Path optimization method and device and computer equipment

Abstract

The invention relates to a path optimization method and device and computer equipment, and relates to the technical field of navigation. The method comprises the following steps: in a vehicle driving process, determining a path adjustment amplitude according to emotion associated data of a driver of the vehicle and a current navigation path of the vehicle; determining a candidate navigation path matched with the emotion associated data; and determining an optimized navigation path corresponding to the current navigation path according to the path adjustment amplitude and the candidate navigation path. By adopting the method, the navigation path can be optimized according to the emotional state of the driver.

Description

Technical Field

[0001] This application relates to the technical field of navigation, and particularly to a path optimization method, apparatus, and computer device. Background Art

[0002] Current in-vehicle navigation systems usually rely on GPS (Global Positioning System), road information, and real-time traffic data for path planning to provide navigation paths for drivers.

[0003] However, in traditional technologies, navigation paths that can reach the destination faster are often provided for drivers only from perspectives such as path distance and driving time, lacking the perception and attention to the driver's emotional state. Therefore, the personal emotional needs of the driver are ignored, making the provided navigation paths not in line with the driver's current emotional state, resulting in a single navigation path selection, lack of intelligence and personalization, and also affecting the driver's driving experience and driving safety. Summary of the Invention

[0004] Based on this, to address the above technical problems, it is necessary to provide a path optimization method, apparatus, and computer device that can optimize navigation paths according to the driver's emotional state.

[0005] In a first aspect, this application provides a path optimization method, including:

[0006] During the driving process of the vehicle, determine the path adjustment amplitude according to the emotion-related data of the driver of the vehicle and the current navigation path of the vehicle;

[0007] Determine candidate navigation paths that match the emotion-related data;

[0008] Determine the optimized navigation path corresponding to the current navigation path according to the path adjustment amplitude and the candidate navigation paths.

[0009] In one embodiment, determining the path adjustment amplitude according to the emotion-related data of the driver of the vehicle and the current navigation path of the vehicle includes: determining the current emotional state of the driver according to the emotion-related data of the driver of the vehicle; determining the target path score according to the current emotional state and the current path score of the current navigation path of the vehicle; and determining the path adjustment amplitude according to the current path score and the target path score.

[0010] In one embodiment, determining a target path score according to the current emotional state and the current path score of the current navigation path of the vehicle includes: determining an emotional index of the driver and an emotional adjustment parameter corresponding to the current emotional state according to the current emotional state; determining the target path score according to the emotional index, the emotional adjustment parameter, and the current path score of the current navigation path of the vehicle.

[0011] In one embodiment, determining the emotional index of the driver according to the current emotional state includes: determining a preset weight of emotional association data according to the current emotional state; using the preset weight to perform weighted summation on the emotional association data to obtain the emotional index of the driver.

[0012] In one embodiment, determining the target path score according to the emotional index, the emotional adjustment parameter, and the current path score of the current navigation path of the vehicle includes: adjusting the emotional index using the emotional adjustment parameter to obtain a target index; determining the target path score according to the product of the target index and the current path score of the current navigation path of the vehicle.

[0013] In one embodiment, determining the path adjustment amplitude according to the current path score and the target path score includes: determining the difference between the target path score and the current path score; determining the target proportion of the difference in the current path score; in the corresponding relationship between the preset adjustment amplitude and the proportion range, searching for the adjustment amplitude corresponding to the proportion range to which the target proportion belongs, and using the found adjustment amplitude as the path adjustment amplitude.

[0014] In one embodiment, determining the optimized navigation path corresponding to the current navigation path according to the path adjustment amplitude and the candidate navigation paths includes: determining the current navigation path as the optimized navigation path when the path adjustment amplitude indicates that the current navigation path matches the emotional association data; when the path adjustment amplitude indicates that the current navigation path does not match the emotional association data, selecting a target navigation path from the candidate navigation paths as the optimized navigation path corresponding to the current navigation path; wherein, the proportion of the difference section between the target navigation path and the non-traveled section of the current navigation path in the non-traveled section is within the proportion range corresponding to the path adjustment amplitude.

[0015] In one embodiment, when the path adjustment amplitude indicates that the current navigation path does not match the emotional association data, the method further includes: outputting a prompt message; wherein, the prompt message is used to prompt the driver to switch the navigation path of the vehicle to the optimized navigation path.

[0016] In a second aspect, the present application further provides a path optimization device, including:

[0017] An amplitude determination module, configured to determine an amplitude of path adjustment according to emotion-related data of a driver of a vehicle and a current navigation path of the vehicle during the driving of the vehicle;

[0018] A path determination module, configured to determine a candidate navigation path matching the emotion-related data;

[0019] A path optimization module, configured to determine an optimized navigation path corresponding to the current navigation path according to the amplitude of path adjustment and the candidate navigation path.

[0020] In a third aspect, the present application further provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the following steps are implemented: during the driving of the vehicle, determine an amplitude of path adjustment according to emotion-related data of a driver of the vehicle and a current navigation path of the vehicle; determine a candidate navigation path matching the emotion-related data; determine an optimized navigation path corresponding to the current navigation path according to the amplitude of path adjustment and the candidate navigation path.

[0021] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: during the driving of the vehicle, determine an amplitude of path adjustment according to emotion-related data of a driver of the vehicle and a current navigation path of the vehicle; determine a candidate navigation path matching the emotion-related data; determine an optimized navigation path corresponding to the current navigation path according to the amplitude of path adjustment and the candidate navigation path.

[0022] In a fifth aspect, the present application further provides a computer program product, including a computer program. When the computer program is executed by a processor, the following steps are implemented: during the driving of the vehicle, determine an amplitude of path adjustment according to emotion-related data of a driver of the vehicle and a current navigation path of the vehicle; determine a candidate navigation path matching the emotion-related data; determine an optimized navigation path corresponding to the current navigation path according to the amplitude of path adjustment and the candidate navigation path.

[0023] The above path optimization method, device, and computer device determine the path adjustment amplitude based on the emotion-related data of the vehicle driver and the current navigation path of the vehicle during vehicle driving, and determine a candidate navigation path that matches the above emotion-related data. Furthermore, an optimized navigation path corresponding to the current navigation path can be determined based on the path adjustment amplitude and the candidate navigation path. In this way, during vehicle driving, when providing a navigation path for the driver, considering the personal emotion needs of the driver, a navigation path that conforms to the driver's current emotional state can be provided for the driver, achieving the effect of adaptively optimizing the navigation path according to the driver's current emotional state. This can not only enrich the factors affecting the selection of the navigation path, improve the intelligence and personalization of the navigation path selection, but also enhance the driving experience and driving safety of the driver, and effectively relieve the driving pressure of the driver. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for describing the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0025] Figure 1 It is a schematic flowchart of a path optimization method provided in an embodiment;

[0026] Figure 2 It is a schematic flowchart of a method for determining a path adjustment amplitude provided in an embodiment;

[0027] Figure 3 It is a schematic flowchart of a method for determining a target path score provided in an embodiment;

[0028] Figure 4 It is a schematic flowchart of a method for determining a path adjustment amplitude provided in another embodiment;

[0029] Figure 5 It is a schematic flowchart of a path optimization method provided in another embodiment;

[0030] Figure 6 It is a schematic flowchart of a path optimization method provided in yet another embodiment;

[0031] Figure 7 It is a structural block diagram of a path optimization device provided in an embodiment;

[0032] Figure 8 It is an internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0033] In order to make the objectives, technical solutions and advantages of the present application more clear and understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0034] In traditional technologies, often only from the perspectives of path distance, driving time, etc., a navigation path that can reach the destination faster is provided for the driver, but the perception and attention to the driver's emotional state are lacking. Therefore, the individual emotional needs of the driver are ignored, resulting in the provided navigation path not conforming to the driver's current emotional state, leading to a single navigation path selection, lack of intelligence and personalization, and also affecting the driver's driving experience and driving safety.

[0035] Based on this, in order to solve the above technical problems, in an exemplary embodiment, a path optimization method is provided. This method can be applied to a computer device, which can be a server or a terminal. Among them, the server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services; the terminal can be an in-vehicle terminal in a vehicle, etc. Hereinafter, an example of applying this method to an in-vehicle terminal will be described. As Figure 1 shown, this method may include the following steps:

[0036] S101, during the driving of the vehicle, determine the path adjustment amplitude according to the emotion-related data of the driver of the vehicle and the current navigation path of the vehicle.

[0037] Generally, a person's physiological data, voice feature data, behavior data, etc. can reflect a person's emotional state to a certain extent. For example, when a person is in different emotional states, their physiological data and voice characteristic data are often different. Exemplarily, the heart rate of a person in a normal state is usually between 60 and 80 beats per minute, while the heart rate of a person in an anxious state is usually between 80 and 100 beats per minute; Exemplarily, the voice volume of a person in a pleasant state is usually between 75 and 85 dB (decibel), while the voice volume of a person in a fatigued state is usually less than 70 dB. Also, for example, in the face of the same scenario, the behaviors of people in different emotional states are often different. Exemplarily, when a fatigued driver is driving, their braking operation is usually slower and there are fewer lane-changing operations, and the driving behavior is relatively single, while when a stressed driver is driving, they often change lanes frequently and rapidly and perform more emergency braking operations.

[0038] Based on this, the data that can reflect a person's emotional state can be called emotion-related data. Since the above-mentioned physiological data, voice feature data, and behavior data can reflect a person's emotional state from different dimensions, the above-mentioned physiological data, voice feature data, and behavior data can be used as a type of emotion-related data respectively. And each type of the above-mentioned emotion-related data can include one or more emotion-related data.

[0039] For example, the above-mentioned physiological data can include heart rate, skin conductivity, facial expression data, eye movement tracking data, etc. Among them, the facial expression data can further include the tilt angle of the eyebrows, the upward / downward angle of the corners of the mouth, the opening range of the eyes, etc., and the eye movement tracking data can further include the blink frequency, fixation time, eyeball movement data, etc.; Another example is that the above-mentioned voice feature data can include speech rate, pitch, volume, tone, frequency of intonation changes, etc.

[0040] According to different scenarios that a person faces, the above-mentioned behavior data can be various types of behavior data that match the scenarios a person faces. For example, in the vehicle driving scenario, the above-mentioned behavior data can be the driving behavior data of the driver, which can include the frequency of lane-changing operations, the number of hard brakes, the number of hard accelerations, etc.

[0041] In an optional embodiment, during the vehicle driving process, at least one type of data among the physiological data, voice feature data, and driving behavior data of the vehicle's driver can be obtained as the emotion-related data of the vehicle's driver. Optionally, the above-mentioned physiological data can include at least one of heart rate, skin conductivity, facial expression data, and eye movement tracking data.

