Personnel information positioning method based on city 3D visualization

Abstract

The invention discloses a personnel information positioning method based on city 3D visualization, and the method comprises the following steps: A, installing a plurality of Bluetooth beacons in a positioning region, enabling a positioning person to carry a Bluetooth signal receiving device to enter the positioning region, enabling the Bluetooth signal receiving device to receive Bluetooth signals transmitted by different Bluetooth beacons, and transmitting the Bluetooth signals to the positioning region; the Bluetooth signal receiving device sends the received Bluetooth signal to the positioning module; b, a positioning module optimizes the Bluetooth signal, then uses the optimized Bluetooth signal to perform positioning, and makes visual information of a positioning coordinate; and C, according to the optimization result of the Bluetooth signal, the installation position of the Bluetooth beacon is adjusted regularly. The defects in the prior art can be overcome, and the three-dimensional positioning precision is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of local precise positioning, and in particular to a personnel information positioning method based on city 3D visualization. Background Art

[0002] With the development of short-range communication technologies such as Bluetooth, the application of accurate three-dimensional positioning using Bluetooth has gradually become popular. In the prior art, the positioning coordinates are calculated by reading the RSSI value of the Bluetooth signal and then using algorithms such as triangulation positioning. However, since the Bluetooth signal will be interfered by the external environment during transmission, this will directly lead to errors in the positioning coordinates. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a personnel information positioning method based on urban 3D visualization, which can solve the shortcomings of the existing technology and improve the three-dimensional positioning accuracy.

[0004] In order to solve the above technical problems, the technical solutions adopted by the present invention are as follows.

[0005] A method for locating personnel information based on urban 3D visualization comprises the following steps:

[0006] A. Install several Bluetooth beacons in the positioning area. After the positioning personnel carry a Bluetooth signal receiving device into the positioning area, the Bluetooth signal receiving device receives the Bluetooth signals emitted by different Bluetooth beacons, and the Bluetooth signal receiving device sends the received Bluetooth signals to the positioning module;

[0007] B. The positioning module optimizes the Bluetooth signal, then uses the optimized Bluetooth signal for positioning, and visualizes the positioning coordinates;

[0008] C. Adjust the installation location of Bluetooth beacons regularly based on the optimization results of Bluetooth signals.

[0009] Preferably, for each Bluetooth beacon, the Bluetooth signal receiving device receives Bluetooth signals several times in sequence in each receiving round.

[0010] Preferably, optimizing the Bluetooth signal includes the following steps:

[0011] Extract the RSSI value of the Bluetooth signal, standardize the RSSI value, use the RSSI value to build a data set, define an optimization strategy, use the optimization strategy to sample the data set, and calculate the sampling output result. Select a new sampling point based on the sampling output result, and input the new sampling point into the data set to update the data set.

[0012] Preferably, the standardization process of the RSSI value comprises the following steps:

[0013] The RSSI value is scaled to the interval [0,1] through linear transformation, and then normalized according to the following formula:

[0014] Where c is a constant greater than 0, σ is a normalization factor, and the value of σ is determined according to the distribution state of the RSSI value. Through normalization, RSSI' is symmetrically distributed around the middle value.

[0015] Preferably, the optimization strategy includes several sampling functions, each sampling function samples once in the data set in each round, the sampling results are composed into a prediction matrix, the gradient of the prediction matrix is ​​calculated, the sampling function is randomly linearly transformed, the sampling is again sampled and the gradient of the prediction matrix is ​​calculated, the sampling functions related to the dimensions that produce a downward trend in the gradient of the prediction matrix are retained, random linear transformations are again performed on other sampling functions, and the above process is repeated until the gradient of the prediction matrix is ​​stable; the sampling points of each round are input into the data set to update the data set.

[0016] Preferably, positioning using the optimized Bluetooth signal includes the following steps:

[0017] Use the triangulation positioning algorithm to perform multiple positioning calculations, and use different Bluetooth signals for each positioning calculation; calculate the cluster center of all positioning points, and select the positioning point closest to the cluster center as the final positioning point output.

