Indoor Positioning Method and System for Ocean-going Vessels Integrating 5G Private Network and GNSS

Abstract

This invention discloses a method and system for indoor positioning of ocean-going vessels that integrates a private 5G network and GNSS, relating to the technical field of 5G communication. The key technical points are: constructing and periodically updating an indoor 5G positioning fingerprint database, which stores the location information of an open-air 5G satellite terminal, the 5G signal strength information of the positioning anchor point, relative position information, and information update time; constructing and training a positioning regression model to obtain a trained model; and triggering a real-time 5G terminal positioning query process when a 5G satellite terminal located indoors is powered on, periodically updates its location, or a local / remote monitoring system initiates a location query. This process locates the terminal based on the trained positioning regression model and the 5G positioning fingerprint database and returns the query result. This invention improves the accuracy of indoor positioning on ocean-going vessels, assists local / remote monitoring centers in quickly locating and tracking targets, improves crew safety, and reduces material loss rates.

Description

Technical Field

[0001] This invention relates to the technical field of 5G communication, and more specifically, to a method and system for indoor positioning of ocean-going vessels that integrates a private 5G network and GNSS. Background Technology

[0002] Indoor positioning systems on ocean-going vessels play a crucial role in real-time monitoring of the status of crew members and critical materials, enhancing crew safety, and preventing material loss. Currently, internal communication on ships primarily relies on wired networks and Wi-Fi. When ships are at sea, this can easily create information silos, making it difficult for land-based monitoring centers to track and locate crew members and materials in real time, posing significant safety risks.

[0003] 5G communication networks offer significant advantages in terms of high bandwidth, low latency, and wide connectivity. Deploying lightweight 5G private networks on ships can effectively support scenarios such as full-element interconnection of ship equipment, real-time high-bandwidth data transmission, and indoor positioning, providing reliable infrastructure for smart shipping. Deeply integrating shipboard 5G private networks with satellite communication networks—using 5G private networks within the ship and communicating with terrestrial 5G networks via satellite—can solve the information silo problem for ocean-going vessels. This allows for real-time transmission of the location information of people and equipment inside the ship to a remote monitoring center, improving the intelligent operation and maintenance capabilities of the integrated management platform for people and equipment.

[0004] Compared with terrestrial 5G private networks, indoor positioning using 5G private networks on ocean-going vessels presents the following challenges:

[0005] Firstly, how to perform indoor positioning of the terminal under test based on a 5G private network? 3GPP Release 16 introduced Uplink Time Difference of Arrival (UTDOA), Observed Time Difference of Arrival (OTDOA), Angle of Arrival (AOA), and Round Trip Time, but these methods require at least two base stations. However, some enclosed spaces on ships may only have one base station deployed. Fingerprinting, which links environmental location to a specific fingerprint and compares the characteristics of the target to those in a fingerprint database, can be implemented with just one base station. However, inside a ship, with multiple decks and base stations distributed across various locations, the signal received by the 5G terminal may come from one or more base stations and contain diverse information. Therefore, constructing a fingerprint database specifically for ship interiors still faces many challenges.

[0006] Secondly, the fingerprint database mainly records the fingerprint features of terminals at specific locations, while the terminals under test are mobile and randomly located within the ship. It is often difficult to find records with the same fingerprints as the terminals under test by directly querying the fingerprints. Therefore, it is urgent to explore a classification or regression method to match the fingerprint features of the terminals under test with those in the fingerprint database in order to locate them.

[0007] Furthermore, the signal pair between indoor 5G base stations and terminals obtains the relative position of the terminals, while ships and the people / materials on board move in the open ocean. How can we combine the Global Navigation Satellite System (GNSS) and 5G private network positioning technology to determine the global location information of people / materials inside the ship in real time?

