Intelligent port positioning method and system based on UWB correction

Abstract

The embodiment of the invention discloses an intelligent port positioning method and system based on UWB correction, and relates to the technical field of positioning. The method comprises the following steps: acquiring a UWB signal of a target object through at least three positioning base stations, and calculating the distance of the target object relative to each positioning base station according to the UWB signal; obtaining distance information of the target object relative to each positioning base station in a specified time period, and obtaining a multi-dimensional distance sequence based on the distance information; predicting the predicted position information of the target object at the target moment based on the multi-dimensional distance sequence; comparing the predicted position information with first position information determined based on a UWB signal corresponding to the target moment so as to judge whether a suspected abnormal condition exists in the first position information; and when a suspected abnormal condition exists in the first position information, performing correction analysis based on the predicted position information and the first position information to obtain target position information corresponding to the target object at the target moment.

Description

Technical Field

[0001] This application relates to the field of positioning technology. Specifically, it relates to a positioning method and system for intelligent ports based on UWB calibration. Background Art

[0002] UWB (Ultra-Wideband) positioning technology is a high-precision positioning technology, which is widely used in indoor positioning, Internet of Things devices, intelligent manufacturing and other fields. Although UWB positioning technology has advantages such as high precision and strong anti-interference ability, it also has some defects and application scenario limitations. For example, in the application scenario of intelligent ports, due to the presence of a large number of metal objects (such as containers, ships, handling equipment, etc.), it may cause reflection, scattering and attenuation of UWB signals, thereby affecting the positioning accuracy (the absorption of UWB pulse signals by metals is extremely serious, which may cause large errors or even inability to position for UWB signals).

[0003] Therefore, how to effectively overcome these defects and influencing factors and improve the accuracy and reliability of UWB positioning technology in the application of intelligent ports has become an urgent problem to be solved. Summary of the Invention

[0004] To solve the above problems, one aspect of the embodiments of this specification provides a positioning method for intelligent ports based on UWB calibration. This method can be applied to an intelligent port system, and the intelligent port system is configured with at least three positioning base stations. The method includes:

[0005] Obtain the UWB signals of the target object through the at least three positioning base stations, and calculate the distance of the target object relative to each positioning base station according to the UWB signals;

[0006] Obtain the distance information of the target object relative to each positioning base station within a specified time period, and arrange the distance information in chronological order to obtain a multi-dimensional distance sequence;

[0007] Predict the predicted position information of the target object at the target moment based on the multi-dimensional distance sequence;

[0008] Compare the predicted position information with the first position information determined based on the UWB signal corresponding to the target moment to determine whether there is a suspected abnormal situation in the first position information;

[0009] If there is a suspected abnormal situation in the first position information, perform calibration analysis based on the predicted position information and the first position information to obtain the target position information corresponding to the target object at the target moment.

[0010] In some embodiments, predicting the predicted position information of the target object at the target moment based on the multi-dimensional distance sequence includes:

[0011] Inputting the multi-dimensional distance sequence into a trained machine learning model to obtain the predicted position information, where the machine learning model includes at least one of a recurrent neural network, a long short-term memory model, or a gated recurrent unit;

[0012] The machine learning model includes an input layer, one or more hidden layers, and an output layer; wherein, the input layer is used to receive the multi-dimensional distance sequence; the one or more hidden layers are used to extract feature information from the multi-dimensional distance sequence and perform position prediction based on the feature information; the output layer is used to obtain the predicted position information based on the output results of the one or more hidden layers.

[0013] In some embodiments, the machine learning model is trained based on the following method:

[0014] Obtaining a plurality of sample multi-dimensional distance sequences and the label information corresponding to each sample multi-dimensional distance sequence, where the sample multi-dimensional distance sequence is obtained based on the distance information of the sample target object relative to each positioning base station within a specified sample time period, and the label information is used to represent the expected prediction result of the position information at the next moment corresponding to each sample multi-dimensional distance sequence;

[0015] Inputting each sample multi-dimensional distance sequence into an initial machine learning model to obtain a corresponding prediction result;

[0016] Iteratively training the parameters of the initial machine learning model based on the difference between the prediction result and the corresponding label information until the trained machine learning model is obtained when a preset condition is satisfied.

[0017] In some embodiments, comparing the predicted position information with the first position information determined based on the UWB signal corresponding to the target moment to determine whether there is a suspected abnormal situation in the first position information includes:

[0018] Calculating the distance between the first position information and the predicted position information; and when the distance between the first position information and the predicted position information is greater than a preset distance threshold, determining that there is a suspected abnormal situation in the first position information.

[0019] In some embodiments, performing calibration analysis based on the predicted position information and the first position information to obtain the target position information corresponding to the target object at the target moment includes:

[0020] Calculate the confidence levels corresponding to the predicted position information and the first position information respectively;

[0021] Based on the confidence levels, determine the predicted position information or the first position information as the target position information corresponding to the target object at the target moment.

[0022] In some embodiments, calculating the confidence levels corresponding to the predicted position information and the first position information respectively includes:

[0023] Obtain N historical position information corresponding to the N nearest historical moments before the target moment;

[0024] Based on the predicted position information and the first position information relative to the N historical position information, determine the anomaly indices corresponding to the predicted position information and the first position information respectively, and based on the anomaly indices, determine the confidence levels corresponding to the predicted position information and the first position information respectively.

[0025] In some embodiments, based on the predicted position information and the first position information relative to the N historical position information, determining the anomaly indices corresponding to the predicted position information and the first position information respectively, and based on the anomaly indices, determining the confidence levels corresponding to the predicted position information and the first position information respectively includes:

[0026] Calculate the difference between each historical position information in the N historical position information and the position information corresponding to the previous moment to obtain N - 1 displacement parameters, and determine the mean and standard deviation corresponding to the N - 1 displacement parameters;

[0027] Obtain a first displacement parameter based on the difference between the first position information and the position information corresponding to the previous moment, and obtain a second displacement parameter based on the difference between the predicted position information and the position information corresponding to the previous moment;

[0028] Calculate a first difference between the first displacement parameter and the mean, and a second difference between the second displacement parameter and the mean;

[0029] Obtain a first anomaly index corresponding to the first position information according to the ratio of the first difference to the standard deviation, and obtain a second anomaly index corresponding to the predicted position information according to the ratio of the second difference to the standard deviation;

[0030] Map the first anomaly index and the second anomaly index through a preset function to obtain a first confidence level corresponding to the first position information and a second confidence level corresponding to the predicted position information;

[0031] Determining the predicted position information or the first position information as the target position information corresponding to the target object at the target moment based on the confidence level includes:

[0032] When the first confidence level is greater than or equal to the second confidence level, taking the first position information as the target position information corresponding to the target object at the target moment; when the first confidence level is less than the second confidence level, taking the predicted position information as the target position information corresponding to the target object at the target moment.

