Position guiding method, system and device for blind person going out and medium

Abstract

The invention discloses a position guiding method, system and device for blind person travel and a medium, and relates to the technical field of blind person travel guiding. The method comprises the following steps: receiving current position information sent by a transmitting end, determining playing content based on the current position information, and playing according to the playing content; when a voice request of a blind person is received, identifying a target position in the voice request; a target route scheme is determined based on the current position information and the target position, the target route scheme comprises a plurality of sub-routes and mark points corresponding to the sub-routes, and the mark points comprise corresponding voice prompts; and playing a corresponding voice prompt according to the real-time position of the blind person sent by the transmitting end and the target route scheme. By implementing the technical scheme provided by the invention, accurate and timely position feedback can be provided for the blind, and the travel requirements of the blind in a complex urban environment are further met.

Description

Technical Field

[0001] This application relates to the technical field of blind people's travel guidance, and specifically relates to a position guidance method, system, device and medium for blind people's travel. Background Art

[0002] With the acceleration of the urbanization process and the continuous improvement of barrier-free facilities, the travel needs of the blind population are increasing day by day. At present, blind people mainly rely on traditional auxiliary tools such as guide dogs and guide canes, which to a certain extent improve the travel safety of blind people.

[0003] At present, although some blind navigation applications based on intelligent terminals have emerged, such applications provide route guidance for blind people by means of fixed and simple voice broadcasts, which to a certain extent make up for the deficiencies of traditional auxiliary tools. However, due to the fixed voice broadcast being difficult for blind people to accurately perceive the clear traveling direction, it is easy for blind people to deviate from the predetermined route, and in actual situations, due to the limitation of positioning accuracy and complex environments, existing navigation applications often cannot provide accurate and timely position feedback for blind people, and it is difficult to meet the travel needs of blind people in complex urban environments. Summary of the Invention

[0004] This application provides a position guidance method, system, device and medium for blind people's travel, which can provide accurate and timely position feedback for blind people and further meet the travel needs of blind people in complex urban environments.

[0005] In a first aspect, this application provides a position guidance method for blind people's travel, which is applied to an intelligent terminal. The intelligent terminal is communicatively connected to a transmitting end, and an RFID chip is built into the transmitting end. The method includes: Receiving the current position information sent by the transmitting end, determining the playback content based on the current position information, and playing according to the playback content; When receiving a voice request from a blind person, identifying the target position in the voice request; Determining a target route plan based on the current position information and the target position. The target route plan includes multiple sub-routes and the corresponding landmark points for each sub-route. Each landmark point includes a corresponding voice prompt; Playing the corresponding voice prompt according to the real-time position of the blind person sent by the transmitting end and the target route plan.

[0006] By adopting the above technical solutions, the current position information of the blind is obtained in real time through the RFID chip built in the transmitting end, and the corresponding playback content is determined based on this position information for playback, providing accurate position perception for the blind; when receiving the voice request of the blind, the system can intelligently identify the target position, and generate a target route plan including multiple sub-routes and landmark points based on the current position information, and corresponding voice prompts are set for each landmark point; during the blind person's progress, the system plays the corresponding voice prompts in a timely manner according to the real-time position information and the target route plan, enabling the blind person to accurately grasp the traveling direction and route information. This guidance method based on RFID positioning and intelligent voice interaction breaks through the limitations of the fixed voice broadcast method in traditional navigation applications, provides more accurate and timely position feedback and route guidance, can effectively prevent the blind from deviating from the predetermined route, and significantly improves the travel safety and convenience of the blind in complex urban environments.

[0007] In the second aspect of the present application, a position guidance system for the blind to travel is provided, which is applied to an intelligent terminal. The intelligent terminal is communicatively connected to a transmitting end, and an RFID chip is built in the transmitting end. The system includes: A position acquisition module, configured to receive the current position information sent by the transmitting end, determine the playback content based on the current position information, and play according to the playback content; A position recognition module, configured to recognize the target position in the voice request when receiving the voice request of the blind; A scheme determination module, configured to determine a target route plan based on the current position information and the target position. The target route plan includes multiple sub-routes and landmark points corresponding to each sub-route, and each landmark point includes a corresponding voice prompt; A voice prompt module, configured to determine a target route plan based on the current position information and the target position. The target route plan includes multiple sub-routes and landmark points corresponding to each sub-route, and each landmark point includes a corresponding voice prompt.

[0008] In the third aspect of the present application, a computer storage medium is provided. The computer storage medium stores multiple instructions, and the instructions are suitable for being loaded and executed by a processor to perform the above method steps.

[0009] In the fourth aspect of the present application, an electronic device is provided, including: a processor and a memory; wherein, the memory stores a computer program, and the computer program is suitable for being loaded and executed by the processor to perform the above method steps.

[0010] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: This application obtains the current location information of the blind in real time through the RFID chip built into the transmitting end, determines the corresponding playback content based on this location information for playback, and provides accurate location perception for the blind; when receiving the voice request of the blind, the system can intelligently identify the target location, and generate a target route plan including multiple sub-routes and landmark points in combination with the current location information, and corresponding voice prompts are set for each landmark point; during the blind person's journey, the system plays the corresponding voice prompts in a timely manner according to the real-time location information and the target route plan, so that the blind person can accurately grasp the traveling direction and route information. This guidance method based on RFID positioning and intelligent voice interaction breaks through the limitations of the fixed voice broadcast method in traditional navigation applications, provides more accurate and timely location feedback and route guidance, can effectively prevent the blind from deviating from the predetermined route, and significantly improves the travel safety and convenience of the blind in complex urban environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 is a schematic flowchart of a location guidance method for the blind to travel provided by an embodiment of the present application; Figure 2 is a schematic block diagram of a location guidance system for the blind to travel provided by an embodiment of the present application; Figure 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

[0012] Description of the reference numerals: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0013] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments.

[0014] In the description of the embodiments of the present application, words such as "for example" or "for illustration" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "for example" or "for illustration" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, the use of words such as "for example" or "for illustration" is intended to present relevant concepts in a specific manner.