[0042] In this way, after obtaining the emotion-related data of the vehicle's driver, the path adjustment amplitude can be determined based on the emotion-related data and the current navigation path.

[0043] To ensure a smooth arrival at the destination and driving safety, the vehicle's driver usually selects a navigation path from the navigation paths provided by the navigation software before starting driving and uses the selected navigation path for navigation during driving. That is, during the vehicle driving process, the vehicle travels along the selected navigation path. Then, during the vehicle driving process, the selected navigation path can be called the vehicle's current navigation path.

[0044] The path adjustment amplitude can characterize the matching degree between the emotion-related data and the current navigation path. Furthermore, the path adjustment amplitude indicates the degree of adjustment of the current navigation path when optimizing the current navigation path. Optionally, the larger the path adjustment amplitude, the smaller the matching degree between the emotion-related data and the current navigation path, and the greater the degree of adjustment of the current navigation path when optimizing the current navigation path. Correspondingly, the smaller the path adjustment amplitude, the greater the matching degree between the emotion-related data and the current navigation path, and the smaller the degree of adjustment of the current navigation path when optimizing the current navigation path.

[0045] In an alternative embodiment, the emotional state of the vehicle driver can be determined based on the emotion-related data of the vehicle driver. Subsequently, the path label corresponding to the emotional state of the vehicle driver is determined, and the path label corresponding to the emotional state is matched with the path label of the current navigation path of the vehicle. In this way, the path adjustment amplitude can be determined according to the obtained matching result.

[0046] S102. Determine the candidate navigation path that matches the emotion-related data.

[0047] It can be understood that when the starting point and the destination are determined, the navigation software can usually determine multiple navigation paths from the starting point to the destination through path planning, and different navigation paths have different characteristics. For example, the navigation path with the shortest distance, the navigation path with the shortest driving time, the navigation path with a large number of complex intersections and traffic lights, the navigation path with less traffic flow, the navigation path with a rest area along the way, the navigation path with a natural scenic area along the way, etc. In order to relieve driving stress and improve driving safety, in different emotional states, the navigation paths selected by the driver have different characteristics. For example, in a normal state, the driver often chooses the navigation path with the shortest distance or the shortest driving time; in an anxious state, the driver often avoids the navigation path with complex sections, congested areas, and dense traffic signals, and chooses a navigation path with simple and intuitive road conditions to avoid increasing psychological pressure; in a fatigued state, the driver often chooses the navigation path with the shortest distance or the shortest driving time, tries to avoid long driving, and will preferentially choose the navigation path with a service area or a rest area along the way for timely rest; in a stressed state, the driver often avoids the navigation path with complex road conditions and intersections, and chooses a navigation path with a wide road surface and less traffic flow to relieve stress; in a pleasant state, the driver often hopes to have a more pleasant driving experience and usually chooses a scenic route or a navigation path with a beautiful surrounding environment to enhance the pleasantness.

[0048] Based on this, during the driving process of the vehicle, after obtaining the emotion-related data of the driver of the vehicle, among the multiple navigation paths determined from the departure place to the destination, a candidate navigation path matching the emotion-related data can be determined.

[0049] Optionally, when planning a navigation path from the departure place to the destination, path labels can be added to each determined navigation path according to path information such as the road conditions, traffic flow, number of complex intersections, number of traffic lights, scenery along the way, driving time, path length, number of rest areas, and number of service areas of the navigation path. After obtaining the emotion-related data of the driver of the vehicle, since the emotion-related data can reflect the emotional state of the driver of the vehicle, the emotional state of the driver of the vehicle can be determined according to the emotion-related data. In this way, according to the preset correspondence between the emotional state and the path label, among the above-mentioned multiple navigation paths, a navigation path whose path label matches the emotional state of the driver of the vehicle can be selected as the candidate navigation path matching the emotion-related data of the driver of the vehicle.

[0050] For example, it is preset in advance that the path labels corresponding to the normal state include the shortest path and the shortest driving time; the path labels corresponding to the anxious state include simple road conditions, few complex intersections, little traffic flow, and few traffic lights; the path labels corresponding to the fatigued state include the shortest path, the shortest driving time, the presence of service areas, and the presence of rest areas; the path labels corresponding to the stressed state include simple road conditions, few complex intersections, little traffic flow, and wide roads; the path labels corresponding to the pleasant state include beautiful scenery and the presence of natural scenic areas. In this way, when the emotion-related data of the driver of the vehicle represents that the emotional state of the driver of the vehicle is the fatigued state, a navigation path with path labels such as the shortest path, the shortest driving time, the presence of service areas, and the presence of rest areas can be selected as the candidate navigation path matching the emotion-related data of the driver of the vehicle.

[0051] S103. Determine an optimized navigation path corresponding to the current navigation path according to the path adjustment amplitude and the candidate navigation path.

[0052] As mentioned above, the path adjustment amplitude can represent the matching degree between the emotion-related data and the current navigation path. Furthermore, the path adjustment amplitude indicates the adjustment degree of the current navigation path when optimizing the path of the current navigation path. The candidate navigation path is a navigation path that matches the emotion-related data of the driver of the vehicle. Therefore, the adjustment degree of the current navigation path can be determined according to the path adjustment amplitude. Thus, according to the adjustment degree, a navigation path whose path difference from the current navigation path of the vehicle meets the above adjustment degree can be determined from the candidate navigation paths as the optimized navigation path corresponding to the current navigation path. Then, after obtaining the above navigation path, it can be determined that the optimization of the current navigation path is completed.

[0053] In an optional embodiment, after determining the optimized navigation path corresponding to the current navigation path, prompt information can be output to the driver of the vehicle in various ways such as playing voice, pop-up windows, etc., to prompt the driver that the above optimized navigation path can be adopted for navigation to obtain a better driving experience.

[0054] In an optional embodiment, in some cases, since there may be at least two navigation paths with relatively close path information, at least two optimized navigation paths corresponding to the current navigation path can be determined from the above candidate navigation paths. In this way, in order to determine the optimized navigation path finally recommended to the driver, according to the driver's navigation path selection preference, the optimized navigation path finally recommended to the driver can be selected from the at least two optimized navigation paths corresponding to the current navigation path. For example, if the driver's navigation path selection preference includes less toll, the optimized navigation path with fewer highway sections can be selected from the at least two optimized navigation paths corresponding to the current navigation path as the optimized navigation path finally recommended to the driver.

[0055] The above path optimization method determines the path adjustment amplitude according to the emotion correlation data of the driver of the vehicle and the current navigation path of the vehicle during the driving process of the vehicle, and determines the candidate navigation paths matching the above emotion correlation data. Furthermore, the optimized navigation path corresponding to the current navigation path can be determined according to the above path adjustment amplitude and candidate navigation paths. In this way, during the driving process of the vehicle, when providing the navigation path for the driver, considering the personal emotion needs of the driver, a navigation path that conforms to the current emotion state of the driver can be provided for the driver, achieving the effect of adaptively optimizing the navigation path according to the current emotion state of the driver. It can not only enrich the factors affecting the navigation path selection, improve the intelligence and personalization of the navigation path selection, but also improve the driving experience and driving safety of the driver, and effectively relieve the driving pressure of the driver.

[0056] Based on the above embodiments, in an exemplary embodiment, the determination of the path adjustment amplitude in S101 is further refined. Optionally, as Figure 2 shown, the following steps can be included:

[0057] S201, determine the current emotion state of the driver according to the emotion correlation data of the driver of the vehicle.

[0058] During the driving process of the vehicle, after obtaining the emotion correlation data of the driver of the vehicle, since the emotion correlation data is the data reflecting the emotion state of people, the current emotion state of the driver of the vehicle can be determined according to the above emotion correlation data.

[0059] In an optional embodiment, the determination of the current emotional state in S201 above can be further refined, and can include any one of the following:

[0060] 1) Input the emotional association data of the driver of the vehicle into an emotional state classification model to obtain the current emotional state of the driver.

[0061] In this embodiment, models such as random forests and deep learning classifiers can be used to train the emotional state classification model. Among them, the emotional state classification model is obtained by training the model with emotional association data as the input and emotional state as the label.

[0062] Optionally, during the driving process of multiple historical vehicles, the emotional association data of the drivers of the vehicles can be obtained, and the emotional states of the drivers of the vehicles can be obtained. Furthermore, the above-mentioned emotional association data of the drivers of the vehicles can be used as the input, and the emotional states of the drivers of the vehicles can be used as the labels to train a preset model to obtain an emotional state classification model.

[0063] Among them, during the training process of the above-mentioned preset model, the preset model will learn the relationship between the emotional association data of each driver and the emotional state of the driver, establish a prediction method for predicting the emotional state of the driver based on the emotional association data of each driver, and through parameter adjustment, make the predicted emotional state gradually approach the real emotional state of the driver until the loss value between the two satisfies a preset loss condition. For example, the loss value between the two is less than a preset threshold to obtain an emotional state classification model. Therefore, during the driving process of the vehicle, after obtaining the emotional association data of the driver of the vehicle, the above-mentioned emotional association data of the driver of the vehicle can be input into the emotional state classification model to obtain the prediction result output by the emotional state classification model, and this prediction result is the current emotional state of the driver.

[0064] 2) Determine the target determination rule satisfied by the emotional association data of the driver of the vehicle from the corresponding relationship between the preset emotional state and the determination rule, and determine the emotional state corresponding to the target determination rule as the current emotional state of the driver.

[0065] As described above, the emotional association data of a person is different under different emotional states. Therefore, through the statistical analysis of the emotional association data of a large number of people in the same emotional state, the determination rules corresponding to each emotional state can be determined. Among them, the determination rule corresponding to each emotional state includes the data conditions that the emotional association data of people in this emotional state conforms to obtained through statistical analysis. Then, after obtaining the emotional association data of the driver of the vehicle, the target determination rule satisfied by the emotional association data of the driver of the vehicle can be determined. Furthermore, from the corresponding relationship between the preset emotional state and the determination rule, the emotional state corresponding to the target determination rule can be searched, and the searched emotional state can be determined as the current emotional state of the driver.

[0066] 3) Determine the target state label corresponding to the emotional association data of the driver of the vehicle from the corresponding relationship between the preset state label and the data condition, and determine the emotional state represented by the target state label with the largest quantity as the current emotional state of the driver.

