An indoor positioning method based on RSSI fingerprint

Abstract

The present invention relates to the field of wireless positioning technology, and specifically to an indoor positioning method based on RSSI fingerprint, comprising: S1: when it is detected that a device to be positioned generates a positioning signal, the signal reception strength of each positioning gateway is obtained respectively; S2: a global a posteriori probability of each fingerprint point is generated according to the signal reception strength and the a priori probability; S3: a positioning result is output according to the global a posteriori probability and the position coordinates of the fingerprint point, and a new a priori probability corresponding to each fingerprint point is generated according to the positioning result and the global a posteriori probability, and then S1 is returned. The beneficial effect of the present invention is that by introducing the positioning result in the continuous positioning process, the next a priori probability for the same device to be positioned is generated, and the fusion of historical data in the continuous positioning process is realized, so that the last positioning is associated with the current positioning, the coordinate jump phenomenon caused by the independent positioning process in the prior art is reduced, and the continuity of the positioning trajectory and the stability of the positioning are improved.

Description

Technical Field

[0001] The present invention relates to the field of wireless positioning technology, and in particular to an indoor positioning method based on RSSI fingerprint. Background Art

[0002] A wireless positioning system is a system that measures the characteristic parameters of received radio waves in a wireless mobile communication network, uses the measured wireless signal data, and adopts a specific algorithm to estimate the geographical location of the mobile terminal, and provides the prepared terminal location information and services. Common wireless positioning technologies based on field strength measurement include the signal propagation model method and the fingerprint matching method. The fingerprint matching method refers to the technology of pre-setting fingerprint points in a specific positioning scenario, collecting the field strength vector at each fingerprint point as the basis for positioning, and matching the device to be positioned in the actual positioning through a comparison algorithm, thereby achieving the positioning effect.

[0003] In the prior art, there are wireless positioning technologies based on comparison algorithms, such as Bayesian algorithms. In this type of technology, the positioning of the device to be positioned is usually regarded as an event, and the fingerprint points collected before the positioning is started are processed as prior probabilities to obtain the posterior probability corresponding to the current signal reception strength, thereby effectively determining the current position of the device to be positioned.

[0004] However, in the actual implementation process, the inventors found that the wireless positioning technology based on the Bayesian algorithm in the prior art often relies on a constant fingerprint library for positioning, that is, in the continuous positioning process for the same device to be positioned, two adjacent positioning behaviors are essentially isolated events. This leads to the situation that when the wireless environment is complex and the signal reception strength fluctuates, the results of the two positioning outputs may have a large coordinate jump, which makes the positioning process unstable and the accuracy deteriorates. Summary of the invention

[0005] In view of the above problems existing in the prior art, an indoor positioning method based on RSSI fingerprint is now provided.

[0006] The specific technical solutions are as follows:

[0007] An indoor positioning method based on RSSI fingerprint, wherein a plurality of positioning gateways are pre-set in a positioning area, and a plurality of fingerprint points are set in the positioning area;

[0008] Then the positioning method includes:

[0009] Step S1: when the positioning gateway detects that a device to be positioned generates a positioning signal, respectively obtaining the signal receiving strength of each positioning gateway corresponding to the positioning signal;

[0010] Step S2: Generate a global a posteriori probability for each fingerprint point according to the signal reception strength and the pre-generated a priori probability;

[0011] Step S3: Generate and output a positioning result according to the global posterior probability and the position coordinates of the fingerprint point, and generate a new prior probability corresponding to each fingerprint point according to the positioning result and the global posterior probability, and then return to step S1.

[0012] Preferably, before the positioning method, a priori probability generation process is also included, and the priori probability generation process is used to generate the pre-generated priori probability;

[0013] The prior probability includes a single point prior probability and an overall prior probability;

[0014] Then the prior probability generation process includes:

[0015] Step S01: Generate the positioning signal at each fingerprint point in turn, and obtain the signal reception strength corresponding to each fingerprint point on each positioning gateway respectively;

[0016] Step S02: Generate the single-point prior probability and the overall prior probability respectively according to the plurality of signal reception strengths.