[0008] Finally, how to represent the location of the target? If a global coordinate system based on latitude and longitude is used, each indoor location must undergo coordinate transformation (since satellite signals cannot be received indoors, the transformation needs to be performed based on the global coordinates of the ship's outdoor 5G satellite terminal and the 3D position difference between the target terminal and the 5G satellite terminal), which greatly increases the complexity of the ship's indoor positioning algorithm. Moreover, the remote monitoring center also needs to perform inverse coordinate transformation to know which floor, which compartment, etc., the target is on. Therefore, the representation of the target's location is a key problem that urgently needs to be solved in the indoor positioning of ocean-going vessels.

[0009] In view of this, the present invention proposes an indoor positioning method and system for ocean-going vessels that integrates ship 5G private network and GNSS. Summary of the Invention

[0010] The purpose of this invention is to provide an indoor positioning method and system for ocean-going vessels that integrates 5G private networks and GNSS, thereby improving the accuracy of indoor positioning for ocean-going vessels, assisting local / remote monitoring centers in quickly locating and tracking targets, improving crew safety, and reducing material loss rates.

[0011] The above-mentioned technical objective of the present invention is achieved through the following technical solution:

[0012] The first aspect of this invention provides an indoor positioning method for ocean-going vessels that integrates a ship's 5G private network and GNSS, comprising the following steps:

[0013] The location computing server constructs and periodically updates the 5G positioning fingerprint database inside the ship. The positioning fingerprint database stores the location information of the outdoor 5G satellite terminal, the 5G signal strength information of the positioning anchor point, the relative position information, and the information update time.

[0014] Construct and train a localization regression model to obtain a well-trained localization regression model;

[0015] When a 5G satellite terminal located indoors on a ship is powered on, or when its location is periodically updated, or when a local / remote monitoring system initiates a location query, a real-time 5G terminal location query process is triggered. This process locates the terminal based on a trained positioning regression model and a 5G positioning fingerprint database, and returns the query results.

[0016] In conjunction with the first aspect, the present invention is further configured such that the construction and periodic updating of the ship's indoor 5G positioning fingerprint database includes the following steps:

[0017] The open-air 5G satellite terminal periodically acquires the global location information of the open-air 5G satellite terminal based on GNSS, and sends the global location information and the terminal identifier of the open-air 5G satellite terminal to the location calculation server on the ship. The location calculation server updates the satellite positioning information table.

[0018] The 5G base station on the ship periodically broadcasts synchronization signal information. After receiving the synchronization signal information broadcast by the 5G base station, the positioning anchor point inside the ship extracts the 5G signal strength information from the synchronization signal information and sends the signal strength and the identifier of the positioning anchor point to the ship's location calculation server.

[0019] The location calculation server constructs or updates the location anchor information table in the location fingerprint database based on the received information of the positioning anchor points inside the ship. The positioning anchor information table includes the identifier of the positioning anchor point, relative position information, 5G signal strength information, and timestamp.

[0020] In conjunction with the first aspect, the present invention is further configured such that: the location calculation server updates the satellite positioning information table as follows: after receiving global location information and the terminal identifier of the exposed 5G satellite terminal, the location calculation server searches the satellite positioning information table in the 5G positioning fingerprint database according to the terminal identifier of the exposed 5G satellite terminal, and updates the record in the table that is the same as the terminal identifier. The satellite positioning information table includes the terminal identifier of the exposed 5G satellite terminal, global location information, relative location information, and timestamp.

[0021] In conjunction with the first aspect, the present invention is further configured such that the real-time location query process for the 5G terminal includes the following steps:

[0022] The 5G satellite terminal inside the ship receives synchronization signal information broadcast by one or more 5G base stations inside the ship's cabin, extracts 5G signal strength information and base station identifier from the synchronization information, and sends the identifier information to the location computing server. The identifier information includes the terminal identifier of the 5G satellite terminal inside the ship's cabin, the 5G signal strength, and the base station identifier.

[0023] The location calculation server determines the cabin layer where the terminal is located by using the identification information, and uses it as the Z-axis position of the terminal.

[0024] The location calculation server preprocesses the 5G signal strength data of the 5G satellite terminal inside the ship's interior, then inputs it into the trained positioning regression model, and outputs the predicted values ​​of the X-axis and Y-axis, which are used as the XY plane position of the 5G satellite terminal inside the ship's interior.

