Multi-site relay type intelligent continuous navigation system, method and terminal

Abstract

The invention provides a multi-site relay type intelligent continuous navigation system and method and a terminal, and the method comprises the steps: collecting the multi-modal biological and behavior data of a current user through site interaction terminals disposed at a plurality of key path node positions of an indoor and outdoor composite space, obtaining the navigation demands and de-identification feature codes of the current user, and obtaining the navigation demands of the current user through the de-identification feature codes; generating a navigation request message of a current user and sending the navigation request message to the navigation central server; analyzing the received navigation request message through a navigation central server connected with each site interaction terminal, executing a path planning operation, calculating a target feasible path meeting a navigation requirement, and sending the target feasible path to the corresponding site interaction terminal; displaying a target feasible path on a three-dimensional digital twinborn map of an indoor and outdoor composite space through each station interaction terminal, and guiding a current user by voice; therefore, cross-terminal relay type navigation is realized, the navigation experience of the user is improved, safe anonymous identification of the user is realized, and privacy leakage is avoided.

Description

Technical Field

[0001] This application relates to the field of intelligent navigation technology, and in particular to a multi-site relay-type intelligent continuous navigation system, method and terminal. Background Technology

[0002] Traditional navigation systems for complex spaces, such as those used in large industrial parks, underground commercial complexes, and subway transfer hubs, typically rely on static signage or mobile GPS navigation. However, static signage cannot be updated dynamically in real time and lacks interactive guidance for individualized routes; furthermore, in underground, enclosed, or multi-story structures, GPS signals are generally weak or frequently fail, making accurate positioning impossible for mobile GPS navigation.

[0003] With advancements in navigation technology, digital twin technology, and human-computer interaction technology, an intelligent navigation system that integrates high-precision positioning, multi-source data fusion, and personalized path planning is becoming the preferred choice for navigation in complex spaces.

[0004] However, most existing intelligent navigation systems adopt a "single-site" independent operation mode, which lacks the ability to continuously navigate complex indoor and outdoor mixed environments. This interrupts the continuous navigation experience for users in different locations, requiring repeated interaction with the navigation system, resulting in a poor navigation experience, especially in underground or multi-level scenarios.

[0005] Furthermore, existing intelligent navigation systems collect a significant amount of user characteristic data during user interaction, but lack user privacy protection and automatic cleanup mechanisms, which may lead to long-term storage risks and privacy leakage risks. Summary of the Invention

[0006] In view of the shortcomings of the prior art described above, the purpose of this application is to provide a multi-site relay intelligent continuous navigation system, method and terminal to solve the technical problems of existing navigation systems in complex spaces, such as lack of continuous navigation capability, poor navigation experience and risk of privacy data storage and leakage.

[0007] To achieve the above and other related objectives, a first aspect of this application provides a multi-site relay intelligent continuous navigation system for continuous navigation in an indoor-outdoor composite space. The multi-site relay intelligent continuous navigation system includes: a navigation hub server and multiple site interaction terminals respectively connected to the navigation hub server; wherein each site interaction terminal is fixedly located at multiple key path nodes in the indoor-outdoor composite space; the system performs continuous navigation in the indoor-outdoor composite space by: collecting multimodal biological and behavioral data of the current user through a site interaction terminal, obtaining the current user's navigation needs and de-identified feature codes, generating a navigation request message for the current user, and sending it to the navigation hub server; the navigation hub server parses the received navigation request message, performs path planning operations, calculates a target feasible path that meets the navigation needs, and sends the target feasible path to the site interaction terminal; the site interaction terminal receives the target feasible path, displays the target feasible path on a three-dimensional digital twin map of the indoor-outdoor composite space, and simultaneously provides voice guidance to the current user.

[0008] In some embodiments of the first aspect of this application, the site interaction terminal includes: a multimodal perception module, configured to, in response to the current user's interaction behavior, collect the current user's multimodal biometric and behavioral data in real time through one or more interaction channels; wherein the multimodal biometric and behavioral data includes one or more combinations of text modal data, voice modal data, and visual modal data; a navigation demand identification module, connected to the multimodal perception module, configured to identify the current user's navigation demand based on the multimodal biometric and behavioral data; and a user feature extraction module, connected to the multimodal perception module, configured to extract user features based on the multimodal biometric and behavioral data. The system extracts key identity features of the current user and generates a de-identified feature code for the current user. A site communication module, connected to the navigation demand identification module and the user feature extraction module, and connected to the navigation hub server, generates a navigation request message for the current user based on the navigation demand and the de-identified feature code, and sends it to the navigation hub server. The site communication module also receives the target feasible path returned by the navigation hub server. A path prompting module, connected to the site communication module, displays the target feasible path on a three-dimensional digital twin map of the indoor and outdoor composite space, and provides voice guidance to the current user.

[0009] In some embodiments of the first aspect of this application, the multimodal perception module includes: a text data acquisition unit, used to acquire one or more text modal data of the current user in real time through a text interaction channel; a voice data acquisition unit, used to acquire one or more voice modal data of the current user in real time through a voice interaction channel; and a visual data acquisition unit, used to acquire one or more visual modal data of the current user in real time.

[0010] In some embodiments of the first aspect of this application, the navigation demand identification module includes: a speech recognition unit connected to the speech data acquisition unit, configured to transcribe each acquired speech modality data into text, generating one or more text transcription data for the current user; a semantic understanding unit connected to the text data acquisition unit and the speech recognition unit, configured to perform text parsing and semantic understanding on each acquired text modality data and each transcribed text transcription data, respectively, to obtain the navigation demand of the current user; and an automatic navigation request unit connected to the visual data acquisition unit, configured to automatically obtain the navigation demand of the current user after the current user has stayed for more than a preset stay duration threshold, based on the acquired visual modality data.

[0011] In some embodiments of the first aspect of this application, the user feature extraction module includes: a voice feature extraction unit connected to the voice data acquisition unit, used to perform acoustic feature extraction and aggregation operations on each voice modality data of the current user to generate an aggregated acoustic feature vector of the current user; a visual feature extraction unit connected to the visual data acquisition unit, used to perform visual feature extraction and aggregation operations on each visual modality data of the current user to generate an aggregated visual feature vector of the current user; and a feature fusion unit connected to the voice feature extraction unit and the visual feature extraction unit, used to fuse the aggregated acoustic feature vector and the aggregated visual feature vector to generate a fused identity feature vector of the current user, and to perform binarization and hash operation on the fused identity feature vector to generate a de-identified feature code of the current user.

