Path planning method and device, electronic equipment and readable storage medium

Abstract

Embodiments of the present application provide a path planning method and device, electronic equipment and a readable storage medium, comprising: obtaining first emotional data of a target user in a current road section; obtaining second emotional data of a reference user in the current road section, wherein the reference user and the target user have the same user type; generating an emotional identifier under the current road section according to the second emotional data; comparing the scene data corresponding to the current road section with the pre-stored historical scene data to obtain a comparison result; predicting an abnormal emotional probability according to the second emotional data and the first emotional data; and generating a target path according to the abnormal emotional probability, the first emotional data, the comparison result and a preset feasible path. Embodiments of the present application can realize path planning based on emotional regulation according to the physiological emotional state of the user in navigation, and provide better navigation experience for the target user group.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of maps, and particularly relates to a path planning method and device, electronic equipment and a readable storage medium. BACKGROUND

[0002] With the rapid development of mobile Internet, people's travel is more and more convenient. In a strange place, a map software can always give us the nearest route. However, for some groups of people, the shortest distance is not the best, such as the visually impaired group. In some noisy and crowded intersections and streets, they will be under great pressure. People with mental disorders will have a strong negative emotional response to specific road sections or scenes. Or people with specific preferences for roads.

[0003] However, in the prior art, the current navigation system lacks interaction with the user, and the recommended route is basically consistent, which cannot plan the route according to the user's demand, resulting in a decrease in the user's experience in special scenarios or special target groups. SUMMARY

[0004] In view of the above problems, the embodiments of the present application are proposed to provide a path planning method, device, electronic equipment and readable storage medium which can overcome the above problems or at least partially solve the above problems.

[0005] In order to solve the above technical problems, the present application is implemented as follows:

[0006] In a first aspect, the present application provides a path planning method, which comprises:

[0007] obtaining first emotional data of a target user in a current road section;

[0008] obtaining second emotional data of a reference user in the current road section, wherein the reference user and the target user have the same user type;

[0009] generating an emotional identifier under the current road section according to the second emotional data;

[0010] performing similarity comparison on scene data corresponding to the current road section and pre-stored historical scene data to obtain a comparison result;

[0011] predicting an abnormal emotional probability according to the second emotional data and the first emotional data;

[0012] generating a target path according to the abnormal emotional probability, the first emotional data, the comparison result and a preset feasible path.

[0013] Optionally, the generating of the target path according to the abnormal emotional probability, the first emotional data, the comparison result and the preset feasible path comprises:

[0014] The abnormal emotion probability, the first emotion data, and the preset feasible path are input into the DL graph neural network for path planning processing, and the target path is output.

[0015] Optionally, obtaining the first emotion data of the target user in the current road segment includes:

[0016] Real-time acquisition of initial physiological signals of target users in the current road segment;

[0017] If the initial physiological signal is found to be missing, the initial physiological signal is subjected to mean filling to obtain the filled initial physiological signal.

[0018] The initial physiological signal after filling is denoised to obtain the physiological signal;

[0019] The physiological signals are preprocessed, and the processed physiological signals are then subjected to feature extraction to obtain target feature data.

[0020] The target feature data is input into a preset emotion recognition model to generate the first emotion data corresponding to the target user.

[0021] Optionally, the step of inputting the target feature data into a preset emotion recognition model to generate the first emotion data corresponding to the target user includes:

[0022] Traverse the target feature data;

[0023] Obtain the conditional mutual information between all the target feature data and the preset emotion tags;

[0024] The target feature data is traversed and sorted according to the conditional mutual information to generate the first emotion data corresponding to the target user.

[0025] Optionally, after the step of generating the emotion identifier for the current road segment based on the second emotion data, the method includes:

[0026] An emotion map is generated based on the emotion identifiers and a preset map. The emotion map includes three types of emotion markers: a first emotion marker, a second emotion marker, and a third emotion marker.

[0027] Optionally, obtaining the reference user's second emotion data in the current road segment includes:

[0028] Pre-obtain the user type corresponding to the target user;

[0029] Based on the user type, big data processing is used to obtain the third emotion data corresponding to the reference user in the current road segment.

[0030] Optionally, the step of comparing the scene data corresponding to the current road segment with pre-stored historical scene data to obtain the comparison result includes:

[0031] Real-time acquisition of map images corresponding to the current road segment;

[0032] The map image is abstracted to obtain the map data;

[0033] If the first emotion data is detected to be abnormal, scene data is generated from the map data based on point cloud technology;

[0034] The similarity of the scene data and the pre-stored historical scene data is compared to obtain the comparison results.