[0025] The location calculation server determines the global location information of the ship based on the latest location information from the open-air 5G satellite terminal;

[0026] The location calculation server combines the ship's global location information with the Z-axis and XY-plane positions of the 5G satellite terminal inside the ship's cabin to form a position vector.

[0027] In conjunction with the first aspect, the present invention is further configured such that: the construction and training of the localization regression model includes the following steps:

[0028] Records are drawn from the location anchor point information table of the location fingerprint database using a random sampling method with playback. Data sets, where integers The datasets have the same sample attributes and sample size. The sample attributes consist of 5G signal strength information and location information recorded in the data. Furthermore, each dataset is divided into a training set and a test set, with the training set accounting for no less than 70%.

[0029] Build A set of regression decision trees, with input variables including 5G signal strength arranged by base station cell identifier, and output variables being the X-axis position and Y-axis position, respectively. Each tree corresponds to the... One of the datasets;

[0030] Construct an additive attention regressor, the input of which is the... The output of the regression decision tree is either the final X-axis position or the Y-axis position. When the X-axis position is used as the training target, the output is the X-axis position; when the Y-axis position is used as the training target, the output is the Y-axis position. The output of the additive attention regressor is a weighted average of the inputs. In the formula, It is the output of the k-th decision tree. These are the weight coefficients of the decision tree, satisfying... ;

[0031] Train the localization regression model to obtain a well-trained localization regression model;

[0032] Training the localization regression model includes obtaining the optimal decision tree parameters and weight coefficients. This minimizes the loss function of the localization regression model, where the loss function is calculated using the following formula: In the formula, It is a truth value. This is the predicted output of the localization regression model, where D represents the size of the total dataset, and the [number]th [item] in the optimal decision tree. Tree parameters satisfy ,here, It is true. This is the output of the tree. This is the input to the tree. This is the size of the dataset for that tree.

[0033] In conjunction with the first aspect, the present invention is further configured such that: the location calculation server determines the cabin layer where the terminal is located through identification information, including the following steps:

[0034] The 5G signals received by the 5G satellite terminal are classified according to the base station identifier to form a set of neighboring base stations of the 5G satellite terminal.

[0035] From the set of neighboring base stations, select neighboring base stations with signal strength not lower than the signal strength threshold to form an effective set of neighboring base stations;

[0036] The Z-axis positions of each base station in the effective neighboring base station set are obtained from the 5G positioning fingerprint database. Then, a majority vote is conducted, and the winning Z-axis position is taken as the cabin layer where the terminal is located.

[0037] A second aspect of the present invention also provides an apparatus / device / system for indoor positioning of ocean-going vessels that integrates a shipboard 5G private network and GNSS, including a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above method.

[0038] A third aspect of the present invention also provides a computer-readable storage medium having a computer program / instructions stored thereon, which, when executed by a processor, implement the steps of the above-described method.

[0039] A fourth aspect of the present invention also provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the above-described method.

[0040] In summary, the present invention has the following beneficial effects:

[0041] 1. This invention deploys a lightweight 5G private network on ships, uses outdoor 5G satellite terminals to obtain the ship's global location based on GNSS, constructs a positioning regression model inside the ship to predict the relative position of indoor 5G terminals, and combines the ship's global location and indoor relative position to locate the indoor 5G terminals. The positioning information is then transmitted back to a ground-based remote monitoring center. This not only meets the need for precise indoor target positioning on ocean-going vessels but also breaks down information silos on ocean-going vessels, enabling remote real-time positioning and tracking of people / objects inside ocean-going vessels, improving crew safety and reducing material loss rates.