[0012] In some embodiments of the first aspect of this application, the navigation hub server includes: a navigation demand parsing module, configured to parse the navigation request message and obtain the current user's starting position and desired destination; a path planning module, connected to the navigation demand parsing module, configured to calculate a target feasible path from the starting position to the desired destination based on a pre-built real-time navigation topology network of the indoor-outdoor composite space; a hub communication module, connected to the navigation demand parsing module and the path planning module, and connected to each station interaction terminal, configured to receive the navigation request message sent by the station interaction terminal and forward it to the navigation demand parsing module; the hub communication module is also configured to send the target feasible path to the corresponding station interaction terminal; and a data storage and cleaning module, connected to the navigation demand parsing module, configured to generate historical navigation request records for the current user based on the current user's de-identified feature code and desired destination, and store them in a pre-built navigation request database; the data storage and cleaning module is also configured to periodically destroy expired historical navigation request records in the navigation request database based on a predefined data cleaning mechanism.

[0013] In some embodiments of the first aspect of this application, the method for obtaining the current user's desired destination includes: parsing the navigation request message, obtaining the current user's de-identified feature code, and determining whether the navigation request message contains the current user's desired destination; if the desired destination is contained, sending the desired destination to the route planning module to perform a route planning operation and updating the current user's historical navigation request record; if the desired destination is not contained, comparing the current user's de-identified feature code with the de-identified feature codes in multiple historical navigation request records stored in the navigation request database, filtering out matching historical navigation request records, and sending the historical desired destination in the historical navigation request record as the current user's desired destination to the route planning module to perform a route planning operation and updating the current user's historical navigation request record.

[0014] In some embodiments of the first aspect of this application, the navigation hub server further includes: a topology network update module, connected to the path planning module and connected to the operation and management system of the indoor and outdoor composite space, for obtaining environmental monitoring data of the indoor and outdoor composite space from the operation and management system, updating the real-time navigation topology network in real time according to the environmental monitoring data, and sending the updated real-time navigation topology network to the path planning module.

[0015] To achieve the above and other related objectives, a second aspect of this application provides a multi-site relay-based intelligent continuous navigation method, applied to a multi-site relay-based intelligent continuous navigation system. The system includes: a navigation hub server and multiple station interaction terminals respectively connected to the navigation hub server. Each station interaction terminal is fixedly installed at multiple key path node locations in an indoor-outdoor composite space. The method includes: collecting multimodal biological and behavioral data of the current user through a station interaction terminal, obtaining the current user's navigation needs and de-identified feature codes, generating a navigation request message for the current user, and sending it to the navigation hub server; parsing the received navigation request message through the navigation hub server, performing path planning operations, calculating a target feasible path that meets the navigation needs, and sending the target feasible path to the station interaction terminal; receiving the target feasible path through the station interaction terminal, displaying the target feasible path on a three-dimensional digital twin map of the indoor-outdoor composite space, and simultaneously providing voice guidance to the current user.

[0016] To achieve the above and other related objectives, a third aspect of this application provides a multi-site relay intelligent continuous navigation terminal, the multi-site relay intelligent continuous navigation terminal comprising: a memory and a processor; the memory for storing a computer program; the processor for executing the computer program stored in the memory, so that the terminal implements the function of the multi-site relay intelligent continuous navigation system described in any of the above embodiments.

[0017] As described above, this application provides a multi-site relay-type intelligent continuous navigation system, method, and terminal. Through station interaction terminals located at multiple key path nodes in an indoor-outdoor complex space, it collects the current user's multimodal biological and behavioral data, obtains the current user's navigation needs and de-identified feature codes, and generates a navigation request message for the current user, which is sent to the navigation hub server. The navigation hub server, connected to each station interaction terminal, parses the received navigation request message, performs path planning operations, calculates a feasible target path that meets the navigation needs, and sends it to the corresponding station interaction terminal. Through each station interaction terminal, the feasible target path is displayed on a 3D digital twin map of the indoor-outdoor complex space, while providing voice guidance to the current user. Therefore, this application has the following beneficial effects: it realizes cross-terminal relay navigation, improves the user navigation experience, and achieves secure anonymous user identification, avoiding privacy leaks, thereby solving the technical problems of existing complex space navigation systems, such as lack of continuous navigation capabilities, poor navigation experience, and risks of privacy data storage and leakage. Attached Figure Description

[0018] Figure 1 The diagram shown is a structural schematic of a multi-site relay intelligent continuous navigation system according to an embodiment of this application.

[0019] Figure 2 The diagram shown is a flowchart of a multi-site relay intelligent continuous navigation method according to an embodiment of this application.

[0020] Figure 3 The diagram shown is a structural schematic of a site interaction terminal in one embodiment of this application.

[0021] Figure 4 The diagram shown is a structural schematic of multiple functional modules of a site interaction terminal in one embodiment of this application.

[0022] Figure 5 The diagram shown is a structural schematic of a navigation hub server in one embodiment of this application.

[0023] Figure 6 The diagram shown is a flowchart of cross-terminal continuous navigation in one embodiment of this application.

[0024] Figure 7 The diagram shown is a structural schematic of a multi-site relay intelligent continuous navigation terminal according to an embodiment of this application. Detailed Implementation

[0025] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0026] In the embodiments of this application, terms such as "first" and "second" are used to distinguish identical or similar items with essentially the same function and purpose. For example, "first site interaction terminal" and "second site interaction terminal" are merely used to distinguish different site interaction terminals and do not limit their order. Those skilled in the art will understand that terms such as "first" and "second" do not limit the quantity or execution order, and that "first" and "second" do not necessarily imply that they are different.

[0027] To address the problems mentioned above, this application provides a multi-site relay-type intelligent continuous navigation system, method, and terminal, aiming to solve the technical problems of existing navigation systems in complex spaces, such as lack of continuous navigation capabilities, poor navigation experience, and risks of privacy data storage and leakage.

