RFID indoor high-precision positioning system and method based on Internet of Things

Abstract

The invention relates to the technical field of RFID positioning, in particular to an RFID indoor high-precision positioning system and method based on the Internet of Things, and the system comprises an RFID tag module, a base station positioning module, an interconnection environment sensing module, a sensor fusion module, a user tracking module, a self-healing feedback module, a multi-mode interaction module, and a cross-domain data sharing module. The RFID tag module is used for integrating the microprocessor and the sensor and performing energy management; the base station positioning module is used for constructing an intelligent base station and performing multi-dimensional positioning; the interconnected environment sensing module is used for environment modeling and signal interference identification; the sensor fusion module is used for heterogeneous sensor integration and spatio-temporal data processing; the user tracking module is used for intelligent path tracking and behavior prediction; according to the RFID indoor high-precision positioning system and method based on the Internet of Things, the technical defects of a traditional system are overcome, and the system has the advantages of being high in precision, high in anti-interference capacity, high in system self-healing capacity, capable of achieving multi-mode interaction and augmented reality, capable of achieving data sharing and safety and capable of achieving continuous optimization and upgrading.

Description

Technical Field

[0001] The present invention relates to the field of RFID positioning technology, and in particular to an RFID indoor high-precision positioning system and method based on the Internet of Things. Background Art

[0002] RFID (Radio Frequency Identification) is a technology that uses radio signals to identify specific targets and read related data. RFID systems are usually composed of tags, readers, and antennas. Tags contain microchips and antennas that can store and transmit information; readers are responsible for sending radio frequency signals to tags and receiving signals returned by tags; antennas are used to send and receive radio frequency signals. The positioning system is a technology or device that can determine the location of a target. In indoor positioning systems, multiple technologies and algorithms are usually used to determine the specific location of targets (such as people, objects, etc.) indoors. Therefore, RFID technology plays an important role in positioning systems. By arranging RFID tags and readers, objects or people attached to the tags can be tracked and located in real time. By receiving the signals sent by the tags, the readers can calculate the distance between the tags and the readers, and then determine the location of the target. Therefore, RFID technology is one of the important means to achieve high-precision indoor positioning.

[0003] However, in general, in complex indoor environments, RFID signals are interfered by various factors such as metal objects and electronic devices, resulting in reduced positioning accuracy. In addition, RFID tags have limited energy and require effective energy management strategies to extend their service life. Traditional positioning algorithms cannot fully utilize all the characteristics of RFID signals, resulting in insufficient positioning accuracy and robustness. When the system fails, the RFID positioning system lacks an effective self-healing mechanism to restore system performance. In terms of data sharing, traditional systems face security risks such as data leakage and tampering.

[0004] In summary, it is necessary to propose an RFID indoor high-precision positioning system and method based on the Internet of Things to solve the above problems. Summary of the invention

[0005] The purpose of the present invention is to provide an RFID indoor high-precision positioning system and method based on the Internet of Things to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The RFID indoor high-precision positioning system based on the Internet of Things includes an RFID tag module, a base station positioning module, an interconnected environment perception module, a sensor fusion module, a user tracking module, a self-healing feedback module, a multimodal interaction module, and a cross-domain data sharing module;

[0008] The RFID tag module is used to integrate a microprocessor and a sensor and perform energy management;

[0009] The base station positioning module is used to build intelligent base stations and multi-dimensional positioning;

[0010] The interconnected environment perception module is used for environment modeling and signal interference identification;

[0011] The sensor fusion module is used for heterogeneous sensor integration and spatiotemporal data processing;

[0012] The user tracking module is used for intelligent path tracking and behavior prediction;

[0013] The self-healing feedback module is used for fault detection and providing a self-healing response mechanism;

[0014] The multimodal interaction module is used to provide user interaction and build an augmented reality interface;

[0015] The cross-domain data sharing module is used for data sharing and providing an API interface.