[0067] As described above, the data conditions satisfied by the same emotional association data under different emotions are different. Therefore, through the statistical analysis of the data values of the same emotional association data under different emotional states, the data conditions satisfied by each emotional association data under different emotional states can be determined. Thus, for each emotional association data, the corresponding relationship between the state label and the data condition of this emotional association data can be established. Furthermore, after obtaining the emotional association data of the driver of the vehicle, for each emotional association data of the driver of the vehicle, the target state label corresponding to the data condition satisfied by this emotional association data of the driver of the vehicle can be determined from the corresponding relationship between the state label and the data condition of this emotional association data. In this way, according to the quantity of the emotional association data of the driver of the vehicle, one or more target state labels can be obtained, and then the emotional state represented by the target state label with the largest quantity can be determined as the current emotional state of the driver.

[0068] Optionally, in some cases, the data conditions satisfied by some emotion-related data may overlap under different emotional states. For example, when the emotional state is the normal state, the skin conductivity value is between 15–25 μS (micro Siemens), and when the emotional state is the fatigue state, the skin conductivity is between 10-20 μS. Obviously, there is an overlapping range of 15-20 μS between the numerical ranges of the skin conductivity values in the above two emotional states. Therefore, when determining the target state label corresponding to the emotion-related data of the vehicle driver, if there is emotion-related data that satisfies the data conditions of multiple emotional states, multiple target state labels can be determined based on this emotion-related data, and the current emotional state of the driver can be determined according to the emotional states guaranteed by the same number of target state labels. That is, when determining the target state label corresponding to the emotion-related data of the vehicle driver, for each emotion-related data, one or more target state labels corresponding to the data conditions satisfied by this emotion-related data of the vehicle driver are determined from the corresponding relationship between the state label and the data condition of this emotion-related data.

[0069] S202. Determine a target path score according to the current emotional state and the current path score of the current navigation path of the vehicle.

[0070] Generally, when the departure place and the destination are determined, when the navigation software performs path planning, it usually uses path planning algorithms such as the shortest time (such as the Dijkstra algorithm) or the shortest path (such as the A* algorithm), relying on real-time traffic data (such as traffic flow, signal light status, construction and accident information), and external factors such as road surface conditions, to determine multiple navigation paths from the departure place to the destination, and score each determined navigation path.

[0071] In this way, during the vehicle driving process, since the current navigation path of the vehicle has a current path score, the target path score can be determined according to the current emotional state and the current path score of the current navigation path of the vehicle. Among them, the target path score can be regarded as the score of the optimized navigation path corresponding to the current navigation path determined in S103 above, that is, the target path score is used to evaluate the above optimized navigation path.

[0072] In an optional embodiment, the adjustment weight of the current path score can be determined according to the above current emotional state, and then the product of the current path score and the adjustment weight can be determined as the target path score.

[0073] S203. Determine the path adjustment amplitude according to the current path score and the target path score.

[0074] As described above, the target path score is used to evaluate the optimized navigation path. Therefore, the difference between the target path score and the current path score can characterize the difference between the current navigation path and the optimized navigation path. Optionally, the greater the difference between the target path score and the current path score, the greater the difference between the current navigation path and the optimized navigation path. Furthermore, when optimizing the current navigation path, the greater the degree of adjustment of the current navigation path. Correspondingly, the smaller the difference between the target path score and the current path score, the smaller the difference between the current navigation path and the optimized navigation path. Furthermore, when optimizing the current navigation path, the smaller the degree of adjustment of the current navigation path. In this way, after obtaining the above target path score, the path adjustment amplitude can be determined according to the current path score and the target path score. In an optional embodiment, the proportion of the current path score in the target path score can be determined as the path adjustment amplitude.

[0075] In this embodiment, when determining the path adjustment amplitude, the current path score of the vehicle's current navigation path is introduced, and the path adjustment amplitude is determined according to the current path score and the target path score of the optimized navigation path to be determined. Thus, the path score is involved in the process of determining the path adjustment amplitude, realizing the quantification of the determination of the path adjustment score, improving the accuracy of the obtained path adjustment amplitude, and further improving the emotional matching degree between the obtained optimized navigation path and the driver's mood of the vehicle, and improving the optimization effect of optimizing the current navigation path.

[0076] Based on the above embodiments, in an exemplary embodiment, the determination of the target path score in S202 above is further refined. Optionally, as Figure 3 shown, the following steps may be included:

[0077] S301, according to the current emotional state, determine the driver's emotional index and the emotional adjustment parameter corresponding to the current emotional state.

[0078] It can be understood that even for the same emotional state, it can have different intensities. For example, even in the state of anxiety, there are differences between general anxiety and extreme anxiety. Based on this, the emotional index can be used to characterize the intensity of the current emotional state of the driver of the vehicle.

[0079] Optionally, the greater the emotional index, the greater the intensity of the current emotional state of the driver of the vehicle. Exemplarily, when the current emotional state of the driver of the vehicle is anxiety, the greater the emotional index, the more intense the anxiety of the driver. Correspondingly, the smaller the emotional index, the smaller the intensity of the current emotional state of the driver of the vehicle.

[0080] Optionally, an emotion index prediction model with the emotional state and emotion-related data as inputs and the emotion index as the label can be established in advance. Thus, the current emotional state of the vehicle driver and the above-mentioned emotion-related data can be input into the emotion index prediction model, and the prediction result output by the emotion index prediction model can be obtained. Then, the prediction result is the emotion index of the vehicle driver.

[0081] In an optional embodiment, the determination of the emotion index in S301 above is further refined. Optionally, the following steps may be included:

[0082] 1. Determine the preset weight of the emotion-related data according to the current emotional state.

[0083] The reflection ability of each emotion-related data to different emotional states is different. That is, when determining different emotional states, the contribution (importance) of the same emotion-related data is different. Therefore, the preset weight of the driver's emotion-related data can be determined according to the current emotional state of the above-mentioned driver.

[0084] Optionally, the corresponding relationship between the emotional state and the preset weight of the emotion-related data can be preset in advance. Thus, after obtaining the current emotional state of the above-mentioned driver, the preset weight of the emotion-related data corresponding to the current emotional state of the driver can be determined in the corresponding relationship between the emotional state and the preset weight of the emotion-related data, and then the preset weight of the driver's emotion-related data is obtained.

[0085] 2. Use the preset weight to perform weighted summation on the emotion-related data to obtain the emotion index of the driver.

[0086] After obtaining the preset weight of the driver's emotion-related data, the preset weight can be used to perform weighted summation on the above-mentioned driver's emotion-related data, and the obtained sum value is the emotion index of the driver.

[0087] Optionally, when there are at least two emotion-related data of the driver, the preset weight includes the preset weight of each emotion-related data. For each emotion-related data of the driver, the product of the emotion-related data and its preset weight can be calculated. Furthermore, the sum value of the obtained multiple products can be calculated, and then the sum value is the emotion index of the driver.

[0088] It is understandable that different emotions have different impacts on people, and under different emotions, people's responses to things also vary in intensity. Therefore, different emotions can be classified into intense emotions and non-intense emotions. For the driver of a vehicle, the intensity and degree of their current emotional state can affect driving safety. Among them, the more intense the current emotional state of the vehicle driver, the greater the impact on driving safety, and thus the greater the safety risk during driving. Furthermore, to ensure the driving safety of the driver, the more intense the current emotional state of the vehicle driver, the greater the amplitude of path adjustment for the current navigation path of the vehicle.

[0089] Based on this, different emotion adjustment parameters can be preset for different emotional states. Each emotion adjustment parameter corresponding to an emotional state can not only represent the amplitude of path adjustment for the current navigation path of the vehicle when the current emotional state of the vehicle driver is this emotional state, but also reflect the emotional type to which this emotional state belongs and the intensity of this emotional state. Among them, the more intense the emotional state, the more likely it is to affect the driving safety of the vehicle driver, and the larger the corresponding emotion adjustment parameter, the more inclined to adjust the current navigation path of the vehicle to avoid risk sections.

[0090] Optionally, the emotion adjustment parameters for intense emotions such as anxiety state and stress state can be larger, while the emotion adjustment parameters for non-intense emotions such as normal state and pleasant state can be smaller.

[0091] Optionally, the corresponding relationship between emotional states and adjustment parameters can be preset. For example, the corresponding relationship between emotional states and adjustment parameters can be recorded in the form of a mapping table. In this way, after obtaining the current emotional state, the adjustment parameter corresponding to the current emotional state can be found from the corresponding relationship between emotional states and adjustment parameters, and the found adjustment parameter is the emotion adjustment parameter corresponding to the current emotional state.

[0092] Optionally, the value range of the emotion adjustment parameter is (0, 1]. Among them, according to different emotional states, appropriate emotion adjustment parameters can be determined. Usually, in intense emotions (such as anxiety state or stress state), the emotion adjustment parameter can be larger and the path adjustment amplitude is larger; in normal state or pleasant state, the emotion adjustment parameter can be smaller and the path adjustment amplitude is smaller.

[0093] Exemplarily, in the case where the emotional state is the normal state, since the driver's emotion of the vehicle is stable and there is no need or only a small amplitude of path intervention, that is, there is no need or a small amplitude of path adjustment for the current navigation path, the emotion adjustment parameter corresponding to the normal state can be at least 0 at the minimum. Furthermore, the emotion adjustment parameter corresponding to the normal state can be selected within the range of 0 - 0.1, for example, 0.05.

[0094] In the case where the emotional state is an anxious state, since the driver of the vehicle is in a relatively tense mood, and in a tense state, the driver is prone to judgment errors, a relatively large adjustment to the current navigation path is required to avoid peak traffic periods, complex road sections, etc. Therefore, the emotion adjustment parameter corresponding to the anxious state can be relatively high, and then the emotion adjustment parameter corresponding to the anxious state can be selected within the range of 0.6 - 0.8, for example, 0.7.

[0095] In the case where the emotional state is a fatigued state, since the driver of the vehicle will have problems such as inattentiveness and slow reaction to the surrounding environment, which affect driving safety, it is necessary to appropriately adjust the current navigation path to reduce high-intensity road sections and shorten the journey, etc. Therefore, the emotion adjustment parameter corresponding to the fatigued state can be relatively high, and then the emotion adjustment parameter corresponding to the fatigued state can be selected within the range of 0.4 - 0.6, for example, 0.5.

[0096] In the case where the emotional state is a stressed state, since the driver of the vehicle will be highly tense and accompanied by a sense of anxiety when driving under high stress, the driving risk is significantly increased, and strong path intervention should be carried out, that is, a relatively large adjustment to the current navigation path is made to preferentially recommend navigation paths that are spacious, quiet, and have few intersections, etc. Therefore, the emotion adjustment parameter corresponding to the stressed state can be relatively high, and then the emotion adjustment parameter corresponding to the fatigued state can be selected within the range of 0.7 - 0.9, for example, 0.9.