[0028] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions in the embodiments of this application are further described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for explaining this application and are not intended to limit this application.

[0029] like Figure 1 The diagram illustrates the structure of a multi-site relay intelligent continuous navigation system according to an embodiment of this application. The multi-site relay intelligent continuous navigation system in this embodiment mainly includes: a navigation hub server and multiple station interaction terminals.

[0030] Each station's interactive terminal is fixedly installed at multiple key path nodes in the indoor-outdoor composite space and is connected to the navigation hub server, forming a distributed relay network.

[0031] It should be understood that the multi-site relay intelligent continuous navigation system is used for continuous navigation of indoor and outdoor composite spaces, such as large hospitals, exhibition halls, industrial parks, underground commercial complexes, and subway transfer hubs. The interactive terminals at each site can be fixedly set at key path nodes such as entrances and exits, elevator entrances, corridors, and parking lots, so that users can seek navigation assistance in a timely manner in the indoor and outdoor composite spaces.

[0032] The multi-site relay intelligent continuous navigation system provides continuous navigation for the indoor-outdoor composite space via the following steps S1-S3: Figure 2 As shown.

[0033] Step S1: Collect the current user's multimodal biological and behavioral data through a site interactive terminal, obtain the current user's navigation needs and de-identified feature code, generate the current user's navigation request message and send it to the navigation hub server.

[0034] In one embodiment, such as Figure 3 As shown, the site interaction terminal includes: a multimodal perception module, a navigation demand identification module, a user feature extraction module, and a site communication module.

[0035] Specifically, the multimodal perception module is used to respond to the current user's interactive behavior and collect the current user's multimodal biological and behavioral data in real time through one or more interactive channels.

[0036] In one specific embodiment, such as Figure 4 As shown, the multimodal perception module includes: a text data acquisition unit, a voice data acquisition unit, and a visual data acquisition unit.

[0037] The text data acquisition unit is used to collect one or more text modal data of the current user in real time through a text interaction channel. Preferably, the text data acquisition unit includes one or more input devices, such as a keyboard or touch screen, installed on the site interaction terminal. In this embodiment, through the text data acquisition unit, the user can directly input their desired destination to ask the site interaction terminal for directions.

[0038] The voice data acquisition unit is used to collect one or more voice modal data of the current user in real time through the voice interaction channel. Preferably, the voice data acquisition unit includes one or more voice acquisition devices, such as microphones, installed on the site interaction terminal. In this embodiment, through the voice data acquisition unit, the user can have a real-time conversation with the site interaction terminal within a preset range (such as within 1 meter of the site interaction terminal), including waking up the site interaction terminal and asking the site interaction terminal for directions.

[0039] The visual data acquisition unit is used to collect one or more visual modal data of the current user in real time. Preferably, the visual data acquisition unit includes one or more image acquisition devices, such as cameras and radar, installed on the site interaction terminal. In this embodiment, the visual data acquisition unit can capture the user's facial image, body contour, and clothing features when the user is near the site interaction terminal, in order to extract the user's key identity features as a basis for user identification.

[0040] Therefore, the multimodal perception module collects one or more text modal data, one or more voice modal data, and one or more visual modal data of the current user through the text data acquisition unit, the voice data acquisition unit, and the visual data acquisition unit, respectively, thereby obtaining the current user's multimodal biological and behavioral data. The multimodal biological and behavioral data includes one or more combinations of text modal data, voice modal data, and visual modal data. For example, if the current user directly inputs their desired destination via the touchscreen, the visual data acquisition unit captures the current user's visual modal data in real time, thus obtaining multimodal biological and behavioral data including both text and visual modal data; similarly, if the current user asks for directions via voice, the visual data acquisition unit captures the current user's visual modal data in real time, thus obtaining multimodal biological and behavioral data including both voice and visual modal data.

[0041] like Figure 3 As shown, the navigation demand identification module is connected to the multimodal perception module and is used to identify the current user's navigation demand based on the multimodal biological and behavioral data.

[0042] In one specific embodiment, such as Figure 4 As shown, the navigation request identification module includes: a voice recognition unit, a semantic understanding unit, and an automatic navigation request unit.

[0043] Among them, such as Figure 4 As shown, the speech recognition unit is connected to the speech data acquisition unit of the multimodal perception module, and is used to transcribe the acquired speech modal data into text respectively, generating one or more text transcription data of the current user.

[0044] In one embodiment, based on a pre-trained speech recognition model, the collected speech modality data can be transcribed into text to generate corresponding text transcription data. The speech recognition model can be trained using unsupervised or semi-supervised learning methods, based on deep neural networks, convolutional neural networks, recurrent neural networks, or long short-term memory networks. It should be noted that the network structure and training method of the speech recognition model are not specifically limited in this application, and users can implement it using existing speech recognition technologies.

[0045] like Figure 4 As shown, the semantic understanding unit is connected to the speech recognition unit and to the text data acquisition unit of the multimodal perception module. It is used to perform text parsing and semantic understanding on the acquired text modal data and the transcribed text data to obtain the current user's navigation needs.

[0046] In one embodiment, a pre-trained semantic understanding model can be used to perform text parsing and semantic understanding on the collected text modal data and transcribed text data to identify the current user's navigation needs. Specifically, text preprocessing and cleaning are performed on each text modal data and transcribed text data, and a word segmenter is used for word segmentation to identify semantic elements in the text and determine the current user's navigation intent and / or desired destination. For example, when the text is identified to contain a preset wake word or navigation word, it is determined that the current user has a navigation intent, thereby enabling the system to provide navigation guidance services to the current user in a timely manner. It should be noted that the navigation needs include: navigation intent and / or desired destination.

[0047] The semantic understanding model can be trained using unsupervised or semi-supervised learning methods, based on convolutional neural networks, recurrent neural networks, classifiers, or large language models. It should be noted that this application does not specifically limit the network structure and training method of the semantic understanding model; users can implement it using existing large language technologies.

[0048] In this embodiment, the semantic understanding unit can accurately identify the user's navigation intent, so that the site interaction terminal only initiates a navigation request to the navigation hub server when the user has a navigation intent, thus avoiding frequent requests to the navigation hub server and wasting computing resources.