[0033] In some embodiments, the method further includes:

[0034] Obtaining the IMU detection data of the target object at each moment within a specified time period, and fusing the IMU detection data with the multi-dimensional distance sequence to obtain a multi-dimensional fusion information sequence;

[0035] Inputting the multi-dimensional fusion information sequence into a trained machine learning model for prediction to obtain the predicted position information of the target object at the target moment.

[0036] In some embodiments, the method further includes:

[0037] Mapping the target position information corresponding to the target object at each moment to the digital twin system of the intelligent port, so as to display the real-time position information of the target object in the digital twin system of the intelligent port.

[0038] Another aspect of the embodiments of this specification further provides an intelligent port positioning system based on UWB correction. This system can be applied to an intelligent port system, and the intelligent port system is configured with at least three positioning base stations. The positioning system includes:

[0039] A first acquisition module, configured to acquire the UWB signal of the target object through the at least three positioning base stations, and calculate the distance of the target object relative to each positioning base station according to the UWB signal;

[0040] A second acquisition module, configured to acquire the distance information of the target object relative to each positioning base station within a specified time period, and arrange the distance information in chronological order to obtain a multi-dimensional distance sequence;

[0041] A position prediction module, configured to predict the predicted position information of the target object at the target moment based on the multi-dimensional distance sequence;

[0042] An anomaly judgment module, configured to compare the predicted position information with the first position information determined based on the UWB signal corresponding to the target moment to judge whether there is a suspected anomaly in the first position information;

[0043] A calibration analysis module, configured to perform calibration analysis based on the predicted position information and the first position information when there is a suspected abnormal situation in the first position information, so as to obtain the target position information corresponding to the target object at the target moment.

[0044] The beneficial effects that the method and system for positioning a smart port based on UWB calibration provided by the embodiments of this specification may bring at least include: predicting the position information of a target object at a target moment by using the distance information of the target object relative to each positioning base station within a specified time period to obtain predicted position information, and then performing calibration analysis on the first position information determined based on the UWB signal corresponding to the target moment by using the predicted position information, so that when the first position information is abnormal due to various interference factors, it can be corrected by using the predicted position information, thereby improving the accuracy and reliability of the positioning result to a certain extent.

[0045] Additional features will be partly described in the following description. For those skilled in the art, it will become obvious by referring to the following content and drawings, or can be understood by generating or operating examples. The features of this specification can be achieved and obtained by practicing or using various aspects of the methods, tools and combinations described in the following detailed examples. Description of the Drawings

[0046] This specification will be further described in the form of exemplary embodiments, and these exemplary embodiments will be described in detail through the drawings. These embodiments are not restrictive. In these embodiments, the same numbers represent the same structures, where:

[0047] Figure 1 is a schematic diagram of an exemplary application scenario of a smart port positioning system based on UWB calibration shown in some embodiments of this specification;

[0048] Figure 2 is an exemplary module diagram of a smart port positioning system based on UWB calibration shown in some embodiments of this specification;

[0049] Figure 3 is an exemplary flowchart of a method for positioning a smart port based on UWB calibration shown in some embodiments of this specification;

[0050] Figure 4 is an exemplary sub-step flowchart of a method for positioning a smart port based on UWB calibration shown in some embodiments of this specification. Detailed Embodiments

[0051] To more clearly illustrate the technical solutions of the embodiments of this specification, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some examples or embodiments of this specification. For those of ordinary skill in the art, without creative efforts, this specification can also be applied to other similar scenarios based on these drawings. Unless obvious from the language context or otherwise stated, the same reference numerals in the figures represent the same structure or operation.

[0052] It should be understood that the "system", "device", "unit" and / or "module" used in this specification are a way to distinguish different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the said words can be replaced by other expressions.

[0053] As shown in this specification and the claims, unless the context clearly indicates an exception, words such as "a", "an", "one" and / or "the" are not specifically singular and may also include the plural. Generally speaking, the terms "including" and "comprising" only indicate the inclusion of the clearly identified steps and elements, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0054] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the operations before or after do not necessarily need to be executed precisely in sequence. On the contrary, they can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0055] The following will detail the UWB calibration-based intelligent port positioning method and system provided by the embodiments of this specification with reference to the drawings.

[0056] Figure 1 It is a schematic diagram of an exemplary application scenario of the UWB calibration-based intelligent port positioning system shown in some embodiments of this specification.

[0057] Refer to Figure 1, in some embodiments, the application scenario 100 of the intelligent port positioning system based on UWB calibration may include a UWB signal acquisition device 110, a storage device 120, a processing device 130, a terminal device 140, and a network 150. Each component in the application scenario 100 can be connected in various ways. For example, the UWB signal acquisition device 110 can be connected to the storage device 120 and / or the processing device 130 through the network 150, or can be directly connected to the storage device 120 and / or the processing device 130. For another example, the storage device 120 can be directly connected to the processing device 130 or connected through the network 150. For another example, the terminal device 140 can be connected to the storage device 120 and / or the processing device 130 through the network 150, or can be directly connected to the storage device 120 and / or the processing device 130.

[0058] The UWB signal acquisition device 110 can acquire UWB signals related to the target object from at least three positioning base stations, and the UWB signals can reflect the distances between the target object and each positioning base station. Specifically, in the embodiments of the present application, the target object can be a port worker (such as a porter), a device (such as a hoisting device, a transport vehicle, etc.), or a cargo (such as a container, etc.). In the embodiments of the present application, a UWB positioning tag (an electronic tag capable of emitting UWB signals) can be equipped for the target object, and the UWB signals emitted by the UWB positioning tag can be received through at least three positioning base stations. It should be noted that in the embodiments of the present application, the UWB positioning tags equipped for different target objects can emit UWB signals with different frequencies, different coding methods, or carrying different information, so as to facilitate the system to distinguish and identify different target objects.

[0059] In the embodiments of the present application, the UWB signal acquisition device 110 can acquire the UWB signal from the positioning base station after the positioning base station receives the UWB signal, and calculate the distance between the target object and the positioning base station through the signal strength and / or the propagation time of the signal. In the embodiments of the present application, the UWB positioning tag can emit UWB signals at a preset frequency (for example, once per second), and the UWB signal acquisition device 110 can arrange the received UWB signals in chronological order. In the embodiments of the present application, the UWB signal acquisition device 110 can have an independent power supply, and can send the acquired UWB signals to other components in the application scenario 100 (such as the storage device 120, the processing device 130, the terminal device 140) in a wired or wireless (such as Bluetooth, Wi-Fi, etc.) manner.