[0016] Preferably, the dynamic RFID tag module further includes a smart tag unit and an energy management unit;

[0017] The smart tag unit is used to integrate a microprocessor and a sensor, and use a machine learning algorithm (support vector machine) to monitor environmental changes (temperature, humidity) to dynamically adjust the operating frequency of the tag and reduce signal interference;

[0018] The energy management unit is used to apply energy collection technology (photovoltaic or thermoelectric power generation) and use an adaptive power control algorithm to extend the service life of the tag.

[0019] Preferably, the adaptive base station positioning module further includes an intelligent base station unit and a multi-dimensional positioning unit;

[0020] The intelligent base station unit is used to be equipped with a movable sensor, and dynamically adjust its position using an augmented reality (AR) algorithm to optimize the signal coverage area;

[0021] The multi-dimensional positioning unit is used to combine three-dimensional spatial coordinate calculations and use deep learning (convolutional neural network) to analyze received signal strength (RSSI) data to provide high-precision three-dimensional positioning.

[0022] Preferably, the interconnected environment perception module further includes an environment modeling unit and a signal interference identification unit;

[0023] The environment modeling unit is used to construct an indoor environment map in real time and identify potential interference sources (metal objects) through an environment modeling algorithm based on Bayesian reasoning;

[0024] The signal interference identification unit is used to analyze signal characteristics through an adaptive filtering algorithm, identify and classify interference sources, and dynamically adjust the base station transmission frequency.

[0025] Preferably, the sensor fusion module further comprises a heterogeneous sensor integration unit and a spatiotemporal data processing unit;

[0026] The heterogeneous sensor integration unit is used to integrate different types of sensors (IMU sensor, infrared sensor), and use the mutual information maximization algorithm in information theory to fuse data to improve positioning accuracy;

[0027] The spatiotemporal data processing unit is used to apply a spatiotemporal pattern recognition algorithm to analyze user movement patterns to improve the accuracy of the positioning algorithm.

[0028] Preferably, the real-time user tracking module further includes an intelligent path tracking unit and a behavior prediction unit;

[0029] The intelligent path tracking unit is used to track the user's moving path in real time through a dynamic time warping (DTW) method, process noise data, and improve the robustness of position estimation;

[0030] The behavior prediction unit is used to analyze user behavior in combination with deep reinforcement learning (DRL) to predict the user's future movement path and behavior.

[0031] Preferably, the self-healing feedback mechanism module further includes a fault detection unit and a self-healing response unit;

[0032] The fault detection unit is used to monitor the system status in real time and identify potential faults through an anomaly detection algorithm (local outlier factor LOF);

[0033] The self-healing response unit is used to automatically adjust system parameters (base station power, frequency) using an automated control algorithm to restore optimal performance of the system.

[0034] Preferably, the multimodal interaction module further comprises a user interaction unit and an augmented reality interface unit;

[0035] The user interaction unit is used to enable the user to control the positioning system through voice commands and obtain location information through voice recognition and natural language processing (NLP) methods;

[0036] The augmented reality interface unit is used to superimpose location information on the user's mobile device screen in real time through AR technology to improve the user interaction experience.

[0037] Preferably, the cross-domain data sharing module further includes a data sharing unit and an API interface unit;

[0038] The data sharing unit is used to realize the secure sharing of positioning data using blockchain technology to ensure the integrity and transparency of the data;

[0039] The API interface unit is used to provide a RESTful API to facilitate third-party applications to access the positioning service and promote linkage between different systems.