[0049] In one embodiment, the method of identifying the current user's navigation needs includes: interacting with the current user in multiple rounds through the multimodal perception module and the navigation needs identification module to confirm the current user's final and unique desired destination.

[0050] For example, if a user asks for directions to a hot pot restaurant through the first station interactive terminal, the multimodal perception module collects the voice modality data and the navigation demand recognition module identifies the user's desired destination as "hot pot restaurant." However, since the destination is not specific, the first station interactive terminal can continue to interact with the user, such as searching for all hot pot restaurants within the indoor and outdoor complex for the user to choose from. Once the user selects a specific hot pot restaurant, the navigation demand recognition module can identify the user's specific desired destination and send it to the navigation hub server to provide the user with a corresponding feasible path.

[0051] In a preferred embodiment, such as Figure 4 As shown, the navigation demand identification module further includes an automatic navigation request unit. The automatic navigation request unit is connected to the visual data acquisition unit of the multimodal perception module. Based on the acquired visual modal data, it determines that the current user has navigation intent after the current user has stayed near the current site's interactive terminal for more than a preset dwell time threshold, automatically obtains the current user's navigation demand, and sends a navigation request message to the navigation hub server.

[0052] The navigation requirements also include the current user's starting location. In one embodiment, the starting location may be determined by the current location of the current site interaction terminal. In other embodiments, it may also be determined by the identifier of the current site interaction terminal and the network layout of the interaction terminals at each site. This application does not limit the specific method used.

[0053] like Figure 3 As shown, the user feature extraction module is connected to the multimodal perception module and is used to extract the key identity features of the current user based on the multimodal biological and behavioral data, and generate the de-identified feature code of the current user.

[0054] In one specific embodiment, such as Figure 4 As shown, the user feature extraction module includes: a voice feature extraction unit, a visual feature extraction unit, and a feature fusion unit.

[0055] like Figure 4 As shown, the speech feature extraction unit is connected to the speech data acquisition unit of the multimodal perception module, and is used to perform acoustic feature extraction and aggregation operations on the speech modal data of the current user to generate the aggregated acoustic feature vector of the current user.

[0056] In one embodiment, an acoustic feature extraction and aggregation operation can be performed on each speech modality data of the current user based on a pre-trained speech feature extraction model to generate an aggregated acoustic feature vector for the current user. Specifically, each speech modality data is preprocessed, including pre-emphasis, framing, and windowing operations. Feature extraction is then performed on the preprocessed speech modality data, calculating the feature vector of each frame of speech signal. The feature vectors are then aggregated to generate the aggregated acoustic feature vector for the current user.

[0057] The speech feature extraction model can be trained using unsupervised or semi-supervised learning methods based on convolutional neural networks, recurrent neural networks, or self-attention and Transformer networks. It should be noted that this application does not specifically limit the network structure and training method of the speech feature extraction model.

[0058] like Figure 4 As shown, the visual feature extraction unit is connected to the visual data acquisition unit of the multimodal perception module, and is used to perform visual feature extraction and aggregation operations on the visual modal data of the current user to generate the aggregated visual feature vector of the current user.

[0059] In one embodiment, a pre-trained visual feature extraction model can be used to extract and aggregate visual features from each visual modality data to generate an aggregated visual feature vector for the current user. The visual feature extraction model can be trained using unsupervised or semi-supervised learning methods based on a convolutional neural network or a Transformer network. It should be noted that the network structure and training method of the visual feature extraction model are not specifically limited in this application.

[0060] like Figure 4 As shown, the feature fusion unit, connected to the speech feature extraction unit and the visual feature extraction unit, is used to fuse the aggregated acoustic feature vector and the aggregated visual feature vector to generate a fused identity feature vector for the current user. The fused identity feature vector is then binarized and hashed to generate a de-identified feature code for the current user. Preferably, the de-identified feature code can be represented using a 128-bit hash value.

[0061] This application, through the user feature extraction module, can capture the current user's voice features, facial features, body features, and clothing features as key identity features of the current user, without retaining the original voice modality data and visual modality data. This achieves secure and anonymous identification through de-identified feature codes, protecting user privacy.

[0062] like Figure 3 As shown, the site communication module connects the navigation demand identification module and the user feature extraction module, and is also connected to the navigation hub server.

[0063] Specifically, the site communication module is used to generate a navigation request message for the current user based on the current user's navigation needs and de-identified feature code, and send it to the navigation hub server. The navigation request message includes at least: the current user's de-identified feature code, starting position, and / or desired destination.

[0064] Step S2: The navigation hub server parses the received navigation request message, performs path planning, calculates the target feasible path that meets the navigation requirements, and sends the target feasible path to the station's interactive terminal.

[0065] In one embodiment, the navigation hub server can be implemented as a cloud server, thereby forming an edge computing and cloud collaboration mode with the interactive terminals of each station set in a fixed location, and realizing flexible system deployment.

[0066] In one embodiment, such as Figure 5 As shown, the navigation hub server includes: a navigation demand analysis module, a path planning module, and a hub communication module.

[0067] like Figure 5 As shown, the central communication module is connected to the interactive terminals of each station. Specifically, the station communication modules connected to the interactive terminals of each station are used to receive the navigation request messages sent by the interactive terminals of each station. Simultaneously, the central communication module is also connected to the navigation demand parsing module, used to forward each navigation request message to the navigation demand parsing module, so that the navigation demand parsing module and the route planning module can process each navigation request message in parallel.

[0068] The navigation request parsing module is used to parse each navigation request message and obtain the starting location and desired destination of one or more current users.

[0069] In one embodiment, obtaining the current user's desired destination includes the following steps.

[0070] ① Parse the navigation request message, obtain the de-identified feature code of the current user, and determine whether the navigation request message contains the current user's expected destination.

[0071] ② If the desired destination is included, the desired destination is sent to the route planning module to perform route planning operations.

[0072] For example, when a user asks for directions for the first time at the first station's interactive terminal, "How do I get to Children's Playground in Area A?", the system recognizes that the user's desired destination is Children's Playground in Area A. At this point, the navigation request parsing module directly sends the desired destination to the route planning module.