[0097] In the case where the emotional state is a pleasant state, although the driver of the vehicle is in a relatively positive and not intense mood, in order to ensure the driving safety and driving experience of the driver, a relatively small adjustment to the current navigation path can be made to avoid high-intensity road sections, etc. through a slight adjustment of the navigation path. Therefore, the emotion adjustment parameter corresponding to the stressed state can be relatively small, and then the emotion adjustment parameter corresponding to the fatigued state can be selected within the range of 0.1 - 0.2, for example, 0.1.

[0098] S302. Determine the target path score according to the emotion index, the emotion adjustment parameter, and the current path score of the current navigation path of the vehicle.

[0099] After obtaining the emotion index of the driver and the emotion adjustment parameter corresponding to the current emotional state, the target path score can be determined according to the emotion index, the emotion adjustment parameter, and the current path score of the current navigation path of the vehicle.

[0100] In an optional embodiment, the determination of the target path score in S302 is further refined. Optionally, the following steps may be included:

[0101] 1. Use an emotion adjustment parameter to adjust the emotion index to obtain a target index.

[0102] After the above emotion index and emotion adjustment parameter, the emotion adjustment parameter can be used to adjust the emotion index to obtain a target index.

[0103] Optionally, the product of the above emotion index and emotion adjustment parameter can be calculated as the target index.

[0104] Optionally, the product of the above emotion index and emotion adjustment parameter can be calculated, and the sum of the above product and a preset value can be calculated as the target index. Among them, the above preset index can be 1.

[0105] 2. Determine the target path score according to the product of the target index and the current path score of the vehicle's current navigation path.

[0106] After obtaining the above target index, the target path score can be determined according to the product of the target index and the current path score of the vehicle's current navigation path. That is, the current path score of the vehicle's current navigation path can be adjusted using the above target index.

[0107] Among them, since the target index is obtained by adjusting the emotion index using an emotion adjustment parameter, and both the emotion index and the emotion adjustment parameter are determined according to the driver's current emotional state, therefore, adjusting the current path score of the vehicle's current navigation path using the above target index can adjust the current path score of the vehicle's current navigation path according to the driver's current emotional state, obtain the score of the optimized navigation path corresponding to the current navigation path determined in S103 above, and realize the evaluation of the above optimized navigation path.

[0108] Optionally, the following formula (1) can be used to calculate the above target path score.

[0109] P final =P default *(1 + k emotion *EI)(1)

[0110] Among them, P final is the target path score, P default is the current path score, k emotion is the emotion adjustment parameter, and EI is the emotion index.

[0111] In this embodiment, when determining the above-mentioned target path score, the driver's emotion index and the emotion adjustment parameter corresponding to the driver's current emotion state are introduced. Thus, the current path score of the vehicle's current navigation path can be adjusted according to the driver's emotion state, improving the matching degree between the evaluation of the target path score for the to-be-determined optimized navigation path and the driver's emotion state. Furthermore, the accuracy of the path adjustment amplitude determined using the target path score is improved, the matching degree between the obtained optimized navigation path and the vehicle driver's emotion is increased, and the optimization effect of path optimization for the current navigation path is enhanced.

[0112] Based on the above embodiments, in an exemplary embodiment, the determination of the path adjustment amplitude in S203 is further refined. Optionally, as Figure 4 shown, the following steps may be included:

[0113] S401, determine the difference between the target path score and the current path score.

[0114] After obtaining the above-mentioned target path score, the difference between the target path score and the current path score can be determined.

[0115] As mentioned above, the current path score is the score of the vehicle's current navigation path, and the target path score is the path score of the to-be-determined optimized navigation path. That is, the target path score is the path score of the navigation path that is expected to be recommended to the driver and matches the driver's emotion state. Then, the difference between the target path score and the current path score can represent the gap between the navigation path that is expected to be recommended to the driver and matches the driver's emotion state, and the vehicle's current navigation path. Among them, the larger the above-mentioned difference, the larger the above-mentioned gap. Correspondingly, the smaller the above-mentioned difference, the smaller the above-mentioned gap.

[0116] S402, determine the target proportion of the difference in the current path score.

[0117] After obtaining the difference between the target path score and the current path score, the target proportion of the difference in the current path score can be further determined.

[0118] As described above, the difference between the above-mentioned target path score and the current path score can represent the gap between the navigation path that is desired to be recommended to the driver and matches the driver's emotional state, and the vehicle's current navigation path. Then, the above-mentioned target ratio can represent the degree of adjustment required for the current navigation path when switching the vehicle's navigation path from the current navigation path to the navigation path that is desired to be recommended to the driver and matches the driver's emotional state. The larger the above-mentioned target ratio, the greater the degree of adjustment required for the above-mentioned current navigation path. Correspondingly, the smaller the above-mentioned target ratio, the smaller the degree of adjustment required for the above-mentioned current navigation path.

[0119] S403. In the corresponding relationship between the preset adjustment range and the ratio range, search for the adjustment range corresponding to the ratio range to which the target ratio belongs, and use the found adjustment range as the path adjustment range.

[0120] As described above, the target ratio can represent the degree of adjustment required for the current navigation path when switching the vehicle's navigation path from the current navigation path to the navigation path that is desired to be recommended to the driver and matches the driver's emotional state. And the path adjustment range to be determined indicates the degree of adjustment of the current navigation path when optimizing the current navigation path. Therefore, the path adjustment range can be determined according to the target ratio.

[0121] Among them, the corresponding relationship between the adjustment range and the ratio range can be preset in advance. Then, after obtaining the target ratio, the adjustment range corresponding to the ratio range to which the target ratio belongs can be searched from the corresponding relationship between the adjustment range and the ratio range, and the found adjustment range can be used as the path adjustment range.

[0122] Exemplarily, the corresponding relationship between the adjustment range and the ratio range as shown below can be preset in advance.

[0123] 1) The adjustment range is no adjustment, and the corresponding ratio range is less than 0.1, that is, |P final -P default | < 0.1P default . Among them, the difference between the target path score and the current path score is very small, and it can be considered that the current navigation path matches the driver's current emotional state well enough and no path adjustment is required.

[0124] 2) The adjustment range is a small adjustment, and the corresponding ratio range is not less than 0.1 and less than 0.3, that is, 0.1 ≤ |P final -P default | < 0.3P defaultAmong them, the difference between the target path score and the current path score is relatively small. It can be considered that the current emotional state of the driver has little impact on the adjustment of the vehicle's navigation path, and a small amount of path adjustment can be continued for the current navigation path, such as avoiding some complex sections or slightly changing the direction of the driving route, etc.

[0125] 3) The adjustment amplitude is a medium adjustment, and the corresponding proportion range is not less than 0.3 and less than 0.6, that is, 0.3 ≤ |P final -P default | < 0.6P default Among them, the difference between the target path score and the current path score is relatively large. It can be considered that the current emotional state of the driver has a significant impact on the adjustment of the vehicle's navigation path, and a medium path adjustment can be made to the current navigation path, such as avoiding complex sections and choosing sections with smoother traffic flow, etc.

[0126] 4) The adjustment amplitude is a large adjustment, and the corresponding proportion range is not less than 0.6, that is, |P final -P default | ≥ 0.6P default Among them, the difference between the target path score and the current path score is very large. It can be considered that the current emotional state of the driver has a great impact on the adjustment of the vehicle's navigation path, and a large path adjustment can be made to the current navigation path, such as avoiding all complex intersections, recommending simpler, wider sections with less traffic flow, and even alternative navigation paths or completely different navigation paths can be selected.

[0127] It should be emphasized that the corresponding relationship between the adjustment amplitude and the proportion range in the above examples is only an example of the corresponding relationship between the adjustment amplitude and the proportion range, rather than a limitation. The present application does not specifically limit the corresponding relationship between the adjustment amplitude and the proportion range.

[0128] In this embodiment, by determining the difference between the target path score and the current path score, and using the gap between the navigation path that is expected to be recommended to the driver and matches the driver's emotional state and the vehicle's current navigation path, the path adjustment amplitude is determined, which can improve the accuracy of the determined path adjustment amplitude, improve the emotional matching degree between the obtained optimized navigation path and the vehicle's driver, and improve the optimization effect of path optimization for the current navigation path.

[0129] Based on the above embodiments, in an exemplary embodiment, the determination of the optimized navigation path in S103 above is further refined. Optionally, the following steps may be included:

[0130] l. When the path adjustment amplitude characterizes the matching of the current navigation path with the emotion-related data, determine the current navigation path as the optimized navigation path.

[0131] As described above, the path adjustment amplitude can characterize the matching degree between the emotion correlation data and the current navigation path, and further indicate the adjustment degree of the current navigation path when optimizing the current navigation path. Then, when the path adjustment amplitude characterizes the matching between the current navigation path and the emotion correlation data, it can be considered that when optimizing the current navigation path, there is no need to adjust the current navigation path. Therefore, the current navigation path can be directly determined as the optimized navigation path.

[0132] 2. When the path adjustment amplitude characterizes the mismatch between the current navigation path and the emotion correlation data, select a target navigation path from the candidate navigation paths as the optimized navigation path corresponding to the current navigation path.

[0133] Among them, the proportion of the different section between the target navigation path and the non-traveled section of the current navigation path in the non-traveled section is within the proportion range corresponding to the path adjustment amplitude.

[0134] When the path adjustment amplitude characterizes the mismatch between the current navigation path and the emotion correlation data, it can be considered that when optimizing the current navigation path, the current navigation path needs to be adjusted. Therefore, the proportion range corresponding to the path adjustment amplitude can be determined first, and then a target navigation path whose proportion of the different section between the non-traveled section of the current navigation path and the emotion correlation data of the vehicle driver in the non-traveled section is within the proportion range can be selected from the candidate navigation paths that match the emotion correlation data of the vehicle driver. This target navigation path can be determined as the optimized navigation path corresponding to the current navigation path.

[0135] In this embodiment, according to whether the path adjustment amplitude characterizes the matching between the current navigation path and the emotion correlation data, determining whether to directly determine the current navigation path as the optimized navigation path or select the optimized navigation path from the candidate navigation paths can avoid blindly selecting the optimized navigation path from the candidate navigation paths while ignoring the situation that the current navigation path can be used as the optimized navigation path, avoid misjudgment of the current navigation path, and improve the optimization effect of path optimization.

[0136] Based on the above embodiments, in an exemplary embodiment, as Figure 5 shown, the path optimization method may include the following steps:

[0137] S501. During the driving of the vehicle, determine the path adjustment amplitude according to the emotion correlation data of the vehicle driver and the current navigation path of the vehicle.