[0042] 2. The indoor positioning method for ocean-going vessels that integrates 5G private networks and GNSS disclosed in this invention uses problem decomposition and multi-dimensional position representation to solve the problem of indoor positioning of ocean-going vessels. Specifically, it obtains the global position of the ship's outdoor 5G satellite terminal through outdoor satellite positioning technology to determine the ship's global position, determines the ship's deck based on majority voting, and constructs a positioning fingerprint database and positioning regression model to determine the planar position of the terminal under test in that deck. This reduces the complexity of solving the problem. Furthermore, the positioning result is represented by (ship satellite position, ship deck, deck planar position), which can help local / remote monitoring personnel to intuitively and quickly find the location of the target under test, reduce search and rescue time, and further improve the safety of the crew.

[0043] 3. The indoor positioning system for ocean-going vessels disclosed in this invention deploys the location calculation server within the ship's 5G private network, which reduces the information exchange overhead between the 5G private network and the ground 5G core network via satellite communication network during the location calculation process, shortens the response delay of 5G terminal positioning query, and saves satellite communication costs. Attached Figure Description

[0044] Figure 1 This is the overall flowchart of the indoor positioning method for ocean-going vessels that integrates ship 5G private network and GNSS in Embodiment 1 of the present invention;

[0045] Figure 2 This is a schematic diagram of the structure of the ocean-going vessel indoor positioning system integrating the ship's 5G private network and GNSS in Embodiment 1 of the present invention;

[0046] Figure 3 This is a flowchart illustrating the method for constructing and periodically updating the 5G positioning fingerprint database inside a ship in this embodiment of the invention.

[0047] Figure 4 This is a flowchart of the localization regression model construction and training process provided in this embodiment of the invention;

[0048] Figure 5 This is a flowchart of the real-time location query process for 5G terminals in an embodiment of the present invention. Detailed Implementation

[0049] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0050] In the embodiments provided in this application, it should be understood that the disclosed methods and systems can be implemented in other ways. The system embodiments described below are merely illustrative. For example, the division of units and modules is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or modules can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, and can be electrical, mechanical, or other forms.

[0051] In addition, each functional unit in the various embodiments of this application can be integrated into a single processor, or each unit can be a separate device, or two or more units can be integrated into a single device; each functional unit in the various embodiments of this application can be implemented in hardware or in the form of hardware plus software functional units.

[0052] Those skilled in the art will understand that all or part of the steps of the following method embodiments can be implemented by program instructions and related hardware. The aforementioned program instructions can be stored in a computer-readable storage medium. When the program instructions are executed, they perform the steps of the following method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), magnetic disks, or optical disks.

[0053] It should be understood that the use of terms such as "system," "device," "unit," and / or "module" in this application is merely one method of distinguishing different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0054] If a flowchart is used in this application, it is used to illustrate the operations performed by the system according to embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0055] It should also be noted that, in this document, terms such as “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase “comprising one…” does not exclude the presence of other identical elements in the article or device that includes the aforementioned element.

[0056] Example 1:

[0057] Figure 1 This is a flowchart illustrating the overall process of the indoor positioning method for ocean-going vessels that integrates 5G private network and GNSS, as provided in this embodiment of the invention. Figure 2 This is a schematic diagram of an indoor positioning system for ocean-going vessels that integrates a private 5G network and GNSS. Figure 2 (a) is a schematic diagram of the positioning system outside the ship's exterior. Figure 2 (b) is a structural diagram of the positioning system inside the ship's interior, combined with... Figure 1-2 ,like Figure 2 As shown, the system includes a private 5G network for ships, a GNSS satellite positioning system, and 5G satellite terminals. The private 5G network is deployed inside the ship's cabin and includes lightweight 5G base stations and a lightweight 5G core network. The lightweight 5G base stations are distributed throughout the cabin, providing 5G access services for the indoor 5G satellite terminals. The lightweight 5G core network includes location service functions, which include a location computing server. The 5G core network provides 5G core network services for the indoor 5G terminals and can interact with the terrestrial 5G network via satellite communication relay. The 5G satellite terminals are equipped with 5G communication modules and satellite communication modules, and include an outdoor 5G satellite terminal, a positioning anchor point, and an indoor 5G terminal to be positioned carried on a person / object.

