0, the traffic decision analysis module determines that the target planned route is the first recommended route, and the traffic decision analysis module outputs the first recommended route as the target planned route;

[0037] When L1 = L0, the traffic decision analysis module determines that the target planned route is the second recommended route, and the traffic decision analysis module outputs the second recommended route as the target planned route;

[0038] When L1 < L0, the traffic decision analysis module determines that the target planned route is the third recommended route, and the traffic decision analysis module outputs the third recommended route as the target planned route.

[0039] Furthermore, when the traffic decision analysis module performs route planning on the target planned route according to the optimization result of the driving behavior characteristic type and the target location, it also plans the target planned route according to the driving behavior characteristic type, where:

[0040] When the traffic decision analysis module determines that the driving behavior characteristic type is aggressive, the traffic decision analysis module calculates the aggressive path recommendation index L2 according to the road passing rate V1, sets L2 = V1 × L1, and the traffic decision analysis module compares the aggressive path recommendation index L2 with the preset path recommendation index L0, and plans the target planned route according to the comparison result, where:

[0041] If L2 > L0, the traffic decision analysis module plans the first recommended route as the target planned route;

[0042] If L2 = L0, the traffic decision analysis module plans the second recommended route as the target planned route;

[0043] If L2 < L0, the traffic decision analysis module plans the third recommended route as the target planned route;

[0044] When the traffic decision analysis module determines that the driving behavior characteristic type is steady, the traffic decision analysis module calculates the steady path recommendation index L3 according to the road condition parameter W1, the road surface flatness W2, the road pothole situation W3, and the construction section status W4, sets L3 = L1 + 0.3×W1 + 0.4×W2 + 0.3×W3 + W4, where when it is set that there is a construction section on the road, W4 = 1, and when it is set that there is no construction section on the road, W4 = 0, and the traffic decision analysis module compares the steady path recommendation index L3 with the preset path recommendation index L0, and plans the target planned route according to the comparison result, where:

[0045] If L3 > L0, the traffic decision analysis module plans the first recommended route as the target planned route;

[0046] If L3 = L0, the traffic decision analysis module plans the second recommended route as the target planned route;

[0047] If L3 < L0, the traffic decision analysis module plans the third recommended route as the target planned route;

[0048] When the traffic decision analysis module determines that the driving behavior characteristic type is cautious, the traffic decision analysis module calculates the cautious path recommendation index L4 based on the traffic participant density H1, sets L4 = 0.59 / H1 + L3, and the traffic decision analysis module compares the cautious path recommendation index L4 with the preset path recommendation index L0, and plans the target planned route according to the comparison result, where:

[0049] If L3 > L0, the traffic decision analysis module plans the first recommended route as the target planned route;

[0050] If L3 = L0, the traffic decision analysis module plans the second recommended route as the target planned route;

[0051] If L3 < L0, the traffic decision analysis module plans the third recommended route as the target planned route.

[0052] Further, the traffic decision interaction module obtains the number of times N1 that the user turns off the voice according to the route planning result and the user preference information, compares the number of times N1 that the user turns off the voice with the preset number of times N0 that the user turns off the voice, makes an information regulation judgment on the information synthesis process of the system output information according to the comparison result, and conducts information regulation on the information synthesis process of the system output information according to the judgment result, where:

[0053] When N1 < N0, the traffic decision interaction module determines not to conduct information regulation on the information synthesis process of the system output information and turns off the voice playback function;

[0054] When N1 ≥ N0, the traffic decision interaction module determines to conduct information regulation on the information synthesis process of the system output information, sets the voice broadcast preference value PH to optimize and adjust the driving behavior index R1 for the route, sets PH = 1 - (N0 - N1) / (N0 + N1), and the driving behavior index for route optimization and adjustment is R3, and sets R3 = PH × R1.

[0055] Compared with the prior art, the beneficial effects of the present invention are as follows. The system collects traffic information and user voice information in real time through the information collection module to provide accurate and timely data input for the system, ensuring that the system can make decisions and interact based on the latest traffic conditions and user needs, improving the response speed and accuracy of the system. The system parses the user voice information through the voice interaction module, synthesizes the system voice response, and judges and corrects the quality of the parsing result and the synthesis result to achieve voice interaction between the user and the system, ensuring the accuracy and fluency of the voice interaction process. The system analyzes the driving behavior characteristics according to the real-time traffic information through the traffic decision analysis module, determines the target location according to the voice parsing result, and combines the user preference information to plan the target route, improving the travel efficiency and safety of the user, and meeting the personalized needs of the user at the same time. The system adjusts the system voice output according to the route planning result through the traffic decision interaction module, and updates the system output information according to the traffic decision interaction index, improving the interaction efficiency and accuracy between the user and the system, enabling the user to timely understand the latest navigation information and system status. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is a schematic structural diagram of the intelligent traffic interaction system based on virtual reality in this embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0057] In order to make the objectives and advantages of the present invention clearer, the present invention will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0058] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention and do not limit the protection scope of the present invention.

[0059] It should be noted that in the description of the present invention, unless otherwise clearly defined and limited, the terms "installation", "connection", and "connection" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, and it can be the communication inside two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0060] Please refer to Figure 1 as shown, which is a schematic structural diagram of the intelligent traffic interaction system based on virtual reality in this embodiment. The system includes:

[0061] An information collection module for collecting real-time traffic information and real-time user voice information;

[0062] A voice interaction module for performing voice parsing on the real-time user voice information, for performing voice synthesis on the system output information, for performing voice interaction standard judgment on the voice parsing result and the voice synthesis result, and for correcting the voice parsing result and the system output information according to the voice interaction standard judgment result. The voice interaction module is connected to the information collection module;

[0063] A traffic decision analysis module for matching a target location according to the voice parsing result, for outputting a driving behavior feature type according to the real-time traffic information, for optimizing the driving behavior feature type output process according to user preference information, and for performing route planning on a target planned route according to the driving behavior feature type optimization result and the target location. The traffic decision analysis module is connected to the information collection module and the voice interaction module;

[0064] A traffic decision interaction module for regulating information in the voice synthesis process of the system output information according to the route planning result and the user preference information. The traffic decision interaction module is connected to the voice interaction module and the traffic decision analysis module.

