Floor positioning method, device and equipment based on Bluetooth data coupling air pressure data

Abstract

The present invention provides a floor positioning method, device and equipment based on Bluetooth data coupling with air pressure data, including: before the floor positioning is turned on, the Bluetooth signal strength values ​​of different floors in the target indoor positioning scene are collected to form corresponding candidate fingerprints, and a Bluetooth fingerprint library is generated; during the floor positioning process, the Bluetooth signal strength value of the floor to be positioned is collected in real time to obtain a Bluetooth fingerprint to be matched; the Bluetooth fingerprint to be matched is matched with the candidate fingerprint in the Bluetooth fingerprint library, and the floor corresponding to the best matching degree is selected as the preliminarily selected floor; based on the preliminarily selected floor and combined with the air pressure data, the final selected floor is obtained. This application overcomes the problem of low universality of the traditional air pressure floor positioning method, overcomes the problem of insufficient robustness of the traditional Bluetooth floor positioning method, and improves the accuracy and reliability of the floor positioning result.

Description

Technical Field

[0001] The present application relates to the field of positioning technology, and in particular to a floor positioning method, device and equipment based on Bluetooth data coupled with air pressure data. Background Art

[0002] With the widespread popularity of smart phones, more and more sensors are integrated into mobile phones. Mobile phones can obtain more data in the environment, which promotes the development of indoor positioning technology. Floor positioning technology has great practicality in indoor positioning systems. Floor positioning can make the information push of floor stores in large shopping malls more accurate; make fire rescue in high-rise buildings more efficient; and make the search for underground parking lots more practical. The initial floor positioning method was mostly the pressure difference floor positioning method, which calculated the elevation by the pressure-altitude model to give the floor. Later, the wireless signal attenuation method was mostly used for floor positioning. Yu Minjie proposed an indoor multi-floor algorithm based on rapid deployment in 2014. It judged the floor by calculating the signal attenuation value, but when calculating the weight of each signal source, the signal strength standard deviation was used as the basis for weight determination, and the judgment delay was too high. In 2017, Li Haitao et al. counted the number of access points (APs) within the threshold of each floor and used the floor with more statistical numbers as the estimated floor. This method did not consider the situation where the statistical numbers were the same and the influence of the signal strength value of the screened AP on the floor determination.

[0003] There are two traditional floor positioning methods. One is to use an air pressure acquisition device to perform air pressure differential to determine the user's behavior of going up and down the stairs. Because the user's current floor may not be known, it is difficult to set the initial floor, and some mobile phones do not have air pressure acquisition devices, resulting in weak universality of this method. Another method is to directly use Bluetooth signal strength to identify the floor. If this method has phenomena such as sudden changes in Bluetooth signal strength, it will produce large observation errors and have a greater impact on the results. Therefore, the traditional floor positioning method has certain limitations: the traditional air pressure floor positioning method has low universality; the traditional Bluetooth floor positioning method is not robust enough; the accuracy and reliability of the traditional floor positioning results are low. Summary of the invention

[0004] In view of the shortcomings of the prior art mentioned above, the purpose of the present application is to provide a floor positioning method, device and equipment based on Bluetooth data coupled with air pressure data, which is used to solve at least one of the technical problems in the prior art, such as the low universality of the traditional air pressure floor positioning method, the lack of robustness of the traditional Bluetooth floor positioning method, and the low accuracy and reliability of the traditional floor positioning results.

[0005] To achieve the above-mentioned purpose and other related purposes, the present application provides a floor positioning method based on Bluetooth data coupling with air pressure data, including: before floor positioning is turned on, collecting Bluetooth signal strength values ​​of different floors in the target indoor positioning scene to form corresponding candidate fingerprints, and generating a Bluetooth fingerprint library; during the floor positioning process, collecting the Bluetooth signal strength value of the floor to be located in real time to obtain a Bluetooth fingerprint to be matched; matching the Bluetooth fingerprint to be matched with the candidate fingerprint in the Bluetooth fingerprint library, and selecting the floor corresponding to the best match as the initially selected floor; based on the initially selected floor and combined with the air pressure data, obtaining the final selected floor.

[0006] In one embodiment of the present application, the Bluetooth signal strength values ​​of different floors in the target indoor positioning scene are collected to form corresponding candidate fingerprints, and a Bluetooth fingerprint library is generated, including the following steps: 1.1) Using a mobile terminal to collect Bluetooth signal strength values ​​at different distances from a Bluetooth node for the same duration, and obtain the average Bluetooth signal strength at different distances; 1.2) Combining the average Bluetooth signal strength and the corresponding distance between the Bluetooth nodes, a simplified logarithmic distance loss model is established: RSSI(d)=A-10n lg(d); wherein RSSI(d) represents the Bluetooth signal strength value received when the distance between the mobile terminal and the Bluetooth node is d; A represents the Bluetooth signal strength value received when the distance between the mobile terminal and the Bluetooth node is 1m; n represents the path loss factor, which changes with the change of the surrounding environment; d represents the distance between the mobile terminal and the Bluetooth node; 1.3) Using a supervised learning optimization algorithm to fit parameters A and n, and inversely derive a ranging formula to calculate the distance between the Bluetooth node and the mobile terminal; 1.4) Deploy a Bluetooth node network and store the MAC addresses of all Bluetooth nodes and their corresponding floor information in the Bluetooth fingerprint library.