[0040] Based on the above system, the present invention also proposes an RFID indoor high-precision positioning method based on the Internet of Things, which specifically includes the following steps:

[0041] S1. Arrange RFID tags in the target area, ensure that each tag has a microprocessor and a sensor, and the base station is installed according to the environmental layout to ensure coverage. The tags regularly collect environmental parameters (temperature, humidity, etc.) and record the signal strength (RSSI), see formula (1);

[0042] textRSSI=P t -20log 10 (d)-20log 10 (f)+C (1);

[0043] Where P t is the power of the signal transmitted by the RFID tag and the base station, d is the distance between the RFID tag and the base station, f is the frequency of signal transmission, and C is the environmental constant, which is used to correct the influence of environmental factors on signal strength, including obstacles and humidity;

[0044] S2. Signal smoothing through Kalman Filter;

[0045] S3. Use a multi-dimensional positioning algorithm to calculate the position through the RSSI values ​​of at least three base stations, see formula (2);

[0046]

[0047] Where, d i is the distance between the ith base station and the RFID tag, RSSI t is the signal strength received by the i-th base station;

[0048] S4. Build an environmental model through Bayesian reasoning and update the location of potential interference sources in real time;

[0049] S5. Use the mutual information maximization algorithm in information theory to fuse data from different sources;

[0050] S6. Monitor system status in real time and identify faults using the local outlier factor (LOF) algorithm;

[0051] S7. Use natural language processing (NLP) and speech recognition to query the location through commands, combined with hidden Markov model (HMM) to improve recognition accuracy;

[0052] S8. Use blockchain technology to achieve secure sharing of positioning data and maintain data integrity;

[0053] S9. Apply Q-learning optimization algorithm to regularly analyze positioning accuracy.

[0054] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention significantly improves the positioning accuracy by combining multi-dimensional positioning algorithm and deep learning technology, realizes centimeter-level or even millimeter-level positioning, effectively extends the service life of RFID tags by applying energy harvesting technology and adaptive power control algorithm, effectively reduces the interference of metal objects, electronic devices and other factors on RFID signals by using adaptive filtering algorithm and signal interference identification technology, improves the robustness of the system, timely discovers and handles system faults and restores system performance by real-time monitoring of system status, fault detection and self-healing response mechanism, realizes natural interaction with users and improves user experience by using speech recognition, natural language processing (NLP) and augmented reality (AR) technology, realizes the secure sharing of positioning data by using blockchain technology, ensures the integrity, transparency and security of data, and provides RESTful API interface to facilitate third-party applications to access positioning services, promote linkage and data sharing between different systems, and continuously optimizes positioning algorithms and system parameters by strengthening learning algorithms and positioning accuracy evaluation mechanisms to realize continuous improvement and optimization of positioning systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a topological diagram of the RFID indoor high-precision positioning system based on the Internet of Things of the present invention;

[0056] Figure 2 This is a flow chart of the RFID indoor high-precision positioning method based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] Example 1

[0059] See also Figure 1 ,The present invention proposes an RFID indoor high-precision positioning system based on the Internet of Things, which includes an RFID tag module, a base station positioning module, an interconnected environment perception module, a sensor fusion module, a user tracking module, a self-healing feedback module, a multimodal interaction module, and a cross-domain data sharing module;

[0060] Among them, it should be noted that the RFID tag module of this system is used to integrate microprocessors and sensors and perform energy management, the base station positioning module of this system is used to build intelligent base stations and multi-dimensional positioning, the interconnected environment perception module of this system is used for environmental modeling and signal interference identification, the sensor fusion module of this system is used for heterogeneous sensor integration and spatiotemporal data processing, the user tracking module of this system is used for intelligent path tracking and behavior prediction, the self-healing feedback module of this system is used for fault detection and providing self-healing response mechanism, the multimodal interaction module of this system is used to provide user interaction and build an augmented reality interface, and the cross-domain data sharing module of this system is used for data sharing and providing API interface.

[0061] In this embodiment, it should also be noted that the dynamic RFID tag module of the present invention also includes a smart tag unit and an energy management unit. The smart tag unit is used to integrate a microprocessor and a sensor, and use a machine learning algorithm (support vector machine) to monitor environmental changes (temperature, humidity) to dynamically adjust the operating frequency of the tag and reduce signal interference. The energy management unit is used to apply energy harvesting technology (photovoltaic or thermoelectric power generation) and use an adaptive power control algorithm to extend the service life of the tag.