[0035] In a second aspect, the present invention provides a path planning device, the device comprising:

[0036] The first acquisition module is used to acquire the first emotion data of the target user in the current road segment;

[0037] The second acquisition module is used to acquire second emotion data of a reference user in the current road segment, wherein the reference user and the target user have the same user type;

[0038] The first generation module is used to generate an emotion identifier for the current road segment based on the second emotion data.

[0039] The comparison module is used to compare the similarity between the scene data corresponding to the current road segment and the pre-stored historical scene data to obtain the comparison result;

[0040] The prediction module is used to predict the probability of abnormal emotions based on the second emotion data and the first emotion data;

[0041] The second generation module is used to generate a target path based on the abnormal emotion probability, the first emotion data, the comparison result, and a preset feasible path.

[0042] Thirdly, the present invention provides an electronic device, comprising: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described path planning method.

[0043] Fourthly, the present invention provides a readable storage medium that, when the instructions in the storage medium are executed by the processor of an electronic device, enables the electronic device to perform the above-described path planning method.

[0044] In this embodiment of the invention, the following steps are taken: First emotion data of a target user in the current road segment is acquired; second emotion data of a reference user in the same road segment is acquired, wherein the reference user and the target user have the same user type; an emotion identifier for the current road segment is generated based on the second emotion data; a similarity comparison is performed between the scene data corresponding to the current road segment and pre-stored historical scene data to obtain a comparison result; the probability of abnormal emotion is predicted based on the second emotion data and the first emotion data; and a target path is generated based on the abnormal emotion probability, the first emotion data, the comparison result, and a preset feasible path. This embodiment of the invention focuses on individuals with visual impairments, mental disorders, and specific requirements for navigation routes. By considering the user's physiological and emotional state during navigation and combining it with emotion map data, it can achieve emotion-regulating navigation route recommendations. This allows the target population to integrate normally into daily life through path planning methods, acquires multimodal data during the navigation process, fully utilizes the data, improves the accuracy of emotion recognition, enhances interactivity by acquiring user emotions, and provides a better navigation experience by recommending walking paths based on user emotions. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a flowchart of the steps of a path planning method provided in an embodiment of the present invention;

[0047] Figure 2 yes Figure 1 The flowchart of step 101 in the path planning method provided in this embodiment of the invention;

[0048] Figure 3 This is a flowchart of another path planning method provided in an embodiment of the present invention;

[0049] Figure 4 This is a structural diagram of a path planning device provided in an embodiment of the present invention;

[0050] Figure 5 This is a structural diagram of an electronic device provided in an embodiment of the present invention;

[0051] Figure 6 This is a schematic diagram of interactive data acquisition provided in an embodiment of the present invention;

[0052] Figure 7This is a schematic diagram of an emotion map provided in an embodiment of the present invention. Detailed Implementation

[0053] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0054] It should be noted that, in the application of this invention to a navigation system that plans routes based on emotions, the navigation system can achieve data sharing based on preset standards, corresponding data collection devices, and GPS connections.

[0055] Figure 1 This is a flowchart of the steps of a path planning method provided in an embodiment of the present invention, as follows: Figure 1 As shown, the method may include:

[0056] Step 101: Obtain the first emotion data of the target user in the current road segment;

[0057] It should be noted that in this embodiment, route planning and navigation are based on user emotions. Therefore, firstly, the emotional data of the target user in the current road segment, i.e., the first emotional data, is obtained. Target users may include, but are not limited to, users with hearing impairments, mental disorders, and visual impairments. When using ordinary navigation systems, it is impossible to achieve efficient and personalized navigation based on the specific characteristics of these user groups. When a navigation command input by the user is received or a change in the current scene is detected requiring navigation, in addition to collecting the user's physiological signals, it is also necessary to collect scene data. The current road segment refers to the road segment where the user is located when the user opens the navigation system.