[0007] In one embodiment of the present application, the real-time acquisition of the Bluetooth signal strength value of the floor to be located to obtain the Bluetooth fingerprint to be matched; matching the Bluetooth fingerprint to be matched with the candidate fingerprints in the Bluetooth fingerprint library, and selecting the floor corresponding to the best matching degree as the initially selected floor, includes the following steps: 2.1) using a mobile terminal to collect the Bluetooth signal strength value of the floor to be located in real time, and calculating the distances d1, d2, d3, ..., d between the m Bluetooth nodes that can be received and the mobile terminal in real time according to the ranging formula m ; 2.2) Arrange the m distance values ​​obtained in descending order and count the number of Bluetooth nodes that can be received on each floor; 2.3) Based on the K nearest neighbor algorithm, adaptively select the k value according to the number of Bluetooth nodes corresponding to the floor with the least number of Bluetooth nodes received; 2.4) Adaptively match the MAC addresses of the Bluetooth nodes corresponding to the first k distances of each floor with the Bluetooth fingerprint library, and select the floor i with the smallest average distance as the initially selected floor.

[0008] In one embodiment of the present application, the final selected floor is obtained based on the initially selected floor and combined with the air pressure data, including the following steps: 3.1) Identify whether the mobile terminal has a built-in air pressure collection device. If there is no air pressure collection device, output i as the final selected floor; if there is an air pressure collection device, record the current time T1, the current air pressure value P1 and the initially selected floor i; 3.2) The time when the floor is identified again is T2, and the air pressure value P2 at this time is recorded. The elevation change Δh in the time period from T1 to T2 is obtained by the air pressure difference. The elevation change Δh is divided by the average height h of each floor to obtain the floor change number ΔF. At this time, the positioning floor obtained by the air pressure difference is I1; and the corresponding positioning floor obtained by Bluetooth real-time positioning is I2; 3.3) When I1=I2, output I1 as the final selected floor; 3.4) When I1≠I2, perform specific analysis and judgment based on the time difference between T2 and T1 and the k' value corresponding to T2.

[0009] In one embodiment of the present application, the expression for locating the floor I1 obtained by the air pressure difference is: I1=i±ΔF; wherein, “±” is related to the increase or decrease in air pressure, “-” indicates an increase in air pressure, and “+” indicates a decrease in air pressure.

[0010] In one embodiment of the present application, the specific analysis and judgment based on the time difference between T2 and T1 and the k' value corresponding to T2 includes the following steps: 3.4.1) When T2-T1≥20min and k'≥3, output I2 as the final selected floor; 3.4.2) When T2-T1<20min and k'<3, output I1 as the final selected floor; 3.4.3) When T2-T1≥20min and 0<k'<3 or T2-T1<20min and k'≥3, set the credible factor c f and the preset threshold t g For analysis: When c f ≥t g Output I2 as the final selected floor; when c f <t g 3.4.4) When k'=0, output I1 as the final selected floor.

[0011] In one embodiment of the present application, the trust factor c f The expression is: Among them, n f represents the number of Bluetooth recognized on the f floor; ρ f represents the Bluetooth distribution density on floor f; N represents the number of Bluetooth signals that can be received at time T2.

[0012] To achieve the above-mentioned purpose and other related purposes, the present application provides a hybrid floor positioning device based on Bluetooth coupled air pressure, including: a Bluetooth fingerprint library generation module, which is used to collect the Bluetooth signal strength values ​​of different floors in the target indoor positioning scene before the floor positioning is turned on to form corresponding candidate fingerprints, and generate a Bluetooth fingerprint library; a real-time positioning module, which is used to collect the Bluetooth signal strength value of the floor to be located in real time during the floor positioning process to obtain a Bluetooth fingerprint to be matched; the Bluetooth fingerprint to be matched is matched with the candidate fingerprint in the Bluetooth fingerprint library, and the floor corresponding to the best match is selected as the initially selected floor; based on the initially selected floor and combined with the air pressure data, the final selected floor is obtained.

[0013] To achieve the above-mentioned purpose and other related purposes, the present application provides a computer device, including: a memory, a processor and a communicator; the memory is used to store computer programs; the processor is used to execute the computer programs stored in the memory so that the device performs the method as described above; the communicator is used to communicate with external devices.

[0014] To achieve the above-mentioned purpose and other related purposes, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements any of the methods described above when executed by a processor.

