Multi-mode fingerprint matching fusion intelligent positioning method and system

Abstract

The invention belongs to the technical field of navigation positioning. The invention provides a multi-mode fingerprint matching fusion intelligent positioning method and system, and the method comprises the steps: carrying out the updating of a multi-mode fingerprint database according to the matching weights of Wi-Fi, Bluetooth, RFID, a laser radar, a visual module and an IMU; performing coarse matching positioning according to the Wi-Fi data, the Bluetooth data, the RFID data and the updated multi-mode fingerprint database; performing fine matching positioning according to the coarse matching positioning result and an SLAM pose generated based on the laser radar data, the visual data and the IMU data to obtain a final positioning result; according to the invention, through a self-adaptive fingerprint matching and fusion mechanism, the environment change can be sensed in real time, the weight of each modal fingerprint is dynamically adjusted, and the precision of intelligent positioning is improved.

Description

Technical Field

[0001] The present invention relates to the field of navigation and positioning technology, and in particular to an intelligent positioning method and system for multi-modal fingerprint matching fusion. Background Art

[0002] In today's intelligent era, precise positioning technology has become one of the key technologies that are indispensable for all kinds of intelligent devices and systems. Especially in complex and changing indoor environments, achieving stable and high-precision positioning is the core challenge to ensure the continuity and effectiveness of intelligent services. Traditional single-mode positioning methods, such as Wi-Fi, Bluetooth or laser, visual inertial navigation, etc., are often limited by problems such as uneven signal coverage, multipath effects, and accumulated errors. It is difficult to maintain high positioning accuracy for a long time in complex and changing scenarios.

[0003] To solve the above problems, multimodal positioning technology came into being. It integrates data from multiple sensors and signal sources in order to make up for the shortcomings of a single modality in terms of complementarity and improve the overall positioning performance. However, even with the use of multimodal technology, how to efficiently and accurately integrate positioning fingerprints of different modalities is still a hot topic and difficulty in research. In particular, how to quickly adapt and update the fingerprint library when the environment changes dynamically to ensure the continuity and accuracy of positioning has become a key factor restricting the widespread application of multimodal positioning technology.

[0004] Existing multimodal fingerprint matching methods mostly rely on regular manual or automated resampling and updating mechanisms. This method is not only inefficient, but also difficult to capture subtle real-time changes in the environment, especially in places with dense crowds and frequent movement of objects, such as large shopping malls and hospitals, where the positioning effect is easily affected. In addition, when dealing with the heterogeneity and correlation of different modal data, traditional fusion algorithms often have problems such as unreasonable weight allocation, insufficient use of information redundancy or complementarity, which limits the further improvement of positioning accuracy. Summary of the invention

[0005] In order to address the shortcomings of the prior art, the present invention provides a multimodal fingerprint matching and fusion intelligent positioning method and system, constructs a multimodal fingerprint database, including but not limited to fingerprint information from multiple data sources such as Wi-Fi, Bluetooth, RFID, lidar, vision, inertial measurement unit, etc., through an adaptive fingerprint matching and fusion mechanism, it can perceive environmental changes in real time, dynamically adjust the weights of each modal fingerprint, and improve the accuracy of intelligent positioning.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: In a first aspect, the present invention provides an intelligent positioning method of multi-modal fingerprint matching fusion.

[0007] An intelligent positioning method based on multi-modal fingerprint matching fusion includes the following processes: Update the multimodal fingerprint library according to the matching weights of Wi-Fi, Bluetooth, RFID, LiDAR, vision module and IMU; Perform rough matching and positioning based on Wi-Fi data, Bluetooth data, RFID data and the updated multimodal fingerprint library; Based on the coarse matching positioning results and the SLAM pose generated based on lidar data, visual data and IMU data, precise matching positioning is performed to obtain the final positioning result.

[0008] As a further limitation of the first aspect of the present invention, during the coarse matching positioning and the fine matching positioning process, the positioning matching confidence of Wi-Fi, Bluetooth, RFID, lidar, vision module and IMU is allocated according to the matching weights.