[0058] Furthermore, Figure 2 yes Figure 1 The flowchart of step 101 in the path planning method provided in this embodiment of the invention is as follows: Figure 2 As shown, step 101 may include:

[0059] Step 1011: Real-time acquisition of the initial physiological signals of the target user in the current road segment;

[0060] It should be noted that in the embodiments of this application, the target user will have different emotional reactions when facing different surrounding scenarios. For example, when the user wears smart glasses to record the generated electroencephalogram (EEG) and electrooculogram (EOG) signals, and uses a physiological electrophysiological sensor to collect skin temperature and heart rate signals, the initial physiological information of the target user under the current road segment can be collected in real time. In the embodiments of this application, the collection devices are all non-invasive, so users can wear them outdoors for a long time. This application does not make specific limitations on the collection devices, and different collection devices connected to the navigation system can be selected according to the actual situation.

[0061] For specific details, please refer to Figure 6 , Figure 6 This is a schematic diagram of interactive data collection provided by an embodiment of the present invention. It is clear that the signals to be collected include not only physiological signals but also user privacy data. This user privacy data is collected with the user's permission. For example, different user types, i.e., different user symptoms, affect different road scenarios in terms of their emotions. Visually impaired individuals may feel uncomfortable and experience negative emotions at noisy or obstacle-filled intersections; those with post-traumatic stress disorder may react strongly to specific road environments; and patients with depression may experience significant mood swings in crowded scenes. Therefore, when performing route planning based on a navigation system, it is necessary to conduct user questionnaires to generate personalized user data. User preferred road features and habitually avoided road sections are used to generate word vectors using TF-IDF technology, which are then used as input data to influence the final navigation recommendation route. Similarly, it is necessary to classify users and label their data to promote accurate route recommendations.

[0062] Step 1012: If the initial physiological signal is found to be missing, the initial physiological signal is subjected to mean filling to obtain the filled initial physiological signal.

[0063] It should be noted that after the initial physiological signal acquisition, due to the navigation process, the sensor will produce artifacts or be subject to electromagnetic interference. Furthermore, the initial physiological signal usually has a large number of small fluctuations caused by the oscillation of the human body's physiological state. Therefore, it is necessary to handle motion artifacts and data loss issues in detail, which means that the initial physiological signal will be missing at this time.

[0064] Specifically, it is necessary to check whether there are any missing initial physiological signals. If missing initial physiological signals are detected, mean-filling processing is performed on the initial physiological signals. If no missing initial physiological signals are detected, the initial physiological signals can be directly processed to the next step. For example, firstly, physiological data segments are extracted using a 3-second serial port function. If the sampling frequency is 60Hz, each window segment contains 180 data points. Discrete wavelet transform is performed on the data to make the signal into a regular signal sample. For windows that do not meet the requirement of 180 data points, missing values ​​are handled by mean-filling. That is, the window function is used to truncate the signal to each segment containing data points, and the missing values ​​are filled by mean-filling.

[0065] Step 1013: The initial physiological signal after filling is subjected to noise reduction processing to obtain the physiological signal;

[0066] After filling the initial physiological signal, wavelet transform can be used to remove noise interference. The original input signal can then be obtained by performing reconstruction filtering on the discrete wavelet transform. Here, is the mother wavelet or basic wavelet function, and is the original signal.

[0067] Step 1014: Preprocess the physiological signal, extract features from the processed physiological signal, and obtain target feature data;

[0068] Step 1015: Input the target feature data into a preset emotion recognition model to generate the first emotion data corresponding to the target user.

[0069] In steps 1014-1015 above, after removing signal artifacts (i.e., after preprocessing the physiological signal), feature extraction is performed on the processed physiological signal to extract target feature data. Then, the optimal features are obtained using a global optimal feature selection algorithm based on conditional mutual information, and these features are concatenated into a one-dimensional vector 1×C (C being the number of features). This vector is input into the pre-trained emotion recognition model to obtain Arousal and Valence values. Arousal represents the degree of arousal, indicating the intensity of the user's excitement; a higher value indicates a more intense emotion. Valence represents the degree of happiness or satisfaction; a higher value indicates a positive emotion, not a negative one. Its dimensional value ranges from 1 to 9 (1 representing the most negative, 9 the most positive), with 5 representing a neutral emotion without a clear bias. The emotional state, i.e., the first emotional data corresponding to the target user, is obtained based on the two-dimensional emotion space.

[0070] In addition, since the process of emotion generation is time-sensitive and continuous, a hidden Markov model that is sensitive to the time domain can be selected as the preset emotion recognition model. Its observation independence assumption and homogeneous Markov assumption are more in line with the needs of personalization. The final value is obtained by iteratively using the Monte Carlo calculation method.