[0015] In summary, the floor positioning method, device and equipment based on Bluetooth data coupling with air pressure data provided by the present application have the following beneficial effects:

[0016] 1. This application performs mean filtering and Gaussian filtering on the Bluetooth signal strength data sequence, which weakens the impact of observation errors caused by abnormal Bluetooth devices, reduces the noise in Bluetooth observation data, and improves the robustness of the results;

[0017] 2. The relationship between Bluetooth signal strength and distance is inversely calculated by modeling, and the K nearest neighbor algorithm with adaptive k value selection is used to match the terminal with the k nearest devices on each floor, which reduces the floor jumping phenomenon often caused by floor positioning and improves the accuracy and continuity of floor positioning results;

[0018] 3. By coupling the data of the air pressure acquisition device, introducing the trust factor, and comprehensively considering the experimental results under various conditions, the robustness of the algorithm is improved;

[0019] 4. This application is not only applicable to mobile terminals with built-in air pressure collection devices, but also to mobile terminals without built-in air pressure collection devices. It is more universal than traditional air pressure floor positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1Shown is a flow chart of a floor positioning method based on Bluetooth data coupled with air pressure data in one embodiment of the present application.

[0021] Figure 2 Shown is a schematic diagram of Bluetooth signal strength values ​​collected by a mobile terminal in one embodiment of the present application.

[0022] Figure 3 Shown is a schematic diagram of the results of fitting parameters based on supervised learning in one embodiment of the present application.

[0023] Figure 4 Shown is a module schematic diagram of a hybrid floor positioning device based on Bluetooth coupled air pressure in one embodiment of the present application.

[0024] Figure 5 Shown is a schematic diagram of the structure of a computer device in one embodiment of the present application. DETAILED DESCRIPTION

[0025] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0026] It should be noted that in the following description, with reference to the accompanying drawings, several embodiments of the present application are described in the accompanying drawings. It should be understood that other embodiments may also be used, and mechanical composition, structure, electrical and operational changes may be made without departing from the spirit and scope of the present application. The following detailed description should not be considered restrictive, and the scope of the embodiments of the present application is limited only by the claims of the published patents. The terms used here are only for describing specific embodiments and are not intended to limit the present application. Spatially related terms, such as "upper", "lower", "left", "right", "below", "below", "lower", "above", "upper", etc., may be used in the text to facilitate the description of the relationship between an element or feature shown in the figure and another element or feature.

[0027] Throughout the specification, unless otherwise clearly specified and limited, the terms "install", "connect", "connect", "fix", "hold" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two components. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0028] Furthermore, as used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context indicates otherwise. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments described here can be implemented in an order other than that illustrated or described here. It should be further understood that the terms "comprising" and "including" indicate the presence of the described features, operations, elements, components, items, kinds, and / or groups, but do not exclude the presence, occurrence or addition of one or more other features, operations, elements, components, items, kinds, and / or groups. The terms "or" and "and / or" used herein are interpreted as inclusive, or mean any one or any combination. Therefore, "A, B or C" or "A, B and / or C" means "any of the following: A; B; C; A and B; A and C; B and C; A, B and C". Exceptions to this definition occur only when a combination of elements, functions, or operations are inherently mutually exclusive in some manner.

[0029] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the technical solution in the embodiments of the present invention is further described in detail through the following embodiments and in combination with the accompanying drawings. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the invention.

[0030] In order to solve the existing problems, the present application proposes a floor positioning method, device and equipment based on Bluetooth data coupled with air pressure data, which is used to solve at least one of the technical problems in the prior art, namely, the low universality of the traditional air pressure floor positioning method, the lack of robustness of the traditional Bluetooth floor positioning method, and the low accuracy and reliability of the traditional floor positioning results.

[0031] like Figure 1 , which is a flow chart of a floor positioning method based on Bluetooth data coupled with air pressure data in one embodiment of the present application, the method comprises the following steps:

[0032] Step S1: Before the floor positioning is started, the Bluetooth signal strength values ​​of different floors in the target indoor positioning scene are collected to form corresponding candidate fingerprints, and a Bluetooth fingerprint library is generated.

[0033] In one embodiment of the present application, the Bluetooth signal strength values ​​of different floors in the target indoor positioning scene are collected to form corresponding candidate fingerprints, and a Bluetooth fingerprint library is generated, which specifically includes the following steps:

[0034] 1.1) Use a mobile terminal to collect Bluetooth signal strength values ​​at different distances from the Bluetooth node for the same duration, and obtain the average Bluetooth signal strength at different distances.

[0035] For example, use a mobile terminal to collect Bluetooth signal strength values ​​and RSSI values ​​at different distances from the Bluetooth node, including: 0.2m, 0.4m, 0.6m, 0.8m, 1m, 2m, 3m, 4m, 5m, etc.; the collection time is unified as 5 minutes. The collected Bluetooth signal results are as follows: Figure 2 As shown: the horizontal axis represents the number of collection points, and the vertical axis represents the collected Bluetooth signal strength value; the curve from top to bottom in the figure indicates that the distance from the Bluetooth node is increasing.