[0062] In this embodiment, it should also be noted that the adaptive base station positioning module of the present invention also includes an intelligent base station unit and a multi-dimensional positioning unit. The intelligent base station unit is used to be equipped with a movable sensor and dynamically adjust its position using an augmented reality (AR) algorithm to optimize the signal coverage area. The multi-dimensional positioning unit is used to combine three-dimensional spatial coordinate calculations and use deep learning (convolutional neural network) to analyze received signal strength (RSSI) data to provide high-precision three-dimensional positioning.

[0063] In this embodiment, it should also be noted that the interconnected environment perception module of the present invention also includes an environment modeling unit and a signal interference identification unit. The environment modeling unit is used to construct an indoor environment map in real time and identify potential interference sources (metal objects) through an environment modeling algorithm based on Bayesian reasoning. The signal interference identification unit is used to analyze signal characteristics through an adaptive filtering algorithm, identify and classify interference sources, and dynamically adjust the base station transmission frequency.

[0064] In this embodiment, it should also be noted that the sensor fusion module of the present invention also includes a heterogeneous sensor integration unit and a spatiotemporal data processing unit. The heterogeneous sensor integration unit is used to integrate different types of sensors (IMU sensors, infrared sensors), and use the mutual information maximization algorithm in information theory to fuse data to improve positioning accuracy. The spatiotemporal data processing unit is used to apply a spatiotemporal pattern recognition algorithm to analyze user movement patterns to improve the accuracy of the positioning algorithm.

[0065] In this embodiment, it should also be noted that the real-time user tracking module of the present invention also includes an intelligent path tracking unit and a behavior prediction unit. The intelligent path tracking unit is used to track the user's movement path in real time through the dynamic time warping (DTW) method, process noise data, and improve the robustness of position estimation. The behavior prediction unit is used to analyze user behavior in combination with deep reinforcement learning (DRL) to predict its future movement path and behavior.

[0066] In this embodiment, it should also be noted that the self-healing feedback mechanism module of the present invention also includes a fault detection unit and a self-healing response unit. The fault detection unit is used to monitor the system status in real time and identify potential faults through an anomaly detection algorithm (local outlier factor LOF). The self-healing response unit is used to automatically adjust system parameters (base station power, frequency) using an automated control algorithm to restore the optimal performance of the system.

[0067] In this embodiment, it should also be noted that the multimodal interaction module of the present invention also includes a user interaction unit and an augmented reality interface unit. The user interaction unit is used to enable the user to control the positioning system through voice commands and obtain location information through voice recognition and natural language processing (NLP) methods. The augmented reality interface unit is used to superimpose the location information on the user's mobile device screen in real time through AR technology to improve the user interaction experience.

[0068] In this embodiment, it should also be noted that the cross-domain data sharing module of the present invention also includes a data sharing unit and an API interface unit. The data sharing unit is used to use blockchain technology to achieve secure sharing of positioning data and ensure the integrity and transparency of the data. The API interface unit is used to provide a RESTful API to facilitate third-party applications to access positioning services and promote linkage between different systems.

[0069] Example 2

[0070] See also Figure 2 Based on the above system, the present invention also proposes an RFID indoor high-precision positioning method based on the Internet of Things. In practical application, specifically, the method includes the following steps:

[0071] S1.1 Tag layout: RFID tags are arranged at a certain density in the target area, and each tag is equipped with a microprocessor and a sensor; base stations are installed according to the environmental layout to ensure signal coverage;

[0072] Used to achieve effective communication between tags and base stations, providing a basis for subsequent positioning;

[0073] S1.2 Environmental parameter collection:

[0074] The tag collects environmental parameters (such as temperature and humidity) regularly and records the signal strength (RSSI);