[0017] Preferably, in step S02, the method for generating the single point prior probability is:

[0018] Among them, P i (RSSI = a | F m ) is the single point prior probability, SUM(RSSI=a|F m ) is the total number of times the i-th positioning gateway generates the signal receiving strength a when the positioning signal is generated at the m-th fingerprint point, SUM(RSSI=any|F m ) is the number of signal reception strengths generated by the ith positioning gateway when the positioning signal is generated at the mth fingerprint point.

[0019] Preferably, in step S02, the method for generating the overall prior probability is:

[0020] Among them, P i (RSSI=a) is the overall prior probability, SUM(RSSI=a) is the total number of times the i-th positioning gateway generates the signal reception strength a, and SUM(RSSI=any) is the number of the signal reception strengths generated by the i-th positioning gateway.

[0021] Preferably, step S2 comprises:

[0022] Step S21: generating a gateway posterior probability of each fingerprint point in each positioning gateway according to the signal reception strength and the prior probability corresponding to each fingerprint point;

[0023] Step S22: Generate the global a posteriori probability corresponding to each fingerprint point according to the plurality of gateway a posteriori probabilities.

[0024] Preferably, the prior probability also includes a positioning prior probability;

[0025] Then in step S21, the method for generating the gateway posterior probability includes:

[0026] Among them, P i (F m RSSI = a) is the gateway posterior probability corresponding to the mth fingerprint point in the i-th positioning gateway, P i (RSSI = a | F m ) is the single point prior probability, P t (F n ) is the positioning prior probability, P i (RSSI=a) is the overall prior probability;

[0027] When the positioning gateway receives the positioning signal generated by the device to be positioned for the first time, the positioning prior probability is Wherein, n is the total number of fingerprint points.

[0028] Preferably, in step S22, the method for generating the global posterior probability includes:

[0029] Acquire the signal reception strengths of the plurality of positioning gateways, sort the positioning gateways from high to low according to the signal reception strengths, and sequentially select z positioning gateways with the largest signal reception strengths as a positioning gateway group;

[0030] Then the global posterior probability corresponding to the fingerprint point Where P(F m ) is the global posterior probability corresponding to the mth fingerprint point, P l (F m |RSSI=a) is the gateway posterior probability corresponding to the mth fingerprint point in the lth positioning gateway in the positioning gateway group, l∈(1, 2, ..., z), and z is the total number of positioning gateways in the positioning gateway group.

[0031] Preferably, the step S3 comprises:

[0032] Step S31: obtaining the global a posteriori probability of each fingerprint point, and sorting the fingerprint points from high to low according to the global a posteriori probability, so as to sequentially select a plurality of fingerprint points with the largest global a posteriori probability as a positioning fingerprint point group;

[0033] Step S32: in the positioning fingerprint point group, generating and outputting the positioning result according to the global posterior probability and the position coordinates of each fingerprint point;

[0034] Step S33: Generate a new prior probability corresponding to each fingerprint point according to the positioning result and the global posterior probability, and then return to step S1.

[0035] Preferably, in step S32, the positioning result The generation methods include:

[0036] in, is the horizontal coordinate of the positioning result, q is the number of fingerprint points in the positioning fingerprint point group, x n is the horizontal coordinate of the position coordinate of the nth fingerprint point in the positioning fingerprint point group, P(F n ) is the global posterior probability of the nth fingerprint point in the positioning fingerprint point group, n∈(1, 2, ..., q);

[0037] in, is the horizontal coordinate of the positioning result, q is the number of fingerprint points in the positioning fingerprint point group, and y n is the ordinate of the position coordinates of the nth fingerprint point in the positioning fingerprint point group, P(F n ) is the global a posteriori probability of the nth fingerprint point in the positioning fingerprint point group, n∈(1, 2, ..., q).

[0038] Preferably, in step S33, the method for generating the new prior probability includes:

[0039] Among them, P t (F m ) is the prior probability corresponding to the mth fingerprint point, P(F g ) is the prior probability of the g-th fingerprint point whose distance from the positioning result is in the first distance interval, g∈(1, 2, ..., e), e is the total number of fingerprint points whose distance from the positioning result is in the first distance interval, P(F h) is the prior probability of the hth fingerprint point whose distance from the positioning result is in the second distance interval, h∈(1, 2, ..., f), and f is the total number of fingerprint points whose distance from the positioning result is in the second distance interval.