[0009] As a further limitation of the first aspect of the present invention, updating the multimodal fingerprint library includes: Calculate the current sampling matching weights of Wi-Fi, Bluetooth, RFID, LiDAR, vision module and IMU respectively. For any current sampling matching weight, when it is less than half of the preset weight, store the current sampling result in a temporary multimodal fingerprint library. The temporary multimodal fingerprint library is partitioned by location area. When the data in a partition reaches a certain amount, use the data in the partition to establish temporary fingerprint data. When sampling is performed in this partition next time, the original fingerprint data and temporary fingerprint data are used to calculate the weight. When the matching weight data calculated using the original fingerprint data is lower than half of the preset weight, and the weight data calculated using the temporary fingerprint data is higher than half of the preset weight, the validity of the temporary fingerprint data is increased by 1. When the validity of the temporary fingerprint data reaches the set number of times, the temporary fingerprint data is used to update the original fingerprint data, and the temporary modal data in the partition is cleared.

[0010] As a further limitation of the first aspect of the present invention, partitioning by location area includes: dividing physical partitions according to a SLAM map.

[0011] As a further limitation of the first aspect of the present invention, initial weights are set respectively, and data quality of Wi-Fi, Bluetooth, RFID, LiDAR, vision module and IMU is evaluated, and matching weights of Wi-Fi, Bluetooth, RFID, LiDAR, vision module and IMU are calculated respectively using the evaluation results; The assessment includes: For LiDAR, vision module and IMU, the positioning covariance of SLAM positioning results is evaluated; for Wi-Fi, Bluetooth and RFID, the signal strength, noise level and data continuity are evaluated.

[0012] As a further limitation of the first aspect of the present invention, the construction of the multimodal fingerprint library includes: Based on the lidar, visual features and IMU data, the SLAM pose is obtained in combination with the SLAM algorithm. The Wi-Fi data, Bluetooth data, RFID data and SLAM pose are timestamped and aligned, and a multimodal fingerprint library is obtained after model training.

[0013] In a second aspect, the present invention provides an intelligent positioning system for multi-modal fingerprint matching fusion.

[0014] An intelligent positioning system for multi-modal fingerprint matching fusion, comprising: The fingerprint library updating unit is configured to: update the multimodal fingerprint library according to the matching weights of Wi-Fi, Bluetooth, RFID, LiDAR, vision module and IMU; The coarse matching and positioning unit is configured to: perform coarse matching and positioning according to Wi-Fi data, Bluetooth data, RFID data and an updated multimodal fingerprint library; The precise matching positioning unit is configured to perform precise matching positioning according to the rough matching positioning result and the SLAM posture generated based on the lidar data, the visual data and the IMU data to obtain the final positioning result.

[0015] In a third aspect, the present invention provides a computer device, comprising: a processor and a computer-readable storage medium; a processor adapted to execute a computer program; A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by the processor, the intelligent positioning method of multimodal fingerprint matching fusion as described in the first aspect of the present invention is implemented.

[0016] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, wherein the computer program is suitable for being loaded by a processor and executing the intelligent positioning method of multimodal fingerprint matching fusion as described in the first aspect of the present invention.

[0017] In a fifth aspect, the present invention provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the intelligent positioning method of multimodal fingerprint matching fusion as described in the first aspect of the present invention.

[0018] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention builds a comprehensive multimodal fingerprint database by integrating multiple sensor technologies such as Wi-Fi, Bluetooth, RFID, lidar, camera and IMU. It deeply mines the complementary information between the sensor data through the deep learning model, effectively improving the validity and reliability of the data.

[0019] 2. During the positioning process, the adaptive fingerprint matching mechanism is combined with the filtering algorithm to further optimize the matching results, ensuring high-precision positioning even in complex and changing environments.

[0020] 3. The environmental perception and self-adaptation capabilities of the present invention can monitor environmental changes in real time and dynamically adjust the update strategy of the fingerprint database accordingly, which not only enhances the adaptability of the system to dynamic environments, but also ensures the stability and effectiveness of long-term positioning without relying on additional on-site markings or complex environmental configurations.

[0021] 4. From sensor deployment to environmental adaptability optimization, the present invention forms a closed-loop, highly integrated intelligent positioning system, which provides strong support for accurate positioning and robustness in various application scenarios.