[0060] In some embodiments, the UWB signal acquisition device 110 may send the UWB signals it acquires to the storage device 120, the processing device 130, the terminal device 140, etc. via the network 150. In some embodiments, the UWB signals acquired by the UWB signal acquisition device 110 may be processed by the processing device 130. For example, the processing device 130 may calculate the distance of the target object relative to each positioning base station based on the UWB signal, and determine the position of the target object based on the distance.

[0061] The network 150 may facilitate the exchange of information and / or data. The network 150 may include any suitable network capable of facilitating the exchange of information and / or data in the application scenario 100. In some embodiments, at least one component of the application scenario 100 (e.g., the UWB signal acquisition device 110, the storage device 120, the processing device 130, the terminal device 140) may exchange information and / or data with at least one other component in the application scenario 100 via the network 150. For example, the processing device 130 may obtain the UWB signals acquired for the target object from the UWB signal acquisition device 110 and / or the storage device 120 via the network 150. For another example, the processing device 130 may obtain user operation instructions from the terminal device 140 via the network 150. Exemplary operation instructions may include, but are not limited to, reading the UWB signals acquired by each positioning base station, or the position information of the target object determined based on the UWB signal, etc.

[0062] In some embodiments, the network 150 may be any form of wired or wireless network, or any combination thereof. By way of example only, the network 150 may include a cable network, a wired network, an optical fiber network, a telecommunications network, an internal network, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network (MAN), a public switched telephone network (PSTN), a Bluetooth network, a ZigBee network, a near field communication (NFC) network, etc. or any combination thereof. In some embodiments, the network 150 may include at least one network access point, and at least one component of the application scenario 100 may be connected to the network 150 via the access point to exchange data and / or information.

[0063] The storage device 120 can store data, instructions, and / or any other information. In some embodiments, the storage device 120 can store data obtained from the UWB signal acquisition device 110, the processing device 130, and / or the terminal device 140. For example, the storage device 120 can store the UWB signals acquired by the UWB signal acquisition device 110; for another example, the storage device 120 can store the position information of the target object calculated by the processing device 130. In some embodiments, the storage device 120 can store the data and / or instructions used by the processing device 130 to execute or complete the exemplary methods described in this specification. In some embodiments, the storage device 120 can include a mass storage device, a removable storage device, a volatile read / write memory, a read-only memory (ROM), etc., or any combination thereof. Exemplary mass storage devices can include magnetic disks, optical disks, solid-state disks, etc. In some embodiments, the storage device 120 can be implemented on a cloud platform. By way of example only, the cloud platform can include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-layer cloud, etc., or any combination thereof.

[0064] In some embodiments, the storage device 120 can be connected to the network 150 to communicate with at least one other component (e.g., the UWB signal acquisition device 110, the processing device 130, the terminal device 140) in the application scenario 100. At least one component in the application scenario 100 can access the data, instructions, or other information stored in the storage device 120 through the network 150. In some embodiments, the storage device 120 can be directly connected to or communicate with one or more components (e.g., the UWB signal acquisition device 110, the terminal device 140) in the application scenario 100. In some embodiments, the storage device 120 can be part of the UWB signal acquisition device 110 and / or the processing device 130.

[0065] The processing device 130 can process data and / or information obtained from the UWB signal acquisition device 110, the storage device 120, the terminal device 140, and / or other components of the application scenario 100. In some embodiments, the processing device 130 can obtain UWB signals from any one or more of the UWB signal acquisition device 110, the storage device 120, or the terminal device 140, calculate the distance of the target object relative to each positioning base station by processing the UWB signals, and determine the position of the target object based on the distance. In some embodiments, the processing device 130 can obtain the pre-stored computer instructions from the storage device 120 and execute the computer instructions to implement the intelligent port positioning method based on UWB calibration described in this specification.

[0066] In some embodiments, the processing device 130 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processing device 130 may be local or remote. For example, the processing device 130 may access information and / or data from the UWB signal acquisition device 110, the storage device 120, and / or the terminal device 140 through the network 150. For another example, the processing device 130 may be directly connected to the UWB signal acquisition device 110, the storage device 120, and / or the terminal device 140 to access information and / or data. In some embodiments, the processing device 130 may be implemented on a cloud platform. For example, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an inter-cloud, a multi-cloud, etc. or any combination thereof.

[0067] The terminal device 140 may receive, send, and / or display data. The received data may include the data acquired by the UWB signal acquisition device 110, the data stored in the storage device 120, the data processed by the processing device 130 (such as the position information of the target object, etc.). For example, the data received and / or displayed by the terminal device 140 may include the UWB signal acquired by the UWB signal acquisition device 110, the position information of the target object determined by the processing device 130 based on the UWB signal, etc.; the data sent may include the input data and operation instructions of the user (such as port management personnel), etc.

[0068] In some embodiments, the terminal device 140 may include a mobile device 141, a tablet computer 142, a laptop computer 143, etc. or any combination thereof. For example, the mobile device 141 may include a mobile phone, a personal digital assistant (PDA), a dedicated mobile terminal, etc. or any combination thereof. In some embodiments, the terminal device 140 may include an input device (such as a keyboard, a touch screen), an output device (such as a display, a speaker), etc. In some embodiments, the processing device 130 may be a part of the terminal device 140.

[0069] It should be noted that the above description of the application scenario 100 is only for illustration and explanation, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to the application scenario 100 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification. For example, the UWB signal acquisition device 110 may include more or fewer functional components.

[0070] Figure 2 is a schematic diagram of the modules of the intelligent port positioning system based on UWB calibration shown in some embodiments of this specification. In some embodiments, Figure 2 The shown intelligent port positioning system 200 based on UWB calibration may be applied to in a software and / or hardware mannerFigure 1 The application scenario 100 shown can be configured into the processing device 130 and / or the terminal device 140 in the form of software and / or hardware, for example, to process the UWB signals acquired by the UWB signal acquisition device 110, calculate the distance of the target object relative to each positioning base station based on the UWB signals, and then determine the position of the target object based on the distance.

[0071] Referring to Figure 2 , in some embodiments, the intelligent port positioning system 200 based on UWB calibration may include a first acquisition module 210, a second acquisition module 220, a position prediction module 230, an anomaly judgment module 240, and a calibration analysis module 250.

[0072] The first acquisition module 210 can be used to acquire the UWB signals of the target object through at least three positioning base stations, and calculate the distance of the target object relative to each positioning base station according to the UWB signals.

[0073] The second acquisition module 220 can be used to acquire the distance information of the target object relative to each positioning base station within a specified time period, and arrange the distance information in chronological order to obtain a multi-dimensional distance sequence.