[0018] Preferably, the movement trajectory of the positioned person is fitted according to the historical data of the output positioning point, the movement trajectory of the positioned person is input into the neural network model, the movement trend of the positioned person is predicted, and the high probability movement area of ​​the positioned person is obtained.

[0019] Preferably, the reception amount of Bluetooth beacon signals located in the area where the positioning personnel have a high probability of moving is increased, and when performing triangulation positioning calculations, Bluetooth beacon signals located in the area where the positioning personnel have a high probability of moving are given priority.

[0020] Preferably, in step C, a normal distribution is fitted to all positioning points with the cluster center of all positioning points as the median value, and then the installation position of the Bluetooth beacons corresponding to the positioning points outside the 3σ range is adjusted to reduce interference with the Bluetooth beacon signals.

[0021] The beneficial effect brought about by adopting the above technical solution is that the present invention effectively reduces the influence of noise signals on positioning accuracy by optimizing the processing of Bluetooth signals, thereby improving the three-dimensional positioning accuracy. DETAILED DESCRIPTION

[0022] Traditional data denoising methods have large computational complexity and obvious lag, and are not suitable for use in the processing of positioning signals in the field of real-time positioning. To address this problem, we have introduced a new data optimization processing flow. After introducing the Bluetooth signal into the three-dimensional positioning process, it will not significantly affect the real-time response of the positioning, and effectively improve the interference of noise data on positioning accuracy. Specifically, it includes the following steps:

[0023] Several Bluetooth beacons are installed in the positioning area. After the positioning personnel enter the positioning area with a Bluetooth signal receiving device, for each Bluetooth beacon, the Bluetooth signal receiving device receives several Bluetooth signals in sequence in each receiving round, and the Bluetooth signal receiving device sends the received Bluetooth signals to the positioning module.

[0024] The positioning module optimizes the Bluetooth signal, then uses the optimized Bluetooth signal for positioning and visualizes the positioning coordinates;

[0025] Optimizing the Bluetooth signal includes the following steps:

[0026] Extract the RSSI value of the Bluetooth signal, scale the RSSI value to the interval [0,1] through linear transformation, and then standardize it according to the following formula:

[0027] Where c is a constant greater than 0, σ is a normalization factor, and the value of σ is determined according to the distribution state of the RSSI value. Through normalization, RSSI' is symmetrically distributed around the middle value.

[0028] A data set is constructed using RSSI values, and an optimization strategy is defined. The optimization strategy includes several sampling functions. Each sampling function samples the data set once in each round, and the sampling results are combined into a prediction matrix. The gradient of the prediction matrix is ​​calculated, and a random linear transformation is performed on the sampling function. The sampling function is sampled again and the gradient of the prediction matrix is ​​calculated. The sampling functions related to the dimensions that produce a downward trend in the gradient of the prediction matrix are retained, and random linear transformations are performed again on other sampling functions. The above process is repeated until the gradient of the prediction matrix is ​​stable; the sampling points of each round are input into the data set to update the data set.

[0029] We use known strategies to construct sampling functions and use the sampling results to iterate the sampling function, so that it can quickly accumulate understanding of the target data. Since each iteration of the sampling function only involves linear transformation and a single sampling process, the iteration speed is fast. By optimizing the Bluetooth signal, the optimal signal set can be quickly obtained and used for positioning calculations.

[0030] Positioning using optimized Bluetooth signals includes the following steps:

[0031] Use the triangulation positioning algorithm to perform multiple positioning calculations, and use different Bluetooth signals for each positioning calculation; calculate the cluster center of all positioning points, and select the positioning point closest to the cluster center as the final positioning point output. Fit the movement trajectory of the positioning personnel based on the historical data of the output positioning points, input the movement trajectory of the positioning personnel into the neural network model, predict the movement trend of the positioning personnel, and obtain the high-probability movement area of ​​the positioning personnel. Increase the reception of Bluetooth beacon signals located in the high-probability movement area of ​​the positioning personnel, and give priority to Bluetooth beacon signals located in the high-probability movement area of ​​the positioning personnel when performing triangulation positioning calculations.

[0032] By optimizing the triangulation positioning results and predicting the movement probability of the positioned person, the recognition accuracy of the Bluetooth signal can be further improved, thereby speeding up the positioning speed.