[0071] Furthermore, the step of inputting the target feature data into a preset emotion recognition model to generate the first emotion data corresponding to the target user includes: traversing the target feature data; obtaining conditional mutual information between all the target feature data and the preset emotion tag; and performing traversal and sorting processing on the target feature data according to the conditional mutual information to generate the first emotion data corresponding to the target user.

[0072] It should be noted that since the target feature data includes time domain, frequency domain and nonlinear domain, multidimensional features may contain feature sets with similar effects or invalid feature sets. Therefore, it is particularly important to design a better feature selection algorithm. In the embodiments of the present invention, the global optimal feature selection algorithm based on conditional mutual information can achieve the selection of the optimal feature.

[0073] It should be noted that mutual information is a measure of the relationship between two (potentially multidimensional) random variables X and Y. By quantifying the amount of relevant information between random variables, it can be expressed as:

[0074]

[0075] In Formula 1 above, P represents probability, I(x, y) represents mutual information, xi and yi are the components of x and y respectively, and N and M represent that there are N and M values ​​respectively.

[0076] Step 102: Obtain the second emotion data of the reference user in the current road segment, wherein the reference user and the target user have the same user type.

[0077] Furthermore, obtaining the second emotion data of the reference user in the current road segment includes: pre-obtaining the user type corresponding to the target user; and obtaining the second emotion data of the reference user in the current road segment based on big data processing according to the user type.

[0078] It should be noted that reference users are users of the same type as target users. Based on big data technology, we can obtain the emotional data of reference users, that is, secondary emotional data.

[0079] User types are determined based on pre-set user tags. For example, user surveys can be conducted to generate personalized user data, user preferences for road features can be identified and tagged, or users can customize user tags on the navigation system's interactive page.

[0080] The purpose of obtaining the emotions of reference users is to serve as a basis for navigation on the current road segment. By using big data storage technology, the emotional reactions of users with the same type as the current user (such as visually impaired people) to the surrounding road segments are read.

[0081] Step 103: Generate an emotion identifier for the current road segment based on the second emotion data;

[0082] It should be noted that the second emotion data is historical data of reference users of the same type as the target user. Emotional labels for the current road segment and preset feasible road segments can be generated based on the second emotion data.

[0083] Among them, emotion labels can be divided into three types, such as negative emotions, calm emotions, and pleasant emotions. Furthermore, different colors can be assigned to different emotion labels. Emotion labels can be used as one of the factors to judge the probability of negative emotions that may occur in future road sections for the current user.

[0084] Furthermore, an emotion map can be constructed based on emotion markers. This involves adding emotion markers to the initial map, which can then serve as a reference for listing feasible paths when the navigation system plans routes. The emotion map represents the mood of the scene, avoiding the recommendation of paths that are more likely to evoke negative emotions, thus providing users with a pleasant navigation experience and ensuring that the user's navigation is guided by positive emotions.

[0085] Step 104: Compare the similarity between the scene data corresponding to the current road segment and the pre-stored historical scene data to obtain the comparison result;

[0086] Furthermore, the step of comparing the scene data corresponding to the current road segment with the pre-stored historical scene data to obtain the comparison result includes: acquiring the map image corresponding to the current road segment in real time; abstracting the map image to obtain the map data; generating scene data from the map data based on point cloud technology when the first emotion data is detected to be abnormal; and comparing the scene data with the pre-stored historical scene data to obtain the comparison result.

[0087] It should be noted that, in this embodiment of the invention, the pre-stored historical scene data includes road segment information where the user has experienced negative emotions. Therefore, the listed paths are compared with the road segments where the user has experienced negative emotions using a similarity algorithm. That is, the scene data corresponding to the current road segment is compared with the pre-stored historical scene data to obtain similarity data.

[0088] Specifically, the Pearson correlation coefficient method can be used for similarity comparison, as shown in Formula 2 below:

[0089]

[0090] Where E represents the expectation, σ Y Let X and Y represent the variance, and let Y represent the path vectors. By filtering out those with high similarity, a path plan can be obtained.