[0074] The position prediction module 230 can be used to predict the predicted position information of the target object at the target time based on the multi-dimensional distance sequence.

[0075] The anomaly judgment module 240 can be used to compare the predicted position information with the first position information determined based on the UWB signals corresponding to the target time, to judge whether there is a suspected anomaly in the first position information.

[0076] The calibration analysis module 250 can be used to perform calibration analysis based on the predicted position information and the first position information when there is a suspected anomaly in the first position information, to obtain the target position information corresponding to the target object at the target time.

[0077] For more details about each of the above modules, reference can be made to other parts of this specification (such as Figures 3 to 4 the relevant descriptions in the [section] and its related content), which will not be elaborated here.

[0078] It should be understood that Figure 2The intelligent port positioning system 200 and its modules based on UWB calibration shown can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented through hardware, software, or a combination of software and hardware. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware. Those skilled in the art can understand that the above methods and systems can be implemented using computer-executable instructions and / or included in processor control code. For example, such code is provided on a carrier medium such as a disk, CD, or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The systems and modules of this specification can be implemented not only by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips and transistors, or programmable hardware devices such as field-programmable gate arrays and programmable logic devices, but also by software executed by various types of processors, or by a combination of the above hardware circuits and software (e.g., firmware).

[0079] It should be noted that the above description of the intelligent port positioning system 200 based on UWB calibration is provided for illustrative purposes only and is not intended to limit the scope of this specification. It can be understood that for those skilled in the art, according to the description of this specification, without departing from this principle, various modules can be arbitrarily combined, or a subsystem can be formed and connected to other modules. For example, Figure 2 the first acquisition module 210, the second acquisition module 220, the position prediction module 230, the anomaly judgment module 240, and the calibration analysis module 250 described in can be different modules in a system, or a module can implement the functions of two or more of the above modules. Such deformations are all within the protection scope of this specification.

[0080] Figure 3 is an exemplary flowchart of an intelligent port positioning method based on UWB calibration shown in some embodiments of this specification. In some embodiments, the intelligent port positioning method based on UWB calibration can be executed by a processing logic, which can include hardware (e.g., circuits, dedicated logic, programmable logic, microcode, etc.), software (instructions running on a processing device to perform hardware simulation), etc., or any combination thereof. In some embodiments, Figure 3 one or more operations in the flowchart of the intelligent port positioning method based on UWB calibration shown can be performed by Figure 1The processing device 130 and / or the terminal device 140 shown implement it. For example, the intelligent port positioning method based on UWB calibration can be stored in the storage device 120 in the form of a computer program and / or instructions, and called and / or executed by the processing device 130 and / or the terminal device 140. The execution process of the intelligent port positioning method based on UWB calibration provided by this application is described below taking the processing device 130 as an example.

[0081] Referring to Figure 3 , the intelligent port positioning method based on UWB calibration provided by the embodiments of this application may include the following steps:

[0082] Step S110, obtain the UWB signals of the target object through at least three positioning base stations, and calculate the distance of the target object relative to each positioning base station according to the UWB signals. In some embodiments, step S110 may be executed by the first acquisition module 210.

[0083] The intelligent port positioning method based on UWB calibration provided by the embodiments of this application can be used in an intelligent port system. This intelligent port system is configured with at least three positioning base stations, which can receive the UWB signals transmitted by the UWB positioning tags configured for the target object. By analyzing these UWB signals, the system can accurately calculate the relative distance between the target object (such as goods, vehicles or port staff) and each positioning base station, and then determine the position information of the target object.

[0084] In some embodiments of this application, the distance of the target object relative to each positioning base station can be calculated by the strength of the UWB signal and / or the transmission time of the signal. Since this process can be regarded as the prior art, this process will not be elaborated in detail in this specification.

[0085] Step S120, obtain the distance information of the target object relative to each positioning base station within a specified time period, and arrange the distance information in chronological order to obtain a multi-dimensional distance sequence. In some embodiments, step S120 may be executed by the second acquisition module 220.

[0086] It can be understood that in an ideal situation, taking each positioning base station as the center of a circle and the distance from the target object to each positioning base station as the radius to draw a circle, the intersection of the three circles can be obtained, and this intersection is the position of the target object. However, in practical applications, due to the existence of various error factors in the environment (such as the influence of many metal objects in the port on the propagation path of the UWB signal or the influence on the signal transmission intensity, etc.), these circles may not completely intersect at one point in special cases, but there will be an intersecting area. At this time, it can only be determined that the target object is located within this intersecting area, and the specific position of the target object cannot be accurately determined.

[0087] For example, when the target object is in a closed or semi-closed area surrounded by multiple containers (or other metal objects), due to the presence of metal objects such as containers, phenomena such as reflection and diffraction may occur during the propagation of the UWB signal, resulting in changes in the signal transmission path and attenuation of the signal strength. These error factors will cause deviations in distance calculation, which in turn will lead to deviations in the position and size of the circle calculated based on this distance information, and finally make the range of the intersection area larger, increasing the uncertainty of positioning. To solve this problem, the present invention proposes a positioning method and system for a smart port based on UWB correction. This method can obtain the distance information of the target object relative to each positioning base station within a specified time period, and arrange this distance information in chronological order to obtain a multi-dimensional distance sequence, and then predict the predicted position information of the target object at the target moment based on this multi-dimensional distance sequence through subsequent steps (the specific prediction process is described in detail later).

[0088] It should be noted that in the embodiments of the present application, this multi-dimensional distance sequence can reflect the change of the distance of the target object relative to each positioning base station within a certain time range. By arranging this distance information in chronological order, the information in the time dimension can be retained, making subsequent analysis and processing more accurate and reliable.

[0089] It should also be noted that in the embodiments of the present application, the above-mentioned specified time period can refer to a certain period of time in the past, such as one minute, five minutes or ten minutes, etc., and the specific duration can be set according to actual needs. In the embodiments of the present application, by obtaining the distance information of the target object relative to each positioning base station within this specified time period, the movement of the target object can be more comprehensively understood, thereby improving the accuracy of subsequent position prediction.

[0090] Only as an example, in some embodiments of the present application, this multi-dimensional distance sequence can be expressed as [d1(t1), d2(t1), d3(t1); d1(t2), d2(t2), d3(t2);...; d1(tn), d2(tn), d3(tn)], where d1(ti), d2(ti) and d3(ti) respectively represent the distances of the target object relative to three positioning base stations (which can be respectively denoted as base station 1, base station 2 and base station 3) at time ti, and n represents the number of time points within this specified time period.

[0091] Step S130, predicting the predicted position information of the target object at the target moment based on the multi-dimensional distance sequence. In some embodiments, step S130 can be executed by the position prediction module 230.