[0036] It should be noted that the distance measurement accuracy is improved by filtering the collected Bluetooth signal strength, and the filtering process includes Gaussian filtering and mean filtering.

[0037] Specifically, the collected Bluetooth signal strength values ​​at different distances are processed by Gaussian filtering to eliminate the observation errors caused by abnormal Bluetooth nodes. The Bluetooth signal strength values ​​processed by Gaussian filtering are then smoothed by linear filtering through mean filtering to reduce the impact of individual inappropriate Bluetooth nodes on the measurement and remove irrelevant details in the image.

[0038] In addition, after mean filtering, the mean value of Bluetooth signal strength at different distances can be obtained, that is: RSSI 0.2 、RSSI 0.4 、RSSI 0.6 、RSSI 0.8 , RSSI1, RSSI2, RSSI3, RSSI4, RSSI5, etc.

[0039] 1.2) Combining the Bluetooth signal strength mean and the corresponding distance between Bluetooth nodes, a simplified logarithmic distance loss model is established:

[0040] RSSI(d) = A-10n lg(d);

[0041] Among them, RSSI(d) represents the Bluetooth signal strength value received when the distance between the mobile terminal and the Bluetooth node is d, that is, the average Bluetooth signal strength; A represents the Bluetooth signal strength value received when the distance between the mobile terminal and the Bluetooth node is 1m; n represents the path loss factor, which changes with the changes in the surrounding environment; d represents the distance between the mobile terminal and the Bluetooth node.

[0042] It should be noted that based on the logarithmic distance loss model:

[0043]

[0044] Wherein, d represents the distance between the Bluetooth node and the mobile terminal; RSSI(d) represents the Bluetooth signal strength value of the mobile terminal receiving the specific signal node when the distance from the Bluetooth node is d; d0 represents the preset reference distance; RSSI(d0) represents the Bluetooth signal strength value received by the mobile terminal at the reference distance d0 from the Bluetooth; n represents the path loss factor, which changes with the changes in the surrounding environment; X σ represents a Gaussian normal random variable with a mean of 0 and a standard deviation of σ;

[0045] When d0 = 1m, X σ It can be ignored in actual measurement, so the logarithmic distance loss model is simplified to:

[0046] RSSI(d) = A-10n lg(d);

[0047] Wherein, A represents the Bluetooth signal strength value received by the mobile terminal from a specific signal node when the Bluetooth distance is 1m; RSSI(d) represents the Bluetooth signal strength value after filtering when the distance between the mobile terminal and the Bluetooth node is d.

[0048] 1.3) Use the supervised learning optimization algorithm to fit the parameters A and n, and invert the ranging formula to calculate the distance between the Bluetooth node and the mobile terminal.

[0049] like Figure 3 As shown, it is a schematic diagram showing the result of supervised learning fitting parameters in one embodiment of the present application. The horizontal axis represents the distance between the mobile terminal and the Bluetooth node; the vertical axis represents the average Bluetooth signal strength obtained after filtering; the dots represent the actual collected data; and the curve is fitted by the supervised learning optimization algorithm.

[0050] For example, in this embodiment, a large amount of experimental data is fitted to obtain parameter A as -38db and n as 2.553.

[0051] It should be noted that after fitting the parameters A and n, the distance between the Bluetooth node and the mobile terminal can be inversely calculated by combining the simplified logarithmic distance loss model. The distance measurement formula is expressed as:

[0052]

[0053] 1.4) Deploy a Bluetooth node network and store the MAC addresses of all Bluetooth nodes and their corresponding floor information in the Bluetooth fingerprint library.

[0054] It should be noted that each fingerprint in the Bluetooth fingerprint library includes: Bluetooth signal strength value, MAC address of the corresponding Bluetooth node, corresponding floor and other information.

[0055] Step S2: During the floor positioning process, the Bluetooth signal strength value of the floor to be positioned is collected in real time to obtain a Bluetooth fingerprint to be matched; the Bluetooth fingerprint to be matched is matched with the candidate fingerprints in the Bluetooth fingerprint library, and the floor corresponding to the best matching degree is selected as the initially selected floor.

[0056] In one embodiment of the present application, the real-time acquisition of the Bluetooth signal strength value of the floor to be located to obtain the Bluetooth fingerprint to be matched; matching the Bluetooth fingerprint to be matched with the candidate fingerprints in the Bluetooth fingerprint library, and selecting the floor corresponding to the best matching degree as the initially selected floor, includes the following steps:

[0057] 2.1) Use the mobile terminal to collect the Bluetooth signal strength value of the floor to be located in real time, and calculate the distances d1, d2, d3, ... d between the m Bluetooth nodes that can be received and the mobile terminal in real time according to the ranging formula m .