[0022] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0024] Figure 1 A schematic diagram of the process of the intelligent positioning method of multimodal fingerprint matching fusion provided in Example 1 of the present invention; Figure 2 A schematic diagram of multimodal fusion provided in Example 1 of the present invention; Figure 3 A schematic diagram of adaptive fingerprint matching and positioning provided in Embodiment 1 of the present invention; Figure 4 A schematic diagram of environmental perception and adaptive updating provided by Embodiment 1 of the present invention; Figure 5 A schematic diagram of a multi-modal fingerprint matching and fusion intelligent positioning system provided in Embodiment 2 of the present invention; Figure 6 A schematic diagram of a computer device provided in Example 3 of the present invention. DETAILED DESCRIPTION

[0025] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0026] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0027] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0028] Embodiment 1: This implementation proposes an intelligent positioning method based on multimodal fingerprint matching and fusion. By integrating data from multiple sensors such as Wi-Fi, Bluetooth, RFID (Radio Frequency Identification), LiDAR, camera and IMU (Inertial Measurement Unit), a multimodal fingerprint database is constructed.

[0029] First, ensure the synchronous collection and preprocessing of multi-source data to improve data quality; then, use deep learning models to extract and fuse features to fully tap the complementary advantages of each modality of data; in the positioning process, use adaptive fingerprint matching mechanism and filtering algorithm to optimize matching results and improve positioning accuracy and stability; at the same time, the system has environmental perception capabilities and can dynamically adjust the update strategy of the fingerprint database according to environmental changes to ensure the stability and effectiveness of long-term positioning. The overall implementation steps include multimodal data collection, database construction, model training, data fusion, adaptive matching and positioning, environmental perception and update, which provide comprehensive support for the accuracy and robustness of the intelligent positioning system.

[0030] Specifically, the above intelligent positioning method, such as Figure 1 As shown, the following process is included: (1) Multimodal data acquisition.

[0031] The key to multimodal data acquisition lies in multimodal data synchronization and preprocessing, the purpose of which is to ensure that the data of each sensor is synchronized in time, and to perform preprocessing such as denoising and filtering on the data to improve data quality.

[0032] In order to keep the data of each sensor synchronized in time, a hardware synchronized data acquisition method is adopted. This method provides a unified clock reference for all sensors involved in data acquisition by synchronizing the system clock signal.

[0033] The sensor receives and responds to synchronization signals in real time through a precise clock synchronization interface, ensuring that all sensors start data collection at the same time point, and maintains a timestamp array for each type of sensor data to record the sampling time of each piece of data. This not only eliminates the time offset caused by internal clock differences between different sensors, but also greatly simplifies the time alignment problem in subsequent data processing.

[0034] To address the noise and interference that may be introduced during the data acquisition process, the hardware synchronization solution is also combined with an efficient data preprocessing mechanism, which uses a dedicated thread for data preprocessing and sets up a data cache queue for each sensor to temporarily store unprocessed data.

[0035] In this implementation, data processing uses digital filtering technology, such as low-pass filters, band-pass filters, etc., to filter out high-frequency noise and interference signals; through denoising algorithms, such as wavelet transform, Kalman filtering, etc., the signal quality is further improved and the impact of noise on data validity is reduced. These preprocessing steps can effectively improve the purity and accuracy of the data, and also lay the foundation for subsequent feature extraction and fusion.

[0036] (2) Construction of multimodal fingerprint library.

[0037] The data structure of the multimodal fingerprint library is created according to the data template, as shown in Table 1. The main fields of the data template include timestamps (such as TimeStamp_0, TimeStamp_1, TimeStamp_2, etc.), feature values ​​of various sensors (MAC address and RSSI, tag identifier and distance, radar point cloud feature points, camera image feature points, IMU acceleration), etc. The database construction first extracts features from each sensor data, and then encodes the extracted feature values ​​into an array to ensure that all modal data are aligned using hardware synchronized timestamps. Finally, the encoded data is stored in the multimodal fingerprint library according to the timestamp index.

[0038] Table 1: Data template

[0039] (3) Multimodal data fusion.

[0040] like Figure 2As shown in the figure, multimodal data fusion mainly includes two levels: data layer fusion and feature layer fusion. For LiDAR, visual features and IMU data, SLAM (Simultaneous Localization and Mapping) is performed through LIO (Laser Odometry and Mapping) and VIO (Visual-Inertial Odometry) to achieve data layer fusion and obtain data layer fusion positioning results.