[0092] In some embodiments of the present application, in order to predict the position information of a target object at a target moment, the multi-dimensional distance sequence may be input into a trained machine learning model to obtain predicted position information. In the embodiments of the present application, the machine learning model may include at least one of a recurrent neural network, a long short-term memory model, or a gated recurrent unit. Specifically, in the embodiments of the present application, the machine learning model may include an input layer, one or more hidden layers, and an output layer; wherein, the input layer may be configured to receive the multi-dimensional distance sequence; the one or more hidden layers may be configured to extract feature information from the multi-dimensional distance sequence and perform position prediction based on the feature information; and the output layer may be configured to obtain the predicted position information corresponding to the target object at the target moment based on the output results of the one or more hidden layers.

[0093] The following briefly introduces the training process of the above machine learning model:

[0094] In the embodiments of the present application, a plurality of sample multi-dimensional distance sequences and the label information corresponding to each of the sample multi-dimensional distance sequences may be obtained, wherein the sample multi-dimensional distance sequence is obtained based on the distance information of a sample target object relative to each positioning base station at each time point within a specified sample time period, and its specific representation may refer to the above multi-dimensional distance sequence. The label information is used to represent the expected prediction result of the position information at the next moment corresponding to each sample multi-dimensional distance sequence. In the embodiments of the present application, the label information may be obtained based on the actual position information of the sample target object at the sample target moment, where the sample target moment is the moment after the last sample time point within the specified sample time period.

[0095] In some embodiments of the present application, the distance information of a sample target object relative to each positioning base station at each time point within a continuous time period, and the actual position information corresponding to each time point may be obtained, and then any data corresponding to an arbitrary time length may be intercepted as a sample multi-dimensional distance sequence, and the actual position information corresponding to the last time point may be used as its corresponding label information.

[0096] Further, in the embodiments of the present application, each of the sample multi-dimensional distance sequences may be input into an initial machine learning model to obtain a corresponding prediction result respectively.

[0097] Furthermore, the parameters of the initial machine learning model can be iteratively trained based on the difference between the prediction result and the corresponding label information until the trained machine learning model is obtained when the preset conditions are met. In the embodiments of the present application, the Euclidean distance can be used to measure the difference between the prediction result and the label information. Then, when the difference is greater than the preset loss threshold, algorithms such as backpropagation and gradient descent are used to optimize the model parameters to minimize the difference between the prediction result and the label information until the difference between the prediction result and the label information is less than the preset loss threshold or the preset number of iterations is reached, and the trained machine learning model is obtained. More details about the training of this machine learning model can be regarded as the prior art and will not be elaborated in this specification.

[0098] After obtaining the trained machine learning model, the above multi-dimensional distance sequence can be processed by the trained machine learning model to predict the predicted position information corresponding to the target object at the target time. Wherein, the target time is the next time point after the last time point in the multi-dimensional distance sequence.

[0099] It should be noted that in the embodiments of the present application, since the label information used in the training process is obtained based on the actual position of the target object, in the process of training based on this label information and the sample multi-dimensional distance sequence, the machine learning model can obtain a certain position correction ability (that is, even when there are certain deviations in the distances of the target object relative to each positioning base station, the position information of the target object at the target time can be predicted more accurately through the linear and / or non-linear processing of the model). Therefore, the predicted position information obtained based on this machine learning model has a certain anti-interference ability.

[0100] In some other embodiments of the present application, technical means such as time series analysis, filtering, or Kalman filtering can also be used to predict or smooth the movement trajectory of the target object, thereby improving the positioning accuracy in the presence of error factors.

[0101] Step S140, comparing the predicted position information with the first position information determined based on the UWB signal corresponding to the target time to determine whether there is a suspected abnormal situation in the first position information. In some embodiments, step S140 can be executed by the anomaly judgment module 240.

[0102] In the embodiments of the present application, the first position information of the target object can be determined through the UWB signal corresponding to the target time (for example, through triangulation or multi-point positioning), and the specific determination process can refer to the above text and will not be elaborated here.

[0103] Further, in the embodiments of the present application, the distance (such as the Euclidean distance) between the first position information and the predicted position information can be calculated, and then it can be determined whether there is a suspected abnormal situation in the first position information according to this distance. For example, when the distance between the first position information and the predicted position information is greater than a preset distance threshold, it can be determined that there is a suspected abnormal situation in the first position information; when the distance between the first position information and the predicted position information is less than or equal to the preset distance threshold, it can be determined that there is no suspected abnormal situation in the first position information. In the embodiments of the present application, the preset distance threshold can be set according to actual needs, and specific limitations are not made herein.

[0104] In some embodiments of the present application, considering that there may be certain errors in the predicted position information obtained by the above method at the moment when the motion state of the target object changes greatly, and thus misjudgment may occur during abnormal detection. Based on this, in some embodiments of the present application, an IMU (Inertial Measurement Unit) sensor can also be configured for the target object to detect the acceleration and rotational motion of the target object.

[0105] Specifically, in some embodiments of the present application, the IMU detection data of the target object at each moment within a specified time period can be obtained, and the IMU detection data can be fused with the multi-dimensional distance sequence based on the time sequence information (for example, the IMU detection data is incorporated as a new data dimension into the foregoing multi-dimensional distance sequence) to obtain a multi-dimensional fusion information sequence; wherein, the IMU detection data can at least include the acceleration data and angular velocity data of the target object at each moment within the specified time period.

[0106] Further, the multi-dimensional fusion information sequence can be input into a trained machine learning model for prediction to obtain the predicted position information of the target object at the target moment.

[0107] It should be noted that when using this multi-dimensional fusion information sequence for position prediction, corresponding sample data needs to be used for special training, so that the machine learning model obtains the ability to perform position prediction based on the IMU detection data of the target object and the distance information of the target object relative to each positioning base station.

[0108] Exemplarily, in some embodiments, multiple sample multi-dimensional fusion information sequences and the label information corresponding to each of the sample multi-dimensional fusion information sequences can be obtained. Among them, the sample multi-dimensional fusion information sequence is obtained based on the IMU detection data of the sample target object at each time point within a specified sample time period and the distance information of the sample target object relative to each positioning base station. The label information is used to represent the expected prediction result of the position information at the next moment corresponding to each sample multi-dimensional fusion information sequence. Further, each of the sample multi-dimensional fusion information sequences can be input into an initial machine learning model to obtain a corresponding prediction result, where the initial machine learning model is similar to the initial machine learning model involved in the above process. Furthermore, the parameters of the initial machine learning model can be iteratively trained based on the difference between the prediction result and the corresponding label information until a trained machine learning model is obtained when a preset condition is met. For more details about the training of this machine learning model, reference can be made to the above text, and details will not be elaborated here.