[0091] Step 105: Predict the probability of abnormal emotions based on the second emotion data and the first emotion data;

[0092] It should be noted that, in this embodiment of the invention, based on the emotion identifier and the comparison result in step 104, the probability that the target user may experience negative emotions in future road segments, i.e., the probability of abnormal emotions, can be predicted. This prediction can be based on a probability formula, as expressed in Formula 3:

[0093]

[0094] Where, p(x 1：T Z represents the probability of generating negative emotions in historical data. t This indicates the user's current mood and calculates the probability of the user experiencing negative emotions on the subsequent routes. Based on the mood map, the navigation system plans reachable paths and generates a list of feasible routes. The mood map represents the mood of the scene, avoiding the recommendation of paths with a high probability of generating negative emotions, thus providing the user with a pleasant navigation experience and ensuring the user maintains a positive mood during navigation.

[0095] Step 106: Generate a target path based on the abnormal emotion probability, the first emotion data, the comparison result, and a preset feasible path, wherein the preset feasible path is generated based on the emotion map corresponding to the emotion identifier.

[0096] Furthermore, the step of generating a target path based on the abnormal emotion probability, the first emotion data, the comparison result, and the preset feasible path includes: inputting the abnormal emotion probability, the first emotion data, and the preset feasible path into a DL graph neural network for path planning processing, and outputting the target path.

[0097] It should be noted that in this embodiment, the source data includes not only user emotions but also path data and probability data of abnormal emotional reactions. For multi-source data, regular neural networks do not perform well; therefore, graph neural networks are used. Graph neural networks can be considered as infinite-dimensional data, so they lack translation invariance. Since emotion recognition is always a changing process, the graph neural network is modified by altering its DropOut mechanism. Instead of randomly deactivating neurons, DropOut is performed based on computation to avoid overfitting. Neurons are layered, and each layer uses Bayesian posterior estimation for gradient estimation during training. DropOut can be used as a trick in training deep neural networks to prevent overfitting.

[0098] Specifically, based on the gradient descent value of the neuron and the probability of the neuron not being selected in the previous training round, the posterior probability of the parameter is obtained. The specific class conditional probability density of the gradient descent of each neuron is obtained according to the form of the posterior probability of the parameter and the class conditional probability density. Finally, the posterior probability of the gradient descent of each neuron is obtained. For the final emotion loss function, since the final result needs to match the route, the loss function needs to be binarized. First, the emotion is divided into positive and negative binary cases (divided into 5), and then the binary cases are further subdivided into various road emotions: such as pleasure, excitement, fear, and stress, so as to better complete the path planning task.

[0099] In addition, real-time route planning needs to combine a list of feasible routes to determine the final recommended route. For road sentiment indicators from big data, the posterior probability of which road segments the user will enter will be calculated, and paths with a high probability of generating negative emotions will be eliminated. Based on the current emotional state of the user, there are two options: if the user is currently in a positive and happy state, then continue according to the current plan; if the user is in a negative emotional state, then the route needs to be changed. Based on road sentiment and the user's historical data, routes that can improve the mood and avoid generating negative emotions are recommended.

[0100] In this embodiment of the invention, the following steps are taken: First emotion data of a target user in the current road segment is acquired; second emotion data of a reference user in the same road segment is acquired, wherein the reference user and the target user have the same user type; an emotion identifier for the current road segment is generated based on the second emotion data; a similarity comparison is performed between the scene data corresponding to the current road segment and pre-stored historical scene data to obtain a comparison result; the probability of abnormal emotion is predicted based on the second emotion data and the first emotion data; and a target path is generated based on the abnormal emotion probability, the first emotion data, the comparison result, and a preset feasible path. This embodiment of the invention focuses on individuals with visual impairments, mental disorders, and specific requirements for navigation routes. By considering the user's physiological and emotional state during navigation and combining it with emotion map data, it can achieve emotion-regulating navigation route recommendations. This allows the target population to integrate normally into daily life through path planning methods, acquires multimodal data during the navigation process, fully utilizes the data, improves the accuracy of emotion recognition, enhances interactivity by acquiring user emotions, and provides a better navigation experience by recommending walking paths based on user emotions.

[0101] Figure 3 This is a flowchart of another path planning method provided in an embodiment of the present invention, as follows: Figure 3 As shown, the method may include:

[0102] Step 101: Obtain the first emotion data of the target user in the current road segment;

[0103] Step 102: Obtain the second emotion data of the reference user in the current road segment, wherein the reference user and the target user have the same user type;

[0104] Step 103: Generate an emotion identifier for the current road segment based on the second emotion data;

[0105] Specifically, the implementation of steps 101-103 above can be referred to the aforementioned description, and will not be repeated here.