[0040] The above technical solution has the following advantages or beneficial effects: by introducing positioning results in the continuous positioning process, generating the next prior probability for the same device to be positioned, the fusion of historical data in the continuous positioning process is realized, so that the previous positioning is associated with the current positioning, reducing the coordinate jump phenomenon caused by the independent positioning process in the prior art, and improving the continuity of the positioning trajectory and the stability of positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The embodiments of the present invention will be described more fully with reference to the attached drawings, which are provided for illustration and description only and are not intended to limit the scope of the present invention.

[0042] Figure 1 A schematic diagram of a positioning area according to an embodiment of the present invention;

[0043] Figure 2 This is a schematic diagram of a positioning method in an embodiment of the present invention;

[0044] Figure 3 Schematic diagram of a priori probability generation process in an embodiment of the present invention;

[0045] Figure 4 This is a schematic diagram of sub-steps of step S2 in an embodiment of the present invention;

[0046] Figure 5 Schematic diagram of sub-steps of step S3 in an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0049] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, but they are not intended to limit the present invention.

[0050] The present invention comprises:

[0051] An indoor positioning method based on RSSI fingerprint, such as Figure 1 As shown, a plurality of positioning gateways A1 are pre-set in a positioning area, and a plurality of fingerprint points A2 are set in the positioning area;

[0052] If Figure 2 As shown, the positioning method includes:

[0053] Step S1: when the positioning gateway A1 detects that a device to be positioned generates a positioning signal, the signal receiving strength corresponding to the positioning signal of each positioning gateway A1 is obtained respectively;

[0054] Step S2: Generate the global posterior probability of each fingerprint point A2 according to the signal reception strength and the pre-generated prior probability;

[0055] Step S3: Generate and output a positioning result according to the global posterior probability and the position coordinates of the fingerprint point A2, and generate new prior probabilities corresponding to each fingerprint point according to the positioning result and the global posterior probability, and then return to step S1.

[0056] Specifically, in order to solve the problem that multiple positioning based on fingerprint points in the prior art are independent of each other, this embodiment introduces the positioning result into the next positioning of the same device to be positioned after the positioning result is generated, and uses it as a parameter in the prior probability of the next positioning. This avoids the problem of positioning coordinate jumps and poor trajectory continuity caused by wireless signal fluctuations in the prior art.

[0057] During the implementation process, the positioning gateway A1 is a receiving device based on the field strength positioning technology, which receives and identifies the positioning signal sent by the device to be positioned, and then locates the device to be positioned according to the signal receiving strength (RSSI, Received Signal Strength lndication) of multiple positioning gateways A1 and the fingerprint points collected in advance. The device to be positioned is a device with wireless communication function, such as a positioning tag (Tag), a mobile phone, a tablet computer, etc., which can generate a positioning signal corresponding to the positioning gateway A1. The positioning signal can be a wireless signal based on the existing technology, such as a Bluetooth signal, a WLAN signal, a ZigBee signal, etc. The fingerprint point A2 refers to a point set in the positioning area for positioning. Before starting positioning, a calibration device identical to the device to be positioned is used on each fingerprint point A2 to generate a calibration signal identical to the positioning signal, so that a signal receiving strength corresponding to the calibration signal is generated on each positioning gateway A1. By recording the signal receiving strength of the calibration signal generated on each fingerprint point A2 on each positioning gateway A1, a signal receiving set RSSI corresponding to each fingerprint point is generated. j =[RSSI1, RSSI2, ...RSSI n](Among them, RSSI j is the signal receiving set corresponding to the jth fingerprint point, RSSI n is the signal receiving strength obtained by the nth positioning gateway) to form a fingerprint database for matching the signal receiving strength generated by the positioning signal to achieve the positioning process.

[0058] As an optional implementation, Figure 1 As shown, a positioning route is set in the positioning area, and the positioning route is a route track composed of multiple locations that the device to be positioned may reach during actual use. Fingerprint points A2 are evenly distributed on the positioning route.