[0138] S502. Determine the candidate navigation paths that match the emotion correlation data.

[0139] S503. When the path adjustment amplitude indicates that the current navigation path matches the emotion correlation data, determine the current navigation path as the optimized navigation path.

[0140] Among them, the specific implementation manners of the above S501 - S503 are the same as those in the above embodiments and will not be elaborated here.

[0141] S504. When the path adjustment amplitude indicates that the current navigation path does not match the emotion correlation data, select a target navigation path from the candidate navigation paths as the optimized navigation path corresponding to the current navigation path, and output a prompt message.

[0142] Among them, the prompt message is used to prompt the driver to switch the navigation path of the vehicle to the optimized navigation path.

[0143] As mentioned above, when the path adjustment amplitude indicates that the current navigation path does not match the emotion correlation data, it can be determined that the current navigation path does not match the driver's emotion correlation data, that is, the current navigation path does not conform to the driver's current emotional state. Therefore, in order to improve the driver's driving experience and ensure driving safety, a different optimized navigation path from the current navigation path is re - selected as the navigation path that is expected to be recommended for the driver to use and matches the driver's current emotional state. Then, in order to enable the driver to smoothly switch the navigation path of the vehicle from the current navigation path to the optimized navigation path, a prompt message can be output, and this prompt message is used to prompt the driver to switch the navigation path of the vehicle to the optimized navigation path.

[0144] Correspondingly, when the path adjustment amplitude indicates that the current navigation path matches the emotion correlation data, the current navigation path is determined as the optimized navigation path, which can indicate that the current navigation path matches the driver's emotion correlation data, that is, the current navigation path conforms to the driver's current emotional state. Therefore, the driver does not need to switch the navigation path, and thus, in order to avoid disturbing the driver, no reminder is required.

[0145] In this embodiment, when the path adjustment amplitude indicates that the current navigation path does not match the emotion correlation data, the driver can be reminded to switch the navigation path, and switch the navigation path of the vehicle from the current navigation path to the optimized navigation path, thereby improving the driver's driving experience and ensuring driving safety.

[0146] Based on the above embodiments, in an exemplary embodiment, as Figure 6 shown, the path optimization method may include the following steps:

[0147] S601. Input the emotion correlation data of the driver of the vehicle into the emotion state classification model to obtain the driver's current emotional state.

[0148] S602. Determine the preset weight of the emotion-related data and the emotion adjustment parameter corresponding to the current emotional state according to the current emotional state.

[0149] S603. Use the preset weight to perform weighted summation on the emotion-related data to obtain the driver's emotion index.

[0150] S604. Use the emotion adjustment parameter to adjust the emotion index to obtain the target index.

[0151] S605. Determine the target path score according to the product of the target index and the current path score of the vehicle's current navigation path.

[0152] S606. Determine the difference between the target path score and the current path score.

[0153] S607. Determine the target proportion of the difference in the current path score.

[0154] S608. In the corresponding relationship between the preset adjustment range and the proportion range, search for the adjustment range corresponding to the proportion range to which the target proportion belongs, and use the found adjustment range as the path adjustment range.

[0155] S609. When the path adjustment range indicates that the current navigation path matches the emotion-related data, determine the current navigation path as the optimized navigation path.

[0156] S610. When the path adjustment range indicates that the current navigation path does not match the emotion-related data, select the target navigation path from the candidate navigation paths as the optimized navigation path corresponding to the current navigation path, and output a prompt message.

[0157] Among them, the specific implementation manners of the above S601 - S610 are the same as those in the above embodiments and will not be elaborated here.

[0158] When the path adjustment range indicates that the current navigation path does not match the emotion-related data, it can be considered that when optimizing the above current navigation path, it is necessary to adjust the above current navigation path. Therefore, the proportion range corresponding to the above path adjustment range can be determined first. Thus, from the candidate navigation paths that match the emotion-related data of the driver of the above vehicle, select the target navigation path whose proportion of the difference section between the un-traveled section of the current navigation path in the un-traveled section is within the above proportion range. This target navigation path can be determined as the optimized navigation path corresponding to the current navigation path.

[0159] Based on the above embodiments, the path optimization method is illustrated by taking five emotional states of normal, anxiety, fatigue, stress and pleasure, as well as heart rate, skin conductivity, facial expression data, eye tracking data, voice feature data and driving behavior data as emotion-related data.

[0160] First, we briefly introduce how to obtain the above-mentioned emotion-related data, such as heart rate, skin conductivity, facial expression data, eye tracking data, voice feature data, and driving behavior data.

[0161] 1) Heart rate (HR), the acquisition device can be a heart rate sensor installed on the steering wheel of the vehicle or a wearable device worn by the driver of the vehicle, such as a smart bracelet, etc. The acquisition frequency can be 1Hz (Hertz), and the collected data is the heart rate value.

[0162] 2) Skin conductivity, also known as Galvanic Skin Response (GSR), the collection device can be a conductivity sensor embedded in the vehicle's steering wheel or seat, the collection frequency can be 4Hz, and the collected data is the skin conductivity value.

[0163] 3) Facial expression data: the acquisition device may be a camera installed in the vehicle, the acquisition frequency may be the image acquisition frequency of the camera, and the acquired data may include the tilt angle of eyebrows, the upward / downward angle of the corners of the mouth, the range of eye opening, etc.

[0164] 4) Eye tracking data: the collection device can be an infrared-based eye tracking camera installed on the top of the dashboard or central control screen in the vehicle. The collection frequency can be 60Hz, and the collected data can include blinking frequency, gaze time, eye movement, etc.

[0165] 5) Voice feature data: the collection device may be a microphone array installed in the vehicle. The feature analysis method may be a voice emotion classification algorithm to analyze the speech speed, pitch, volume changes, etc. of the driver of the vehicle. The collected data may include speech speed, pitch, tone, etc.

[0166] 6) Driving behavior data. The collection equipment can be vehicle modules such as the car EDR (Event Data Recorder), the vehicle central control, etc. The collected data may include the number of sudden accelerations, the frequency of sudden braking, the steering wheel rotation range, etc.

[0167] Furthermore, examples are given of the values ​​of the emotion-related data such as heart rate, skin conductivity, facial expression data, eye tracking data, voice feature data and driving behavior data under different emotions such as normal, anxiety, fatigue, stress and pleasure.

[0168] 1) Normal state, the values of the above-mentioned emotion-related data are all within the normal range. Specifically:

[0169] 1. Heart rate, heart rate value: 60–80 beats per minute (the heart rate is in a stable state, without tension or excessive relaxation).

[0170] 2. Skin conductivity, skin conductivity value: 15–25 μS (micro Siemens) (the conductivity is relatively stable, and there is no significant sweating or emotional fluctuation on the skin).

[0171] 3. Facial expression data, upward curvature of the mouth corner: 0°–5° (natural state, the mouth corner turns up slightly or is horizontal); eyebrow position: the eyebrows are natural, upward curvature: 0°–5°, or remain horizontal; eye opening degree: 70%–100% (the eyes are fully open, and the eyelids are in a natural state).

[0172] 4. Eye movement tracking data, fixation time: the eyes are stable, focused forward, with a long fixation time, average fixation time > 3 seconds; eye movement: less eye movement, and the eye movement trajectory is within a small range (the field of view is roughly concentrated, and the eye scanning time > 2 seconds); blink frequency: 15–20 times per minute (stable).

[0173] 5. Speech feature data, speech rate: 120–160 words per minute (normal speech rate, clear sentences); intonation: stable, pitch between 80–100 Hz; volume: moderate, 70–80 dB, clear speech; tone: natural, peaceful, neutral tone, with few intonation changes.

[0174] 6. Driving behavior data, acceleration: smooth acceleration (0.1–0.3 m / s 2 ); braking: smooth braking (deceleration 0.2–0.4 m / s 2 ); lane change: occasional lane change, with reasonable intervals.

[0175] 2) Anxiety state, abnormal heart rate, skin conductivity and facial expressions (such as a combination of a tense expression and sudden braking), specifically:

[0176] 1. Heart rate, heart rate value: 80–110 beats per minute (emotionally tense, heart beating faster, usually accompanied by rapid breathing).

[0177] 2. Skin conductivity, skin conductivity value: 25–40 μS (significantly increased, usually accompanied by tension and sweating, and active sympathetic nerves).

[0178] 3. Facial expression data, upward curvature of the corners of the mouth: 0°–2° (lips closed or slightly open, showing tension); position of the eyebrows: eyebrows furrowed, upward curvature: >5° or downward pressure >5°; eye opening degree: >90% (eyes wide open, eyelids tightened); eye movement: frequent left - right saccades, and small - scale eye jitters may occur in the eyes (rapid eye movement, >15 times / minute).

[0179] 4. Eye - movement tracking data, fixation time: short fixation time, often saccading around, fixation time usually <1 second; eye movement: eyes frequently saccade around, eye movement trajectory: fast and extensive, and frequent left - right eye rotations may occur, scanning the surrounding environment; blink frequency: >25 times / minute (increased blink frequency is often caused by tension).

[0180] 5. Speech feature data, speech rate: >160 words per minute (increased speech rate, tense tone); intonation: high - pitched and rapid, pitch between 100–120 Hz; volume: increased, >80 dB, and the speech may be tremulous; tone: unstable and tense, tone rapid or jerky.

[0181] 6. Driving behavior data, acceleration: rapid acceleration (acceleration greater than 0.4 m / s 2 ); braking: rapid braking (deceleration greater than 0.5 m / s 2 ); lane - changing: frequent lane - changing, unstable driving.

[0182] 3) Fatigue state, eye - movement fatigue characteristics, low heart rate, and prolonged driving behavior reaction time. Specifically:

[0183] 1. Heart rate, heart rate value: 60–70 beats per minute (stable and low, showing fatigue and slow reaction to the surrounding environment).

[0184] 2. Skin conductivity, skin conductivity value: 10–20 μS (low, stable and inactive skin conductivity, showing a sense of tiredness and low reactivity).

[0185] 3. Facial expression data, upward curvature of the corners of the mouth: 0°–1° (mouth slightly open, lips relaxed); position of the eyebrows: eyebrows slightly drooping, downward pressure: 5°–10°; eye opening degree: 40%–60% (eyelids drooping, reduced eye - opening degree, prone to blinking); eye movement: eyes not focused, eye blink frequency: >20 times / minute.

[0186] 4. Eye - movement tracking data, fixation time: eyes difficult to focus, fixation time usually <2 seconds; eye movement: eyes move slowly, eye movement trajectory: small, and the fixation position is unstable; blink frequency: >25 times / minute, with frequent blinking and drooping eyelids.