[0015] In the description of the embodiments of the present application, the term "a plurality of" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The terms "comprise", "include", "have" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0016] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments.

[0017] The position guidance system involved in the embodiments of the present application includes two main parts: a transmitting end and a smart terminal. Among them, the transmitting end adopts a design with an embedded RFID chip and can be deployed at various key location points in the city, such as intersections, bus stops, building entrances, etc. Each RFID chip stores accurate positioning information of this location point. This RFID-based positioning method has higher accuracy and stability compared to GPS positioning and is particularly suitable for use in complex urban environments.

[0018] The smart terminal can be a portable device such as a mobile phone or a smart bracelet, including but not limited to the following functional modules: an RFID signal receiving module for receiving the location information sent by the transmitting end; a Bluetooth audio module for playing voice prompts to the blind through a Bluetooth headset; a voice recognition module for receiving and processing the voice commands of the blind; a navigation processing module integrating API interfaces of navigation services such as Amap for route planning; and a voice synthesis module for converting navigation information into voice prompts.

[0019] Exemplarily, the principle of the embodiments of the present application can be as follows: When the blind person carries the smart terminal past a certain RFID transmitting end, the smart terminal will receive the information of this location point and inform the blind person of the current location through voice broadcast. If the blind person needs to go to other places, the destination can be input by voice. The navigation processing module of the smart terminal will combine the current location information, call the navigation service to plan the optimal route, and convert the navigation guidance into voice prompts to play for the blind person. During the blind person's journey, by continuously receiving the signals of the RFID transmitting ends along the way, the system can track the blind person's location in real time and provide accurate navigation prompts in a timely manner.

[0020] Please refer to Figure 1, a flowchart of a position guiding method for blind people traveling is proposed. This method can be implemented depending on a computer program, can be implemented depending on a single-chip microcomputer, or can run on a position guiding system for blind people traveling. This computer program can be integrated in a computer device or can run as an independent tool application. Specifically, this method includes steps 10 to 40, and the above steps are as follows: Step 10: Receive the current position information sent by the transmitting end, determine the playback content based on the current position information, and play according to the playback content.

[0021] In the embodiments of the present application, the current position information refers to the geographical coordinates of the blind person's current location, and also includes the environmental characteristic information of this position point. For example, when an RFID chip is deployed at a certain position point, the accurate coordinate information of this position point, the functional attributes of the position point (such as intersections, bus stops, building entrances, etc.), the surrounding environmental characteristics (such as crosswalks, steps, turning points, etc.), possible safety hazard information, etc.

[0022] In the embodiments of the present application, the playback content refers to the complete voice prompt information generated according to the current position information, including but not limited to position description information (such as "You are currently at XX intersection"), environmental prompt information (such as "There is a crosswalk 5 meters ahead"), direction guiding information (such as "Please walk eastward along the blind path"), safety reminder information (such as "Please pay attention to the steps down on the right side").

[0023] Specifically, after the intelligent terminal receives the current position information of the RFID transmitting end, it first matches this information with the pre-set electronic map to determine the specific attributes of the position point. The system analyzes the surrounding environmental characteristics of this position point, including road types, obstacle distributions, etc., and selects a suitable playback template from the pre-set voice prompt template library. Then, according to the forward direction of the blind person, the system converts the environmental information into a relative orientation description based on the blind person's perspective, such as "There is an intersection 3 meters ahead on the left front". At the same time, the system automatically increases the playback frequency and detail level by analyzing the walking state of the blind person in real time, and provides a more detailed environmental description when detecting that the blind person slows down or stops, so as to help the blind person better plan the next action.

[0024] Based on the above embodiments, as an optional embodiment, the step of determining the playback content based on the current position information and playing according to the playback content may further include the following steps: Step 101: Obtain the spatial acoustic characteristic parameters and text playback content corresponding to the current position information.

[0025] Specifically, after receiving the location information, the smart terminal first queries the pre-set acoustic feature database, which stores acoustic parameters in different scenarios, including reverberation time, sound pressure level, sound wave attenuation coefficient, etc. The system matches the corresponding acoustic parameter group according to the type of the current location point (such as an open square, a narrow lane, an intersection, etc.). At the same time, the system extracts the corresponding text content template from the location information voice template library and fills the template with real-time environmental data to generate the complete text playback content. This scene-based acoustic parameter matching method provides basic data support for the subsequent construction of a real sound field environment.

[0026] Step 102: Based on the spatial acoustic feature parameters, match the corresponding location feature sound from the pre-set sound library.

[0027] Specifically, according to the obtained acoustic feature parameters, retrieve the environmental sound with the highest matching degree from the pre-set sound material library, which contains typical sounds in different scenarios, such as the traffic flow sound at a traffic intersection, the human voice in a commercial area, the natural environmental sound in a park, etc. The system uses a voiceprint recognition algorithm to extract features and calculate similarity for the sound materials, and selects the audio segment that is closest to the acoustic features of the current scene as the location feature sound. This intelligent matching mechanism ensures the authenticity and scene relevance of the environmental sound effects.

[0028] Step 103: Construct a three-dimensional sound field model with azimuth directivity according to the blind person's traveling direction and location feature sound.

[0029] Specifically, obtain the blind person's real-time traveling direction through the gyroscope and direction sensor built in the smart terminal. Combine the audio attributes of the location feature sound and use HRTF (Head-Related Transfer Function) technology to construct a three-dimensional sound field model. This model takes into account factors such as the sound source position, propagation distance, and spatial reflection, and can simulate the propagation characteristics of sound in three-dimensional space. The system creates a sound field environment with a clear sense of direction by adjusting the spatial position and intensity distribution of the sound source, enabling the blind person to accurately perceive the spatial layout of the surrounding environment.

[0030] Step 104: Perform spatial reconstruction processing on the text playback content based on the three-dimensional sound field model to obtain playback parameters.