[0109] It should be noted that in the embodiments of the present application, by fusing the IMU detection data and the multi-dimensional distance sequence, the motion state information of the target object can be further enriched, thereby improving the accuracy of the predicted position information and reducing the misjudgment in the process of judging the suspected abnormal situation of the first position information.

[0110] Step S150, when there is a suspected abnormal situation in the first position information, perform correction analysis based on the predicted position information and the first position information to obtain the target position information corresponding to the target object at the target moment. In some embodiments, step S150 can be executed by the correction analysis module 250.

[0111] In the embodiments of the present application, when the distance between the first position information and the predicted position information (the predicted position information here can refer to the predicted position information obtained based on the above multi-dimensional distance sequence or the predicted position information obtained based on the above multi-dimensional fusion information sequence) is greater than a preset distance threshold, it indicates that there may be a suspected abnormal situation in the first position information (this situation may be caused by the target object entering or exiting an area with strong interference). In this case, the confidence levels corresponding to the predicted position information and the first position information can be calculated first, and then the predicted position information or the first position information is determined as the target position information corresponding to the target object at the target moment based on the confidence level. Among them, the confidence level can be used to represent the reliability of the predicted position information and the first position information.

[0112] In some embodiments of the present application, N historical location information corresponding to the most recent N historical moments before the target moment can be obtained, and then the anomaly indexes corresponding to the predicted location information and the first location information respectively are determined based on the predicted location information and the first location information relative to the N historical location information, and the confidence levels corresponding to the predicted location information and the first location information respectively are determined based on the anomaly indexes.

[0113] Figure 4 This is an exemplary sub-step flow chart of a smart port positioning method based on UWB correction according to some embodiments of this specification. Figure 4 In some embodiments, the process of calculating the confidence of the predicted position information and the first position information may include the following sub-steps:

[0114] Sub-step S151, obtaining N historical location information corresponding to the latest N historical moments before the target moment.

[0115] In some embodiments of the present application, N can be set to 10, that is, 10 historical location information corresponding to the last 10 historical moments are obtained. These historical location information can reflect the movement trajectory of the target object in the past period of time, and then help determine its current possible movement trend and speed. By analyzing these historical location information, the confidence of the predicted location information and the first location information can be more accurately evaluated.

[0116] Sub-step S152, calculating the difference between each of the N historical position information and the position information corresponding to the previous moment, obtaining N-1 displacement parameters, and determining the mean and standard deviation corresponding to the N-1 displacement parameters.

[0117] In the embodiment of the present application, the displacement parameter can reflect the moving distance of the target object per unit time, the mean can reflect the average distance moved by the target object per unit time in the past period of time, and the standard deviation reflects the volatility of its movement. If the mean is large, it may mean that the target object has moved more frequently in the past period of time or has moved a longer distance per unit time; if the standard deviation is large, it may mean that the movement pattern of the target object is relatively unstable, sometimes fast and sometimes slow or the direction is changeable.

[0118] Sub-step S153, obtaining a first displacement parameter based on a difference between the first position information and the position information corresponding to the previous moment, and obtaining a second displacement parameter based on a difference between the predicted position information and the position information corresponding to the previous moment.

[0119] In the embodiment of the present application, the first displacement parameter may represent the moving distance of the target object at the target moment relative to the previous moment measured based on the UWB signal, and the second displacement parameter may represent the moving distance of the target object at the target moment relative to the previous moment reflected by the predicted position information.

[0120] Sub-step S154, calculate a first difference between the first displacement parameter and the mean value, and a second difference between the second displacement parameter and the mean value.

[0121] In the embodiment of the present application, the first difference may reflect the deviation degree of the moving distance of the target object at the target moment measured based on the UWB signal from the average moving distance in the past period of time, while the second difference may reflect the deviation degree of the moving distance of the target object at the target moment reflected by the predicted position information from the average moving distance. In the embodiment of the present application, the first difference and the second difference may refer to the absolute value of the difference.

[0122] Sub-step S155, obtain a first anomaly index corresponding to the first position information according to the ratio of the first difference to the standard deviation, and obtain a second anomaly index corresponding to the predicted position information according to the ratio of the second difference to the standard deviation.

[0123] In the embodiment of the present application, the calculation processes of the first anomaly index and the second anomaly index can be expressed by the following formulas:

[0124]

[0125] Where, I 1 represents the first anomaly index corresponding to the first position information, I 2 represents the second anomaly index corresponding to the predicted position information; W 1 represents the above-mentioned first displacement parameter, W 2 represents the above-mentioned second displacement parameter; μ represents the mean value corresponding to the above-mentioned N-1 displacement parameters, and σ represents the standard deviation corresponding to the above-mentioned N-1 displacement parameters; W 1 -μ represents the above-mentioned first difference, W 2 -μ represents the above-mentioned second difference.

[0126] It can be seen from the above calculation formulas that in the embodiment of the present application, when the above-mentioned first difference or second difference is certain, the more stable the moving law of the target object is, that is, the smaller σ is, the larger the corresponding anomaly index is, and vice versa, the smaller the anomaly index is. When σ is certain, the larger the above-mentioned first difference or second difference is, the larger the corresponding anomaly index is, and vice versa, the smaller the anomaly index is.

[0127] Sub-step S156: Map the first anomaly index and the second anomaly index through a preset function to obtain the first confidence corresponding to the first position information and the second confidence corresponding to the predicted position information.

[0128] In some embodiments of the present application, the preset function can be expressed as follows:

[0129] F 1 = 1 - I 1

[0130] F 2 = 1 - I 2

[0131] Wherein, F 1 represents the first confidence corresponding to the first position information, and F 2 represents the second confidence corresponding to the predicted position information. It should be noted that in the embodiments of the present application, when the above W 1 and / or W 2 is relatively large, it is possible that the above first anomaly index and / or second anomaly index is greater than 1 (indicating an extremely high anomaly index). At this time, the first confidence and / or the second confidence may be negative (indicating an extremely low confidence).

[0132] In some embodiments, a normalization operation can be added to the above preset function to normalize the first anomaly index and the second anomaly index to the interval [0, 1], and then use the difference between the maximum value 1 and the normalization result as the corresponding confidence.

[0133] Through the above steps, the first confidence corresponding to the first position information and the second confidence corresponding to the predicted position information can be calculated respectively. Further, in the embodiments of the present application, when the first confidence is greater than or equal to the second confidence, the first position information can be used as the target position information corresponding to the target object at the target moment, or when the first confidence is less than the second confidence, the predicted position information can be used as the target position information corresponding to the target object at the target moment.