[0065] Specifically, the system is set in the vehicle intelligent transportation interaction control terminal of virtual reality and is applicable to the traffic interaction of the intelligent cockpit driving system. Through the real-time traffic information and the real-time user voice information, intelligent voice interaction and traffic decision analysis are carried out. At the same time, according to the user preference information and the target location, the target planned route is optimized and adjusted to achieve the precise planning of the target planned route, improving the intelligent level of vehicle traffic interaction. Among them, the system uses the information collection module to collect traffic information and user voice information in real time to provide accurate and timely data input for the system, ensuring that the system can make decisions and interact based on the latest traffic conditions and user needs, improving the response speed and accuracy of the system. The system uses the voice interaction module to parse the user voice information, synthesize the system voice reply, and perform quality judgment and correction on the parsing result and the synthesis result to achieve voice interaction between the user and the system, ensuring the accuracy and fluency of the voice interaction process. The system uses the traffic decision analysis module to analyze the driving behavior characteristics according to the real-time traffic information, determine the target location according to the voice parsing result, and combine the user preference information to plan the target planned route, improving the travel efficiency and safety of users, and at the same time meeting the personalized needs of users. The system uses the traffic decision interaction module to adjust the system voice output according to the route planning result, and update the system output information according to the traffic decision interaction index, improving the interaction efficiency and accuracy between the user and the system, enabling the user to timely understand the latest navigation information and system status.

[0066] Specifically, when the information collection module collects real-time traffic information and real-time user voice information, it collects real-time traffic information through a traffic information collection device and collects real-time user voice information through an audio noise reduction device.

[0067] Specifically, the real-time traffic information refers to a set of traffic parameters collected in real time by traffic information collection devices, including user steering wheel operation parameter A, user foot pedal operation parameter B, user vehicle acceleration C, user vehicle trajectory parameter D, user line of sight focus parameter E, and external traffic situation parameters. The user steering wheel operation parameter A refers to the parameter of the user's operation on the vehicle's steering wheel during vehicle driving, such as the steering wheel angle. The user foot pedal operation parameter B refers to the parameter of the user's operation on the accelerator pedal and brake pedal during vehicle driving, such as the depression depth of the accelerator pedal. The user vehicle acceleration C refers to the acceleration value of the user vehicle during driving. The user vehicle trajectory parameter D refers to the trajectory information of the user vehicle when driving on the road, such as the driving path of the user vehicle. The user line of sight focus parameter E refers to the focus position of the user's line of sight during driving, such as the direction of the user's line of sight. The external traffic situation parameters refer to the parameters in the external traffic environment other than the user vehicle, including other vehicle operation state parameters, traffic signal state parameters, and road condition parameters. The other vehicle operation state parameters refer to the operation state parameters of other vehicles on the road other than the user vehicle. The traffic signal state parameters refer to the current state information of traffic lights and traffic signs. The road condition parameters refer to the real-time state parameters of the road, such as road surface condition parameters. The traffic information collection device refers to a set of sensors used to collect the real-time traffic information in real time, including a steering wheel rotation sensor, a pressure sensor, an acceleration sensor, a GPS sensor, a vision sensor, and a lidar. The information collection module collects the user steering wheel operation parameter A through the steering wheel rotation sensor, collects the user foot pedal operation parameter B through the pressure sensor, collects the user vehicle acceleration C through the acceleration sensor, collects the user vehicle trajectory parameter D through the GPS sensor, collects the user line of sight focus parameter E and the traffic signal state parameters through the vision sensor, and collects the other vehicle operation state parameters and road condition parameters through the lidar. The real-time user voice information refers to the voice information of the user collected in real time by an audio noise reduction device. The audio noise reduction device refers to a device used to reduce the noise of the real-time user voice information. In this embodiment, the type of the audio noise reduction device is not specifically limited, and those skilled in the art can set it according to the actual situation, as long as the requirement of collecting and reducing the noise of the real-time user voice information is met. For example, the audio noise reduction device can be set as an active noise reduction function microphone.

[0068] Specifically, the information collection module can efficiently collect real-time traffic information and real-time user voice information simultaneously. The traffic information collection device ensures the accuracy and timeliness of traffic information, and the audio noise reduction device improves the clarity and recognizability of user voice information, effectively reducing the interference of background noise.

[0069] Specifically, in the voice interaction module, the real-time user voice information is parsed by a voice parsing method, and the voice parsing method includes:

[0070] Step A01: Train a convolutional neural network model according to a preset user voice data set, output the convolutional neural network model that meets the preset accuracy rate as a user voice text recognition model, and recognize the real-time user voice information according to the user voice text recognition model to obtain actual user voice text type information;

[0071] Step A02: Conduct semantic understanding on the actual user voice text type information through natural language processing methods.