[0031] Specifically, based on the constructed three-dimensional sound field model, the system performs spatial audio processing on the text playback content. First, convert the text content into a voice signal, and then calculate the acoustic transfer functions in different azimuths according to the sound field model to perform spatial filtering and phase modulation on the voice signal. The system adjusts parameters such as the binaural sound pressure difference and time difference to achieve the spatial positioning effect of the voice prompt. The finally generated playback parameters include information such as the sound source position, volume, and spectrum, ensuring that the voice prompt can accurately indicate the azimuth.

[0032] Step 105: Play the text playback content in combination with the walking parameters and playback parameters of the blind person.

[0033] Specifically, the walking data of the blind person, including the walking frequency, stride length, and walking speed, are collected in real time through the motion sensor of the intelligent terminal. According to these parameters, the rhythm and speech rate of the playback are dynamically adjusted to ensure that the voice prompt is coordinated with the walking rhythm of the blind person. At the same time, the system controls the left and right channel outputs of the stereo headphones according to the previously generated playback parameters to achieve voice playback with a sense of spatial orientation. This adaptive playback mechanism enables the blind person to receive environmental information more naturally during walking, improving the accuracy and practicality of navigation.

[0034] Based on the above embodiments, as another alternative embodiment, the step of playing the text playback content in combination with the walking parameters and playback parameters of the blind person may further include the following steps: Step 1051: Collect the walking frequency data of the blind person in real time and convert the walking frequency data into a walking speed change curve.

[0035] Specifically, the built-in three-axis acceleration sensor of the intelligent terminal is used, and the sampling frequency is set to 100 Hz. The acceleration data in the vertical direction (Z-axis) is mainly collected. The data collection process is divided into the following processing links: First, the original acceleration signal is preprocessed using a second-order Butterworth low-pass filter with a cut-off frequency set to 3 Hz to eliminate high-frequency noise; Second, the dynamic threshold detection algorithm is applied to identify the peak points of the acceleration waveform, and the time interval between two adjacent peak points is defined as a single-step period. The threshold parameter is dynamically adjusted according to the mean value of the acceleration peaks in the recent 5 seconds, and the initial threshold is set to 1.2 g; Then, the system calculates the average walking frequency in the recent 30 seconds every 100 ms, and at the same time reads the personal average stride length data from the user profile (if there is no preset, the default value of 0.65 meters is taken); Finally, the walking frequency and stride length data are substituted into the speed calculation formula v = sf (where s is the stride length and f is the walking frequency), and the Kalman filtering algorithm is used to smooth the calculation result. The process noise covariance is taken as 0.1, and the measurement noise covariance is taken as 0.5. Finally, a continuous speed change curve with a sampling interval of 100 ms is generated. This processing flow can effectively filter out the interference caused by factors such as hand shaking and accurately reflect the actual walking state of the blind person. Step 1052: Calculate the playback adjustment coefficient according to the walking speed change curve.

[0036] Specifically, the system calculates the rate of change of speed every 200 ms. The first derivative of the speed curve is calculated using the central difference method, i.e., δv = (v(t + Δt) - v(t - Δt)) / 2Δt. Secondly, the calculated rate of change of speed is compared with the rate of change of the standard walking speed (preset to 1.2 m / s). When the absolute value of the rate of change of speed exceeds the preset threshold (0.2 m / s²), the adjustment coefficient calculation process is started. The adjustment coefficient is calculated using an adaptive weight algorithm. The speech rate adjustment factor K1 = 1 + α * (v - v0) / v0, where v is the current speed, v0 is the standard speed, and α is the weight coefficient (taking the value of 0.5). The pause duration factor K2 = 1 - β * |δv|, where β is the sensitivity coefficient (taking the value of 0.3). Through this precise adjustment coefficient calculation method, the system can achieve an accurate match between the voice prompt and the walking state of the blind person.

[0037] Step 1053: Based on the adjustment coefficient, determine the speech rate and pause period of the text playback content.

[0038] Specifically, the system uses a speech synthesis technology based on the PSOLA (Pitch Synchronous Overlap and Add) algorithm to process the text content. The initial speech rate is set to 250 words per minute. The speech rate adjustment factor K1 is directly applied to the duration of the phoneme, i.e., T' = T / K1, where T is the original phoneme duration and T' is the adjusted phoneme duration. The system determines the pause insertion points by analyzing the semantic structure, mainly setting pause marks at punctuation marks and between key information words. For each pause point, the basic pause duration is set to 300 ms, and the actual pause duration S' = S * K2, where S is the basic pause duration. At the same time, the system also monitors the importance of the statement. For statements containing warning words such as "attention" and "danger", their pause durations are increased by an additional 50%. This fine-grained regulation of the speech rhythm ensures the clarity and real-time nature of information transmission.

[0039] Step 1054: Combine the three-dimensional sound field information in the playback parameters and add directional acoustic features to the text playback content.

[0040] Specifically, extract the sound source spatial coordinates (x, y, z) from the playback parameters, and calculate the azimuth angle θ and elevation angle φ relative to the user; adopt a personalized HRTF (Head-Related Transfer Function) database, which contains the transfer functions of the horizontal plane and vertical plane sampled at 15° intervals; calculate the HRTF in any direction through the trilinear interpolation algorithm; for stereo processing, the system calculates the attenuation coefficients of the left and right ears: AL = cos²(θ / 2), AR = sin²(θ / 2); at the same time, introduce a distance-based attenuation model: A(r) = 1 / (1 + kr), where r is the sound source distance and k is the attenuation coefficient (taking the value of 0.1); apply the HRTF in the frequency domain to modulate the amplitude spectrum and phase spectrum of the signal to achieve a real spatial positioning effect; finally, add early reflections and reverberation effects according to the environmental acoustic characteristics, and the reverberation time RT60 is dynamically set according to the scene type (300ms for open fields, 600ms for streets, 800ms for narrow alleys). This fine acoustic processing ensures the accuracy and naturalness of the direction cues.

[0041] Step 1055: Play the text playback content according to the adjusted speech rate, pause period, and directional acoustic characteristics.