[0187] 5. Voice feature data: speaking speed: <120 words per minute (speaking speed slows down, language is dragging); tone: low, pitch is between 60-80Hz; volume: low, <70dB, voice sounds tired or weak; tone: monotonous tone, lack of change, and often pauses.

[0188] 6. Driving behavior data, acceleration: Smooth acceleration, slow (acceleration less than 0.2m / s 2 ); Braking: Braking operation is slow; Lane changing: Lane changes are rare and driving is relatively simple.

[0189] 4) Stress state, with significant increase in skin electricity, high fluctuation in heart rate and rapid acceleration in driving behavior, specifically:

[0190] 1. Heart rate: 90-110 beats / minute (manifested as high tension, accelerated and continuously rising heartbeat, accompanied by anxiety).

[0191] 2. Skin conductivity, skin conductivity value: 30-50μS (conductivity increases significantly, which is common in long-term stress or momentary emotional conflicts).

[0192] 3. Facial expression data: mouth corners raised: 0°–2° (mouth tightly closed, possibly slightly clenched); eyebrow position: eyebrows tightly furrowed, downward pressure: >10°; eye openness: >90% (eyes wide open, showing a high degree of alertness to the external environment); eye movement: eye movement is intense, eye movement frequency: >20 times / minute.

[0193] 4. Eye tracking data, fixation time: longer fixation time, eyes fixed on the front, usually >2 seconds; eye movement: vigorous eye movement, frequent scanning, eye movement trajectory: rapid and intense, may appear as nervous gaze, highly concentrated attention; blinking frequency: <10 times / minute (blinking frequency is reduced, expression is serious and nervous).

[0194] 5. Voice feature data: speaking speed: >180 words per minute (rapid speaking speed, urgent language); tone: sharp or unstable, pitch between 110-130Hz; volume: very loud, >85dB, voice appears impatient or angry; tone: urgent, unstable, and nervous.

[0195] 6. Driving behavior data, acceleration: rapid acceleration or repeated acceleration (acceleration exceeding 0.4m / s 2 ); Braking: sudden braking, which may cause a sudden stop (deceleration exceeding 0.5m / s 2 ); Lane changes: Frequent and rapid lane changes, which indicates impatient driving.

[0196] 5) Pleasant state, relaxed expression, normal heart rate and no significant behavioral abnormalities, specifically:

[0197] 1. Heart rate, heart rate value: 60–75 beats per minute (relatively stable, low fluctuation, showing relaxation and pleasure).

[0198] 2. Skin conductivity, skin conductivity value: 15–25 μS (slight increase in conductivity or maintained in a stable range, showing mild pleasure and relaxation).

[0199] 3. Facial expression data, upward curvature of the corners of the mouth: >2° (big smile, corners of the mouth turned up); position of the eyebrows: eyebrows slightly raised, upward curvature: 5°–10°; eye opening degree: 100% (eyes fully open, bright, pupils slightly dilated); eye movement: eyes stable, blink frequency moderate (15–20 times per minute).

[0200] 4. Eye movement tracking data, fixation time: long fixation time, eyes fixated steadily ahead, fixation time usually >3 seconds; eye movement: smooth eye movement, fixation trajectory concentrated ahead, eyes stable (almost no saccades to other places); blink frequency: 15–20 times per minute (moderate, stable).

[0201] 5. Speech feature data, speech rate: about 150 words per minute (moderate or slightly fast speech rate, fluent); intonation: intonation rising, pitch between 90–110 Hz; volume: moderate, 75–85 dB, tone pleasant and clear; tone: pleasant and natural, intonation gentle.

[0202] 6. Driving behavior data, acceleration: smooth acceleration (0.2–0.3 m / s 2 ); braking: smooth braking (deceleration 0.2–0.4 m / s 2 ); lane change: lane changes are infrequent, driving behavior is regular.

[0203] Next, since the facial expression data, eye movement tracking data, voice feature data, and driving behavior data can all include multiple data, for the facial expression data, eye movement tracking data, voice feature data, and driving behavior data, comprehensive evaluations can be respectively conducted based on the multiple data they include to obtain comprehensive scores, which are used to participate in the determination of the driver's emotion index. Among them, for the facial expression data, the facial expression recognition score can be determined according to the included eyebrow tilt angle, mouth corner upward / downward angle, eye opening range, etc., and this facial expression recognition score is used to characterize the intensity of the driver's emotion state reflected by the facial expression data; for the eye movement tracking data, the eye movement tracking score can be determined according to the included blink frequency, fixation time, eye movement, etc., and this eye movement tracking score is used to characterize the intensity of the driver's emotion state reflected by the eye movement tracking data; for the voice feature data, the voice analysis score can be determined according to the included speech rate, intonation, and tone, and this voice analysis score is used to characterize the intensity of the driver's emotion state reflected by the voice feature data; for the driving behavior data, the behavior analysis score can be determined according to the included number of hard accelerations, hard braking frequency, steering wheel rotation amplitude, lane change frequency, etc., and this behavior analysis score is used to characterize the intensity of the driver's emotion state reflected by the driving behavior data.

[0204] Optionally, a CNN (Convolutional Neural Networks) model can be used to obtain the above facial expression recognition score. Among them, during the driving process of multiple historical vehicles, facial expression data of the driver of the vehicle, the emotional state of the driver of the vehicle, and the score value of the emotional state of the driver of the vehicle can be obtained. Among them, the score value of the emotional state of the driver of the vehicle is used to characterize the intensity of the emotional state of the driver of the vehicle. For example, if the driver of the vehicle is very anxious, it can be determined that the emotional state of the driver of the vehicle is an anxious state, and the score value is 0.9; for another example, if the driver of the vehicle is slightly anxious, it can be determined that the emotional state of the driver of the vehicle is an anxious state, and the score value is 0.3. Among them, during the process of obtaining the above data, the score value can be determined according to the driver's self-feeling and experience value. Furthermore, the above facial expression data of the driver of the vehicle can be used as input, and the emotional state of the driver of the vehicle and the above score value can be used as labels to train a preset initial CNN model to obtain a first classification model. After that, during the driving process of the vehicle, the obtained facial expression data of the driver of the vehicle is input into the above first classification model to obtain the probabilities and score values that the current emotional states of the driver of the vehicle output by the above first classification model are respectively in a normal state, an anxious state, a fatigued state, a stressed state, and a pleasant state, and the determined score value of the current emotional state of the driver of the vehicle is used as the facial expression recognition score. Optionally, in some cases, the above first classification model can determine the emotional state with the highest probability as the emotional state of the driver of the vehicle for output. Then the first classification model can only output the emotional state with the highest probability and the score value, and then the score value output by the first classification model can be directly used as the facial expression recognition score.

[0205] Optionally, data such as the blink frequency, fixation time, and eye movement in the obtained eye movement tracking data of the driver of the vehicle can be used to calculate features such as PERCLOS (Percentage of Eyelid Closure over Time), fixation distribution information, and saccade frequency. Furthermore, according to the above features such as PERCLOS, fixation distribution information, and saccade frequency, the attention and fatigue state score of the driver of the vehicle is determined as the eye movement tracking score. Among them, PERCLOS is determined by calculating the ratio of the eye closure time to the total duration. The magnitude of PERCLOS can reflect the fatigue degree of the driver of the vehicle. When PERCLOS is greater than a specified threshold (such as 75%), it can be considered that the driver of the vehicle is in a fatigued state.

[0206] For example, a pre-set attention and fatigue state scoring model can be used to obtain the above eye movement tracking score. Among them, during the driving process of multiple historical vehicles, the eye movement tracking data of the driver of the vehicle and the emotional state of the driver of the vehicle can be obtained. According to the above eye movement tracking data, features such as the driver's PERCLOS, fixation distribution information, and saccade frequency of the driver of the vehicle are calculated. And according to the above eye movement tracking data and the emotional state of the driver of the vehicle, the attention and fatigue state score of the driver of the vehicle is evaluated as the emotional state score value of the driver of the vehicle. Furthermore, the above features such as PERCLOS, fixation distribution information, and saccade frequency can be used as inputs, and the attention and fatigue state score of the driver of the vehicle can be used as a label to train a pre-set initial model to obtain an attention and fatigue state scoring model. Then, during the driving process of the vehicle, after obtaining the eye movement tracking data of the driver of the vehicle, according to the eye movement tracking data of the driver of the vehicle, features such as the driver's PERCLOS, fixation distribution information, and saccade frequency of the driver of the vehicle are calculated, and the calculated features are input into the above attention and fatigue state scoring model to obtain the attention and fatigue state score output by the above attention and fatigue state scoring model as the eye movement tracking score.

[0207] Optionally, a pre-set emotion recognition model can be used to obtain the above speech analysis score. Among them, during the driving process of multiple historical vehicles, the speech feature data of the driver of the vehicle, the emotional state of the driver of the vehicle, and the emotional state score value of the driver of the vehicle can be obtained, and features such as the speed change, pitch change, and intonation curvature in the above speech feature data are extracted. Furthermore, the above features such as speed change, pitch change, and intonation curvature can be used as inputs, and the emotional state of the driver of the vehicle and the above score value can be used as labels to train a pre-set initial model to obtain an emotion recognition model. Then, during the driving process of the vehicle, after obtaining the speech feature data of the driver of the vehicle, features such as the speed change, pitch change, and intonation curvature in the speech feature data of the driver of the vehicle are extracted, and the extracted features are input into the above emotion recognition model to obtain the probabilities and score values that the current emotional states of the driver of the vehicle output by the above emotion recognition model are normal state, anxiety state, fatigue state, stress state, and pleasure state respectively, and the determined score value of the current emotional state of the driver of the vehicle is used as the speech analysis score. Optionally, in some cases, the above emotion recognition model can determine the emotional state with the highest probability as the emotional state of the driver of the vehicle for output. Then the emotion recognition model can only output the emotional state with the highest probability and the score value, and the score value output by the emotion recognition model can be directly used as the speech analysis score.