[0072] Specifically, the user speech text recognition model refers to a model that meets a preset accuracy rate obtained by training a convolutional neural network model according to a preset user speech data set. The preset user speech data set refers to a data set preset for training the convolutional neural network model in the storage form of user speech information - actual user speech text type information. The convolutional neural network model refers to a machine learning model used to extract features from real-time user speech information and predict the actual user speech text type information. In this embodiment, the training method of the convolutional neural network model is not limited, and those skilled in the art can freely set it as long as it meets the requirement of recognizing the real-time user speech information. For example, 75% of the preset user speech data set can be divided into a user speech data training set, and 25% can be divided into a user speech data test set. The user speech data training set is input into the convolutional neural network model for training, and the user speech data test set is input into the trained convolutional neural network model to optimize and iterate the parameters in the convolutional neural network model until the accuracy rate of the output result of the user speech data test set of the convolutional neural network model reaches the preset accuracy rate. Then, the convolutional neural network model is output as the user speech text recognition model. The preset accuracy rate refers to a preset value of the accuracy rate reflecting the training situation of the convolutional neural network model. In this embodiment, the value of the preset accuracy rate is not limited, and those skilled in the relevant art can freely set it as long as it meets the requirement of reflecting the training situation of the convolutional neural network model. For example, the preset accuracy rate can be set to 95%. The actual user speech text type information refers to the text information obtained by converting the real-time user speech information through the user speech text recognition model. The natural language processing method refers to a method for processing natural language text based on the theories of computer science, artificial intelligence, and linguistics. In this embodiment, the specific implementation scheme of the natural language processing method is not limited, and those skilled in the relevant art can freely set it as long as it meets the requirement of semantic understanding of the actual user speech text type information. For example, the natural language processing method can be set as a context understanding method, and the semantic understanding of the actual user speech text type information is carried out according to the context understanding method.

[0073] Specifically, through the preset user speech data set in step A01, a user speech text recognition model that meets the preset accuracy rate is trained for the convolutional neural network model, and the real-time user speech information is recognized, so as to achieve accurate recognition of the real-time user speech information. Through step A02, according to the natural language processing method, semantic understanding of the actual user speech text type information is carried out, so as to achieve accurate parsing and semantic understanding of the real-time user speech information.

[0074] Specifically, in the voice interaction module, the system output information is synthesized into voice through a voice synthesis method, and the voice synthesis method includes:

[0075] Step BO1: Extract features from the system output information according to a signal processing algorithm to obtain system output feature information;

[0076] Step BO2: Determine the voice synthesis type of the voice synthesis engine according to the system output feature information, determine the voice synthesis target of the voice synthesis engine according to the voice synthesis requirement scheme, and perform voice synthesis on the system output feature information according to the voice synthesis type and the voice synthesis target to obtain a voice synthesis result.

[0077] Specifically, the signal processing algorithm refers to the method for processing the system output information. In this embodiment, the specific implementation of the signal processing algorithm is not limited, and those skilled in the relevant art can freely set it as long as it meets the requirement of extracting features from the system output information. For example, the signal processing algorithm can be set as the Mel Frequency Cepstral Coefficient (MFCC) extraction algorithm, and features are extracted from the system output information according to the MFCC extraction algorithm. The system output information refers to the information that converts text information into voice form through the voice interaction module, including the target location and external traffic condition parameters. The system output feature information refers to the information obtained by extracting features from the system output information according to the signal processing algorithm. The voice synthesis engine refers to the software that converts the actual user voice text type information into voice. The voice synthesis type refers to the set of voice information determined by the voice synthesis engine according to the system output feature information, including voice type information and voice speed information. The voice synthesis requirement scheme refers to the preset standard for voice synthesis, such as setting a standard for voice speed. The voice synthesis target refers to the purpose of voice synthesis determined by the voice synthesis engine according to the voice synthesis requirement scheme, such as language fluency. The voice synthesis result refers to the voice synthesis of the system output feature information according to the voice synthesis type and the voice synthesis target.

[0078] Specifically, by performing feature extraction on the system output information according to the signal processing algorithm in step BO1, the accuracy and naturalness of voice synthesis are improved. By performing voice synthesis on the system output feature information according to the voice synthesis requirement scheme and the voice synthesis engine in step BO2, the personalized voice synthesis requirements of users can be met, and the flexibility and applicability of the system can be enhanced.

[0079] Specifically, the voice interaction module calculates the semantic understanding matching rate x1 according to the vector of the semantic understanding standard and the vector of the semantic understanding result and sets Denote a vector and the vector of the dot product, Denote a vector of the modulus length, Denote a vector of the modulus length. The voice interaction module compares the semantic understanding matching rate x1 with the preset semantic understanding matching rate x0, judges the semantic understanding situation according to the comparison result, and corrects the semantic understanding result according to the judgment result, where:

[0080] When x1≥x0, the voice interaction module determines that the semantic understanding situation meets the standard, and the voice interaction module does not correct the semantic understanding result;

[0081] When x1<x0, the voice interaction module determines that the semantic understanding situation does not meet the standard, the voice interaction module corrects the semantic understanding result, and adjusts the error information of the semantic understanding result according to the default information of the semantic understanding standard;

[0082] The voice interaction module calculates the speech synthesis matching rate y1 according to the vector of the speech synthesis standard and the vector of the speech synthesis result, and sets Denote a vector and the vector of the dot product, Denote a vector of the modulus length, Denote a vector of the modulus length. The voice interaction module compares the speech synthesis matching rate y1 with the preset speech synthesis matching rate y0, judges the speech synthesis situation according to the comparison result, and corrects the system output information according to the judgment result, where:

[0083] When y1≥y0, the voice interaction module determines that the speech synthesis situation meets the standard, and the voice interaction module does not correct the system output information;

[0084] When y1<y0, the voice interaction module determines that the speech synthesis situation does not meet the standard, the voice interaction module corrects the system output information, and adjusts the error information of the system output information according to the correction method in the speech synthesis standard.