[0075] The RSSI value is directly measured by the tag's built-in sensor, as shown in formula (1):

[0076] textRSSI=P t -20log 10 (d)-20log 10 (f)+C (1);

[0077] Where P t is the power of the signal transmitted by the RFID tag and the base station, d is the distance between the RFID tag and the base station, f is the frequency of signal transmission, and C is the environmental constant, which is used to correct the influence of environmental factors on signal strength, including obstacles and humidity;

[0078] Step S1.2 is intended to provide environmental parameters and signal strength data for subsequent positioning and data analysis;

[0079] S1.3 Data preprocessing: Perform preliminary processing on the collected environmental parameters and RSSI values, including denoising and normalization, to improve the accuracy and reliability of the data and provide high-quality data for subsequent steps;

[0080] S2.1 Kalman filter initialization: Initialize the state variables and covariance matrix of the Kalman filter to provide initial conditions for signal smoothing;

[0081] S2.2 Kalman filter prediction: Use the Kalman filter prediction step to predict the current state based on the state at the previous moment;

[0082] The state prediction formula is:

[0083] The covariance prediction formula is: P k =P k-1 +Q;

[0084] In the formula, is the state estimate (prediction value) at the current time k, is the state estimate (known value) of the previous moment k-1, P k is the state covariance matrix at the current time k, indicating the uncertainty of the state estimation, P k-1 is the state covariance matrix of the previous time k-1, Q is the process noise covariance matrix, which represents the uncertainty or noise in the dynamic changes of the system;

[0085] Step S2.2 aims to predict the current state based on the previous state;

[0086] S2.3 Kalman filter update: Using the Kalman filter update step, the state estimate is updated through the observation value to achieve signal smoothing;

[0087] The specific algorithm includes calculating the Kalman gain: K k =P k H T (HP k H T +R) -1 ;

[0088] Update status:

[0089] Update covariance: P k =(IK k H)P k ;

[0090] In the formula, K k is the Kalman gain matrix, which is used to weigh the weights of the predicted value and the observed value in updating the state estimate. H is the observation matrix, which maps the state space to the observation space. T is the transpose of the observation matrix, R is the observation noise covariance matrix, which represents the uncertainty or noise in the observation, I is the identity matrix, which is used for identity transformation in matrix operations, and z k is the observed value of k at the current time;

[0091] S3.1 RSSI value collection: Collect RSSI values ​​from at least three base stations to provide data for subsequent distance calculation and positioning;

[0092] S3.2 Distance calculation: Calculate the distance between the tag and the base station based on the RSSI value as shown in formula (2);

[0093]

[0094] Where, di is the distance between the ith base station and the RFID tag, RSSI t is the signal strength received by the i-th base station, converting the RSSI value into a distance value;

[0095] S3.3 Position calculation: Using the distance information of three or more base stations, the position of the tag in three-dimensional space is calculated through a multi-dimensional positioning algorithm (such as least squares method, triangulation positioning method, etc.);

[0096] S4.1 Initial model establishment: Establish an initial environment model based on prior knowledge to provide a basis for Bayesian reasoning;

[0097] S4.2 Bayesian update: Based on the newly observed data, the environmental model is updated using the Bayesian update formula to reflect the current environmental status in real time;

[0098] S4.3 Interference source identification: Identify potential interference sources based on the updated environment model to provide a basis for subsequent signal interference processing;

[0099] S5.1 Heterogeneous sensor data collection: Collect data from different types of sensors (such as IMU, infrared sensor) to provide a basis for multi-source data fusion;

[0100] S5.2 Mutual Information Maximization: The data from different sources are integrated through the mutual information maximization algorithm to improve the positioning accuracy and robustness by maximizing the mutual information;

[0101] S5.3 Fusion result output: Output the fused data as input for subsequent steps to provide accurate data support for real-time positioning;