[0208] Optionally, a CNN model can be used to obtain the above-mentioned behavior analysis score. Among them, during the driving processes of multiple historical vehicles, driving behavior data of the driver of the vehicle, the emotional state of the driver of the vehicle, and the score value of the emotional state of the driver of the vehicle can be obtained. Furthermore, the above-mentioned driving behavior data of the driver of the vehicle can be used as input, and the emotional state of the driver of the vehicle and the above-mentioned score value can be used as labels to train a preset initial CNN model to obtain a second classification model. Furthermore, during the driving of the vehicle, the obtained driving behavior data of the driver of the vehicle is input into the above-mentioned second classification model to obtain the probabilities and score values that the current emotional states of the driver of the vehicle output by the above-mentioned second classification model are respectively the normal state, the anxious state, the fatigued state, the stressed state, and the pleasant state, and the score value of the determined current emotional state of the driver of the vehicle is used as the behavior analysis score. Optionally, in some cases, the above-mentioned second classification model can determine the emotional state with the highest probability as the emotional state of the driver of the vehicle for output. Then, the second classification model can only output the emotional state with the highest probability and the score value, and the score value output by the second classification model can be directly used as the behavior analysis score.

[0209] Based on this, the current emotional index of the above-mentioned driver can be calculated according to the following formula (2).

[0210] EI = w HR *HR + W GSR *GSR + W FE *FE + W ET *ET + W SA *SA

[0211] + W BA *BA(2)

[0212] Among them, EI is the current emotional index, HR is the score corresponding to the heart rate. Among them, the unit of the heart rate is bpm (beats per minute, the number of beats per second), then the collected heart rate can be directly used as the score corresponding to the heart rate, W HR is the preset weight of the heart rate. For example, if the collected heart rate of the driver of the vehicle is 90 bpm, then the value of HR can be determined to be 90; GSR is the score corresponding to the skin conductance. Among them, the unit of the skin conductance is μS, then the collected skin conductance can be directly used as the score corresponding to the skin conductance, W GSR is the preset weight of the skin conductance. For example, if the collected skin conductance of the driver of the vehicle is 3.2 μS, then the value of GSR can be determined to be 3.2; FE is the facial expression recognition score, W FE is the preset weight of the facial expression recognition score; ET is the eye movement tracking score, W ETis the preset weight for the eye movement tracking score; SA is the speech analysis score, W SA is the preset weight for the speech analysis score; BA is the behavior analysis score, W BA is the preset weight for the behavior analysis score. Moreover, the value ranges of FE, ET, SA, and BA are (0, 1).

[0213] Among them, for the weight values of the preset weights in the above formula (2), they can be set according to the application requirements of the actual scenario, the influence of different emotions on the physiological data of the vehicle driver and the vehicle driving data, the experience of the vehicle driver's self - perception of various emotion - related data and their own emotional state, as well as the experimental values of multiple tests.

[0214] Moreover, under normal conditions, the various emotion - related data are relatively stable. Therefore, the preset weights are relatively average, and then W HR = 0.15, w GSR = 0.15, W FE = 0.2, w ET = 0.2, W SA = 0.15, W BA = 0.15.

[0215] Under the anxiety state, the fluctuations of heart rate, skin conductivity, and facial expressions are relatively large. Therefore, the preset weights of the recognition scores of heart rate, skin conductivity, and facial expressions increase, and then W HR = 0.25, W GSR = 0.25, W FE = 0.2, W ET = 0.1, W SA = 0.1, w BA = 0.1.

[0216] Under the fatigue state, the preset weights of the eye movement tracking score, facial expression recognition score, and behavior analysis score increase, especially for the perception of blink frequency and reaction speed, and then W HR = 0,1, W GSR = 0.15, W FE = 0.2, w ET = 0.25, W SA = 0.1, w BA = 0.2.

[0217] Under the stress state, the preset weights of the facial expression recognition score, speech analysis score, and behavior analysis score are higher, especially for the characteristics with larger reactions to emotional fluctuations (such as sudden braking, sharp turning, and increased speech speed), and then w HR = 0.2, W GSR = 0.25, w FE = 0.25, w ET = 0.15, wSA = 0.1, w BA = 0.05.

[0218] In a pleasant state: the preset weights of heart rate, skin conductivity, and facial expression recognition scores are relatively high. Especially considering the strong influence of pleasantness on facial expressions and physiological responses, then W HR = 0.2, W GSR = 0.1, w FE = 0.3, W ET = 0.1, W SA = 0.2, W BA = 0.1.

[0219] Among them, as mentioned above, in the above formula (2), even though the value of HR is relatively large compared to GSR, FE, ET, SA, and BA, the reason for still using HR is as follows:

[0220] 1. Immediacy of physiological response: Heart rate is the most direct and rapid physiological indicator reflecting emotional changes. When people are in emotional states such as stress, anxiety, or pleasure, the heart rate changes rapidly, and it can accurately and quickly capture emotional changes. For example, the heart rate accelerates during anxiety, and may become slower during fatigue. This characteristic of rapid change makes heart rate a key indicator for measuring emotional states.

[0221] 2. Strong correlation with emotional states: The fluctuation of heart rate has a direct physiological connection with human emotional states. For example, in a state of anxiety or stress, the body activates the sympathetic nervous system, resulting in an increase in heart rate; while in a state of relaxation or pleasure, the parasympathetic nerve dominates and the heart rate decreases. Therefore, heart rate can effectively reflect the intensity and type of emotions, providing more intuitive data support for navigation path adjustment.

[0222] 3. Relationship between emotions and driving safety: Heart rate, as a physiological signal, is directly related to the driving state. An overly high heart rate usually means that the driver is under high stress, and in this case, the path selection should avoid complex and busy routes, but rather choose safer and more stable routes. A too low heart rate may mean fatigue, and the navigation system can adjust the path to recommend locations for rest within a short time or change the route to ensure driving safety.

[0223] 4. Data availability and ease of use: Compared with other emotion-related data (such as emotional facial expressions, voice changes, etc.), heart rate data can be obtained more conveniently and with high precision through wearable devices (such as smart watches). As a physiological signal, heart rate data can be monitored all day long and is applicable to various driving scenarios.

[0224] Exemplarily, assuming the driver is in an anxious state, then the current emotion index (EI) of the driver can be calculated according to the following formula (3).

[0225] EI = 0.25 * HR + 0.25 * GSR + 0.2 * FE + 0.1 * ET + 0.1 * SA + 0.1

[0226] * BA(3)

[0227] Assume that the driver's heart rate (HR) is 105 bpm, the galvanic skin response (GSR) is 4.5 μS, the facial expression recognition score (FE) is 0.7, the eye movement tracking score (ET) is 0.6, the speech analysis score (SA) is 0.5, and the behavior analysis score (BA) is 0.4. Then the driver's current emotional index (EI) is as follows:

[0228] EI = 0.25 * 105 + 0.25 * 4.5 + 0.2 * 0.7 + 0.1 * 0.6 + 0.1 * 0.5 + 0.1

[0229] * 0.4 = 27.92

[0230] According to the above current emotional index (EI) and the emotional adjustment parameter (k emotion = 0.8) under the preset anxiety state, calculate the target path score. Among them, the default original path score P default = 500.

[0231] P final = 500 * (1 + 0.8 * 27.92) = 11670

[0232] According to the example of the corresponding relationship between the adjustment amplitude and the proportion range shown in S603 above, P final exceeds 60% of P default above, then it can be determined that a large-scale path adjustment will be made to the current navigation path, such as avoiding complex intersections and busy traffic sections, selecting a route with less traffic flow and lower complexity, or even choosing a completely different section of the road to reduce the impact of emotional stress on the driver's driving experience.

[0233] Next, taking the above normal, anxious, fatigued, stressed, and pleasant states as examples, continue to give examples for illustration.

[0234] 1) Normal state

[0235] 1. Optimization strategy: Based on time - first path planning, calculate the route with the shortest time or the shortest distance. Avoid excessive interference with the route.

[0236] 2. Technical means: Use traditional shortest-time (Dijkstra algorithm) or shortest-distance (A* algorithm) path planning algorithms, which rely heavily on real-time traffic data (such as traffic flow, signal light status, construction and accident information), and consider traffic flow and road conditions for navigation path selection. Usually, based on external factors such as traffic density and road surface conditions, the optimal driving route is recommended.

[0237] For example, assume the driver's starting point is "Location A" and the destination is "Location B". Under normal conditions, the navigation system will calculate the shortest-time path from A to B and display it on the map. At this time, the system will not make additional complex adjustments, only focusing on road condition information (such as traffic, road section restrictions, etc.).

[0238] 2) Anxious state

[0239] 1. Optimization strategy: Avoid complex intersections and road sections; Select paths with relatively stable traffic flow and no large-scale traffic signals, and try to avoid road sections that require frequent driver decisions; Prioritize the recommendation of "simple and intuitive" paths, without passing through too many complex road sections, so as to avoid causing additional psychological burden to the driver during navigation.

[0240] 2. Technical means:

[0241] Emotion and path weight weighting: By analyzing emotion-related data such as heart rate, skin conductivity, and facial expression data, determine that the emotion state label corresponding to the driver's emotion-related data is "anxious". Select an optimized navigation path through a weighting method: Avoid complex intersections and dense traffic signals; Prioritize the selection of roads with relatively stable and intuitive traffic flow, and avoid complex routes; Add an additional "emotion stability weight" during path planning to reduce the complexity of such road sections.

[0242] Emotion-based path optimization algorithm: A path planning model based on emotion feedback (such as weighted A* algorithm) can be used to determine an optimized navigation path for drivers in an anxious state, avoiding high-risk and high-difficulty driving environments.

[0243] For example, when the driver travels from City A to City B, there are multiple complex intersections and congested areas on the path. Since the driver is in an anxious state, an optimized navigation path that bypasses these complex road sections will be selected, and the "simplified route" along the way will be marked on the map. Voice navigation prompt: "The upcoming intersection is complex. To simplify the driving experience, a more direct route has been planned for you. Please drive according to the new route."

[0244] 3) Fatigued state

[0245] 1. Optimization Strategy: Recommend the shortest path in terms of time to minimize driving time and reduce fatigue; prefer routes with rest areas or service areas so that drivers can stop for rest at any time; the route should avoid long periods of highway driving or single sections as much as possible to prevent drivers from concentrating on driving for a long time.

[0246] 2. Technical Means:

[0247] Fatigue Detection Algorithm: Combine eye movement tracking data and facial expression data to judge the driver's fatigue state, and at the same time, combine heart rate, skin conductivity and voice feature data to trigger fatigue judgment.

[0248] Route Adjustment Algorithm: Based on the fatigue state, preferentially recommend optimized navigation routes with service areas or rest areas to avoid long driving times. Through dynamic route adjustment, reduce long periods of highway driving and single sections, and recommend optimized navigation routes with rest points. By analyzing real-time traffic flow, vehicle speed and road grade, calculate the optimal route when the driver is fatigued as the optimized navigation route.