[0058] Indoor positioning methods for ocean-going vessels that integrate 5G private networks and GNSS, such as Figure 1 As shown, it includes the following steps:

[0059] S100. The location calculation server constructs and periodically updates the 5G positioning fingerprint database inside the ship. The positioning fingerprint database stores the location information of the open-air 5G satellite terminal, the 5G signal strength information of the positioning anchor point, the relative position information, and the information update time.

[0060] S200. The location computing server constructs and trains a location regression model to obtain a trained location regression model;

[0061] S300. When the 5G satellite terminal located indoors on the ship is powered on, or when the location is updated periodically, or when the local / remote monitoring system initiates a location query, the 5G terminal location real-time query process is triggered. This process locates the terminal based on a trained positioning regression model and a 5G positioning fingerprint database, and returns the query results.

[0062] In step S100 of this embodiment, the construction and periodic updating of the ship's indoor 5G positioning fingerprint database, as follows: Figure 3 As shown in Tables 1 and 2, the steps include the following:

[0063] S101. The open-air 5G satellite terminal periodically acquires the global location information of the open-air 5G satellite terminal based on GNSS, and sends the global location information and the terminal identifier of the open-air 5G satellite terminal to the location calculation server on the ship. The location calculation server updates the satellite positioning information table.

[0064] The location calculation server updates the satellite positioning information table as follows: After receiving the global location information and the terminal identifier of the exposed 5G satellite terminal, the location calculation server searches the satellite positioning information table in the 5G positioning fingerprint database based on the terminal identifier of the exposed 5G satellite terminal, and updates the record in the table that is the same as the terminal identifier. The satellite positioning information table includes the terminal identifier of the exposed 5G satellite terminal, global location information, relative location information, and timestamp. The global location information consists of a (longitude, latitude, altitude) triplet, and the relative location information consists of a (Z-axis, XY plane) triplet. The Z-axis records which floor the terminal is on in the ship's cabin, and the XY plane represents the XY plane coordinates of the terminal on that floor.

[0065] Table 1. Schematic diagram of the satellite positioning information table in the positioning fingerprint database

[0066]

[0067] For example, Table 1 shows the updated satellite positioning information at a certain time (202511100000). As shown in Table 1, the global position of 5G satellite terminal 1 at the latest time is (33.908, 116.39, 45), which means that the latitude and longitude of the terminal is 33.908°N, 116.39°E, 45, the altitude is 45 meters, the terminal is located on the 0th floor (open-air floor) of the ship, and the plane coordinates of the terminal are (0, 10) meters.

[0068] S102. The 5G base station on the ship periodically broadcasts synchronization signal information. After receiving the synchronization signal information broadcast by the 5G base station, the positioning anchor point inside the ship extracts the 5G signal strength information from the synchronization signal information and sends the signal strength and the identifier of the positioning anchor point to the location calculation server on the ship.

[0069] Among them, the 5G base station on the ship periodically broadcasts synchronization signal information. For example, according to the 3GPP TS38 series specifications, the 5G gNodeB base station periodically (e.g., every 20ms) sends a synchronization signal block (SSB) in each cell. The SSB contains 20 resource blocks in the frequency domain and 4 OFDM symbols in the time domain. It contains the primary synchronization signal PSS, the secondary synchronization signal SSS and the physical broadcast channel information PBCH.

[0070] The extracted 5G signal strength information consists of one or more signal strength records, which are distinguished by base station cell identifiers. A single signal strength record includes the cell identifier of the transmitted signal, SSB identifier, Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), Received Signal Strength Indicator (RSSI), and Signal-to-Noise Ratio (SNR). For example, a positioning anchor point k(k, where k is the set of positioning anchor points) inside a ship receives signal from indoor base station n(k, where n is the set of positioning anchor points). ,in The RSRP formula for the indoor base station set on the ship is as follows: It is confirmed that, among them, This represents the sum of the reference signal power received by the anchor point from the base station n. RSRQ represents the number of resource blocks in the measured bandwidth, and is determined by a formula. ,in, The received signal strength indicator (RSSI) is indicated. Indicates the number of resource blocks carrying RSSI measurement bandwidth;

[0071] S103. The location calculation server constructs or updates the location anchor information table in the location fingerprint database based on the received information of the positioning anchor points inside the ship. The positioning anchor information table includes the identifier of the positioning anchor point, relative position information, 5G signal strength information, and timestamp.