[0059] As an optional implementation, in the process of generating the fingerprint database, the calibration device continuously generates a calibration signal and passes through each fingerprint point A2 from the first end of a certain positioning route to the second end of the positioning route at a specific speed v. The acquisition time of each fingerprint point A2 can be obtained based on the time T1 when the calibration device passes through the first end, the time T2 when it passes through the second end, and the length s of the positioning route, which specifically includes:

[0060] First, obtain the acquisition time of each fingerprint point A2 in is the acquisition time of each fingerprint point A2, T1 is the time when the calibration device passes through the first end, T2 is the time when the calibration device passes through the second end, and s is the length of the positioning route;

[0061] Then in this positioning route, the collection time of the jth fingerprint point is in is the acquisition time of the jth fingerprint point, T1 is the time when the calibration device passes through the first end, T2 is the time when the calibration device passes through the second end, is the collection time of each fingerprint point A2, and j is the serial number of the fingerprint point in the positioning route. Since the fingerprint points A2 are evenly distributed on the positioning route, the specific collection time of each fingerprint point A2 can be located in the continuous collection process according to the above method, and then the collection log of the positioning gateway A1 can be read by the collection time to quickly obtain the received signal strength generated by each fingerprint point A2, thereby shortening the time required to generate the fingerprint database.

[0062] In a preferred embodiment, before the positioning method, a priori probability generation process is also included, and the priori probability generation process is used to generate a pre-generated priori probability;

[0063] Prior probability includes single-point prior probability and overall prior probability;

[0064] If Figure 3 As shown in Figure 2, the prior probability generation process includes:

[0065] Step S01: Generate a positioning signal at each fingerprint point A2 in sequence, and obtain the signal reception strength corresponding to each fingerprint point A2 on each positioning gateway A1 respectively;

[0066] Step S02: Generate a single-point prior probability and an overall prior probability respectively according to multiple signal reception strengths.

[0067] Specifically, in order to achieve a better positioning effect, in this embodiment, a single-point prior probability of each positioning gateway A1 obtaining a specific signal reception strength at each fingerprint point A2 is generated according to the signal reception strength, and an overall prior probability of each positioning gateway obtaining a specific signal reception strength in the entire positioning area is generated, thereby achieving a better positioning effect.

[0068] In a preferred embodiment, in step SO2, the method for generating the single point prior probability is:

[0069] Among them, P i (RSSI = a | F m ) is the single point prior probability, SUM(RSSI=a|F m ) is the total number of times the i-th positioning gateway generates a signal receiving strength a when generating a positioning signal at the m-th fingerprint point, SUM(RSSI=any|F m ) is the number of signal reception strengths generated by the i-th positioning gateway when generating a positioning signal at the m-th fingerprint point.

[0070] In a preferred embodiment, in step S02, the method for generating the overall prior probability is:

[0071] Among them, P i (RSSI=a) is the overall prior probability, SUM(RSSI=a) is the total number of times the i-th positioning gateway generates a signal reception strength of a, and SUM(RSSI=any) is the number of signal reception strengths generated by the i-th positioning gateway.

[0072] During the implementation process, the fingerprint database stores the signal strength set of all fingerprint points and positioning gateways:

[0073] Among them, RSSI is the signal strength set, is the signal reception strength of the jth fingerprint point received by the ith positioning gateway. The single point prior probability and the overall prior probability can be generated respectively according to the signal strength set.

[0074] In a preferred embodiment, Figure 4 As shown, step S2 includes:

[0075] Step S21: Generate a gateway posterior probability of each fingerprint point in each positioning gateway according to the signal reception strength and the prior probability corresponding to each fingerprint point;

[0076] Step S22: Generate a global a posteriori probability corresponding to each fingerprint point according to the multiple gateway a posteriori probabilities.

[0077] Specifically, in order to achieve a better positioning effect, in this embodiment, the gateway posterior probability of each fingerprint point generated by matching the signal reception strength is generated in each positioning gateway respectively, and then the global posterior probability of each fingerprint point is comprehensively obtained, and then the fingerprint points with higher probability are screened out to obtain a more accurate positioning result.