[0042] Specifically, establish an audio output buffer with a size of 2048 samples, a sampling rate of 48kHz, and a bit depth of 24bit; adopt a multi-buffer queue technology for real-time audio processing to ensure the continuity of the audio stream; the system converts the digital signal into an analog signal through the audio processor of the smart terminal, and independently controls the gain of the left and right channels; during the audio output process, the system continuously monitors the playback state, and collects the buffer state and playback progress every 10ms; ensure the precise control of the speech rate change and pause period through the audio timestamp technology, with a time accuracy of 1ms; at the same time, realize the real-time modulation of acoustic characteristics, including sound image positioning (stereo pan range -60° to +60°) and spatial effects (reverberation depth adjustable from 0 to 100%); the system will also automatically adjust the output volume according to the environmental noise level (collected in real time through the terminal microphone) to keep the signal-to-noise ratio not less than 15dB. This precise playback control mechanism ensures that the voice prompts can maintain the best listening effect in various usage scenarios.

[0043] Step 20: When receiving the speech request of the blind person, identify the target location in the speech request.

[0044] In the embodiments of the present application, the speech request refers to the natural language navigation instruction issued by the blind user through the speech input interface of the smart terminal. It may include but is not limited to the following information: the description information of the target location (such as "Take me to the nearby Agricultural Bank"), the navigation preference settings (such as "Walk on the sidewalk", "Avoid crowded sections as much as possible"), the real-time interaction instructions (such as "Describe the current location in detail", "Repeat the previous prompt"), and the emergency help information (such as "I seem to be lost").

[0045] The target location in the embodiments of the present application refers to the specific navigation end point parsed and determined by the system according to the voice request.

[0046] Specifically, the voice request of the blind person is collected through the microphone of the intelligent terminal, and a hybrid neural network model is used for speech recognition to convert the voice signal into text. The system first performs word segmentation and part-of-speech tagging on the text, and extracts keyword groups related to locations. Subsequently, the system uses a preset location recognition semantic model and combines it with a context understanding algorithm to extract target location information from the keywords. For fuzzy expressions (such as "the bank nearby"), the system will combine the POI data of the current location and screen out specific locations that meet the conditions through the nearest neighbor search algorithm, and confirm with the blind person through voice inquiry. This intelligent recognition method can accurately understand the intentions of the blind and quickly locate the target location.

[0047] On the basis of the above embodiments, as another optional embodiment, the step of identifying the target location in the voice request may further include the following steps: Step 201: Analyze the intonation change characteristics in the voice request to identify the emphasized key points and fuzzy expressions.

[0048] Specifically, the voice signal is converted into a spectrogram through short-time Fourier transform, the sampling rate is set to 16 kHz, the frame length is 25 ms, and the frame shift is 10 ms; then, acoustic parameters such as the fundamental frequency contour (F0), energy envelope, and spectral tilt are extracted, and the intonation pattern is identified through a recurrent neural network; the system presets four basic intonation patterns: rising tone (indicating a question or uncertainty), falling tone (indicating a statement or certainty), high-level tone (indicating emphasis), and low-level tone (indicating a general statement). For the identification of emphasized key points, the system detects the peak of the pitch and the sudden change of energy. When the F0 peak of a certain syllable exceeds 20% of the adjacent syllables and the energy increases by more than 6 dB, it is marked as an emphasized key point. For fuzzy expressions, the system judges by identifying modal particles ("seem", "may", etc.) and intonation characteristics (frequent pauses, slower speech rate, etc.). Through this refined acoustic analysis, the system can accurately understand the tone characteristics and key information in the expression of the blind.

[0049] Step 202: Build a language habit model of the blind person based on the historical interaction records.

[0050] Specifically, a personalized language habit model is constructed based on the user's historical interaction records, and the processing process is as follows: Establish a user interaction log database to record all voice requests within the last three months, including the original voice, recognized text, timestamp, and scenario tags; adopt a combination of N-gram language model and word vector model to extract the user's commonly used vocabulary and sentence patterns; for each user, establish a personalized dictionary, including their habitual appellations (such as mapping "Agricultural Bank" to "Agricultural Bank of China") and location reference methods (such as the specific meaning of "old place"); the system will also statistically analyze the user's expression habits, such as the frequency of omitting the subject and the preference for using locative words. Calculate the word order conversion probability through the Markov chain model, and the weight parameters are obtained through maximum likelihood estimation. The model adopts an incremental learning method to update the parameters after each interaction to ensure that the model can dynamically adapt to changes in user habits.

[0051] Step 203: Use the language habit model to perform context completion processing on the voice request.

[0052] Specifically, establish a session state manager to maintain the context information of the last five rounds of conversations; adopt a context understanding model based on BERT to perform semantic parsing on the current voice request; the system extracts the user's personalized expression patterns from the language habit model to supplement the omitted information; for fuzzy or incomplete expressions, the system performs sequence labeling through a conditional random field (CRF) model to identify the semantic slots that need to be supplemented; the supplementation process considers spatio-temporal relevance, such as inferring possible destinations based on the current time (weekday / weekend) and location; the system sets a confidence threshold (default 0.85), and when the confidence of the completion result is lower than the threshold, interact with the user through a voice confirmation mechanism. The completed semantic representation adopts a unified framework structure, including fields such as intention type, entity information, and attribute features.

[0053] Step 204: Map the completed semantic content to a preset spatial topological relationship graph, and locate the target position through the graph inference algorithm.

[0054] Specifically, a multi-level spatial knowledge graph is established, which includes three levels: POI nodes, road network nodes, and regional nodes; each node stores spatial coordinates, attribute labels, and association relationships; the edges in the graph represent physical connection relationships and semantic association relationships, and the edge weights are dynamically updated according to distance and access frequency; the system uses a graph attention network (GAT) for node matching to align the location descriptions in the semantic content with the graph nodes; for ambiguous location descriptions, the system uses the PageRank algorithm to calculate the importance of nodes and selects the most likely target location in combination with the user's historical behavior; the system also considers time constraints and reachability constraints, calculates the optimal path through the A* algorithm, and ensures that the recommended target location is actually reachable. Finally, the system encapsulates the positioning result in a standard format, including the precise coordinates of the target location, the description of the surrounding environment, and the reachability information.