[0033] In addition, a normal distribution is fitted to all positioning points with the cluster center of all positioning points as the median value, and then the installation positions of the Bluetooth beacons corresponding to the positioning points outside the 3σ range are periodically adjusted to reduce interference with the Bluetooth beacon signals.

[0034] The three-dimensional positioning method disclosed in the present application can effectively improve the contradictory relationship between positioning speed and positioning accuracy in the existing positioning technology, and achieve a significant improvement in positioning accuracy without substantially increasing the hardware investment in the positioning system.

[0035] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A personnel information positioning method based on urban 3D visualization, characterized in that The following steps are involved: A. Install several Bluetooth beacons in the positioning area. After the positioning personnel carry a Bluetooth signal receiving device into the positioning area, the Bluetooth signal receiving device receives the Bluetooth signals emitted by different Bluetooth beacons, and the Bluetooth signal receiving device sends the received Bluetooth signals to the positioning module; B. The positioning module optimizes the Bluetooth signal, then uses the optimized Bluetooth signal for positioning, and visualizes the positioning coordinates; C. Adjust the installation location of Bluetooth beacons regularly based on the optimization results of Bluetooth signals.

2. The method for locating personnel information based on urban 3D visualization according to claim 1, characterized in that: For each Bluetooth beacon, the Bluetooth signal receiving device receives Bluetooth signals several times in a time sequence in each receiving round.

3. The method for locating personnel information based on urban 3D visualization according to claim 2, characterized in that: Optimizing the Bluetooth signal includes the following steps: Extract the RSSI value of the Bluetooth signal, standardize the RSSI value, use the RSSI value to build a data set, define an optimization strategy, use the optimization strategy to sample the data set, and calculate the sampling output result. Select a new sampling point based on the sampling output result, and input the new sampling point into the data set to update the data set.

4. The method for locating personnel information based on urban 3D visualization according to claim 3, characterized in that: The normalization process of RSSI value includes the following steps, The RSSI value is scaled to the interval [0,1] through linear transformation, and then normalized according to the following formula: Where c is a constant greater than 0, σ is a normalization factor, and the value of σ is determined according to the distribution state of the RSSI value. Through normalization, RSSI' is symmetrically distributed around the middle value.

5. The method for locating personnel information based on urban 3D visualization according to claim 4, characterized in that: The optimization strategy includes several sampling functions. Each sampling function samples the data set once in each round, and the sampling results are combined into a prediction matrix. The gradient of the prediction matrix is ​​calculated, and a random linear transformation is performed on the sampling function. The sampling function is sampled again and the gradient of the prediction matrix is ​​calculated. The sampling functions related to the dimensions that produce a downward trend in the gradient of the prediction matrix are retained. For other sampling functions, random linear transformation is performed again, and the above process is repeated until the gradient of the prediction matrix is ​​stable; the sampling points of each round are input into the data set to realize the update of the data set.

6. The method for locating personnel information based on urban 3D visualization according to claim 5, characterized in that: Positioning using optimized Bluetooth signals includes the following steps: Use the triangulation positioning algorithm to perform multiple positioning calculations, and use different Bluetooth signals for each positioning calculation; calculate the cluster center of all positioning points, and select the positioning point closest to the cluster center as the final positioning point output.

7. The method for locating personnel information based on urban 3D visualization according to claim 6, characterized in that: The movement trajectory of the positioned person is fitted according to the historical data of the output positioning point, and the movement trajectory of the positioned person is input into the neural network model to predict the movement trend of the positioned person and obtain the high probability movement area of ​​the positioned person.

8. The method for locating personnel information based on urban 3D visualization according to claim 7, characterized in that: Increase the amount of Bluetooth beacon signals received within the area where the positioned person has a high probability of moving. When performing triangulation calculations, give priority to Bluetooth beacon signals within the area where the positioned person has a high probability of moving.

9. The method for locating personnel information based on urban 3D visualization according to claim 6, characterized in that: In step C, a normal distribution is fitted to all the positioning points with the cluster center of all the positioning points as the median value, and then the installation positions of the Bluetooth beacons corresponding to the positioning points outside the 3σ range are adjusted to reduce interference to the Bluetooth beacon signals.

Images