[0085] Specifically, the semantic understanding standard refers to the standard that the voice interaction module can understand and correctly interpret the user's speech. For example, the voice interaction module correctly understands what the user says "Turn on the light in the car". The semantic understanding matching rate x1 refers to the vector of the semantic understanding standard and the vector of the semantic understanding result The matching degree therebetween. The preset semantic understanding matching rate x0 refers to a preset value used to measure the semantic understanding matching degree between the semantic understanding result and the semantic understanding standard. In this embodiment, the specific value of the preset semantic understanding matching rate x0 is not limited, and those skilled in the art can freely set it as long as the requirement for correcting the semantic understanding result is satisfied. For example, the preset semantic understanding matching rate x0 can be set to 98%. The semantic understanding result refers to the result of semantic understanding of the actual user speech text type information through natural language processing methods. The semantic understanding situation refers to the result of the speech interaction module's understanding of the user's speech information. The default information of the semantic understanding standard refers to the preset information used to adjust the error information when x1 < x0. The speech synthesis standard refers to the standard for evaluating whether the speech synthesis result meets the user's expected speech quality and expression requirements, such as whether the speech rate conforms to the natural speaking habit of humans. The speech synthesis matching rate y1 refers to the vector of the speech synthesis standard and the vector of the speech synthesis result The matching degree therebetween. The preset speech synthesis matching rate y0 refers to a preset value used to measure the semantic synthesis matching degree between the speech synthesis result and the speech synthesis standard. In this embodiment, the specific value of the preset speech synthesis matching rate y0 is not limited, and those skilled in the art can freely set it as long as the requirement for correcting the system output information is satisfied. For example, the preset speech synthesis matching rate y0 can be set to 98%. The speech synthesis situation refers to the result of the speech interaction module converting text information into speech. The correction method in the speech synthesis standard refers to the method used to adjust the speech synthesis result when y1 < y0. For example, if the speech rate of the speech synthesis result is too fast, the correction method is to adjust the speech parameters.

[0086] Specifically, through the speech interaction module, according to the semantic understanding standard and the speech synthesis standard, the user's speech input is accurately parsed and synthesized with high quality. When the speech interaction module determines that the semantic understanding situation does not meet the standard, it can ensure that the output information is accurate and meets the user's expectations. When the speech interaction module determines that the speech synthesis situation does not meet the standard, it can improve the accuracy and naturalness of the speech interaction.

[0087] Specifically, the traffic decision analysis module determines the target location text information Te based on the location information obtained by matching in the location database according to the speech parsing result, and calculates the target location matching degree S1 based on the target location text information Te, setting S1 = max(Sim(Te, DB_i)), where DB_i represents the i-th record in the location database, Sim(Te, DB_i) represents the matching degree between the target location text information Te and the i-th record DB_i in the location database, and max(Sim(Te, DB_i)) represents the maximum value of the matching degree between the target location text information Te and the i-th record DB_i in the location database;

[0088] The traffic decision analysis module compares the target location matching degree S1 with the preset target location matching degree S0, and matches the target location according to the comparison result, where:

[0089] When S1 ≥ S0, the traffic decision analysis module determines the positioning information of the corresponding record of the target location matching degree S1 in the location database as the target location;

[0090] When S1 < S0, the traffic decision analysis module recalculates the target location matching degree S1 until S1 ≥ S0.

[0091] Specifically, the speech parsing result refers to the result of speech parsing of the real-time user speech information by the speech parsing method, the target location text information Te refers to the text information of the target location extracted from the speech parsing result, the preset target location matching degree S0 refers to the preset value used to judge the target location matching degree S1. In this embodiment, the specific value of the preset target location matching degree S0 is not limited, and those skilled in the art can freely set it as long as it meets the requirement of matching the target location. For example, the preset target location matching degree S0 can be set to 95%. The target location refers to the final determined destination after being processed by the traffic decision analysis module. The location database refers to the database used to store the location name and the positioning information corresponding to the location name. The positioning information refers to the geographical location information corresponding to the target location matching degree in the location database.

[0092] Specifically, by calculating the target location matching degree S1 between the target location text information and each record in the location database and comparing it with the preset target location matching degree S0, the traffic decision analysis module can more accurately determine the location that the user wants to reach and reduce the error in identifying the target location.

[0093] Specifically, the traffic decision analysis module calculates the driving behavior index R1 based on the user's steering wheel operation parameter A, the user's foot pedal operation parameter B, the user's vehicle acceleration C, the user's vehicle trajectory parameter D, and the user's line of sight focus parameter E, and sets R1 = 0.25×A + 0.1×B + 0.3×C + 0.25×D + 0.1×E;

[0094] The traffic decision analysis module compares the driving behavior index R1 with the preset driving behavior index R0, and outputs the driving behavior characteristic type according to the comparison result, where:

[0095] If R1 > R0, the traffic decision analysis module outputs the driving behavior characteristic type as aggressive;

[0096] If R1 = R0, the traffic decision analysis module outputs the driving behavior characteristic type as steady;

[0097] If R1 < R0, the traffic decision analysis module outputs the driving behavior characteristic type as cautious.

[0098] Specifically, the preset driving behavior index R0 refers to a preset value used to evaluate the driving behavior characteristic type of the user. In this embodiment, the specific value of the preset driving behavior index R0 is not limited, and those skilled in the art can freely set it as long as it meets the requirement of outputting the driving behavior characteristic type. For example, the preset driving behavior index R0 can be set to 1.5. The driving behavior characteristic type refers to the driving style type comprehensively evaluated according to the user's steering wheel operation parameter A, the user's foot pedal operation parameter B, the user's vehicle acceleration C, the user's vehicle trajectory parameter D, and the user's line of sight focus parameter E, including aggressive, cautious, and steady. The aggressive type refers to the driving behavior characteristics of the user operating quickly, accelerating rapidly, and changing lanes to overtake in the driving process. The cautious type refers to the driving behavior characteristics of the user operating cautiously, decelerating slowly, and maintaining a safe distance in the driving process. The steady type refers to the driving behavior characteristics of the user operating smoothly and having a moderate acceleration in the driving process.