[0055] Step 30: Determine a target route plan based on the current location information and the target location. The target route plan includes multiple sub-routes and the corresponding landmark points for each sub-route, and each landmark point includes a corresponding voice prompt.

[0056] In the embodiment of the present application, the target route plan refers to the complete navigation path planned by the system from the current location of the blind person to the target location. It includes multiple sub-routes, where a sub-route is several consecutive paths divided according to road section characteristics, and each sub-path corresponds to a landmark point. A landmark point refers to a characteristic location on the sub-route that has a key prompting effect on navigation, and each landmark point includes a corresponding voice prompt, that is, the sound information played to the blind person during navigation.

[0057] Specifically, the route is planned based on a deep reinforcement learning model, and the most suitable path for the blind person to pass through is selected through multiple rounds of iterative optimization. When planning the route, the sidewalk and barrier-free passage are preferred, and construction areas and crowded sections are avoided. The system uses a semantic segmentation algorithm to identify road section characteristics and combines road sections with the same passage characteristics into sub-routes. Landmark points are set at each turning point, dangerous point, and key reference object location, and the density of landmark points is dynamically adjusted according to the real-time road conditions. The system generates personalized voice prompts for each landmark point through a natural language generation model to ensure that the prompt information is concise and clear.

[0058] On the basis of the above embodiment, as another alternative embodiment, the step of determining a target route plan based on the current location information and the target location may further include the following steps: Step 301: Input the current location information and the target location into a preset electronic map to obtain multiple alternative routes.

[0059] Specifically, the embodiments of the present application use a high-precision electronic map as the basis for path planning. The map data includes multi-layer information such as road networks, buildings, and facility distributions. The obtained current position is optimized by combining IMU data through the Kalman filter algorithm; the optimized current position and the determined target position are input into the improved A* algorithm for path search. During the search process, the system sets the maximum search radius to 5 kilometers and the search time threshold to 2 seconds; the search direction is guided by a heuristic function, and the function weights are set as follows: distance factor 0.4, road type factor 0.3, and traffic condition factor 0.3. The system simultaneously calculates 5 different alternative routes, and each route meets the basic traffic requirements, including a sidewalk coverage rate of not less than 80%, a main road section width of not less than 1.2 meters, and no serious construction occupying the road, etc. The search results include a complete path coordinate sequence, road section type markers, and key node information.

[0060] Step 302: Conduct a comprehensive evaluation of the safety, comfort, and complexity of each alternative route, and select the alternative route with the highest comprehensive evaluation score as the target route.

[0061] Specifically, each alternative route is evaluated in multiple dimensions, and the evaluation index system is as follows: safety evaluation (full score 100 points), considering sidewalk integrity (weight 0.3), intersection signal configuration (weight 0.2), pedestrian flow density (weight 0.2), lighting conditions (weight 0.2), and construction conditions (weight 0.1); comfort evaluation (full score 100 points), including road surface flatness (weight 0.3), shading facilities (weight 0.2), noise level (weight 0.2), slope change (weight 0.2), and rest facilities (weight 0.1); complexity evaluation (full score 100 points), evaluating the number of turns (weight 0.3), the number of intersections (weight 0.2), obstacle distribution (weight 0.2), road sign clarity (weight 0.2), and reference object density (weight 0.1). The system calculates the comprehensive evaluation score through weighted summation, and the weight distribution is: safety 0.4, comfort 0.3, and complexity 0.3. Select the route with the highest comprehensive evaluation score as the target route. If there is a tie for the highest score, the route with the shortest distance is preferred.

[0062] Step 303: Divide the target route into multiple sub-routes bounded by sound markers and tactile markers, and set characteristic voice prompts for each marker corresponding to each sub-route.

[0063] Specifically, the target route is intelligently segmented according to road section characteristics. First, sound landmark points and tactile landmark points are identified. Sound landmark points include: turning points (with a turning angle greater than 30 degrees), intersection points (where traffic lights are set), facility points (such as bus stops, mall entrances), and safety reminder points (such as construction areas, temporary obstacles); tactile landmark points include: raised textures on sidewalks, starting and ending points of blind paths, points of change in road surface materials, and ramp edges. The system verifies the effectiveness of landmark points in real time through a distributed sensor network and keeps the distance between adjacent landmark points within the range of 20 - 50 meters. For each landmark point, the system generates a structured voice prompt template, which includes direction instructions (8 basic directions), distance information (accurate to meters), environmental features (no more than 10 keywords), and safety reminders (if needed). The voice prompts are designed hierarchically: arrival prompts, warning prompts, and confirmation prompts, and the prompt timing is dynamically adjusted according to the walking speed of the blind person.

[0064] Step 304: Generate a target route plan that includes each sub - route and the corresponding voice prompts.

[0065] Specifically, the processed information is integrated into a target route plan in a standard format. The data structure includes: route summary (total length, estimated time, difficulty level), sub - route sequence (each sub - route includes start and end coordinates, length, type marker), landmark point information (position coordinates, type marker, priority), and voice prompt package (text content, trigger condition, playback parameters). The system encapsulates the data in JSON format and establishes an index structure to improve access efficiency. To ensure the reliability of the plan, the system conducts route rationality checks, including: continuity check (ensuring seamless connection of sub - routes), coverage check (ensuring that there are corresponding prompts for all key positions), and consistency check (ensuring that the prompt information matches the actual situation).

[0066] Step 40: According to the real - time position of the blind person sent by the transmitter and the target route plan, play the corresponding voice prompts.

[0067] Specifically, obtain the real - time position of the blind person sent by the transmitter, and perform real - time matching of the real - time position with the landmark point sequence in the target route plan. When the distance between the blind person and the next landmark point is less than 20 meters, the system starts to prepare for playing voice prompts. The voice prompts adopt a hierarchical playback strategy: first, a warning prompt is played at a distance of 15 meters from the landmark point, a detailed instruction is played at 10 meters, and a confirmation prompt is played when arriving. The system outputs the voice through bone - conduction headphones and dynamically adjusts the playback timing according to the real - time walking speed of the blind person to ensure the accuracy and timeliness of the prompts. This intelligent playback mechanism can help the blind person accurately grasp the navigation rhythm.