[0058] 2.2) Arrange the m distance values ​​obtained in descending order and count the number of Bluetooth nodes on each floor that can be received.

[0059] It should be noted that the sum of the number of Bluetooth nodes on each floor that can be received is m.

[0060] For example, the number of Bluetooth nodes on each floor that can be received can be directly counted through mobile phone Bluetooth scanning.

[0061] 2.3) Based on the K-nearest neighbor algorithm, the k value is adaptively selected according to the number of Bluetooth nodes corresponding to the floor with the least number of Bluetooth nodes.

[0062] Specifically, the floor with the least number of received Bluetooth nodes is selected, and the corresponding number of Bluetooth nodes is assigned to k, so as to adaptively select the k value of the K nearest neighbor algorithm.

[0063] It should be noted that if a fixed k value is used, underfitting or overfitting will occur when the Bluetooth space distribution is uneven; so in order to avoid this situation, it must be adaptively selected.

[0064] 2.4) Adaptively match the MAC addresses of the Bluetooth nodes corresponding to the first k distances of each floor with the Bluetooth fingerprint library, and select the floor i with the smallest average distance as the initial selected floor.

[0065] Specifically, the above 2.1)-2.4) are specific steps in the Bluetooth positioning stage.

[0066] Step S3: Based on the initially selected floor and in combination with the air pressure data, a final selected floor is obtained.

[0067] In one embodiment of the present application, the final selected floor is obtained based on the initially selected floor and combined with the air pressure data, specifically including the following steps:

[0068] 3.1) Identify whether the mobile terminal has a built-in air pressure collection device. If there is no air pressure collection device, output i as the final selected floor; if there is an air pressure collection device, record the current time T1, the current air pressure value P1 and the initially selected floor i.

[0069] It should be noted that the air pressure collection device is used to obtain air pressure data, such as a barometer, an air pressure sensor, etc.

[0070] 3.2) The time for identifying the floor again is T2, and the air pressure value P2 at this time is recorded. The altitude change Δh in the time period from T1 to T2 is obtained by the air pressure difference. The elevation change Δh is divided by the average height h of each floor to obtain the floor change number ΔF. The positioning floor obtained by the air pressure difference at this time is I1; and the corresponding positioning floor obtained by Bluetooth real-time positioning is I2.

[0071] In one embodiment of the present application, the expression for the positioning floor I1 obtained by the air pressure difference is:

[0072] I1=i±ΔF;

[0073] Among them, "±" is related to the increase or decrease of air pressure, "-" indicates the increase of air pressure, and "+" indicates the decrease of air pressure.

[0074] It should be noted that the positioning floor I2 obtained by real-time positioning via Bluetooth is obtained through step S2 at time T2.

[0075] 3.3) When I1=I2, output I1 as the final selected floor.

[0076] It should be noted that when the positioning floor I1 obtained by air pressure difference is consistent with the positioning floor I2 obtained by Bluetooth real-time positioning, either of them can be used as the final selected floor.

[0077] 3.4) When I1≠I2, make a specific analysis and judgment based on the time difference between T2 and T1 and the k' value corresponding to T2.

[0078] Specifically, 3.1) to 3.4) above are specific steps for coupling air pressure positioning with Bluetooth positioning to obtain a positioning result with higher credibility.

[0079] It should be noted that when the positioning floor I1 obtained by air pressure difference is inconsistent with the positioning floor I2 obtained by Bluetooth real-time positioning, further analysis is required.

[0080] In one embodiment of the present application, the specific analysis and judgment based on the time difference between T2 and T1 and the k' value corresponding to T2 specifically includes the following steps:

[0081] 3.4.1) When T2-T1≥20min and k'≥3, output I2 as the final selected floor;

[0082] 3.4.2) When T2-T1<20min and k'<3, output I1 as the final selected floor;

[0083] 3.4.3) When T2-T1≥20min and 0<k'<3 or T2-T1<20min and k'≥3, set the trust factor c f and the preset threshold t g For analysis:

[0084] When c f ≥t g Output I2 as the final selected floor; when c f <t g Output I1 as the final selected floor.

[0085] It should be noted that the credibility factor c f The expression is:

[0086]

[0087] Among them, n f represents the number of Bluetooth nodes identified on floor f; ρ f represents the Bluetooth distribution density on floor f; N represents the number of Bluetooth nodes that can be received at time T2.

[0088] It should be noted that based on the principle of differential pressure altimetry, experiments show that when the time difference is within 20 minutes, the temperature difference has little effect on the air pressure, so the time difference between T2 and T1 is preferably set to 20 minutes to avoid the impact of temperature changes on the barometer.

[0089] It should be noted that in order to improve the credibility of the experimental results, more than three Bluetooth devices must be scanned, so the judgment standard of k' is set to 3.