[0099] Specifically, by comparing the driving behavior index R1 with the preset driving behavior index R0 through the traffic decision analysis module and outputting the driving behavior characteristic type according to the comparison result, the driving behavior characteristic types of different drivers can be distinguished, and thus the evaluation of driving behavior is made more accurate.

[0100] Specifically, the traffic decision analysis module obtains the user driving behavior query count K1 according to the user preference information, compares the user driving behavior query count K1 with a preset user driving behavior query count K0, optimally determines the output process of the driving behavior feature type according to the comparison result, and optimizes the driving behavior feature type in the output process of the driving behavior feature type according to the determination result, where:

[0101] When K1 ≥ K0, the traffic decision analysis module determines not to optimize the output process of the driving behavior feature type;

[0102] When K1 < K0, the traffic decision analysis module determines to optimize the output process of the driving behavior feature type, and sets a driving behavior analysis optimization parameter β to adjust the driving behavior index R1, and sets e is the base of the natural logarithm, the adjusted driving behavior index is R2, and it is set that R2 = β × R1.

[0103] Specifically, the user preference information refers to the information that the user's attention frequency to the interaction behavior of the intelligent transportation interaction system exceeds the preset attention frequency, including the information query frequency. The information query frequency refers to the frequency of querying information types. For example, the frequency of querying road conditions and traffic regulations by the user. The attention frequency refers to the frequency of querying the information output by the system when the user interacts with the intelligent transportation interaction system. The preset attention frequency refers to a preset value used for comparison with the attention frequency. For example, querying road conditions 5 times in 10 minutes. The user driving behavior query count K1 refers to the count corresponding to the driving behavior determined according to the user preference information. The preset user driving behavior query count K0 refers to a preset value used for comparison with the user driving behavior query count K1. In this embodiment, the specific value of the preset user driving behavior query count K0 is not limited, and those skilled in the art can freely set it as long as it meets the requirement of optimizing the driving behavior feature type in the output process of the driving behavior feature type. For example, the preset user driving behavior query count K0 can be set to 5 times. The driving behavior analysis optimization parameter β refers to the parameter used to optimize the driving behavior analysis process after the traffic decision analysis module determines to optimize the driving behavior analysis process.

[0104] Specifically, the traffic decision analysis module determines the user driving behavior query count K1 according to the user preference information, compares the user driving behavior query count K1 with the preset user driving behavior query count K0, and optimizes the driving behavior feature type in the output process of the driving behavior feature type according to the comparison result, can automatically obtain the driving behavior analysis optimization parameter β, optimize the driving behavior analysis process, and improve the accuracy and practicality of the analysis.

[0105] Specifically, when the traffic decision analysis module plans the target planned route based on the optimization result of the driving behavior characteristic type and the target location, it matches the target location with each driving behavior characteristic type in the optimization result of the driving behavior characteristic type to obtain the location information corresponding to each driving behavior characteristic type, and obtains the corresponding arrival time T1 according to the location information, and calculates the path recommendation index L1 according to the arrival time T1, the traffic congestion degree J1, and the meteorological condition index q1, and sets Wherein, represents the weight coefficient used to adjust the traffic congestion degree J1, represents the weight coefficient used to adjust the meteorological condition index q1, represents the weight coefficient used to adjust the arrival time T1, and sets J1 = a×q1, where a represents the coefficient for adjusting the meteorological condition index q1, and 0 < a < 1;

[0106] When the traffic decision analysis module plans the target planned route based on the optimization result of the driving behavior characteristic type and the target location, it also compares the path recommendation index L1 with the preset path recommendation index L0, judges the route type of the target planned route according to the comparison result, and outputs according to the judgment result, where:

[0107] When L1 > L0, the traffic decision analysis module determines that the target planned route is the first recommended route, and the traffic decision analysis module outputs the first recommended route as the target planned route;

[0108] When L1 = L0, the traffic decision analysis module determines that the target planned route is the second recommended route, and the traffic decision analysis module outputs the second recommended route as the target planned route;

[0109] When L1 < L0, the traffic decision analysis module determines that the target planned route is the third recommended route, and the traffic decision analysis module outputs the third recommended route as the target planned route.

[0110] Specifically, the optimized result of the driving behavior feature type refers to the result of optimizing the output process of the driving behavior feature type according to the user preference information. The arrival time T1 refers to the time it takes for the user to travel from the current location to the target location according to the target planned route. The traffic congestion degree J1 refers to an index of the current road congestion condition. The meteorological situation index q1 refers to an index describing the impact of the current weather condition on traffic, such as rainfall. The preset route recommendation index L0 refers to a preset value used for comparison with the route recommendation index L1. In this embodiment, the specific value of the preset route recommendation index L0 is not limited, and those skilled in the art can freely set it as long as it meets the requirement of judging the route type of the target planned route. For example, the preset route recommendation index L0 can be set to 1.2. The target planned route refers to the route planned for the user from the current location to the target location according to the optimization judgment result. The route type refers to the set of target planned routes obtained by analyzing the route recommendation index L1 and the preset route recommendation index L0, including the first recommended route, the second recommended route, and the third recommended route. The first recommended route refers to the target planned route where the route recommendation index L1 is greater than the preset route recommendation index L0. The second recommended route refers to the target planned route where the route recommendation index L1 is equal to the preset route recommendation index L0. The third recommended route refers to the target planned route where the route recommendation index L1 is less than the preset route recommendation index L0. The location information refers to the location information corresponding to the target location and specifically corresponding to each driving behavior feature type.