[0102] S6.1 System status monitoring: Real-time monitoring of system status, including tags, base stations, and communication links, to detect potential faults in a timely manner;

[0103] S6.2 Fault detection: Use the local outlier factor (LOF) algorithm to identify abnormal points in the system state and accurately locate the fault point;

[0104] S6.3 Self-healing response: According to the fault detection results, the system parameters (such as base station power and frequency) are automatically adjusted to restore system performance and realize the self-healing function of the system;

[0105] S7.1 Voice command reception: Receive user voice commands through voice recognition technology to achieve natural interaction between users and the system;

[0106] S7.2 Command parsing and processing: Use natural language processing (NLP) technology combined with hidden Markov model (HMM) to parse user commands, extract key information and perform corresponding operations;

[0107] S7.3 Location information query and feedback: query location information according to user commands and provide feedback to users through voice or interface to meet user location query needs;

[0108] S8.1 Data collation and packaging: collate positioning data into a standard format for easy sharing;

[0109] S8.2 Application of blockchain technology: Use blockchain technology to achieve secure sharing of positioning data to ensure data integrity, transparency and security. Specific methods include PoW or PoS blockchain consensus methods;

[0110] S8.3 API interface provision: Provide RESTful API interface to facilitate third-party applications to access positioning services and promote linkage and data sharing between different systems;

[0111] S9.1 Positioning accuracy assessment: Regularly assess the accuracy and performance of the positioning system to identify positioning errors and performance bottlenecks;

[0112] S9.2 Reinforcement learning application: Optimize positioning algorithms and parameters through reinforcement learning algorithms (such as Q-learning) to continuously improve positioning accuracy and system performance;

[0113] S9.3 Application of optimization results: Apply the optimization results to the actual positioning system, update the algorithm and parameters, and achieve continuous improvement and optimization of the positioning system.

[0114] In summary, the RFID indoor high-precision positioning system and method based on the Internet of Things of the present invention overcomes the technical shortcomings of traditional systems, and has the advantages of high precision, strong anti-interference ability, system self-healing ability, multimodal interaction and augmented reality, data sharing and security, and continuous optimization and upgrading.

[0115] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. The RFID indoor high-precision positioning system based on the Internet of Things is characterized by: Including RFID tag module, base station positioning module, interconnected environment perception module, sensor fusion module, user tracking module, self-healing feedback module, multimodal interaction module, and cross-domain data sharing module; The RFID tag module is used to integrate a microprocessor and a sensor and perform energy management; The base station positioning module is used to build intelligent base stations and multi-dimensional positioning; The interconnected environment perception module is used for environment modeling and signal interference identification; The sensor fusion module is used for heterogeneous sensor integration and spatiotemporal data processing; The user tracking module is used for intelligent path tracking and behavior prediction; The self-healing feedback module is used for fault detection and providing a self-healing response mechanism; The multimodal interaction module is used to provide user interaction and build an augmented reality interface; The cross-domain data sharing module is used for data sharing and providing an API interface.

2. The RFID indoor high-precision positioning system based on the Internet of Things according to claim 1 is characterized in that: The dynamic RFID tag module also includes a smart tag unit and an energy management unit; The smart tag unit is used to integrate a microprocessor and a sensor, and use a support vector machine to monitor changes in temperature and humidity environments; The energy management unit is used to apply energy harvesting technology.

3. The RFID indoor high-precision positioning system based on the Internet of Things according to claim 2 is characterized in that: The adaptive base station positioning module also includes an intelligent base station unit and a multi-dimensional positioning unit; The intelligent base station unit is used to be equipped with a movable sensor and dynamically adjust its position using an augmented reality (AR) algorithm; The multi-dimensional positioning unit is used to combine three-dimensional spatial coordinate calculation and use deep learning to analyze received signal strength (RSSI) data.