[0073] In one embodiment, such as Figure 5 As shown, the navigation hub server further includes a data storage and cleanup module. This module is connected to the navigation request parsing module and is used to generate historical navigation request records for the current user based on the current user's de-identified feature code and desired destination, and store these records in a pre-built navigation request database. The historical navigation request records include, but are not limited to, the de-identified feature code, desired destination, request time, and user interaction records.

[0074] If the navigation request message contains the current user's desired destination, then the current user's historical navigation request record is generated or updated. Specifically, the current user's de-identified feature code is compared with the de-identified feature codes in multiple historical navigation request records stored in the navigation request database. If a historical navigation request record is matched, the current user is determined to be a returning user who has previously asked the system for directions, and the desired destination, request time, and user interaction records in that historical navigation request record are updated. If no historical navigation request record is matched, the current user is determined to be a new user who is asking the system for directions for the first time, and a new historical navigation request record is generated and stored in the navigation request database.

[0075] ③ If the desired destination is not included, the de-identified feature code of the current user is compared with the de-identified feature codes of multiple historical navigation request records stored in the navigation request database. The matching historical navigation request record is selected, and the historical desired destination in the historical navigation request record is sent to the route planning module as the desired destination of the current user to perform the route planning operation.

[0076] For example, if a user asks for directions at the first interactive terminal, "How do I get to Children's Playground A?", and then stops at the second interactive terminal, the system automatically recognizes the user's navigation intent and confirms that the user's desired destination is still Children's Playground A. At this point, the navigation request parsing module resends the desired destination to the route planning module. This eliminates the need for the user to repeatedly input information, enabling continuous navigation across terminals.

[0077] At the same time, update the current user's historical navigation request record, specifically updating the request time and user interaction record in the historical navigation request record.

[0078] The purpose of this design in this embodiment is to provide timely navigation guidance without requiring users to repeatedly input the same desired destination, establishing a multi-site relay navigation system that greatly enhances the user's continuous navigation experience. Furthermore, this application uses de-identified biometric codes to identify users, avoiding the storage of original user feature data, such as voice and visual modal data, thereby achieving secure and anonymous identification, protecting user privacy, and avoiding the risks of privacy storage and leakage.

[0079] In one embodiment, the data storage and cleaning module is further configured to periodically destroy expired historical navigation request records in the navigation request database based on a predefined data cleaning mechanism. Specifically, this includes periodically querying the request time of each historical navigation request record and determining whether the storage duration of each historical navigation request record exceeds a temporary data storage duration threshold defined in the data cleaning mechanism. If the temporary data storage duration threshold is exceeded, the historical navigation request record is deleted; otherwise, the historical navigation request record is retained.

[0080] For example, the temporary data storage duration threshold is set to 30 minutes. When a user asks for directions for the first station interaction terminal for the first time, a historical navigation request record is generated and stored in the navigation request database. If the user does not ask for directions from any station interaction terminal within 30 minutes, the request time of the historical navigation request record is periodically checked. If the historical navigation request record has exceeded the temporary data storage duration threshold, it should be deleted. If the user asks for directions from a second station interaction terminal within 30 minutes, the request time of the historical navigation request record is updated. If the request time of the historical navigation request record is periodically checked and it has not exceeded the temporary data storage duration threshold, the historical navigation request record is retained until the user no longer asks for directions from any station interaction terminal, at which point it is destroyed.

[0081] This application uses the data cleaning mechanism to periodically destroy expired historical navigation request records, destroy user de-identified feature codes and user interaction records, realizing data "use and burn", taking into account data privacy and continuity, and avoiding the risks of long-term data storage and privacy leakage.

[0082] like Figure 5 As shown, the path planning module is connected to the navigation demand analysis module and is used to calculate the target feasible path from the starting position to the desired destination based on the pre-built real-time navigation topology network of the indoor and outdoor composite space.

[0083] The real-time navigation topology network includes multiple path nodes and feasible paths connecting these path nodes. It should be noted that each path node can be set up according to the spatial layout of the indoor and outdoor composite space, serving as a landmark location such as entrances / exits, elevator entrances, corridors, signage shops, and interactive terminals to guide users.

[0084] In one embodiment, the method of calculating a target feasible path from the starting position to the desired destination based on the real-time navigation topology network includes the following steps.

[0085] ① Map the starting position and the desired destination to the real-time navigation topology network.

[0086] ②Based on the real-time navigation topology network, a path search algorithm is used to calculate one or more candidate feasible paths from the starting position to the desired destination in real time.

[0087] The candidate feasible path includes: the starting position, the desired destination, and one or more path nodes.

[0088] In one specific embodiment, the path search algorithm includes, but is not limited to, the shortest path first (Dijkstra) algorithm, the optimal heuristic search algorithm, the fast randomized tree search (RRT) algorithm, and its variants. It should be noted that users can choose a suitable path search algorithm according to their needs, and this application does not specifically limit the choice.

[0089] ③ Based on the preset path evaluation criteria, each candidate feasible path is scored, and the candidate feasible path with the highest score is taken as the target feasible path.

[0090] The route evaluation criteria include one or more of the following: route length, travel time, and road congestion status.

[0091] In one embodiment, such as Figure 5 As shown, the navigation hub server also includes a topology network update module.

[0092] like Figure 5 As shown, the topology network update module is connected to the path planning module and the operation management system of the indoor and outdoor composite space. It is used to obtain environmental monitoring data of the indoor and outdoor composite space from the operation management system, update the real-time navigation topology network in real time according to the environmental monitoring data, and send the updated real-time navigation topology network to the path planning module.

[0093] The environmental monitoring data includes at least: passenger flow monitoring data, road congestion monitoring data, and operating equipment status monitoring data of the indoor and outdoor composite space. These data can be obtained through multiple sensors installed at various locations in the indoor and outdoor composite space. This data is used to update the availability status of each path node and the availability and congestion status of each feasible path in the real-time navigation topology network in real time. This optimizes the target feasible path calculated based on the real-time updated navigation topology network, providing the most suitable navigation guidance for the current user.

[0094] In a preferred embodiment, the topology network update module also supports manual updating of the real-time navigation topology network.