[0111] Specifically, the traffic decision analysis module determines the arrival time T1 according to the optimized result of the driving behavior feature type and the target location, calculates the route recommendation index L1 based on the arrival time T1, the traffic congestion degree J1, and the meteorological situation index q1, compares the route recommendation index L1 with the preset route recommendation index L0, and judges the route type of the target planned route according to the comparison result, which can comprehensively evaluate the overall performance of the route, intelligently distinguish and recommend target planned routes of different levels, thereby improving travel efficiency and safety.

[0112] Specifically, when the traffic decision analysis module plans the target planned route according to the optimized result of the driving behavior feature type and the target location, it also plans the target planned route according to the driving behavior feature type, where:

[0113] When the traffic decision analysis module determines that the driving behavior characteristic type is aggressive, the traffic decision analysis module calculates the aggressive path recommendation index L2 based on the road passing rate V1, sets L2 = V1 × L1, and the traffic decision analysis module compares the aggressive path recommendation index L2 with the preset path recommendation index L0, and plans the target planned route according to the comparison result, where:

[0114] If L2 > L0, the traffic decision analysis module plans the first recommended route as the target planned route;

[0115] If L2 = L0, the traffic decision analysis module plans the second recommended route as the target planned route;

[0116] If L2 < L0, the traffic decision analysis module plans the third recommended route as the target planned route;

[0117] When the traffic decision analysis module determines that the driving behavior characteristic type is steady, the traffic decision analysis module calculates the steady path recommendation index L3 based on the road condition parameter W1, the road surface flatness W2, the road pothole situation W3, and the construction section status W4, sets L3 = L1 + 0.3×W1 + 0.4×W2 + 0.3×W3 + W4, where when it is set that there is a construction section on the road, W4 = 1, and when it is set that there is no construction section on the road, W4 = 0. The traffic decision analysis module compares the steady path recommendation index L3 with the preset path recommendation index L0, and plans the target planned route according to the comparison result, where:

[0118] If L3 > L0, the traffic decision analysis module plans the first recommended route as the target planned route;

[0119] If L3 = L0, the traffic decision analysis module plans the second recommended route as the target planned route;

[0120] If L3 < L0, the traffic decision analysis module plans the third recommended route as the target planned route;

[0121] When the traffic decision analysis module determines that the driving behavior characteristic type is cautious, the traffic decision analysis module calculates the cautious path recommendation index L4 based on the traffic participant density H1, sets L4 = 0.59 / H1 + L3, and the traffic decision analysis module compares the cautious path recommendation index L4 with the preset path recommendation index L0, and plans the target planned route according to the comparison result, where:

[0122] If L3 > L0, the traffic decision analysis module plans the first recommended route as the target planned route;

[0123] When L3 = L0, the traffic decision analysis module plans the second recommended route as the target planned route;

[0124] When L3 < L0, the traffic decision analysis module plans the third recommended route as the target planned route.

[0125] Specifically, the road passing rate V1 refers to the ratio of the actual number of vehicles passing on the road to the designed traffic capacity of the road. For example, assume that the designed traffic capacity of a certain road is 1000 vehicles per hour, and the actual number of vehicles passing on the road is 800 vehicles, then the road passing rate V1 is 80%. The road surface flatness W2 refers to the flatness of the road surface. The road pothole situation W3 refers to the actual situation of defects on the road. For example, after a heavy rain, water puddles form on a road section. The construction section status W4 refers to whether there is a section of the road where construction activities are ongoing. The traffic participant density H1 refers to the number of traffic participants such as pedestrians and vehicles existing on the road per unit area within the road area.

[0126] Specifically, by identifying the driving behavior characteristic type through the traffic decision analysis module, personalized route recommendations can be provided for users with different driving styles, improving driving comfort and safety.

[0127] Specifically, the traffic decision interaction module obtains the number of times N1 that the user closes the voice according to the route planning result and the user preference information, compares the number of times N1 that the user closes the voice with the preset number of times N0 that the user closes the voice, makes an information regulation judgment on the information voice synthesis process of the system output according to the comparison result, and conducts information regulation on the information voice synthesis process of the system output according to the judgment result, where:

[0128] When N1 < N0, the traffic decision interaction module determines not to conduct information regulation on the information voice synthesis process of the system output and closes the voice playback function;

[0129] When N1 ≥ N0, the traffic decision interaction module determines to conduct information regulation on the information voice synthesis process of the system output, sets the voice broadcast preference value PH to optimize and adjust the driving behavior index R1 for the route, sets PH = 1 - (N0 - N1) / (N0 + N1), and the driving behavior index after route optimization and adjustment is R3, and sets R3 = PH × R1.

[0130] Specifically, the route planning result refers to the result of the traffic decision analysis module planning the target planned route based on the optimization result of the driving behavior feature type, the driving behavior feature type, and the target location. The number of times N1 that the user closes the voice refers to the number of times the user actively closes the system voice broadcast during actual driving. The preset number of times N0 that the user closes the voice refers to a preset value used to compare with the number of times N1 that the user closes the voice. In this embodiment, the specific value of the preset number of times N0 that the user closes the voice is not limited, and those skilled in the art can freely set it as long as it meets the requirement of information regulation during the speech synthesis process of the system output information. For example, the preset number of times N0 that the user closes the voice can be set to 10 times. The voice playback function refers to the function of converting text information into voice information and playing it out. The voice broadcast preference value PH refers to a value used to measure the user's preference for the voice broadcast function. The speech synthesis process of the system output information refers to the process of converting text information into speech through the voice interaction module. The information regulation refers to the process of judging the number of times the user closes the voice according to the route planning result and the user preference information, and adjusting the speech synthesis process according to the judgment result.