[0041] For sensor data such as WIFI, Bluetooth, and RFID, they are first aligned according to timestamps, and then a machine learning algorithm is used to train the model on the data with aligned timestamps in the database. Commonly used algorithms include K-nearest neighbor (K-NN), support vector machine (SVM), and decision tree.

[0042] The training results are aligned with the positioning results fused with the data layer through the hardware-synchronized timestamp to build a multimodal fingerprint library, which contains a large number of modal fingerprints of known locations and their corresponding WIFI, Bluetooth, and RFID signal characteristics.

[0043] (4) Adaptive fingerprint matching and positioning.

[0044] like Figure 3 As shown, the key to adaptive fingerprint matching and positioning lies in a complete weight adjustment mechanism, which can adaptively adjust the weights of different sensor data in the fingerprint matching process according to environmental changes.

[0045] First, the data of each sensor is collected in real time, and the existing SLAM algorithm is used to process the lidar, vision and IMU information. At the same time, the WIFI, Bluetooth, RFID and other signals are pre-processed to extract the eigenvalues ​​of each signal; then, the initial weight is set for each sensor, and the data quality of each sensor is evaluated. For lidar, vision, and IMU data, the positioning covariance of the SLAM positioning results is mainly evaluated. For other sensors, the signal strength, noise level and data continuity are mainly evaluated.

[0046] The weight of each sensor data is calculated using the above evaluation results. The calculation method can use weighted summation, fuzzy logic, Bayesian reasoning, etc. For example, the weighted summation example is as follows: (1); in, It is a sensor The weight of is the number of evaluation metrics, is the number of sensors, It is a sensor In the evaluation index The importance coefficient on (this coefficient is set according to the application scenario), It is a sensor In the evaluation index The evaluation value on (normalized).

[0047] The positioning process is the process of posture matching through fingerprints, in which WIFI, Bluetooth, RFID data are matched with the feature data of the fingerprint library for coarse matching positioning, and then lidar, camera, IMU data and SLAM map are used for precise matching. During the positioning process, the confidence of each matching result is allocated through the weight of the above sensors.

[0048] In this implementation, the positioning results of all sensors can be expressed as a state that satisfies the Gaussian distribution. This state is the robot posture estimated by different sensors. Some sensors have high stability but low accuracy, while some have high accuracy but low stability. The positioning is completed by fusing these states. The fusion method can be weighted summation or Bayesian filtering.

[0049] (5) Environmental perception and adaptive updating.

[0050] Adaptive data update is to evaluate the consistency between the data perceived by the current environment and the data in the multimodal fingerprint library. When the evaluation result reaches the preset threshold, the update mechanism is automatically triggered. Specifically, Figure 4 As shown, including: For a certain sampling, the weight obtained by calculation When the weight is less than half of the preset weight, the sampling result is stored in a temporary multimodal database, which is partitioned by location area (location area is a physical area divided according to the SLAM map). When the sensor's data in a partition reaches a certain amount (i.e., datasize>size), the data in the partition is used to establish temporary fingerprint data. When sampling in this area next time, the original fingerprint data and temporary fingerprint data are used to calculate the weight (respectively , , ···and , , ···), when the weight data calculated using the original fingerprint data is less than half of the preset weight (i.e. <threshold / 2), and the weight data calculated using the temporary fingerprint data is higher than half of the preset weight (i.e. >threshold / 2), the validity of the temporary fingerprint data is increased by one. When the validity reaches the set number of times, the temporary fingerprint data is used to update the original fingerprint data and the temporary modal data in the partition is cleared.

[0051] Embodiment 2: like Figure 5 As shown, this implementation provides an intelligent positioning system for multi-modal fingerprint matching fusion, including: The fingerprint library updating unit is configured to: update the multimodal fingerprint library according to the matching weights of Wi-Fi, Bluetooth, RFID, LiDAR, vision module and IMU; The coarse matching and positioning unit is configured to: perform coarse matching and positioning according to Wi-Fi data, Bluetooth data, RFID data and an updated multimodal fingerprint library; The precise matching positioning unit is configured to perform precise matching positioning according to the rough matching positioning result and the SLAM posture generated based on the lidar data, the visual data and the IMU data to obtain the final positioning result.

[0052] The specific working process of each of the above units is described in Example 1 and will not be repeated here.