[0095] like Figure 5 As shown, the central communication module is also connected to the path planning module, and further connected to the interactive terminals of each station. The central communication module is also used to send the target feasible path calculated by the path planning module to the corresponding station interactive terminal.

[0096] Step S3: Receive the target feasible path through the site's interactive terminal, display the target feasible path on the three-dimensional digital twin map of the indoor and outdoor composite space, and provide voice guidance to the current user.

[0097] In one embodiment, such as Figure 2 As shown, the site interaction terminal further includes a path suggestion module. The path suggestion module is connected to the site communication module. The site communication module is also used to receive the feasible target path returned by the navigation hub server and forward it to the path suggestion module.

[0098] The path prompting module is used to display the target feasible path on a 3D digital twin map of the indoor-outdoor composite space, while simultaneously providing voice guidance to the current user. In one embodiment, the target feasible path can be displayed on a display screen on the 3D digital twin map of the indoor-outdoor composite space, and voice guidance can be provided to the current user via a voice playback device. Preferably, the display screen can be a touch screen, which displays the target feasible path on one hand, and on the other hand serves as a text data acquisition unit to collect one or more text modal data input by the current user.

[0099] In one embodiment, to enhance the interactive experience, the site interactive terminal can provide a digital human interactive interface, employing a digital human interaction engine to engage in human-like interaction with the user. This includes communicating with the user through a chat box on a touchscreen or via voice, collecting the user's text modal data and / or voice modal data for use in the multimodal perception module; and guiding the user to the desired destination via voice according to the target feasible path for use in the path prompting module. This application introduces a digital human interactive interface, which can effectively improve information comprehension and user trust.

[0100] To better describe the specific process of continuous navigation in indoor and outdoor composite spaces by the multi-site relay intelligent continuous navigation system, especially the human-computer interaction process between the user and the interactive terminals of each station in the system, as well as the cross-terminal continuous navigation process, the present invention provides a specific embodiment for detailed explanation.

[0101] Example 1: A multi-site relay intelligent continuous navigation system applied to commercial complexes

[0102] The multi-site relay-type intelligent continuous navigation system includes a navigation hub server and 12 station interactive terminals connected to the navigation hub server. Each station interactive terminal is located at key path nodes such as the entrance, elevator lobby, corridor nodes, and parking lot exit of the commercial complex.

[0103] In this embodiment, each site interactive terminal is equipped with a touch screen, microphone, camera and voice playback device.

[0104] The navigation hub server is pre-built with a real-time navigation topology network including 134 path nodes and 268 feasible paths for performing path planning operations.

[0105] To more clearly describe the human-computer interaction process between users and various site terminals, as well as the cross-terminal continuous navigation process, such as Figure 6 As shown, the multi-site relay intelligent continuous navigation system performs cross-terminal continuous navigation in the following steps.

[0106] Step S601: The current user stays at the first station interactive terminal. The touch screen of the first station interactive terminal collects one or more text modal data of the current user, the microphone of the first station interactive terminal collects one or more voice text modal data of the current user, and the camera of the first station interactive terminal collects one or more visual modal data of the current user.

[0107] Step S602: Through the first station interactive terminal, based on the collected text modal data, voice modal data and visual modal data, identify the current user's navigation intention, starting position and expected destination, extract the current user's key identity features, generate the current user's de-identified feature code, and generate the current user's navigation request message to be sent to the navigation hub server.

[0108] Step S603: Through the navigation hub server, based on the pre-built real-time navigation topology network, calculate the target feasible path from the starting position to the desired destination and send it to the first station interactive terminal, and generate the current user's historical navigation request record and store it in the pre-built navigation request database.

[0109] Step S604: Display the target feasible path on the three-dimensional digital twin map of the commercial complex through the touch screen of the first station interactive terminal, and simultaneously guide the current user through voice playback device.

[0110] Step S605: The current user stops at the second station interactive terminal according to the guidance. There is no need to repeatedly enter the desired destination. The camera of the first station interactive terminal collects one or more visual modal data of the current user. After the current user stays for more than a preset stay time threshold, the starting position and de-identified feature code of the current user are automatically obtained, and a navigation request message of the current user is generated and sent to the navigation hub server.

[0111] Step S606: The navigation hub server compares the de-identified feature code of the current user with the de-identified feature codes of multiple historical navigation request records stored in the navigation request database, filters out matching historical navigation request records, and uses the historical expected destination in the historical navigation request record as the expected destination of the current user, so as to calculate the target feasible path from the starting position to the expected destination and send it to the second station interaction terminal, while updating the historical navigation request record of the current user.

[0112] Step S607: Display the target feasible path on the three-dimensional digital twin map of the commercial complex through the touch screen of the second station interactive terminal, and simultaneously guide the current user through voice playback device.

[0113] The multi-site relay intelligent continuous navigation system described in this application realizes cross-terminal relay navigation in GPS-free environments. Experiments show that path continuity can be improved by about 42% in complex multi-layer composite spatial environments, and the single path update delay is less than 0.2 seconds, thereby reducing the user's repeated inquiry rate by 73% and increasing the satisfaction with guidance continuity to 4.7 points (out of 5), verifying its practicality and reliability in intelligent continuous navigation scenarios in indoor and outdoor composite spaces.

[0114] Furthermore, the multi-site relay intelligent continuous navigation system achieves temporary and continuous user identification through anonymous de-identified feature codes, eliminating the need for user account login and protecting user privacy. Experiments show that, with an average passenger density of 2.3 people / m², the cross-terminal user identification success rate based on de-identified feature codes reaches as high as 96.1%, further enhancing the user navigation experience. The multi-site relay intelligent continuous navigation system also utilizes a data cleanup mechanism to dynamically clean up expired de-identified feature codes and user interaction records, further protecting user privacy, avoiding leakage risks, and ensuring data compliance and minimal data retention.

[0115] Therefore, the multi-site relay intelligent continuous navigation system described in this application forms a complete intelligent interaction link, realizing full-process intelligence and privacy compliance from user identification, navigation demand identification, navigation guidance to data destruction, and solving the technical problems of existing navigation systems in complex spaces, such as lack of continuous navigation capability, poor navigation experience, and risk of privacy data storage and leakage.