[0078] In a preferred embodiment, the prior probability also includes a positioning prior probability;

[0079] Then in step S21, the method for generating the gateway posterior probability includes:

[0080] Among them, P i (Fm|RSSI=a) is the gateway posterior probability corresponding to the mth fingerprint point in the i-th positioning gateway, P i (RSSI = a | F m ) is the single point prior probability, P t (F m ) is the positioning prior probability, P i (RSSI = a) is the overall prior probability;

[0081] When the positioning gateway A1 receives the positioning signal generated by the device to be positioned for the first time, the positioning prior probability is Where n is the total number of fingerprint points.

[0082] Specifically, in order to address the problem in the prior art that the current positioning behavior cannot be adjusted according to historical positioning results, this embodiment introduces the parameter of positioning prior probability in the process of generating gateway posterior probability, thereby achieving adjustment of the posterior probability in each positioning process, thereby achieving better positioning continuity for the same device to be located in the continuous positioning process.

[0083] In a preferred embodiment, in step S22, the method for generating the global posterior probability includes:

[0084] Acquire signal reception strengths of multiple positioning gateways, sort the positioning gateways from high to low according to the signal reception strengths, and select z positioning gateways with the largest signal reception strengths in turn as a positioning gateway group;

[0085] Then the global posterior probability corresponding to the fingerprint point is Where P(F m ) is the global posterior probability corresponding to the mth fingerprint point, P l (F m |RSSI=a) is the gateway posterior probability corresponding to the mth fingerprint point in the lth positioning gateway in the positioning gateway group, l∈(1, 2, ..., z), and z is the total number of positioning gateways in the positioning gateway group.

[0086] Specifically, in this embodiment, the positioning gateways are grouped by signal reception strength, thereby filtering out some positioning gateways that are too far from the device to be positioned and have low signal reception strength, thereby shortening the processing time of the global posterior probability of each fingerprint point and improving positioning efficiency.

[0087] In a preferred embodiment, Figure 5 As shown, step S3 includes:

[0088] Step S31: obtaining the global posterior probability of each fingerprint point, and sorting the fingerprint points from high to low according to the global posterior probability, so as to sequentially select multiple fingerprint points with the largest global posterior probability as a positioning fingerprint point group;

[0089] Step S32: in the positioning fingerprint point group, generate and output the positioning result according to the global posterior probability and the position coordinates of each fingerprint point;

[0090] Step S33: Generate new prior probabilities corresponding to each fingerprint point according to the positioning results and the global posterior probability, and then return to step S1.

[0091] Specifically, in order to address the problem in the prior art that multiple positioning behaviors are independent of each other and the next positioning cannot be adjusted according to historical positioning results during the continuous positioning process, in this embodiment, by introducing the positioning results to generate the prior probability used for the next positioning, better continuity is achieved during the continuous positioning process for a single device to be located.

[0092] During the implementation process, the adjustment of the prior probability depends on the positioning prior probability, which is achieved by obtaining the positioning result and predicting the fingerprint points around the positioning result. That is, the device to be positioned should only move to fingerprint points within a certain range near the positioning result in a single positioning cycle, thereby adjusting the positioning prior probability of this part of the fingerprint points to improve the continuity of the positioning trajectory in the next positioning process.

[0093] In a preferred embodiment, in step S32, the positioning result The generation methods include:

[0094] in, is the horizontal coordinate of the positioning result, q is the number of fingerprint points in the positioning fingerprint point group, x n is the horizontal coordinate of the position coordinate of the nth fingerprint point in the fingerprint point group, P(F n ) is the global posterior probability of locating the nth fingerprint point in the fingerprint point group, n∈(1, 2, ..., q);

[0095] in, is the horizontal coordinate of the positioning result, q is the number of fingerprint points in the positioning fingerprint point group, y n is the vertical coordinate of the position coordinate of the nth fingerprint point in the fingerprint point group, P(F n ) is the global posterior probability of locating the nth fingerprint point in the fingerprint point group, n∈(1, 2, ..., q).