[0053] It is understandable that the above-mentioned units can be separately or completely combined into one or several other units to constitute, or one (some) of the units can be further divided into multiple smaller units in function to constitute, which can achieve the same operation without affecting the realization of the technical effects of the embodiments of the present application. The above-mentioned units are divided based on logical functions. In practical applications, the functions of one unit can also be implemented by multiple units, or the functions of multiple units can be implemented by one unit. In other embodiments of the present application, the system may also include other units. In practical applications, these functions can also be implemented with the assistance of other units, and can be implemented by the collaboration of multiple units.

[0054] According to another embodiment of the present application, the system described in this embodiment can be constructed, and the method of Example 1 of the present application can be implemented by running a computer program (including program code) capable of executing the steps involved in the corresponding method described in Example 1 on a general-purpose computing device such as a computer, which includes processing elements and storage elements such as a central processing unit (CPU), random access memory (RAM), and read-only memory (ROM). The computer program can be recorded on, for example, a computer-readable recording medium, and loaded into the above-mentioned computing device through the computer-readable recording medium and run therein.

[0055] Embodiment 3: like Figure 6 As shown, this implementation provides an electronic device, which includes a processor 1001, a communication interface 1002, and a computer-readable storage medium 1003. The processor 1001, the communication interface 1002, and the computer-readable storage medium 1003 may be connected via a bus or other means.

[0056] Among them, the communication interface 1002 is used to receive and send data, the computer-readable storage medium 1003 can be stored in the memory of the electronic device, the computer-readable storage medium 1003 is used to store a computer program, the computer program includes program instructions, and the processor 1001 is used to execute the program instructions stored in the computer-readable storage medium 1003.

[0057] The processor 1001 (or CPU (Central Processing Unit)) is the computing core and control core of the electronic device, which is suitable for implementing one or more instructions, and specifically suitable for loading and executing one or more instructions to implement corresponding method processes or corresponding functions.

[0058] The processor 1001 is configured to execute the following process: Update the multimodal fingerprint library according to the matching weights of Wi-Fi, Bluetooth, RFID, LiDAR, vision module and IMU; Perform rough matching and positioning based on Wi-Fi data, Bluetooth data, RFID data and the updated multimodal fingerprint library; Based on the coarse matching positioning results and the SLAM pose generated based on lidar data, visual data and IMU data, precise matching positioning is performed to obtain the final positioning result.

[0059] The specific working process is described in Example 1 and will not be repeated here.

[0060] Embodiment 4: This implementation provides a computer-readable storage medium (Memory), which is a memory device in an electronic device for storing programs and data. It is understandable that the computer-readable storage medium here can include both built-in storage media in the electronic device and, of course, extended storage media supported by the electronic device. The computer-readable storage medium provides a storage space that stores the processing system of the electronic device.

[0061] In addition, the storage space also stores one or more instructions suitable for being loaded and executed by the processor, and these instructions may be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here may be a high-speed RAM memory, or a non-volatile memory, such as at least one disk memory; optionally, it may also be at least one computer-readable storage medium located away from the aforementioned processor.

[0062] In one embodiment, the computer-readable storage medium stores one or more instructions; the processor loads and executes the one or more instructions stored in the computer-readable storage medium to implement the following process: Update the multimodal fingerprint library according to the matching weights of Wi-Fi, Bluetooth, RFID, LiDAR, vision module and IMU; Perform rough matching and positioning based on Wi-Fi data, Bluetooth data, RFID data and the updated multimodal fingerprint library; Based on the coarse matching positioning results and the SLAM pose generated based on lidar data, visual data and IMU data, precise matching positioning is performed to obtain the final positioning result.

[0063] The specific working process is described in Example 1 and will not be repeated here.

[0064] Embodiment 5: The present implementation provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device performs the following process: Update the multimodal fingerprint library according to the matching weights of Wi-Fi, Bluetooth, RFID, LiDAR, vision module and IMU; Perform rough matching and positioning based on Wi-Fi data, Bluetooth data, RFID data and the updated multimodal fingerprint library; Based on the coarse matching positioning results and the SLAM pose generated based on lidar data, visual data and IMU data, precise matching positioning is performed to obtain the final positioning result.

[0065] The specific working process is described in Example 1 and will not be repeated here.