[0068] Based on the above embodiments, as another alternative embodiment, the step of playing corresponding voice prompts according to the real-time position of the blind person sent by the transmitting end and the target route plan may further include the following steps: Step 401: Obtain the real-time position of the blind person sent by the transmitting end, and calculate the deviation amount between the real-time position and the position of the next landmark in the target route plan.

[0069] Specifically, obtain the real-time position of the blind person sent by the transmitting end, perform real-time calculation on the coordinates of the obtained real-time position and the coordinates of the next landmark in the target route plan, and use the Haversine formula to calculate the great circle distance as the position deviation amount. For example, when the blind person is located at coordinates (39.915, 116.404) and the next landmark is located at (39.916, 116.405), the deviation amount calculated by the system is 89 meters. At the same time, the system will also calculate the angle between the moving direction of the blind person and the ideal path direction to provide a reference for subsequent navigation. This precise deviation calculation provides a reliable data basis for real-time navigation.

[0070] Step 402: When the deviation amount is within the preset deviation range and the blind person enters the preset range of the next landmark, play the voice prompt corresponding to the next landmark.

[0071] Specifically, the embodiments of the present application set up multi-level preset ranges for navigation control. The preset deviation range uses an adaptive threshold, which is set to 3 meters on the main road, 2 meters on the small road, and 1 meter in the narrow alley. The preset range of the landmark adopts a concentric circle structure: the outer warning area (radius 30 meters), the middle instruction area (radius 15 meters), and the inner confirmation area (radius 5 meters). When the position deviation of the blind person is within the preset range and enters the warning area of the landmark, the system starts a hierarchical playback mechanism: first, play "There is an intersection 300 meters ahead" in the warning area; when entering the instruction area, play detailed guidance such as "Please continue to walk 100 meters along the sidewalk and then turn right 90 degrees"; when reaching the confirmation area, play "Have arrived at the intersection and can turn right now". The system outputs the voice through a bone conduction headset, uses natural voice synthesis technology, the speech rate is 250 words per minute, and automatically adjusts the volume according to the ambient noise. This hierarchical playback strategy ensures the continuity and accuracy of navigation information.

[0072] Step 403: When the deviation amount is not within the preset deviation range, calculate the deviation direction and deviation degree between the real-time position and the position of the next landmark in the target route plan, and generate and play a voice prompt for correction guidance based on the deviation direction and deviation degree.

[0073] Specifically, when it is detected that the position deviation exceeds the preset range, the system activates the correction guidance mechanism. First, the system calculates the deviation direction and degree from the target route based on the current position and the motion vector. The deviation direction is determined by calculating the interior angle of the triangle formed by the real-time position, the current landmark, and the next landmark; the deviation degree is calculated based on the vertical distance. For example, when the blind person deviates 4 meters to the right of the predetermined route, the system immediately generates a correction prompt: "You have deviated 4 meters to the right of the route. Please turn left 30 degrees to return to the sidewalk." If the deviation continues or the deviation distance continues to increase, the system upgrades the prompt level: "Please stop moving forward and wait in place. The system will re-plan the route." The correction prompt is played in an urgent voice mode, with the speaking speed reduced to 200 words per minute, and the sound source position in the correct direction is simulated through stereo effects. This real-time correction mechanism can prevent the blind person from deviating from the predetermined route in a timely manner and improve navigation safety.

[0074] Exemplarily, for the sake of easy understanding, an example is given with a complete interaction process: Suppose the blind person is going to a hospital and is currently on the sidewalk of a commercial street. The system detects that the position of the blind person is at (39.915, 116.404), and the next landmark is a right-turn intersection at (39.916, 116.405). When the blind person walks along the sidewalk, the system continuously monitors the position deviation. When the deviation remains within 2 meters, the system normally plays the landmark prompt. When the blind person deviates 4 meters from the sidewalk while avoiding pedestrians, the system immediately plays a correction prompt: "You have deviated 4 meters from the sidewalk. Please adjust your direction to the left front", and indicates the correct direction through stereo effects. After the blind person adjusts to the correct position, the system resumes the normal navigation prompt: "The entrance of the hospital outpatient department is 50 meters ahead. Please continue to go straight along the sidewalk."

[0075] Based on the above embodiments, as an alternative embodiment, a position guidance method for the blind to travel may further include the following process: Specifically, the walking characteristic data of the blind are collected through multi-source sensors built into the intelligent terminal, including: obtaining step frequency and step amplitude data using a three-axis acceleration sensor (sampling frequency 100Hz); detecting the body swing amplitude through a gyroscope (sampling frequency 50Hz); and monitoring the heart rate change in combination with a heart rate sensor (sampling interval 1 second). The system performs real-time calculations using a preset energy evaluation system, which is constructed based on a human motion biomechanics model and includes the following calculation parameters: basal metabolic rate (preset according to the user's age, gender, and weight), exercise intensity coefficient (calculated from the step frequency and step amplitude), and environmental resistance coefficient (considering temperature, humidity, slope, etc.). The fatigue accumulation index F is obtained through a weighted calculation formula: F = α×E + β×H + γ×S, where E is the energy consumption value, H is the heart rate change rate, S is the gait stability index, and α, β, and γ are the weight coefficients (default values are 0.5, 0.3, and 0.2 respectively). For example, when it is detected that the step frequency drops from the initial 112 steps / minute to 95 steps / minute, the heart rate rises from 75 beats / minute to 95 beats / minute, and the gait stability decreases by 20%, the calculated fatigue accumulation index will increase significantly. This multi-dimensional fatigue monitoring mechanism can accurately evaluate the physical condition of the blind.