[0249] For example, assume the driver departs from City C to City D and the driver's fatigue state is detected. The original route plan is to pass through multiple sections of highways with a long driving time. A reminder will be given in the navigation: "Long driving may cause fatigue. It is recommended that you go to the nearest service area to rest." At the same time, the optimized navigation route is determined to be a route passing through multiple service areas and avoiding long uninterrupted highway driving.

[0250] 4) Stress State

[0251] 1. Optimization Strategy: Avoid routes with complex road conditions, busy intersections, dense traffic flows and peak traffic periods; recommend wide roads with less traffic to reduce the driver's burden; when planning the route, try to avoid sections that require complex judgments by the driver and reduce sections with frequently changing traffic lights.

[0252] 2. Technical Means:

[0253] Stress Detection and Route Optimization Model: Real-time detect the driver's stress level through facial expression data, voice feature data and heart rate. Once a high stress value is detected, preferentially recommend routes with less traffic and wide roads as the optimized navigation route to avoid busy sections and complex intersections. At the same time, combined with traffic data, the optimized navigation route will be adjusted in real time to avoid peak traffic congestion areas.

[0254] Stress Reduction Mechanism: Based on the stress state, use real-time traffic information to adjust the route plan, reduce sections that require frequent decision-making in the optimized navigation route, and remind the driver to avoid frequent lane changes on highway sections as much as possible.

[0255] For example, assume that the driver is traveling from City G to City H, and the current navigation route includes multiple busy intersections during peak hours and multiple traffic lights. Since it is detected that the driver is in a stressed state, a less congested and wider secondary road is selected as the optimized navigation route, and the driver is advised to avoid traffic congestion areas. Voice prompt: "Your current emotional state is stress. A more relaxed route has been planned for you. Please drive with confidence."

[0256] 5) Pleasant state

[0257] 1. Optimization strategy: Provide a landscape-priority route, considering the scenery and comfort along the road; select a route with a better surrounding environment, such as passing through natural landscape areas like parks and lakes to enhance the driver's mood; encourage the driver to enjoy the driving process and avoid excessive intervention and hasty route selection.

[0258] 2. Technical means:

[0259] Emotion priority adjustment: By determining the driver's current emotional state, adjust the priority of each planned navigation route. In a pleasant state, a route with beautiful scenery, comfortable road conditions, and pleasant environment will be preferentially recommended as the optimized navigation route. For example, when planning a route, scenic spots, lakes, natural scenery areas, etc. will be highlighted. It can also be reminded to the driver through the voice system: "The weather is great today, and the scenery along the way is pleasant. You will enjoy a pleasant driving journey."

[0260] Scene-aware route planning: Use a scene planning algorithm that senses the emotional state to preferentially select a route with natural scenery and suitable for sightseeing driving as the optimized navigation route, and reduce the focus on fast passage. Among them, the above-mentioned optimized navigation route is usually obtained through historical data analysis to ensure that the driver will not feel any discomfort when in a pleasant mood.

[0261] For example, assume that the driver is traveling from City E to City F, and it is detected that the driver is in a pleasant state. The current navigation route is a relatively direct highway route. A route passing through a scenic rural road can be selected as the optimized navigation route, and a voice prompt can be given: "You are driving on one of the most beautiful routes, and you can enjoy the beautiful scenery of lakes and mountains along the way. Have a pleasant drive."

[0262] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0263] Based on the same inventive concept, an embodiment of the present application also provides a path optimization device for implementing the path optimization method involved above. The solution provided by this device to solve the problem is similar to the solution recorded in the above method. Therefore, the specific limitations in one or more embodiments of the path optimization device provided below can refer to the limitations on the path optimization method in the above text, and will not be repeated here.

[0264] In an exemplary embodiment, as Figure 7 shown, a path optimization device is provided, including:

[0265] An amplitude determination module 710, configured to determine a path adjustment amplitude according to the emotion correlation data of the vehicle driver and the current navigation path of the vehicle during the vehicle driving process;

[0266] A path determination module 720, configured to determine a candidate navigation path that matches the emotion correlation data;

[0267] A path optimization module 730, configured to determine an optimized navigation path corresponding to the current navigation path according to the path adjustment amplitude and the candidate navigation path.

[0268] In an exemplary embodiment, the amplitude determination module 710 includes: a state determination unit, configured to determine the current emotion state of the driver according to the emotion correlation data of the vehicle driver; a score determination unit, configured to determine a target path score according to the current emotion state and the current path score of the current navigation path of the vehicle; an amplitude determination unit, configured to determine the path adjustment amplitude according to the current path score and the target path score.

[0269] In an exemplary embodiment, the scoring determination unit includes: a data determination subunit, configured to determine the driver's emotion index and the emotion adjustment parameter corresponding to the current emotion state according to the current emotion state; a scoring determination subunit, configured to determine the target path score according to the emotion index, the emotion adjustment parameter, and the current path score of the current navigation path of the vehicle.

[0270] In an exemplary embodiment, the data determination subunit is specifically configured to: determine the preset weight of the emotion-related data according to the current emotion state; use the preset weight to perform weighted summation on the emotion-related data to obtain the driver's emotion index.

[0271] In an exemplary embodiment, the scoring determination subunit is specifically configured to: adjust the emotion index by using the emotion adjustment parameter to obtain a target index; determine the target path score according to the product of the target index and the current path score of the current navigation path of the vehicle.

[0272] In an exemplary embodiment, the amplitude determination unit is specifically configured to: determine the difference between the target path score and the current path score; determine the target proportion of the difference in the current path score; search in the corresponding relationship between the preset adjustment amplitude and the proportion range for the adjustment amplitude corresponding to the proportion range to which the target proportion belongs, and use the found adjustment amplitude as the path adjustment amplitude.

[0273] In an exemplary embodiment, the path optimization module 730 is specifically configured to: determine the current navigation path as the optimized navigation path when the path adjustment amplitude indicates that the current navigation path matches the emotion-related data; select a target navigation path from the candidate navigation paths as the optimized navigation path corresponding to the current navigation path when the path adjustment amplitude indicates that the current navigation path does not match the emotion-related data; wherein, the proportion of the different section between the target navigation path and the non-traveled section of the current navigation path in the non-traveled section is within the proportion range corresponding to the path adjustment amplitude.

[0274] In an exemplary embodiment, the path optimization device further includes: a prompt module, configured to output a prompt message when the path adjustment amplitude indicates that the current navigation path does not match the emotion-related data; wherein, the prompt message is used to prompt the driver to switch the navigation path of the vehicle to the optimized navigation path.

[0275] Each module in the above path optimization device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in the form of hardware or be independent of it, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above respective modules.

[0276] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structural diagram may be as shown in Figure 8 . The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface and the display unit are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a path optimization method. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen.

[0277] Those skilled in the art can understand that Figure 8 the structure shown in is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0278] In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0279] In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0280] In an embodiment, a computer program product is provided, including a computer program. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0281] It should be noted that the information involved in this application (including but not limited to the driving starting point and destination of the vehicle driver, the current navigation path of the vehicle) and data (including but not limited to the emotion-related data of the vehicle driver, etc.) are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of the relevant data need to comply with the relevant regulations.

[0282] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in this application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., without limitation.

[0283] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this application.

[0284] The above-described embodiments merely represent several implementation manners of this application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of this application. It should be noted that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can still be made, and these all belong to the protection scope of this application. Therefore, the protection scope of this application shall be subject to the appended claims.

Claims

1. A path optimization method, characterized in that, The method includes: During the driving of the vehicle, determining a path adjustment amplitude according to the emotion-related data of the driver of the vehicle and the current navigation path of the vehicle; Determining a candidate navigation path that matches the emotion-related data; Determining an optimized navigation path corresponding to the current navigation path according to the path adjustment amplitude and the candidate navigation path.

2. The method according to claim 1, characterized in that, Determining a path adjustment amplitude according to the emotion-related data of the driver of the vehicle and the current navigation path of the vehicle includes: Determining the current emotional state of the driver according to the emotion-related data of the driver of the vehicle; Determining a target path score according to the current emotional state and the current path score of the current navigation path of the vehicle; Determining a path adjustment amplitude according to the current path score and the target path score.

3. The method according to claim 2, wherein Determining a target path score according to the current emotional state and the current path score of the current navigation path of the vehicle includes: Determining an emotion index of the driver and an emotion adjustment parameter corresponding to the current emotional state according to the current emotional state; Determining a target path score according to the emotion index, the emotion adjustment parameter, and the current path score of the current navigation path of the vehicle.

4. The method according to claim 3, characterized in that Determining an emotion index of the driver according to the current emotional state includes: Determining a preset weight of the emotion-related data according to the current emotional state; Using the preset weight to perform weighted summation on the emotion-related data to obtain the emotion index of the driver.

5. The method according to claim 3, wherein Determining a target path score according to the emotion index, the emotion adjustment parameter, and the current path score of the current navigation path of the vehicle includes: Adjusting the emotion index by using the emotion adjustment parameter to obtain a target index; Determining a target path score according to the product of the target index and the current path score of the current navigation path of the vehicle.

6. The method according to claim 2, wherein Determining a path adjustment amplitude according to the current path score and the target path score includes: Determining the difference between the target path score and the current path score; Determining a target proportion of the difference in the current path score; In the corresponding relationship between the preset adjustment amplitude and the proportion range, searching for the adjustment amplitude corresponding to the proportion range to which the target proportion belongs, and using the found adjustment amplitude as the path adjustment amplitude.

7. The method according to any one of claims 1-6, characterized in that, Determining an optimized navigation path corresponding to the current navigation path according to the path adjustment amplitude and the candidate navigation path includes: When the path adjustment amplitude indicates that the current navigation path matches the emotion-related data, determining the current navigation path as the optimized navigation path; When the path adjustment amplitude indicates that the current navigation path does not match the emotion-related data, selecting a target navigation path from the candidate navigation paths as the optimized navigation path corresponding to the current navigation path; wherein, the proportion of the different sections between the target navigation path and the non-driven sections of the current navigation path in the non-driven sections is within the proportion range corresponding to the path adjustment amplitude.

8. The method according to claim 7, characterized in that, When the path adjustment amplitude indicates that the current navigation path does not match the emotion-related data, the method further includes: Outputting a prompt message; wherein the prompt message is used to prompt the driver to switch the navigation path of the vehicle to the optimized navigation path.

9. A path optimization device, characterized in that, The device includes: An amplitude determination module, configured to determine a path adjustment amplitude according to the emotion-related data of the driver of the vehicle and the current navigation path of the vehicle during the driving of the vehicle; A path determination module, configured to determine a candidate navigation path that matches the emotion-related data; A path optimization module, configured to determine an optimized navigation path corresponding to the current navigation path according to the path adjustment amplitude and the candidate navigation path.

10. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images