[0066] A person skilled in the art can appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0067] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted through a computer-readable storage medium. The computer instructions can be transmitted from a website site, a computer, a server or a data center to another website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data processing device such as a server, a data center, etc. that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

[0068] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent positioning method based on multimodal fingerprint matching fusion, characterized in that: The process includes: Update the multimodal fingerprint library according to the matching weights of Wi-Fi, Bluetooth, RFID, LiDAR, vision module and IMU; Perform rough matching and positioning based on Wi-Fi data, Bluetooth data, RFID data and the updated multimodal fingerprint library; Based on the coarse matching positioning results and the SLAM pose generated based on lidar data, visual data and IMU data, precise matching positioning is performed to obtain the final positioning result.

2. The intelligent positioning method of multimodal fingerprint matching fusion as claimed in claim 1, characterized in that: During the coarse matching and fine matching positioning processes, the positioning matching confidence of Wi-Fi, Bluetooth, RFID, LiDAR, vision module and IMU is allocated according to the matching weights.

3. The intelligent positioning method of multimodal fingerprint matching fusion as claimed in claim 1, characterized in that: Update the multimodal fingerprint library, including: Calculate the current sampling matching weights of Wi-Fi, Bluetooth, RFID, LiDAR, vision module and IMU respectively. For any current sampling matching weight, when it is less than half of the preset weight, store the current sampling result in a temporary multimodal fingerprint library. The temporary multimodal fingerprint library is partitioned by location area. When the data in a partition reaches a certain amount, use the data in the partition to establish temporary fingerprint data. When sampling is performed in this partition next time, the original fingerprint data and temporary fingerprint data are used to calculate the weight. When the matching weight data calculated using the original fingerprint data is lower than half of the preset weight, and the weight data calculated using the temporary fingerprint data is higher than half of the preset weight, the validity of the temporary fingerprint data is increased by 1. When the validity of the temporary fingerprint data reaches the set number of times, the temporary fingerprint data is used to update the original fingerprint data, and the temporary modal data in the partition is cleared.

4. The intelligent positioning method of multimodal fingerprint matching fusion as claimed in claim 3, characterized in that: Partitioning by location area, including: dividing physical partitions according to SLAM maps.

5. The intelligent positioning method of multimodal fingerprint matching fusion as claimed in claim 1, characterized in that: Set initial weights respectively, evaluate the data quality of Wi-Fi, Bluetooth, RFID, LiDAR, vision module and IMU, and use the evaluation results to calculate the matching weights of Wi-Fi, Bluetooth, RFID, LiDAR, vision module and IMU respectively; The assessment includes: For LiDAR, vision module and IMU, the positioning covariance of SLAM positioning results is evaluated; for Wi-Fi, Bluetooth and RFID, the signal strength, noise level and data continuity are evaluated.

6. The intelligent positioning method of multimodal fingerprint matching fusion as claimed in claim 1, characterized in that: The construction of multimodal fingerprint library includes: Based on the lidar, visual features and IMU data, the SLAM pose is obtained in combination with the SLAM algorithm. The Wi-Fi data, Bluetooth data, RFID data and SLAM pose are timestamped and aligned, and a multimodal fingerprint library is obtained after model training.

7. An intelligent positioning system for multimodal fingerprint matching fusion, characterized in that: include: The fingerprint library updating unit is configured to: update the multimodal fingerprint library according to the matching weights of Wi-Fi, Bluetooth, RFID, LiDAR, vision module and IMU; The coarse matching and positioning unit is configured to: perform coarse matching and positioning according to Wi-Fi data, Bluetooth data, RFID data and an updated multimodal fingerprint library; The precise matching positioning unit is configured to perform precise matching positioning according to the rough matching positioning result and the SLAM posture generated based on the lidar data, the visual data and the IMU data to obtain the final positioning result.

8. A computer device, characterized in that: include: a processor and a computer readable storage medium; a processor adapted to execute a computer program; A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by the processor, the intelligent positioning method of multimodal fingerprint matching fusion as described in any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor and executing the intelligent positioning method for multimodal fingerprint matching fusion as described in any one of claims 1 to 6.

10. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, the intelligent positioning method of multimodal fingerprint matching fusion as described in any one of claims 1 to 6 is implemented.

Images