[0072] Specifically, a record is created for each anchor point in the anchor point information table, indexed by the anchor point identifier. The record contains the anchor point identifier, location information, 5G signal strength information, and a timestamp. The location information is relative, consisting of a (Z-axis, XY-plane) triplet, indicating the anchor point's floor within the ship's cabin and its planar coordinates within that floor. The timestamp indicates the moment the 5G signal strength information in the record is updated. Upon receiving information from an anchor point inside the ship's cabin, the record in the anchor point information table with the same anchor point identifier is searched. The 5G signal strength information in this record is updated to the received 5G signal strength information, and the timestamp is updated to the current moment. For example, Table 2 shows the updated anchor point information at a certain moment (202511100000). Figure 2 As shown, both anchor points 0 and 1 can receive the signal from cell 354, but due to their different locations from the base station, the 5G signal strength information they receive is different.

[0073] Table 2. Schematic diagram of the location anchor point information table in the location fingerprint database.

[0074]

[0075] In step S200 of this embodiment, the localization regression model includes at least one regression decision tree and an additive attention regressor.

[0076] In this model, the input to the regression tree is the attribute of the object to be regressed, and the output of the regression tree is the target attribute of the object to be regressed under that tree structure, i.e., the prediction result. The input to the additive attention regressor is the output of each regression tree, and the output of the additive attention regressor is the final output of the local regression model, i.e., the prediction result of the local regression model, such as... Figure 4 As shown, the localization regression model construction process and training method include:

[0077] S201: Records are drawn from the location anchor point information table of the location fingerprint database using a random sampling method with playback. Data sets, where integers The datasets have the same sample attributes and sample size. The sample attributes consist of 5G signal strength information and location information recorded in the data. Furthermore, each dataset is divided into a training set and a test set, with the training set accounting for no less than 70%.

[0078] S202: Construction Each tree represents a regression decision tree. The input variables (i.e., the attributes of the regression object) include 5G signal strength arranged by base station cell identifier. The output variables (i.e., the target attributes) are the X-axis position and the Y-axis position, respectively. Each tree corresponds to the... One of the datasets;

[0079] S203: Construct an additive attention regressor, the input of which is the... The output of the regression decision tree is either the final X-axis position or the Y-axis position. When the X-axis position is used as the training target, the output is the X-axis position; when the Y-axis position is used as the training target, the output is the Y-axis position. The output of the additive attention regressor is a weighted average of the inputs. In the formula, It is the output of the k-th decision tree. These are the weight coefficients of the decision tree, satisfying... ;

[0080] S204: Train the localization regression model to obtain a trained localization regression model.

[0081] The localization regression model, consisting of a regression decision tree and an additive attention regressor, is trained to obtain the optimal decision tree parameters and weight coefficients. This minimizes the loss function of the localization regression model, where the loss function is calculated using the following formula: In the formula, It is a truth value. This is the predicted output of the localization regression model, where D represents the size of the total dataset, and the [number]th [item] in the optimal decision tree. Tree parameters satisfy ,here, It is true. This is the output of the tree. This is the input to the tree. This is the size of the dataset for that tree.

[0082] In step S300 of this embodiment, combined with Figure 5 The real-time location query process for 5G terminals includes the following steps:

[0083] S301: The 5G satellite terminal receives synchronization signal information broadcast by one or more 5G base stations in the cabin, extracts 5G signal strength information and base station identifier from the synchronization signal information, and sends the identifier information to the location computing server. The identifier information includes the terminal identifier, the 5G signal strength, and the base station identifier.