[0096] Specifically, in order to achieve a better positioning effect, in this embodiment, the global posterior probability is regarded as the weight of the screened fingerprint points, and then the actual positioning coordinates are obtained through weighted calculation, thereby achieving a better judgment on the actual position of the device to be positioned and improving the accuracy of positioning.

[0097] In a preferred embodiment, in step S33, the method for generating a new prior probability includes:

[0098] Among them, P t (F m ) is the prior probability corresponding to the mth fingerprint point, P(F g ) is the prior probability of the gth fingerprint point whose distance from the positioning result is in the first distance interval, g∈(1, 2, ..., e), e is the total number of fingerprint points whose distance from the positioning result is in the first distance interval, P(F h ) is the prior probability of the hth fingerprint point whose distance from the positioning result is in the second distance interval, h∈(1, 2, ..., f), and f is the total number of fingerprint points whose distance from the positioning result is in the second distance interval.

[0099] Specifically, in order to address the problem in the prior art that the two positioning behaviors are independent of each other and the poor positioning continuity easily leads to coordinate jumps, in this embodiment, by estimating the movement trajectory of the device to be positioned in the positioning area, the movement of the device to be positioned in the positioning area is regarded as a condition that affects the next positioning result, thereby adjusting the positioning prior probability of the fingerprint points around the positioning result, thereby realizing the introduction of the previous positioning result in the next positioning process, and improving the continuity of the positioning trajectory.

[0100] During the implementation process, the average moving speed V1 and the maximum moving speed V2 of the device to be located in the positioning area are collected in advance through experiments during the positioning process. Then, according to the positioning period, the range that the device to be located may reach during the two positioning processes can be obtained, including the range d1 that the device to be located can reach based on the average moving speed V1, and the range d2 that the device to be located can reach based on the maximum moving speed V2. The range of the first distance interval is [0, d1], and the range of the second distance interval is (d1, d2]. Based on the first distance interval and the second distance interval, and the probability that the device to be located may be located in the first distance interval or the second distance interval in the next positioning, a new positioning prior probability can be generated, thereby achieving the effect of adjusting the next positioning according to the current positioning result.

[0101] The beneficial effects of the present invention are as follows: by introducing positioning results in a continuous positioning process, generating the next prior probability for the same device to be positioned, the fusion of historical data in the continuous positioning process is achieved, and the previous positioning is associated with the current positioning, thereby reducing the coordinate jump phenomenon caused by the independent positioning process in the prior art, and improving the continuity of the positioning trajectory and the stability of positioning.

[0102] The above are only preferred embodiments of the present invention, and are not intended to limit the implementation methods and protection scope of the present invention. Those skilled in the art should be aware that all solutions obtained by equivalent substitutions and obvious changes made using the description and illustrations of the present invention should be included in the protection scope of the present invention.

Claims

1. An indoor positioning method based on RSSI fingerprint, characterized in that: A plurality of positioning gateways are pre-set in a positioning area, and a plurality of fingerprint points are set in the positioning area; Then the positioning method includes: Step S1: when the positioning gateway detects that a device to be positioned generates a positioning signal, respectively obtaining the signal receiving strength of each positioning gateway corresponding to the positioning signal; Step S2: Generate a global a posteriori probability for each fingerprint point according to the signal reception strength and the pre-generated a priori probability; Step S3: generating and outputting a positioning result according to the global posterior probability and the position coordinates of the fingerprint point, and generating new a priori probabilities corresponding to each fingerprint point according to the positioning result and the global posterior probability, and then returning to step S1; The step S3 comprises: Step S31: obtaining the global a posteriori probability of each fingerprint point, and sorting the fingerprint points from high to low according to the global a posteriori probability, so as to sequentially select a plurality of fingerprint points with the largest global a posteriori probability as a positioning fingerprint point group; Step S32: in the positioning fingerprint point group, generating and outputting the positioning result according to the global posterior probability and the position coordinates of each fingerprint point; Step S33: Generate a new prior probability corresponding to each fingerprint point according to the positioning result and the global posterior probability, and then return to step S1; In step S33, the method for generating the new prior probability includes: Among them, P t (F m ) is the prior probability corresponding to the mth fingerprint point, P(F g ) is the prior probability of the g-th fingerprint point whose distance from the positioning result is in the first distance interval, g∈(1, 2, ..., e), e is the total number of fingerprint points whose distance from the positioning result is in the first distance interval, P(F h ) is the prior probability of the hth fingerprint point whose distance from the positioning result is in the second distance interval, h∈(1, 2, ..., f), and f is the total number of fingerprint points whose distance from the positioning result is in the second distance interval.