[0076] When it is detected that the fatigue accumulation index exceeds the preset threshold (default value is 80%), the rest point recommendation mechanism is activated. The system maintains a dynamically updated rest point database, which contains information about facilities such as public seats, rest areas, and indoor waiting areas. Each rest point includes a type label, a comfort score, and the situation of barrier-free facilities. The system first sets a search radius of 200 meters centered on the current position of the blind and uses the nearest neighbor algorithm to screen candidate rest points. When screening, the distance factor (weight 0.4), comfort factor (weight 0.3), and safety factor (weight 0.3) are comprehensively considered for sorting. After determining the optimal rest point, the system generates a hierarchical voice prompt: first play the reminder message "It is detected that you may need to rest", then play the navigation information "There is a bus stop with seats 100 meters ahead on the right", and finally provide auxiliary information "There is a sunshade and barrier-free facilities there". For example, when the blind person walks in the commercial area for 30 minutes and the system detects that the fatigue index reaches 85%, it immediately recommends the nearest shopping mall rest area and guides the blind person there through clear voice prompts. This timely rest reminder and accurate location guidance effectively prevent the blind from over-fatigue and improve travel safety.

[0077] Please refer to Figure 2 , which is a schematic diagram of the modules of a position guiding system for the blind to travel provided by an embodiment of the present application. Among them, the system includes: A position acquisition module, configured to receive the current position information sent by the transmitting end, determine the playback content based on the current position information, and perform playback according to the playback content; A location recognition module, configured to recognize a target location in the voice request when receiving a voice request from a blind person; A solution determination module, configured to determine a target route solution based on the current location information and the target location, where the target route solution includes a plurality of sub-routes and landmark points corresponding to each sub-route, and each landmark point includes a corresponding voice prompt; A voice prompt module, configured to determine a target route solution based on the current location information and the target location, where the target route solution includes a plurality of sub-routes and landmark points corresponding to each sub-route, and each landmark point includes a corresponding voice prompt.

[0078] Optionally, the location acquisition module is further configured to acquire a spatial acoustic feature parameter and a text playback content corresponding to the current location information; Match a corresponding location feature sound from a preset sound library based on the spatial acoustic feature parameter; Construct a three-dimensional sound field model with azimuth directivity according to the walking direction of the blind person and the location feature sound; Perform spatial reconstruction processing on the text playback content based on the three-dimensional sound field model to obtain playback parameters; Play the text playback content in combination with the walking parameters of the blind person and the playback parameters.

[0079] Optionally, the location acquisition module is further configured to collect step frequency data of the blind person in real time and convert the step frequency data into a walking speed change curve; Calculate a playback adjustment coefficient according to the walking speed change curve; Determine the speech rate and pause period of the text playback content based on the adjustment coefficient; Add a directional acoustic feature to the text playback content in combination with the three-dimensional sound field information in the playback parameters; Play the text playback content according to the adjusted speech rate, pause period, and directional acoustic feature.

[0080] Optionally, the location recognition module is further configured to analyze the intonation change feature in the voice request and recognize the emphasized key points and ambiguous expressions; Construct a language habit model of the blind person based on the historical interaction record; Perform context completion processing on the voice request by using the language habit model; Map the completed semantic content to a preset spatial topological relationship map and locate the target location through a map reasoning algorithm.

[0081] Optionally, the solution determination module is further configured to input the current location information and the target location into a preset electronic map to obtain multiple alternative routes; Perform a comprehensive evaluation of the safety, comfort, and complexity of each of the alternative routes, and select the alternative route with the highest comprehensive score as the target route; Divide the target route into multiple sub-routes bounded by voice landmark points and tactile landmark points, and set characteristic voice prompts for each landmark point corresponding to each sub-route; Generate a target route solution including each of the sub-routes and the corresponding voice prompts.

[0082] Optionally, the voice prompt module is further configured to obtain the real-time location of the blind person sent by the transmitter, and calculate the deviation amount between the real-time location and the location of the next landmark point in the target route solution; When the deviation amount is within a preset deviation range and the blind person enters the preset range of the next landmark point, play the voice prompt corresponding to the next landmark point; When the deviation amount is not within the preset deviation range, calculate the deviation direction and deviation degree between the real-time location and the location of the next landmark point in the target route solution, and generate and play a voice prompt for correction guidance based on the deviation direction and deviation degree.

[0083] Optionally, the voice prompt module is further configured to monitor the walking characteristics of the blind person, and calculate the fatigue accumulation index of the blind person in real time based on a preset energy evaluation system and the walking characteristics; When the fatigue index exceeds a preset fatigue threshold, determine the location of the nearest rest point according to the real-time location of the blind person, and play the voice prompt corresponding to the location of the rest point.

[0084] It should be noted that: when the system provided in the above embodiments implements its functions, only the above-mentioned division of each functional module is used for illustration. In practical applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be repeated here.

[0085] The embodiments of the present application further provide a computer storage medium, which can store multiple instructions. The instructions are suitable for being loaded and executed by a processor to perform a method for guiding the location of a blind person to travel in the above embodiments. The specific execution process can refer to the specific description in the above embodiments and will not be repeated here.

[0086] Please refer to Figure 3The present application also discloses an electronic device. Figure 3 It is a schematic structural diagram of an electronic device disclosed in an embodiment of the present application. The electronic device 300 may include: at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0087] Among them, the communication bus 302 is used to realize the connection and communication between these components.

[0088] Among them, the user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may further include a standard wired interface and a wireless interface.

[0089] Among them, the network interface 304 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0090] Among them, the processor 301 may include one or more processing cores. The processor 301 connects various parts within the entire server through various interfaces and lines, and by running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and by calling data stored in the memory 305, it executes various functions of the server and processes data. Optionally, the processor 301 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 301 may integrate one or several combinations of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interface, and application programs, etc.; the GPU is responsible for the rendering and drawing of the content to be displayed on the display screen; the modem is used to process wireless communication. It can be understood that the above-mentioned modem may not be integrated into the processor 301 and may be implemented separately by a single chip.

[0091] Among them, the memory 305 may include a Random Access Memory (RAM), or may also include a Read-Only Memory. Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area. Among them, the program storage area can store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area can store the data involved in the above-mentioned method embodiments. Optionally, the memory 305 may also be at least one storage device located far from the aforementioned processor 301. Refer to Figure 3 , the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program for a location guiding method for blind people to travel.