[0090] For example, the preset threshold t g Indicates the degree of credibility in space; based on experience, the threshold t can be set g It is 0.016.

[0091] 3.4.4) When k'=0, output I1 as the final selected floor.

[0092] It should be noted that the present application provides a floor positioning method based on Bluetooth data coupled with air pressure data, which is not only applicable to mobile terminals (such as smart phones) with built-in Bluetooth and air pressure collection devices (such as barometers), and the air pressure data is coupled with Bluetooth data to select the result with high credibility as the final selected floor; it is also applicable to mobile terminals (such as smart phones) with only one of Bluetooth or air pressure collection devices (such as barometers) built-in, and the positioning result is determined by corresponding Bluetooth positioning or based on existing air pressure positioning. The present application is more universal than traditional air pressure floor positioning.

[0093] like Figure 4 FIG. 4 is a schematic diagram of a hybrid floor positioning device based on Bluetooth coupling air pressure in an embodiment of the present application. The hybrid floor positioning device based on Bluetooth coupling air pressure 400 includes:

[0094] The Bluetooth fingerprint library generation module 410 is used to collect Bluetooth signal strength values ​​of different floors in the target indoor positioning scene to form corresponding candidate fingerprints and generate a Bluetooth fingerprint library before the floor positioning is turned on;

[0095] The real-time positioning module 420 is used to collect the Bluetooth signal strength value of the floor to be located in real time during the floor positioning process to obtain the Bluetooth fingerprint to be matched; match the Bluetooth fingerprint to be matched with the candidate fingerprints in the Bluetooth fingerprint library, and select the floor corresponding to the best matching degree as the initially selected floor; based on the initially selected floor and combined with the air pressure data, obtain the final selected floor.

[0096] It should be understood that the division of the various modules of the above device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software called by processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. For example, the real-time positioning module 420 can be a separately established processing element, or it can be integrated in a chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called and executed by a processing element of the above device. The function of the above real-time positioning module 420. The implementation of other modules is similar. In addition, all or part of these modules can be integrated together, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.

[0097] For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASICs), or one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs). For another example, when a module is implemented in the form of a processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processors that can call program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0098] like Figure 5 As shown, it is a schematic diagram of the structure of a computer device 500 in one embodiment of the present application. The computer device 500 includes: a memory 510, a processor 520 and a communicator 530; the memory 510 is used to store computer instructions; the processor 520 executes the computer instructions to implement the following Figure 1 The method; the communicator 530 is used to communicate with external devices.

[0099] For example, the external device may be a cloud server; or it may be a user's mobile terminal, such as a mobile phone, PC, tablet, etc.

[0100] In some embodiments, the number of the memory 510, the processor 520, and the communicator 530 in the computer device 500 can be one or more. Figure 5 Take one as an example.

[0101] In one embodiment of the present application, the processor 520 in the computer device 500 will follow the following steps: Figure 1 In the above steps, one or more instructions corresponding to the process of the application are loaded into the memory 510, and the processor 520 runs the application stored in the memory 510, thereby achieving the following Figure 1 The method described.

[0102] The memory 510 may include a random access memory (RAM) or a non-volatile memory, such as at least one disk storage. The memory 510 stores an operating system and operating instructions, executable modules or data structures, or a subset thereof, or an extended set thereof, wherein the operating instructions may include various operating instructions for implementing various operations. The operating system may include various system programs for implementing various basic services and processing hardware-based tasks.

[0103] The processor 520 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0104] The communicator 530 is used to realize the communication connection between the database access device and other devices (such as a client, a read-write library, and a read-only library). The communicator 530 may include one or more modules of different communication modes, for example, a CAN communication module connected to a CAN bus communication. The communication connection may be one or more wired / wireless communication modes and combinations thereof. The communication modes include: any one or more of the Internet, CAN, intranet, wide area network (WAN), local area network (LAN), wireless network, digital subscriber line (DSL) network, frame relay network, asynchronous transfer mode (ATM) network, virtual private network (VPN) and / or any other suitable communication network. For example: any one or more of WIFI, Bluetooth, NFC, GPRS, GSM, and Ethernet and a variety of combinations.

[0105] In some specific applications, the various components of the computer device 500 are coupled together through a bus system, wherein the bus system may include a power bus, a control bus, and a status signal bus in addition to a data bus. However, for the sake of clarity, Figure 5 In the text, all kinds of buses are called bus systems.

[0106] In one embodiment of the present application, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the following Figure 1 The method described.

[0107] For example, the computer-readable storage medium stores a model program, an inversion method program, related data, and the like.