[0106] Step 107: Generate an emotion map based on the emotion identifier and the preset map. The emotion map includes three types of emotion markers: a first emotion marker, a second emotion marker, and a third emotion marker.

[0107] It should be noted that, as Figure 7 As shown, Figure 7 This is a schematic diagram of an emotion map provided by an embodiment of the present invention. The emotion markers can be divided into three types: a first emotion marker, a second emotion marker, and a third emotion marker. Specifically, for example, negative emotions, calm emotions, and pleasant emotions. Furthermore, different colors can be assigned to different emotion markers. The emotion markers can be used as one of the factors to determine the probability of negative emotions that may occur in future road segments for the current user.

[0108] Furthermore, an emotion map can be generated on the initial map based on emotion markers. This involves adding emotion markers to the initial map, which can then serve as a reference for listing feasible paths when the navigation system performs route planning. The emotion map represents the mood of the scene, avoiding the recommendation of paths with a high probability of generating negative emotions, thus providing users with a pleasant navigation experience and ensuring that users navigate with positive emotions. The preset map can be any map that can be used in a navigation system; this application does not impose any specific limitations.

[0109] The emotion map, as a recognition result, can be visualized and displayed to the target users. Specifically, feasible roads can be marked in yellow. Big data analysis shows that different colors represent different emotions for the same type of users regarding road sections: red for negative emotions, blue for calm emotions, and green for positive emotions. The area of ​​each color represents the number of times that emotion is marked. The interface clearly shows which road sections are most likely to evoke negative emotions. For visually impaired users, voice prompts can be provided.

[0110] To facilitate user interaction, if a target user disagrees with the sentiment map results during navigation, they can manually color the path to interact with the system and achieve personalized path recommendations.

[0111] This invention focuses on individuals with visual impairments, mental disorders, and specific navigation requirements. By considering the user's physiological and emotional state during navigation and combining it with emotional map data, it can recommend navigation routes based on emotion regulation. This allows the target population to integrate into their daily lives through route planning methods, acquire multimodal data during the navigation process, fully utilize the data, improve the accuracy of emotion recognition, enhance interactivity by acquiring user emotions, and provide a better navigation experience by recommending walking routes based on user emotions.

[0112] In addition, by constructing an emotion map, which marks the real emotional reactions of users of the same type to the current location, and integrating big data technology, the emotion map is made more intuitive and easier for users to identify by color and area of ​​color. Users can modify the emotion map according to their real state to enhance interactivity and make the identification more accurate, which can effectively help users maintain a good emotional state during navigation.

[0113] Figure 4 This is a structural diagram of a path planning device provided in an embodiment of the present invention. The device may include:

[0114] The first acquisition module 401 is used to acquire the first emotion data of the target user in the current road segment;

[0115] The second acquisition module 402 is used to acquire second emotion data of a reference user in the current road segment, wherein the reference user and the target user have the same user type;

[0116] The first generation module 403 is used to generate an emotion identifier for the current road segment based on the second emotion data.

[0117] The comparison module 404 is used to compare the scene data corresponding to the current road segment with the pre-stored historical scene data to obtain the comparison result;

[0118] Prediction module 405 is used to predict the probability of abnormal emotion based on the second emotion data and the first emotion data;

[0119] The second generation module 406 is used to generate a target path based on the abnormal emotion probability, the first emotion data, the comparison result, and a preset feasible path.

[0120] This invention focuses on individuals with visual impairments, mental disorders, and specific navigation requirements. By considering the user's physiological and emotional state during navigation and combining it with emotional map data, it can recommend navigation routes based on emotion regulation. This allows the target population to integrate into their daily lives through route planning methods, acquire multimodal data during the navigation process, fully utilize the data, improve the accuracy of emotion recognition, enhance interactivity by acquiring user emotions, and provide a better navigation experience by recommending walking routes based on user emotions.

[0121] The present invention also provides an electronic device, see [link to relevant documentation]. Figure 5 It includes: a processor 601, a memory 602, and a computer program 6021 stored in the memory and executable on the processor, wherein the processor executes the program to implement the method of the foregoing embodiments.

[0122] The present invention also provides a readable storage medium that, when the instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to perform the methods of the foregoing embodiments.

[0123] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0124] The algorithms and displays provided herein are not inherently related to any particular computer, virtual system, or other device. The structure required to construct such a system is readily apparent from the above description. Furthermore, this invention is not directed to any particular programming language. It should be understood that the contents of the invention described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of the invention.