[0092] In Figure 3 In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user to obtain the data input by the user; and the processor 301 can be used to call the application program for a location guiding method for blind people to travel stored in the memory 305. When executed by one or more processors 301, the electronic device 300 is caused to execute the method of one or more of the above embodiments. It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0093] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0094] In several embodiments provided by the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling, direct coupling, or communication connection between each other can be through some service interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical or other form.

[0095] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0096] In addition, the functional units in each embodiment of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0097] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in each embodiment of the present application. And the aforementioned memory includes various media such as USB flash drives, mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0098] The above are only exemplary embodiments of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure still fall within the scope covered by the present disclosure. Those skilled in the art will easily think of other implementation schemes of the present disclosure after considering the specification and the practice of the present disclosure.

[0099] The present application aims to cover any variations, uses, or adaptive changes of the present disclosure. These variations, uses, or adaptive changes follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not recorded in the present disclosure. The specification and the embodiments are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A position guiding method for the blind to travel, characterized in that, Applied to an intelligent terminal, the intelligent terminal is communicatively connected to a transmitting end, and an RFID chip is built in the transmitting end. The method includes: Receiving the current location information sent by the transmitting end, determining the playback content based on the current location information, and playing according to the playback content; When receiving a voice request from a blind person, identifying the target location in the voice request; Determining a target route plan based on the current location information and the target location, the target route plan including a plurality of sub-routes and corresponding landmark points for each of the sub-routes, and each landmark point including a corresponding voice prompt; According to the real-time location of the blind person sent by the transmitting end and the target route plan, playing the corresponding voice prompt.

2. The position guiding method for blind people to travel according to claim 1, characterized in that, The determining the playback content based on the current location information and playing according to the playback content includes: Obtaining the spatial acoustic feature parameters and the text playback content corresponding to the current location information; Based on the spatial acoustic feature parameters, matching the corresponding location feature sound from a preset sound library; According to the walking direction of the blind person and the location feature sound, constructing a three-dimensional sound field model with azimuth directivity; Performing spatial reconstruction processing on the text playback content based on the three-dimensional sound field model to obtain playback parameters; Playing the text playback content in combination with the walking parameters of the blind person and the playback parameters.

3. The position guiding method for blind people to travel according to claim 2, characterized in that, The playing the text playback content in combination with the walking parameters of the blind person and the playback parameters includes: Real-time collecting the step frequency data of the blind person and converting the step frequency data into a walking speed change curve; Calculating a playback adjustment coefficient according to the walking speed change curve; Based on the adjustment coefficient, determining the speech rate and pause period of the text playback content; Combining the three-dimensional sound field information in the playback parameters, adding a directional acoustic feature to the text playback content; Playing the text playback content according to the adjusted speech rate, pause period and directional acoustic feature.

4. The position guiding method for blind people to travel according to claim 1, characterized in that, The identifying the target location in the voice request includes: Analyzing the intonation change characteristics in the voice request, identifying the emphasized key points and ambiguous expressions; Based on the historical interaction records, constructing a language habit model of the blind person; Performing context completion processing on the voice request by using the language habit model; Mapping the completed semantic content to a preset spatial topology relationship map, and positioning the target location through a map inference algorithm.

5. The position guiding method for blind people to travel according to claim 1, characterized in that The determining the target route plan based on the current location information and the target location includes: Inputting the current location information and the target location into a preset electronic map to obtain a plurality of alternative routes; Performing a comprehensive evaluation of the safety, comfort and complexity of each of the alternative routes, and selecting the alternative route with the highest comprehensive evaluation score as the target route; Dividing the target route into a plurality of sub-routes bounded by sound landmark points and tactile landmark points, and setting characteristic voice prompts for each landmark point corresponding to each of the sub-routes; Generating a target route plan including each of the sub-routes and the corresponding voice prompts.

6. The position guiding method for blind people to travel according to claim 1, characterized in that, Playing corresponding voice prompts according to the real-time position of the blind person sent by the transmitting end and the target route plan, including: Obtaining the real-time position of the blind person sent by the transmitting end, and calculating the deviation amount between the real-time position and the position of the next landmark in the target route plan; When the deviation amount is within a preset deviation range and the blind person enters the preset range of the next landmark, playing the voice prompt corresponding to the next landmark; When the deviation amount is not within the preset deviation range, calculating the deviation direction and deviation degree between the real-time position and the position of the next landmark in the target route plan, and generating and playing a voice prompt for correction guidance based on the deviation direction and deviation degree.

7. The position guiding method for blind people to travel according to claim 1, characterized in that, The method further includes: Monitoring the walking characteristics of the blind person, and calculating the fatigue accumulation index of the blind person in real time based on a preset energy assessment system and the walking characteristics; When the fatigue index exceeds a preset fatigue threshold, determining the position of the nearest rest point according to the real-time position of the blind person, and playing the voice prompt corresponding to the position of the rest point.

8. A position guiding system for blind people to travel, characterized in that, Applied to an intelligent terminal, the intelligent terminal is communicatively connected to a transmitting end, and an RFID chip is built in the transmitting end. The system includes: A position acquisition module, configured to receive the current position information sent by the transmitting end, determine the playback content based on the current position information, and perform playback according to the playback content; A position recognition module, configured to recognize the target position in the voice request when receiving the voice request of the blind person; A scheme determination module, configured to determine a target route plan based on the current position information and the target position, where the target route plan includes a plurality of sub-routes and the landmarks corresponding to each sub-route, and each landmark includes a corresponding voice prompt; A voice prompt module, configured to determine a target route plan based on the current position information and the target position, where the target route plan includes a plurality of sub-routes and the landmarks corresponding to each sub-route, and each landmark includes a corresponding voice prompt.

9. A computer-readable storage medium, characterized in that, A computer-readable storage medium stores multiple instructions, and the instructions are suitable for being loaded and executed by a processor to perform the method according to any one of claims 1-7.

10. An electronic device, characterized in that, Including a processor, a memory, a user interface, and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device performs the method according to any one of claims 1-7.

Images