[0116] It should be understood that the module division in the embodiments of this application is illustrative and only represents a logical functional division. In actual implementation, there may be other division methods. Furthermore, the functional modules in the various embodiments of this application can be integrated into a single processor or functional module, exist as separate physical entities, or be divided into more functional modules. The integrated modules or units described above can be implemented in hardware or as software functional modules.

[0117] This application also provides a multi-site relay-based intelligent continuous navigation method. This method can be applied to any of the multi-site relay-based intelligent continuous navigation systems described in the above embodiments, thereby providing continuous navigation in indoor and outdoor composite spaces. The specific process of the multi-site relay-based intelligent continuous navigation method is as follows: Figure 2 As shown.

[0118] It should be understood that the multi-site relay intelligent continuous navigation method and the multi-site relay intelligent continuous navigation system provided in the above embodiments belong to the same inventive concept. The specific process of performing the multi-site relay intelligent continuous navigation method to continuously navigate indoor and outdoor composite spaces has been described in detail in the above system embodiments, and will not be repeated here for the sake of brevity.

[0119] Figure 7 This is a structural schematic diagram of the multi-site relay intelligent continuous navigation terminal 700 provided in an embodiment of this application. Figure 7As shown, the multi-site relay intelligent continuous navigation terminal 700 includes: at least one processor 701, a memory 702, at least one network interface 703, and a user interface 705. The various components in the terminal are coupled together via a bus system 704 to implement the functions of the multi-site relay intelligent continuous navigation system described in the above embodiments. It is understood that the bus system 704 is used to realize the connection and communication between these components. In addition to a data bus, the bus system 704 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in… Figure 7 The general will label all buses as bus systems.

[0120] The user interface 705 may include a monitor, keyboard, mouse, trackball, clicker, button, touchpad, or touch screen.

[0121] It is understood that memory 702 can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM) or programmable read-only memory (PROM), which serves as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM) and synchronous static random access memory (SSRAM). The memories described in the embodiments of this application are intended to include, but are not limited to, these and any other suitable categories of memory.

[0122] In this embodiment, the memory 702 is used to store various types of data to support the operation of the multi-site relay intelligent continuous navigation terminal 700. Examples of this data include: any executable program for operation on the multi-site relay intelligent continuous navigation terminal 700, such as operating system 7021 and application program 7022; operating system 7021 includes various system programs, such as framework layer, core library layer, driver layer, etc., for implementing various basic services and handling hardware-based tasks. Application program 7022 may include various applications, such as media player, browser, etc., for implementing various application services. The implementation of the multi-site relay intelligent continuous navigation method provided in this embodiment can be included in application program 7022.

[0123] The multi-site relay intelligent continuous navigation method disclosed in the above embodiments of this application can be applied to or implemented by the processor 701. The processor 701 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the multi-site relay intelligent continuous navigation method can be completed by the integrated logic circuits in the hardware of the processor 701 or by instructions in software form. The processor 701 can be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 701 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor 701 can be a microprocessor or any conventional processor, etc. The steps of the multi-site relay intelligent continuous navigation method provided in the embodiments of this application can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software modules can be located in a storage medium, which is located in a memory. The processor reads information from the memory and, in conjunction with its hardware, completes the steps of the aforementioned method.

[0124] In an exemplary embodiment, the multi-site relay intelligent continuous navigation terminal 700 may be used by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), or complex programmable logic devices (CPLDs) to perform the aforementioned method.

[0125] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented using computer program-related hardware. The aforementioned computer program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0126] In the embodiments provided in this application, the computer-readable and writable storage medium may include read-only memory, random access memory, EEPROM, CD-ROM or other optical disc storage devices, disk storage devices or other magnetic storage devices, flash memory, USB flash drive, portable hard drive, or any other medium capable of storing desired program code in the form of instructions or data structures and accessible by a computer. Additionally, any connection may be appropriately referred to as a computer-readable medium. For example, if instructions are transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of medium. However, it should be understood that computer-readable and writable storage media and data storage media do not include connections, carrier waves, signals, or other transient media, but are intended for non-transient, tangible storage media. The disks and optical discs used in the application include compact optical discs (CDs), laser optical discs, optical discs, digital multifunction optical discs (DVDs), floppy disks, and Blu-ray discs, where disks typically copy data magnetically, while optical discs use lasers to copy data optically.

[0127] In summary, this application provides a multi-site relay-type intelligent continuous navigation system, method, and terminal. Through station interaction terminals located at multiple key path nodes in an indoor-outdoor complex space, it collects the current user's multimodal biological and behavioral data, obtains the current user's navigation needs and de-identified feature codes, and generates a navigation request message for the current user, which is then sent to the navigation hub server. The navigation hub server, connected to each station interaction terminal, parses the received navigation request message, performs path planning operations, calculates a feasible target path that meets the navigation requirements, and sends it to the corresponding station interaction terminal. Through each station interaction terminal, the feasible target path is displayed on a 3D digital twin map of the indoor-outdoor complex space, while simultaneously providing voice guidance to the current user. This achieves cross-terminal relay navigation, improves the user navigation experience, and enables secure anonymous user identification, preventing privacy leaks.

[0128] Therefore, this application effectively overcomes the various shortcomings of the prior art and has high industrial application value.

[0129] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A multi-site relay-type intelligent continuous navigation system for continuous navigation in indoor-outdoor composite spaces, characterized in that, include: A navigation hub server and multiple station interaction terminals respectively connected to the navigation hub server; The interactive terminals at each site are fixedly installed at multiple key path nodes in the indoor-outdoor composite space. The system performs continuous navigation of the indoor-outdoor composite space in the following ways: Through a site-interactive terminal, the system collects the current user's multimodal biological and behavioral data, obtains the current user's navigation needs and de-identified feature codes, generates the current user's navigation request message, and sends it to the navigation hub server. The navigation hub server parses the received navigation request message, performs path planning, calculates the target feasible path that meets the navigation requirements, and sends the target feasible path to the station's interactive terminal. The system receives the target feasible path through the interactive terminal at the site and displays the target feasible path on a three-dimensional digital twin map of the indoor and outdoor composite space, while providing voice guidance to the current user.