[0134] It can be understood that in the embodiments of the present application, by predicting the position information of the target object at the target moment based on the distance information of the target object relative to each positioning base station within a specified time period, obtaining the predicted position information, and then performing a correction analysis on the first position information determined based on the UWB signal corresponding to the target moment through the predicted position information, it is possible to correct the first position information when it is abnormal due to various interference factors through the predicted position information, thereby improving the accuracy and reliability of the positioning result to a certain extent.

[0135] In some embodiments of the present application, the target position information corresponding to the target object at each moment (when there is no suspected anomaly in the first position information, the target position information is the first position information at the corresponding moment) can be mapped to the digital twin system of the intelligent port, so as to display the real-time position information of the target object in the digital twin system of the intelligent port. It should be noted that in the embodiments of the present application, the digital twin system of the intelligent port can be understood as a virtual model system, which can reflect the operating status of the actual port through real-time data. Specifically, the digital twin system of the intelligent port can map multi-dimensional data such as the real-time position information, operating status, and environmental changes of a number of target objects into a virtual model to construct a virtual scene highly consistent with the real world. Thus, it provides accurate real-time data monitoring for port managers and timely warns when data anomalies or system failures occur, effectively improving the operating efficiency and safety of the port.

[0136] In the digital twin system of the intelligent port, the position information of the target object can be static or have the ability to be dynamically updated in real time. In some embodiments, by continuously obtaining the target position information corresponding to the target object at each moment and mapping it to the digital twin system of the intelligent port, the whole process tracking of the target object can be realized, so as to facilitate relevant management personnel to intuitively understand the operating status of the port.

[0137] In summary, the beneficial effects that the embodiments of this specification may bring include, but are not limited to: (1) In the UWB calibration-based intelligent port positioning method and system provided in some embodiments of this specification, by predicting the position information of a target object at a target moment based on the distance information of the target object relative to each positioning base station within a specified time period, obtaining predicted position information, and then performing calibration analysis on the first position information determined based on the UWB signal corresponding to the target moment through the predicted position information, it is possible to correct the first position information through the predicted position information when the first position information is abnormal due to various interference factors, thereby improving the accuracy and reliability of the positioning result to a certain extent; (2) In the UWB calibration-based intelligent port positioning method and system provided in some embodiments of this specification, by jointly training the label information obtained based on the actual position of the target object with the relevant sample multi-dimensional distance sequences during the training process, the machine learning model can obtain a certain position correction ability (that is, even when there are certain deviations in the distances of the target object relative to each positioning base station, the model can still accurately predict the position information of the target object at the target moment through linear and / or non-linear processing of the model), thereby improving the anti-interference ability of the predicted position information obtained based on the machine learning model to a certain extent; (3) In the UWB calibration-based intelligent port positioning method and system provided in some embodiments of this specification, by fusing the IMU detection data and the multi-dimensional distance sequences obtained based on the distance information of the target object relative to each positioning base station within a specified time period, obtaining a multi-dimensional fusion information sequence, and making predictions based on the multi-dimensional fusion information sequence, it is possible to further enrich the motion state information of the target object, thereby improving the accuracy of the predicted position information and reducing misjudgments during the process of judging suspected abnormal situations of the first position information.

[0138] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced can be any one or several combinations of the above, or any other beneficial effects that may be obtained.

[0139] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only an example and does not constitute a limitation to this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are proposed in this specification, so such modifications, improvements, and corrections still fall within the spirit and scope of the exemplary embodiments of this specification.

[0140] In the meantime, this specification uses specific terms to describe the embodiments of this specification. For example, "an embodiment", "one embodiment", and / or "some embodiments" mean a certain feature, structure, or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that the "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more at different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0141] In addition, those skilled in the art can understand that various aspects of this specification can be illustrated and described by several patentable types or situations, including any new and useful process, machine, product, or composition of matter, or any new and useful improvement thereof. Accordingly, various aspects of this specification can be executed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software can all be referred to as "data blocks", "modules", "engines", "units", "components", or "systems". In addition, various aspects of this specification may be embodied as a computer product located in one or more computer-readable media, which includes computer-readable program code.

[0142] A computer storage medium may contain a propagated data signal containing computer program code, such as on a baseband or as part of a carrier wave. This propagated signal may have various forms of representation, including electromagnetic form, optical form, etc., or a suitable combination thereof. A computer storage medium can be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, apparatus, or device to implement communication, propagation, or transmission for use of the program. The program code located on the computer storage medium can be propagated through any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.

[0143] The computer program codes required for the operations of each part of this specification can be written in any one or more programming languages, including object-oriented programming languages such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., conventional procedural programming languages such as C language, Visual Basic, Fortran2003, Perl, COBOL2002, PHP, ABAP, dynamic programming languages such as Python, Ruby and Groovy, or other programming languages. This program code can run entirely on the user's computer, or run as an independent software package on the user's computer, or partially run on the user's computer and partially run on a remote computer, or run entirely on a remote computer or processing device. In the latter case, the remote computer can be connected to the user's computer through any network form, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., through the Internet), or in a cloud computing environment, or used as a service such as software as a service (SaaS).

[0144] In addition, unless clearly stated in the claims, the order of the processing elements and sequences, the use of numbers and letters, or the use of other names in this specification are not used to limit the order of the processes and methods of this specification. Although some currently considered useful embodiments of the invention are discussed through various examples in the above disclosure, it should be understood that such details only serve the purpose of illustration, and the appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that conform to the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only through software solutions, such as installing the described system on existing processing devices or mobile devices.

[0145] Similarly, it should be noted that, in order to simplify the expression of the disclosure of this specification and thus help the understanding of one or more embodiments of the invention, in the previous description of the embodiments of this specification, sometimes multiple features are merged into one embodiment, drawing or description thereof. However, this disclosure method does not mean that the features required by the object of this specification are more than those mentioned in the claims. In fact, the features of the embodiments are less than all the features of the individual embodiments disclosed above.

[0146] In some embodiments, numbers are used to describe components and the quantity of attributes. It should be understood that such numbers used in the description of embodiments are, in some examples, modified by the modifiers "about", "approximately" or "substantially". Unless otherwise specified, "about", "approximately" or "substantially" indicate that the said numbers allow a variation of ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may vary according to the characteristics required by individual embodiments. In some embodiments, the numerical parameters should consider the specified significant digits and adopt the method of retaining the general number of digits. Although the numerical ranges and parameters used in some embodiments of this specification to confirm the breadth of their scope are approximate values, in specific embodiments, such numerical settings are as precise as possible within the feasible range.