[0084] S302: After obtaining the identification information, the position calculation server determines the cabin level where the terminal is located and uses it as the terminal's Z-axis position information; specifically:

[0085] a) Classify the 5G signals received by the 5G satellite terminal according to the base station identifier to form a set of neighboring base stations of the 5G satellite terminal;

[0086] b) Extract neighboring base stations with signal strength not lower than the signal strength threshold from the neighboring base station set to form an effective neighboring base station set;

[0087] c) Obtain the Z-axis position of each base station in the effective neighboring base station set from the positioning fingerprint database, and then conduct a majority vote. The Z-axis position that wins the vote is taken as the cabin layer where the terminal is located, that is, as the Z-axis position of the terminal.

[0088] S303: The location calculation server preprocesses the 5G signal strength of the terminal, which may be normalization, and then inputs it into the positioning regression model to obtain the predicted values ​​of the X-axis and Y-axis, and uses them as the XY plane position of the terminal.

[0089] S304: The location calculation server determines the global location information of the vessel based on the latest location information from the open-air 5G satellite terminal;

[0090] Specifically: when only one open-air 5G satellite terminal on the ship obtains satellite positioning information, the triplet of satellite positioning information (longitude, latitude, and altitude) of that terminal is taken as the ship's global position; otherwise, the centroid of the polyhedron formed by the positions of all open-air 5G satellite terminals on the ship is taken as the ship's global position. For example, suppose that 5G satellite terminals are symmetrically deployed on the open-air layer of the ship. Let the m-th 5G satellite terminal be a satellite positioning triplet. Then the global position of the ship can be represented as .

[0091] S305: The location calculation server combines the global location information of the ship with the Z-axis position and XY plane position of the 5G satellite terminal inside the ship's cabin to form a position vector (ship's global position, Z-axis position, XY plane position), and feeds it back as the positioning result of the terminal.

[0092] Example 2:

[0093] The present invention also provides an apparatus / device / system for indoor positioning of ocean-going vessels that integrates 5G private network and GNSS, including a memory, a processor and a computer program stored in the memory, characterized in that the processor executes the computer program to implement the steps of the above method.

[0094] The present invention also provides a computer-readable storage medium having a computer program / instructions stored thereon, which, when executed by a processor, implement the steps of the above-described method.

[0095] The present invention also provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the above-described method.

[0096] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0097] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0098] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0099] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0100] The technical solutions provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for fusing ship 5G private network and GNSS for ocean-going ship indoor positioning, characterized in that: Includes the following steps: The location computing server constructs and periodically updates the 5G positioning fingerprint database inside the ship. The positioning fingerprint database stores the location information of the outdoor 5G satellite terminal, the 5G signal strength information of the positioning anchor point, the relative position information, and the information update time. The location computing server constructs and trains a localization regression model to obtain a trained localization regression model. When a 5G satellite terminal located indoors on a ship is powered on, or when its location is periodically updated, or when a local / remote monitoring system initiates a location query, a real-time 5G terminal location query process is triggered. This process locates the terminal based on a trained positioning regression model and a 5G positioning fingerprint database, and returns the query results.

2. The positioning method of claim 1, wherein: The construction and periodic updating of the ship's indoor 5G positioning fingerprint database includes the following steps: The open-air 5G satellite terminal periodically acquires the global location information of the open-air 5G satellite terminal based on GNSS, and sends the global location information and the terminal identifier of the open-air 5G satellite terminal to the location calculation server on the ship. The location calculation server updates the satellite positioning information table. The 5G base station on the ship periodically broadcasts synchronization signal information. After receiving the synchronization signal information broadcast by the 5G base station, the positioning anchor point inside the ship extracts the 5G signal strength information from the synchronization signal information and sends the signal strength and the identifier of the positioning anchor point to the location calculation server on the ship. The location calculation server constructs or updates the location anchor information table in the location fingerprint database based on the received information of the positioning anchor points inside the ship. The positioning anchor information table includes the identifier of the positioning anchor point, relative position information, 5G signal strength information, and timestamp.