[0108] The computer-readable storage medium, as can be understood by ordinary technicians in this field, can be implemented by hardware related to the computer program. The aforementioned computer program can be stored in a computer-readable storage medium. When the program is executed, it executes the embodiments including the aforementioned system and the functions of each unit; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0109] In summary, the present application provides a floor positioning method, device and equipment based on Bluetooth data coupling with air pressure data, including: before the floor positioning is turned on, the Bluetooth signal strength values ​​of different floors in the target indoor positioning scene are collected to form corresponding candidate fingerprints, and a Bluetooth fingerprint library is generated; during the floor positioning process, the Bluetooth signal strength value of the floor to be located is collected in real time to obtain the Bluetooth fingerprint to be matched; the Bluetooth fingerprint to be matched is matched with the candidate fingerprint in the Bluetooth fingerprint library, and the floor corresponding to the best match is selected as the preliminary selected floor; based on the preliminary selected floor and combined with the air pressure data, the final selected floor is obtained.

[0110] The present application performs mean filtering and Gaussian filtering on the Bluetooth signal strength data sequence, thereby weakening the impact of observation gross errors caused by abnormal Bluetooth devices, reducing the noise in Bluetooth observation data, and improving the robustness of the results; the relationship between Bluetooth signal strength and distance is inversely calculated by modeling, and the K nearest neighbor algorithm with adaptive selection of k values ​​is used to match the terminal with the k devices closest to each floor, thereby weakening the floor jumping phenomenon often caused in floor positioning and improving the accuracy and continuity of floor positioning results; by coupling the data of the air pressure collection device, a credible factor is introduced, and the experimental results under various situations are comprehensively considered to improve the robustness of the algorithm; the present application is not only applicable to mobile terminals with built-in air pressure collection devices, but also to mobile terminals that do not have air pressure collection devices inside, and is more universal than traditional air pressure floor positioning.

[0111] The present invention effectively overcomes various shortcomings of the prior art and has high industrial utilization value.

[0112] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. A floor positioning method based on Bluetooth data coupling with air pressure data, characterized in that: include: Before floor positioning is turned on, the Bluetooth signal strength values ​​of different floors in the target indoor positioning scene are collected to form corresponding candidate fingerprints, and a Bluetooth fingerprint library is generated; In the process of floor positioning, the Bluetooth signal strength value of the floor to be positioned is collected in real time to obtain a Bluetooth fingerprint to be matched; the Bluetooth fingerprint to be matched is matched with the candidate fingerprints in the Bluetooth fingerprint library, and the floor corresponding to the best matching degree is selected as the initially selected floor; Based on the initially selected floor and in combination with the air pressure data, a final selected floor is obtained, including the following steps: 3.1) Identify whether the mobile terminal has a built-in air pressure collection device. If there is no air pressure collection device, output i as the final selected floor; if there is an air pressure collection device, record the current time T1, the current air pressure value P1 and the initially selected floor i; 3.2) The time for identifying the floor again is T2, and the air pressure value P2 at this time is recorded. The elevation change Δh in the time period from T1 to T2 is obtained by air pressure difference. The elevation change Δh is divided by the average height h of each floor to obtain the floor change number ΔF. The positioning floor obtained by air pressure difference at this time is I1; and the corresponding positioning floor obtained by Bluetooth real-time positioning is I2; 3.3) When I1=I2, output I1 as the final selected floor; 3.4) When I1≠I2, a specific analysis and judgment is performed based on the time difference between T2 and T1 and the k value corresponding to T2. The k value is adaptively selected based on the K nearest neighbor algorithm by the number of Bluetooth nodes corresponding to the floor that receives the least number of Bluetooth nodes. The judgment process includes: 3.4.1) When T2-T1≥20min and k≥3, output I2 as the final selected floor; 3.4.2) When T2-T1<20min and k<3, output I1 as the final selected floor; 3.4.3) When T2-T1≥20min and 0<k<3 or T2-T1<20min and k≥3, set the trust factor c f and the preset threshold t g For analysis: When c f ≥t g Output I2 as the final selected floor; when c f <t g Output I1 as the final selected floor; 3.4.4) When k=0, output I1 as the final selected floor; The trust factor c f The expression is: Among them, n f represents the number of Bluetooth nodes identified on floor f; ρ f represents the Bluetooth distribution density on floor f; N represents the number of Bluetooth nodes that can be received at time T2.

2. A floor positioning method based on Bluetooth data coupling with air pressure data according to claim 1, characterized in that: The collecting of Bluetooth signal strength values ​​of different floors in the target indoor positioning scene to form corresponding candidate fingerprints and generating a Bluetooth fingerprint library includes the following steps: 1.1) Using a mobile terminal to collect Bluetooth signal strength values ​​at different distances from a Bluetooth node for the same duration, and obtaining the average Bluetooth signal strength at different distances; 1.2) Combining the Bluetooth signal strength mean and the corresponding distance between Bluetooth nodes, a simplified logarithmic distance loss model is established: RSSI(d) = A-10n lg(d); RSSI(d) represents the Bluetooth signal strength value received when the distance between the mobile terminal and the Bluetooth node is d; A represents the Bluetooth signal strength value received when the distance between the mobile terminal and the Bluetooth node is 1m; n represents the path loss factor, which changes with the changes in the surrounding environment; d represents the distance between the mobile terminal and the Bluetooth node; 1.3) Use the supervised learning optimization algorithm to fit the parameters A and n, and invert the ranging formula to calculate the distance between the Bluetooth node and the mobile terminal; 1.4) Deploy a Bluetooth node network and store the MAC addresses of all Bluetooth nodes and their corresponding floor information in the Bluetooth fingerprint library.