[0131] Specifically, by comparing the number of times N1 that the user closes the voice with the preset number of times N0 that the user closes the voice, the usage strategy of the voice broadcast function can be intelligently adjusted to reduce unnecessary voice interference. By calculating the voice broadcast preference value, the user's needs and preferences for the voice broadcast can be more accurately understood, and thus more personalized services can be provided. Combining the voice broadcast preference value with the driving behavior index can further optimize the target planned route and provide a driving route that better meets the user's preferences and needs.

[0132] So far, the technical solution of the present invention has been described in combination with the preferred embodiments shown in the drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the protection scope of the present invention.

Claims

1. An intelligent traffic interaction system based on virtual reality, characterized in that: include: Information collection module, used to collect real-time traffic information and real-time user voice information; A voice interaction module, used to perform voice analysis on the real-time user voice information, and also used to perform voice synthesis on the system output information, and also used to perform voice interaction standard judgment on the voice analysis results and the voice synthesis results, and modify the voice analysis results and the system output information according to the voice interaction standard judgment results; a traffic decision analysis module, for matching a target location according to the speech analysis result, for outputting a driving behavior feature type according to the real-time traffic information, for optimizing a driving behavior feature type output process according to user preference information, and for planning a target planned route according to the driving behavior feature type optimization result and the target location; The traffic decision interaction module is used to control the system output information speech synthesis process according to the route planning results and the user preference information.

2. The intelligent traffic interaction system based on virtual reality according to claim 1 is characterized in that: In the voice interaction module, the real-time user voice information is voice analyzed by a voice analysis method, and the voice analysis method includes: Step A01, training a convolutional neural network model according to a preset user voice data set, outputting the convolutional neural network model that meets a preset accuracy rate as a user voice and text recognition model, and recognizing the real-time user voice information according to the user voice and text recognition model to obtain actual user voice and text type information; Step A02: semantically understand the actual user voice text type information through a natural language processing method.

3. The intelligent traffic interaction system based on virtual reality according to claim 2 is characterized in that: In the voice interaction module, the system output information is voice synthesized by a voice synthesis method, and the voice synthesis method includes: Step BO1, extracting features from the system output information according to a signal processing algorithm to obtain system output feature information; Step BO2, determines the speech synthesis type of the speech synthesis engine according to the system output feature information, and determines the speech synthesis target of the speech synthesis engine according to the speech synthesis requirement scheme, and performs speech synthesis on the system output feature information according to the speech synthesis type and the speech synthesis target to obtain a speech synthesis result.

4. The intelligent traffic interaction system based on virtual reality according to claim 3 is characterized in that: The voice interaction module understands the vector of the semantic standard and the vector of semantic understanding results Calculate the semantic understanding matching rate x1 and set Representation vector With vector The dot product of Representation vector The module length, Representation vector The voice interaction module compares the semantic understanding matching rate x1 with the preset semantic understanding matching rate x0, judges the semantic understanding situation according to the comparison result, and modifies the semantic understanding result according to the judgment result, wherein: When x1≥x0, the voice interaction module determines that the semantic understanding meets the standard, and the voice interaction module does not modify the semantic understanding result; When x1<x0, the voice interaction module determines that the semantic understanding does not meet the standard, and the voice interaction module corrects the semantic understanding result and adjusts the error information of the semantic understanding result according to the default information of the semantic understanding standard; The speech interaction module is based on the vector of the speech synthesis standard and the vector of speech synthesis results Calculate the speech synthesis matching rate y1 and set Representation vector With vector The dot product of Representation vector The module length, Representation vector The voice interaction module compares the voice synthesis matching rate y1 with the preset voice synthesis matching rate y0, judges the voice synthesis situation according to the comparison result, and modifies the system output information according to the judgment result, wherein: When y1≥y0, the voice interaction module determines that the voice synthesis condition meets the standard, and the voice interaction module does not modify the system output information; When y1<y0, the voice interaction module determines that the voice synthesis situation does not meet the standard, the voice interaction module corrects the system output information, and adjusts the error information of the system output information according to the correction method in the voice synthesis standard.

5. The intelligent traffic interaction system based on virtual reality according to claim 4 is characterized in that: The traffic decision analysis module determines the target location text information Te according to the location information matched in the location database by the speech analysis result, and calculates the target location matching degree S1 according to the target location text information Te, and sets S1=max(Sim(Te,DB_i)), wherein DB_i represents the i-th record in the location database, Sim(Te,DB_i) represents the matching degree between the target location text information Te and the i-th record DB_i in the location database, and max(Sim(Te,DB_i)) represents the maximum value of the matching degree between the target location text information Te and the i-th record DB_i in the location database; The traffic decision analysis module compares the target location matching degree S1 with the preset target location matching degree S0, and matches the target location according to the comparison result, wherein: When S1≥S0, the traffic decision analysis module determines the location information corresponding to the target location matching degree S1 recorded in the location database as the target location; When S1<S0, the traffic decision analysis module recalculates the target location matching degree S1 until S1≥S0.

6. The intelligent traffic interaction system based on virtual reality according to claim 5 is characterized in that: The traffic decision analysis module calculates the driving behavior index R1 according to the user's steering wheel operation parameter A, the user's pedal operation parameter B, the user's vehicle acceleration C, the user's vehicle trajectory parameter D and the user's sight focus parameter E, and sets R1=0.25×A+0.1×B+0.3×C+0.25×D+0.1×E; The traffic decision analysis module compares the driving behavior index R1 with the preset driving behavior index R0, and outputs the driving behavior feature type according to the comparison result, wherein: R1>R0, the traffic decision analysis module outputs the driving behavior characteristic type as aggressive; R1=R0, the traffic decision analysis module outputs the driving behavior feature type as a robust type; R1<R0, the traffic decision analysis module outputs the driving behavior characteristic type as cautious type.