3. The positioning method of claim 2, wherein: The location computing server updates the satellite positioning information table as follows: After receiving the global location information and the terminal identifier of the exposed 5G satellite terminal, the location computing server searches the satellite positioning information table in the 5G positioning fingerprint database based on the terminal identifier of the exposed 5G satellite terminal, and updates the record in the table that is the same as the terminal identifier. The satellite positioning information table includes the terminal identifier of the exposed 5G satellite terminal, global location information, relative location information, and timestamp.

4. The positioning method of claim 1, wherein: The localization regression model includes at least one regression decision tree and an additive attention regressor.

5. The positioning method of claim 4, characterized by: The real-time location query process for 5G terminals includes the following steps: The 5G satellite terminal inside the ship receives synchronization signal information broadcast by one or more 5G base stations inside the cabin, extracts 5G signal strength information and base station identifier from the synchronization signal information, and sends the identifier information to the location computing server. The identifier information includes the terminal identifier of the 5G satellite terminal inside the ship, the 5G signal strength, and the base station identifier. The location calculation server determines the cabin layer where the terminal is located by using the identification information, and uses it as the Z-axis position of the terminal. The location calculation server preprocesses the 5G signal strength data of the 5G satellite terminal inside the ship's interior, then inputs it into the trained positioning regression model, and outputs the predicted values ​​of the X-axis and Y-axis, which are used as the XY plane position of the 5G satellite terminal inside the ship's interior. The location calculation server determines the global location information of the ship based on the latest location information from the open-air 5G satellite terminal; The location calculation server combines the ship's global location information with the Z-axis and XY-plane positions of the 5G satellite terminal inside the ship's cabin to form a location vector. This location vector is then used as the positioning result of the 5G satellite terminal inside the ship's cabin and fed back.

6. The positioning method of claim 1, wherein: The construction and training of the localization regression model includes the following steps: The record is extracted from a positioning anchor information table of the positioning fingerprint library by using a random sampling method with playback to form a data set , wherein an integer , the data sets have the same sample attributes and sample quantities, the sample attributes are composed of 5G signal strength information and position information in the record, and each data set is further divided into a training set and a test set, wherein the proportion of the training set is not less than 70%. Build A set of regression decision trees, with input variables including 5G signal strength arranged by base station cell identifier, and output variables being the X-axis position and Y-axis position, respectively. Each tree corresponds to the... One of the datasets; Construct an additive attention regressor, the input of which is the... The output of the regression decision tree is either the final X-axis position or the Y-axis position. When the X-axis position is used as the training target, the output is the X-axis position; when the Y-axis position is used as the training target, the output is the Y-axis position. The output of the additive attention regressor is a weighted average of the inputs. In the formula, It is the output of the k-th decision tree. These are the weight coefficients of the decision tree, satisfying... ; Train the localization regression model to obtain a well-trained localization regression model; Training the localization regression model includes obtaining the optimal decision tree parameters and weight coefficients. This minimizes the loss function of the localization regression model, where the loss function is calculated using the following formula: In the formula, It is a truth value. This is the predicted output of the localization regression model, where D represents the size of the total dataset, and the [number]th [item] in the optimal decision tree. Tree parameters satisfy ,here, It is true. This is the output of the tree. This is the input to the tree. This is the size of the dataset for that tree.

7. The positioning method according to claim 5, characterized in that: The location calculation server determines the cabin level where the terminal is located using identification information, including the following steps: The 5G signals received by the 5G satellite terminal are classified according to the base station identifier to form a set of neighboring base stations of the 5G satellite terminal. From the set of neighboring base stations, select neighboring base stations with signal strength not lower than the signal strength threshold to form an effective set of neighboring base stations; The Z-axis positions of each base station in the effective neighboring base station set are obtained from the 5G positioning fingerprint database. Then, a majority vote is conducted, and the winning Z-axis position is taken as the cabin layer where the terminal is located.

8. A device / equipment / system for indoor positioning of ocean-going vessels integrating 5G private network and GNSS, including a memory, a processor, and a computer program stored in the memory, characterized in that... The processor executes the computer program to implement the steps of the method according to any one of claims 1-7.

9. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method described in any one of claims 1-7.

10. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method described in any one of claims 1-7.

Images