3. A floor positioning method based on Bluetooth data coupling with air pressure data according to claim 2, characterized in that: The real-time collection of the Bluetooth signal strength value of the floor to be located to obtain the Bluetooth fingerprint to be matched; matching the Bluetooth fingerprint to be matched with the candidate fingerprints in the Bluetooth fingerprint library, and selecting the floor corresponding to the best matching degree as the initially selected floor, includes the following steps: 2.1) Use the mobile terminal to collect the Bluetooth signal strength value of the floor to be located in real time, and calculate the distances d1, d2, d3, ... d between the m Bluetooth nodes that can be received and the mobile terminal in real time according to the ranging formula m ; 2.2) Arrange the m distance values ​​obtained in descending order and count the number of Bluetooth nodes on each floor that can be received; 2.3) Based on the K-nearest neighbor algorithm, the k value is adaptively selected according to the number of Bluetooth nodes corresponding to the floor with the least number of Bluetooth nodes received; 2.4) Adaptively match the MAC addresses of the Bluetooth nodes corresponding to the first k distances of each floor with the Bluetooth fingerprint library, and select the floor i with the smallest average distance as the initial selected floor.

4. The floor positioning method based on Bluetooth data coupling with air pressure data according to claim 1 is characterized in that: The expression of the positioning floor I1 obtained by the air pressure difference is: I1=i±ΔF; Among them, "±" is related to the increase or decrease of air pressure, "-" indicates an increase in air pressure, and "+" indicates a decrease in air pressure.

5. A floor positioning device based on Bluetooth data coupled with air pressure data, characterized in that: include: The Bluetooth fingerprint library generation module is used to collect the Bluetooth signal strength values ​​of different floors in the target indoor positioning scene before the floor positioning is turned on to form the corresponding candidate fingerprints and generate the Bluetooth fingerprint library; The real-time positioning module is used to collect the Bluetooth signal strength value of the floor to be located in real time during the floor positioning process to obtain the Bluetooth fingerprint to be matched; match the Bluetooth fingerprint to be matched with the candidate fingerprints in the Bluetooth fingerprint library, and select the floor corresponding to the best matching degree as the initially selected floor; Based on the initially selected floor and in combination with the air pressure data, a final selected floor is obtained; comprising the following steps: 3.1) Identify whether the mobile terminal has a built-in air pressure collection device. If there is no air pressure collection device, output i as the final selected floor; if there is an air pressure collection device, record the current time T1, the current air pressure value P1 and the initially selected floor i; 3.2) The time for identifying the floor again is T2, and the air pressure value P2 at this time is recorded. The elevation change Δh in the time period from T1 to T2 is obtained by air pressure difference. The elevation change Δh is divided by the average height h of each floor to obtain the floor change number ΔF. The positioning floor obtained by air pressure difference at this time is I1; and the corresponding positioning floor obtained by Bluetooth real-time positioning is I2; 3.3) When I1=I2, output I1 as the final selected floor; 3.4) When I1≠I2, a specific analysis and judgment is performed based on the time difference between T2 and T1 and the k value corresponding to T2. The k value is adaptively selected based on the K nearest neighbor algorithm by the number of Bluetooth nodes corresponding to the floor that receives the least number of Bluetooth nodes. The judgment process includes: 3.4.1) When T2-T1≥20min and k≥3, output I2 as the final selected floor; 3.4.2) When T2-T1<20min and k<3, output I1 as the final selected floor; 3.4.3) When T2-T1≥20min and 0<k<3 or T2-T1<20min and k≥3, set the trust factor c f and the preset threshold t g For analysis: When c f ≥t g Output I2 as the final selected floor; when c f <t g Output I1 as the final selected floor; 3.4.4) When k=0, output I1 as the final selected floor; The trust factor c f The expression is: Among them, n f represents the number of Bluetooth nodes identified on floor f; ρ f represents the Bluetooth distribution density on floor f; N represents the number of Bluetooth nodes that can be received at time T2.

6. A computer device, characterized in that: The device comprises: a memory, a processor and a communicator; The memory is used to store computer programs; the processor is used to execute the computer programs stored in the memory, so that the device performs the method according to any one of claims 1 to 4; and the communicator is used to communicate with an external device.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method described in any one of claims 1 to 4 is implemented.

Images