7. The intelligent traffic interaction system based on virtual reality according to claim 6 is characterized in that: The traffic decision analysis module obtains the user driving behavior query number K1 according to the user preference information, and compares the user driving behavior query number K1 with the preset user driving behavior query number K0, optimizes the driving behavior feature type output process according to the comparison result, and optimizes the driving behavior feature type output process according to the judgment result, wherein: When K1≥K0, the traffic decision analysis module determines not to optimize the driving behavior feature type output process; When K1<K0, the traffic decision analysis module determines to optimize the output process of the driving behavior feature type, and sets the driving behavior analysis optimization parameter β to adjust the driving behavior index R1, setting β=0.7*e -0.5(K1-K0) , e is the base of the natural logarithm, the adjusted driving behavior index is R2, and R2 = β × R1 is set.

8. The intelligent traffic interaction system based on virtual reality according to claim 7 is characterized in that: When the traffic decision analysis module plans the target planned route according to the driving behavior feature type optimization result and the target location, the target location is matched with each driving behavior feature type in the driving behavior feature type optimization result to obtain the location information corresponding to each driving behavior feature type, and the corresponding arrival time T1 is obtained according to the location information, and the path recommendation index L1 is calculated according to the arrival time T1, the traffic congestion level J1 and the weather condition index q1, and the setting in, represents a weight coefficient for adjusting the traffic congestion level J1, represents the weight coefficient used to adjust the meteorological condition index q1, represents the weight coefficient used to adjust the arrival time T1, set J1=a×q1, where a represents a coefficient for adjusting the meteorological condition index q1, 0<a<1; When the traffic decision analysis module plans the target planned route according to the optimization result of the driving behavior characteristic type and the target location, it also compares the path recommendation index L1 with the preset path recommendation index L0, judges the line type of the target planned route according to the comparison result, and outputs it according to the judgment result, wherein: When L1>L0, the traffic decision analysis module determines that the target planned route is the first recommended route, and the traffic decision analysis module outputs the first recommended route as the target planned route; When L1=L0, the traffic decision analysis module determines that the target planned route is the second recommended route, and the traffic decision analysis module outputs the second recommended route as the target planned route; When L1<L0, the traffic decision analysis module determines that the target planned route is the third recommended route, and the traffic decision analysis module outputs the third recommended route as the target planned route.

9. The intelligent traffic interaction system based on virtual reality according to claim 8 is characterized in that: When the traffic decision analysis module performs route planning on the target planned route according to the driving behavior feature type optimization result and the target location, the target planned route is also planned according to the driving behavior feature type, wherein: When the traffic decision analysis module determines that the driving behavior characteristic type is an aggressive type, the traffic decision analysis module calculates the aggressive path recommendation index L2 according to the road traffic rate V1, sets L2=V1×L1, and compares the aggressive path recommendation index L2 with the preset path recommendation index L0, and plans the target planning route according to the comparison result, wherein: If L2>L0, the traffic decision analysis module plans the first recommended route as the target planned route; If L2=L0, the traffic decision analysis module plans the second recommended route as the target planned route; If L2<L0, the traffic decision analysis module plans the third recommended route as the target planned route; When the traffic decision analysis module determines that the driving behavior feature type is robust, the traffic decision analysis module calculates the robust path recommendation index L3 according to the road condition parameter W1, the road surface flatness W2, the road pothole situation W3 and the construction section state W4, and sets L3=L1+0.3×W1+0.4×W2+0.3×W3+W4, wherein, when the road has a construction section, W4=1, and when the road does not have a construction section, W4=0, the traffic decision analysis module compares the robust path recommendation index L3 with the preset path recommendation index L0, and plans the target planning route according to the comparison result, wherein: If L3>L0, the traffic decision analysis module plans the first recommended route as the target planned route; If L3=L0, the traffic decision analysis module plans the second recommended route as the target planned route; If L3<L0, the traffic decision analysis module plans the third recommended route as the target planned route; When the traffic decision analysis module determines that the driving behavior characteristic type is cautious, the traffic decision analysis module calculates the cautious path recommendation index L4 according to the traffic participant density H1, sets L4=0.59 / H1+L3, and compares the cautious path recommendation index L4 with the preset path recommendation index L0, and plans the target planning route according to the comparison result, wherein: If L3>L0, the traffic decision analysis module plans the first recommended route as the target planned route; If L3=L0, the traffic decision analysis module plans the second recommended route as the target planned route; If L3<L0, the traffic decision analysis module plans the third recommended route as the target planned route.

10. The intelligent traffic interaction system based on virtual reality according to claim 9 is characterized in that: The traffic decision interaction module obtains the number of times N1 the user turns off the voice according to the route planning result and the user preference information, and compares the number of times N1 the user turns off the voice with the preset number of times N0 the user turns off the voice, and performs information regulation and judgment on the system output information voice synthesis process according to the comparison result, and performs information regulation and control on the system output information voice synthesis process according to the judgment result, wherein: When N1<N0, the traffic decision interaction module determines not to perform information regulation on the system output information speech synthesis process, and turns off the speech playback function; When N1≥N0, the traffic decision interaction module determines to perform information regulation on the system output information speech synthesis process, and sets the voice broadcast preference value PH to optimize the route of the driving behavior index R1, setting PH=1-(N0-N1) / (N0+N1), the driving behavior index of the route optimization adjustment is R3, and setting R3=PH×R1.

Images