2. The multi-site relay intelligent continuous navigation system according to claim 1, characterized in that, The site interaction terminal includes: A multimodal perception module is used to respond to the current user's interactive behavior and collect the current user's multimodal biometric and behavioral data in real time through one or more interaction channels; wherein, the multimodal biometric and behavioral data includes one or more combinations of text modal data, voice modal data and visual modal data; A navigation demand identification module, connected to the multimodal perception module, is used to identify the current user's navigation demand based on the multimodal biological and behavioral data; The user feature extraction module, connected to the multimodal perception module, is used to extract the key identity features of the current user based on the multimodal biological and behavioral data, and generate the de-identified feature code of the current user. The site communication module connects to the navigation demand identification module and the user feature extraction module, and is also connected to the navigation hub server. It is used to generate a navigation request message for the current user based on the navigation demand and the de-identified feature code, and send it to the navigation hub server. The site communication module is also used to receive the target feasible path returned by the navigation hub server. The path suggestion module, connected to the site communication module, is used to display the feasible path to the target on the three-dimensional digital twin map of the indoor and outdoor composite space, and provide voice guidance to the current user.

3. The multi-site relay intelligent continuous navigation system according to claim 2, characterized in that, The multimodal sensing module includes: The text data acquisition unit is used to collect one or more text modal data of the current user in real time through the text interaction channel; The voice data acquisition unit is used to collect one or more voice modal data of the current user in real time through the voice interaction channel; The visual data acquisition unit is used to acquire one or more visual modal data of the current user in real time.

4. The multi-site relay intelligent continuous navigation system according to claim 3, characterized in that, The navigation requirement identification module includes: The speech recognition unit, connected to the speech data acquisition unit, is used to transcribe each acquired speech modality data into text, generating one or more text transcription data for the current user. The semantic understanding unit, connected to the text data acquisition unit and the speech recognition unit, is used to perform text parsing and semantic understanding on the acquired text modal data and the transcribed text data to obtain the current user's navigation needs. An automatic navigation request unit, connected to the visual data acquisition unit, is used to automatically obtain the navigation needs of the current user after the current user has stayed for more than a preset stay duration threshold, based on the acquired visual modal data.

5. The multi-site relay intelligent continuous navigation system according to claim 3, characterized in that, The user feature extraction module includes: The speech feature extraction unit, connected to the speech data acquisition unit, is used to perform acoustic feature extraction and aggregation operations on each speech modality data of the current user to generate the aggregated acoustic feature vector of the current user. The visual feature extraction unit, connected to the visual data acquisition unit, is used to perform visual feature extraction and aggregation operations on the visual modal data of the current user, and generate the aggregated visual feature vector of the current user. The feature fusion unit, connected to the speech feature extraction unit and the visual feature extraction unit, is used to fuse the aggregated acoustic feature vector and the aggregated visual feature vector to generate the fused identity feature vector of the current user, and to perform binarization and hash operation on the fused identity feature vector to generate the de-identified feature code of the current user.

6. The multi-site relay intelligent continuous navigation system according to claim 1, characterized in that, The navigation hub server includes: The navigation request parsing module is used to parse the navigation request message and obtain the current user's starting location and desired destination; The path planning module, connected to the navigation demand analysis module, is used to calculate the target feasible path from the starting position to the desired destination based on the pre-built real-time navigation topology network of the indoor and outdoor composite space. The central communication module connects the navigation requirement parsing module and the path planning module, and is also connected to the interactive terminals of each station. It is used to receive the navigation request message sent by the interactive terminals of each station and forward it to the navigation requirement parsing module. The central communication module is also used to send the target feasible path to the corresponding interactive terminal. The data storage and cleaning module, connected to the navigation request parsing module, is used to generate historical navigation request records for the current user based on the current user's de-identified feature code and desired destination, and store them in a pre-built navigation request database. The data storage and cleaning module is also used to periodically destroy expired historical navigation request records in the navigation request database based on a predefined data cleaning mechanism.

7. The multi-site relay intelligent continuous navigation system according to claim 6, characterized in that, The methods for obtaining the current user's desired destination include: Parse the navigation request message to obtain the de-identified feature code of the current user, and determine whether the navigation request message contains the current user's expected destination; If the desired destination is included, the desired destination is sent to the route planning module to perform route planning operations and update the current user's historical navigation request record. If the desired destination is not included, the current user's de-identified feature code is compared with the de-identified feature codes of multiple historical navigation request records stored in the navigation request database. A matching historical navigation request record is selected, and the historical desired destination in the historical navigation request record is sent to the route planning module as the current user's desired destination to perform route planning operations and update the current user's historical navigation request record.

8. The multi-site relay intelligent continuous navigation system according to claim 6, characterized in that, The navigation hub server also includes: The topology network update module is connected to the path planning module and the operation management system of the indoor and outdoor composite space. It is used to obtain environmental monitoring data of the indoor and outdoor composite space from the operation management system, update the real-time navigation topology network in real time according to the environmental monitoring data, and send the updated real-time navigation topology network to the path planning module.

9. A multi-site relay-based intelligent continuous navigation method, characterized in that, An application is made to a multi-site relay-based intelligent continuous navigation system. The system includes a navigation hub server and multiple station interaction terminals connected to the navigation hub server. Each station interaction terminal is fixedly located at multiple key path nodes in an indoor / outdoor composite space. The method includes: Through a site-interactive terminal, the system collects the current user's multimodal biological and behavioral data, obtains the current user's navigation needs and de-identified feature codes, generates the current user's navigation request message, and sends it to the navigation hub server. The navigation hub server parses the received navigation request message, performs path planning, calculates the target feasible path that meets the navigation requirements, and sends the target feasible path to the station's interactive terminal. The system receives the target feasible path through the interactive terminal at the site and displays the target feasible path on a three-dimensional digital twin map of the indoor and outdoor composite space, while providing voice guidance to the current user.

10. A multi-site relay-type intelligent continuous navigation terminal, characterized in that, include: Memory and processor; The memory is used to store computer programs; The processor is used to execute the computer program stored in the memory to enable the terminal to perform the functions of the multi-site relay intelligent continuous navigation system as described in any one of claims 1 to 8.

Images