[0125] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0126] Similarly, it should be understood that, in order to simplify the invention and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof. However, this method of disclosure should not be construed as reflecting an intention that the claimed invention requires more features than expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into this detailed description, wherein each claim itself is a separate embodiment of the invention.

[0127] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0128] The various component embodiments of the present invention can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components in the sorting device according to the present invention. The present invention can also be implemented as a device or apparatus program for performing part or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0129] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

[0130] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0131] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0132] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

[0133] It should be noted that the various data-related processes in the embodiments of this application are carried out in compliance with the relevant data protection laws and policies of the country where the location is located, and with the authorization granted by the owner of the corresponding device.

Claims

1. A path planning method, characterized in that, The method includes: Obtain the first emotional data of the target user in the current road segment; Obtain second emotion data of a reference user in the current road segment, wherein the reference user and the target user have the same user type; Generate an emotion identifier for the current road segment based on the second emotion data; The similarity of the scene data corresponding to the current road segment and the pre-stored historical scene data is compared to obtain the comparison result; Predict the probability of abnormal emotions based on the second emotion data and the first emotion data; A target path is generated based on the abnormal emotion probability, the first emotion data, the comparison result, and a preset feasible path, wherein the preset feasible path is generated based on the emotion map corresponding to the emotion identifier.

2. The method according to claim 1, characterized in that, The step of generating a target path based on the abnormal emotion probability, the first emotion data, the comparison result, and a preset feasible path includes: The abnormal emotion probability, the first emotion data, and the preset feasible path are input into the DL graph neural network for path planning processing, and the target path is output.

3. The method according to claim 1, characterized in that, The acquisition of the target user's first emotional data in the current road segment includes: Real-time acquisition of initial physiological signals of target users in the current road segment; If the initial physiological signal is found to be missing, the initial physiological signal is subjected to mean filling to obtain the filled initial physiological signal. The initial physiological signal after filling is denoised to obtain the physiological signal; The physiological signals are preprocessed, and the processed physiological signals are then subjected to feature extraction to obtain target feature data. The target feature data is input into a preset emotion recognition model to generate the first emotion data corresponding to the target user.

4. The method according to claim 2, characterized in that, The step of inputting the target feature data into a preset emotion recognition model to generate the first emotion data corresponding to the target user includes: Traverse the target feature data; Obtain the conditional mutual information between all the target feature data and the preset emotion tags; The target feature data is traversed and sorted according to the conditional mutual information to generate the first emotion data corresponding to the target user.

5. The method according to claim 1, characterized in that, After the step of generating the emotion identifier for the current road segment based on the second emotion data, the method includes: An emotion map is generated based on the emotion identifiers and a preset map. The emotion map includes three types of emotion markers: a first emotion marker, a second emotion marker, and a third emotion marker.

6. The method according to claim 1, characterized in that, The acquisition of the reference user's second emotion data in the current road segment includes: Pre-obtain the user type corresponding to the target user; Based on the user type, big data processing is used to obtain the second emotion data corresponding to the reference user in the current road segment.

7. The method according to claim 1, characterized in that, The step of comparing the scene data corresponding to the current road segment with the pre-stored historical scene data to obtain the comparison results includes: Real-time acquisition of map images corresponding to the current road segment; The map image is abstracted to obtain the map data; If the first emotion data is detected to be abnormal, scene data is generated from the map data based on point cloud technology; The similarity of the scene data and the pre-stored historical scene data is compared to obtain the comparison results.

8. A path planning device, characterized in that, The device includes: The first acquisition module is used to acquire the first emotion data of the target user in the current road segment; The second acquisition module is used to acquire second emotion data of a reference user in the current road segment, wherein the reference user and the target user have the same user type; The first generation module is used to generate an emotion identifier for the current road segment based on the second emotion data. The comparison module is used to compare the similarity between the scene data corresponding to the current road segment and the pre-stored historical scene data to obtain the comparison result; The prediction module is used to predict the probability of abnormal emotions based on the second emotion data and the first emotion data; The second generation module is used to generate a target path based on the abnormal emotion probability, the first emotion data, the comparison result, and a preset feasible path.

9. An electronic device, characterized in that, include: A processor, a memory, and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the program, implements the path planning method as described in any one of claims 1-7.

10. A readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device is able to perform the path planning method according to any one of claims 1-7.

Images