4. The RFID indoor high-precision positioning system based on the Internet of Things according to claim 3 is characterized in that: The interconnected environment perception module also includes an environment modeling unit and a signal interference identification unit; The environment modeling unit is used to construct an indoor environment map in real time and identify potential interference sources through an environment modeling algorithm based on Bayesian reasoning; The signal interference identification unit is used to analyze signal characteristics through an adaptive filtering algorithm, identify and classify interference sources, and dynamically adjust the base station transmission frequency.

5. The RFID indoor high-precision positioning system based on the Internet of Things according to claim 4 is characterized in that: The sensor fusion module also includes a heterogeneous sensor integration unit and a spatiotemporal data processing unit; The heterogeneous sensor integration unit is used to integrate sensors of different types and fuse data using a mutual information maximization algorithm in information theory; The spatiotemporal data processing unit is used to apply a spatiotemporal pattern recognition algorithm to analyze user movement patterns.

6. The RFID indoor high-precision positioning system based on the Internet of Things according to claim 5 is characterized in that: The real-time user tracking module also includes an intelligent path tracking unit and a behavior prediction unit; The intelligent path tracking unit is used to track the user's moving path in real time by using a dynamic time warping (DTW) method and process noise data; The behavior prediction unit is used to analyze user behavior in combination with deep reinforcement learning (DRL) to predict the user's future movement path and behavior.

7. The RFID indoor high-precision positioning system based on the Internet of Things according to claim 6 is characterized in that: The self-healing feedback mechanism module also includes a fault detection unit and a self-healing response unit; The fault detection unit is used to monitor the system status in real time through an abnormality detection algorithm; The self-healing response unit is used to automatically adjust the system base station power and frequency parameters using an automated control algorithm.

8. The RFID indoor high-precision positioning system based on the Internet of Things according to claim 7 is characterized in that: The multimodal interaction module also includes a user interaction unit and an augmented reality interface unit; The user interaction unit is used to enable the user to control the positioning system through voice commands and obtain location information through voice recognition and natural language processing (NLP) methods; The augmented reality interface unit is used to superimpose location information on the user's mobile device screen in real time through AR technology.

9. The RFID indoor high-precision positioning system based on the Internet of Things according to claim 8 is characterized in that: The cross-domain data sharing module also includes a data sharing unit and an API interface unit; The data sharing unit is used to realize the secure sharing of positioning data using blockchain technology; The API interface unit is used to provide a RESTful API.

10. An RFID indoor high-precision positioning method based on the Internet of Things, according to any one of claims 1 to 9, characterized in that: The following steps are involved: S1. Arrange RFID tags in the target area, ensure that each tag has a microprocessor and a sensor, and the base station is installed according to the environmental layout. The tags collect environmental parameters (temperature, humidity, etc.) and record the signal strength (RSSI) at regular intervals, see formula (1); textRSSI=P t -20log 10 (d)-20log 10 (f)+C (1); Where P t is the power of the signal transmitted by the RFID tag and the base station, d is the distance between the RFID tag and the base station, f is the frequency of signal transmission, and C is the environmental constant, which is used to correct the influence of environmental factors on signal strength, including obstacles and humidity; S2. Signal smoothing through Kalman Filter; S3. Use a multi-dimensional positioning algorithm to calculate the position through the RSSI values ​​of at least three base stations, see formula (2); Where, d i is the distance between the ith base station and the RFID tag, RSSI t is the signal strength received by the i-th base station; S4. Build an environmental model through Bayesian reasoning and update the location of potential interference sources in real time; S5. Use the mutual information maximization algorithm in information theory to fuse data from different sources; S6. Monitor system status in real time and identify faults using the local outlier factor (LOF) algorithm; S7. Use natural language processing (NLP) and speech recognition to query the location through commands, combined with hidden Markov model (HMM) to improve recognition accuracy; S8. Realize secure sharing of location data through blockchain technology; S9. Apply Q-learning optimization algorithm to regularly analyze positioning accuracy.

Images