[0147] For each patent, patent application, patent application publication and other materials cited in this specification, such as articles, books, specifications, publications, documents, etc., their entire contents are hereby incorporated into this specification by reference. Except for the application history documents that are inconsistent with or conflict with the content of this specification, and also except for the documents that limit the broadest scope of the claims of this specification (currently or subsequently attached to this specification). It should be noted that if there are any inconsistencies or conflicts between the descriptions, definitions, and / or uses of terms in the attached materials of this specification and the content described in this specification, the descriptions, definitions, and / or uses of terms in this specification shall prevail.

[0148] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be considered to be consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A smart port positioning method based on UWB correction, characterized in that: Applied to a smart port system, the smart port system is configured with at least three positioning base stations, and the method comprises: Acquire UWB signals of the target object through the at least three positioning base stations, and calculate the distance of the target object relative to each positioning base station according to the UWB signals; Acquire the distance information of the target object relative to each positioning base station within a specified time period, and arrange the distance information in a time sequence to obtain a multi-dimensional distance sequence; Predicting predicted position information of the target object at a target time based on the multidimensional distance sequence; Comparing the predicted location information with the first location information determined based on the UWB signal corresponding to the target time to determine whether there is a suspected abnormality in the first location information; If there is a suspected abnormality in the first position information, a correction analysis is performed based on the predicted position information and the first position information to obtain the target position information corresponding to the target object at the target time.

2. The method according to claim 1, characterized in that The predicting the predicted position information of the target object at the target time based on the multidimensional distance sequence includes: Inputting the multidimensional distance sequence into a trained machine learning model to obtain the predicted position information, wherein the machine learning model includes at least one of a recurrent neural network, a long short-term memory model, or a gated recurrent unit; The machine learning model includes an input layer, one or more hidden layers and an output layer; wherein the input layer is used to receive the multidimensional distance sequence; the one or more hidden layers are used to extract feature information in the multidimensional distance sequence and perform position prediction based on the feature information; the output layer is used to obtain the predicted position information based on the output results of the one or more hidden layers.

3. The method according to claim 2, characterized in that The machine learning model is trained based on the following method: Acquire multiple sample multidimensional distance sequences and label information corresponding to each of the sample multidimensional distance sequences, wherein the sample multidimensional distance sequences are obtained based on the distance information of the sample target object relative to each positioning base station within a specified sample time period, and the label information is used to indicate the expected prediction result of the position information at the next moment corresponding to each sample multidimensional distance sequence; Input each of the sample multidimensional distance sequences into the initial machine learning model to obtain a corresponding prediction result; The parameters of the initial machine learning model are iteratively trained based on the difference between the prediction result and the corresponding label information until the trained machine learning model is obtained when preset conditions are met.

4. The method according to claim 1, characterized in that The comparing the predicted location information with the first location information determined based on the UWB signal corresponding to the target time to determine whether there is a suspected abnormality in the first location information includes: Calculating the distance between the first location information and the predicted location information; and when the distance between the first location information and the predicted location information is greater than a preset distance threshold, determining that there is a suspected abnormality in the first location information.

5. The method according to claim 1, characterized in that The performing correction analysis based on the predicted position information and the first position information to obtain the target position information corresponding to the target object at the target time includes: Calculating the confidences corresponding to the predicted position information and the first position information respectively; The predicted position information or the first position information is determined based on the confidence level as the target position information corresponding to the target object at the target time.

6. The method according to claim 5, characterized in that The calculating the confidences respectively corresponding to the predicted position information and the first position information includes: Obtain N historical location information corresponding to the latest N historical moments before the target moment; Based on the predicted location information and the first location information relative to the N historical location information, abnormality indexes corresponding to the predicted location information and the first location information are determined, and based on the abnormality indexes, confidence levels corresponding to the predicted location information and the first location information are determined.

7. The method according to claim 5, characterized in that The determining, based on the predicted location information and the first location information relative to the N historical location information, anomaly indexes corresponding to the predicted location information and the first location information, and determining, based on the anomaly indexes, confidence levels corresponding to the predicted location information and the first location information, respectively, includes: Calculate the difference between each of the N historical position information and the position information corresponding to the previous moment to obtain N-1 displacement parameters, and determine the mean and standard deviation corresponding to the N-1 displacement parameters; obtaining a first displacement parameter based on a difference between the first position information and the position information corresponding to the previous moment, and obtaining a second displacement parameter based on a difference between the predicted position information and the position information corresponding to the previous moment; Calculating a first difference of the first displacement parameter relative to the mean value, and a second difference of the second displacement parameter relative to the mean value; Obtaining a first abnormality index corresponding to the first position information according to a ratio of the first difference to the standard deviation, and obtaining a second abnormality index corresponding to the predicted position information according to a ratio of the second difference to the standard deviation; Mapping the first abnormality index and the second abnormality index through a preset function to obtain a first confidence level corresponding to the first position information and a second confidence level corresponding to the predicted position information; The determining, based on the confidence level, the predicted position information or the first position information as the target position information corresponding to the target object at the target time includes: When the first confidence level is greater than or equal to the second confidence level, the first position information is used as the target position information corresponding to the target object at the target moment; when the first confidence level is less than the second confidence level, the predicted position information is used as the target position information corresponding to the target object at the target moment.

8. The method according to claim 1, characterized in that The method further comprises: Acquire IMU detection data of the target object at each moment in a specified time period, and fuse the IMU detection data with the multidimensional distance sequence to obtain a multidimensional fusion information sequence; The multi-dimensional fusion information sequence is input into a trained machine learning model for prediction to obtain the predicted position information of the target object at the target time.

9. The method according to any one of claims 1 to 8, characterized in that The method further comprises: The target location information corresponding to the target object at each moment is mapped to the smart port digital twin system, so that the real-time location information of the target object is displayed in the smart port digital twin system.

10. A smart port positioning system based on UWB correction, characterized in that: Applied to a smart port system, the smart port system is configured with at least three positioning base stations, and the positioning system includes: A first acquisition module, configured to acquire a UWB signal of a target object through the at least three positioning base stations, and calculate a distance of the target object relative to each positioning base station according to the UWB signal; A second acquisition module is used to acquire the distance information of the target object relative to each positioning base station within a specified time period, and arrange the distance information in a time sequence to obtain a multi-dimensional distance sequence; A position prediction module, used to predict the predicted position information of the target object at a target time based on the multidimensional distance sequence; an abnormality judgment module, used to compare the predicted position information with the first position information determined based on the UWB signal corresponding to the target time, so as to judge whether there is a suspected abnormality in the first position information; A correction analysis module is used to perform correction analysis based on the predicted position information and the first position information when there is a suspected abnormality in the first position information, so as to obtain the target position information corresponding to the target object at the target time.

Images