2. The indoor positioning method according to claim 1, characterized in that: Prior to the positioning method, a priori probability generation process is also included, wherein the priori probability generation process is used to generate the pre-generated priori probability; The prior probability includes a single point prior probability and an overall prior probability; Then the prior probability generation process includes: Step S01: Generate the positioning signal at each fingerprint point in turn, and obtain the signal reception strength corresponding to each fingerprint point on each positioning gateway respectively; Step S02: Generate the single-point prior probability and the overall prior probability respectively according to the plurality of signal reception strengths.

3. The indoor positioning method according to claim 2, characterized in that: In step S02, the method for generating the single point prior probability is: Among them, P i (RSSI = a | F m ) is the single point prior probability, SUM(RSSI=a|F m ) is the total number of times the i-th positioning gateway generates the signal receiving strength a when the positioning signal is generated at the m-th fingerprint point, SUM(RSSI=any|F m ) is the number of signal reception strengths generated by the ith positioning gateway when the positioning signal is generated at the mth fingerprint point.

4. The indoor positioning method according to claim 2, characterized in that: In step S02, the method for generating the overall prior probability is: Among them, P i (RSSI=a) is the overall prior probability, SUM(RSSI=a) is the total number of times the i-th positioning gateway generates the signal reception strength a, and SUM(RSSI=any) is the number of the signal reception strengths generated by the i-th positioning gateway.

5. The indoor positioning method according to claim 2, characterized in that: The step S2 comprises: Step S21: generating a gateway posterior probability of each fingerprint point in each positioning gateway according to the signal reception strength and the prior probability corresponding to each fingerprint point; Step S22: Generate the global a posteriori probability corresponding to each fingerprint point according to the plurality of gateway a posteriori probabilities.

6. The indoor positioning method according to claim 5, characterized in that: The prior probability also includes a positioning prior probability; Then in step S21, the method for generating the gateway posterior probability includes: Among them, P i (F m RSSI = a) is the gateway posterior probability corresponding to the mth fingerprint point in the i-th positioning gateway, P i (RSSI = a | F m ) is the single point prior probability, P t (F m ) is the positioning prior probability, P i (RSSI=a) is the overall prior probability; When the positioning gateway receives the positioning signal generated by the device to be positioned for the first time, the positioning prior probability is Wherein, n is the total number of fingerprint points.

7. The indoor positioning method according to claim 5, characterized in that: In step S22, the method for generating the global posterior probability includes: Acquire the signal reception strengths of the plurality of positioning gateways, sort the positioning gateways from high to low according to the signal reception strengths, and sequentially select z positioning gateways with the largest signal reception strengths as a positioning gateway group; Then the global posterior probability corresponding to the fingerprint point Where P(F m ) is the global posterior probability corresponding to the mth fingerprint point, P l (F m |RSSI=a) is the gateway posterior probability corresponding to the mth fingerprint point in the lth positioning gateway in the positioning gateway group, l∈(1, 2, ..., z), and z is the total number of positioning gateways in the positioning gateway group.

8. The indoor positioning method according to claim 1, characterized in that: In step S32, the positioning result The generation methods include: in, is the horizontal coordinate of the positioning result, q is the number of fingerprint points in the positioning fingerprint point group, x n is the horizontal coordinate of the position coordinate of the nth fingerprint point in the positioning fingerprint point group, P(F n ) is the global posterior probability of the nth fingerprint point in the positioning fingerprint point group, n∈(1,2,...,q); in, is the ordinate of the positioning result, q is the number of fingerprint points in the positioning fingerprint point group, and y n is the ordinate of the position coordinates of the nth fingerprint point in the positioning fingerprint point group, P(F n ) is the global posterior probability of the nth fingerprint point in the positioning fingerprint point group, n∈(1,2,...,q).

Images