Indoor positioning method, device, electronic device and storage medium

Abstract

The present invention provides an indoor positioning method, device, electronic device and storage medium, wherein the method comprises: obtaining received signal strength indication (RSSI) data of a terminal to be detected, wherein the RSSI data comprises an RSSI sequence obtained by measuring the signal of the terminal to be detected by multiple small radio remote units (pRRUs), and the RSSI sequence comprises multiple RSSI values; generating an RSSI difference sequence of the terminal to be detected based on the RSSI data; matching the RSSI difference sequence of the terminal to be detected with the RSSI difference sequence of fingerprint data in a fingerprint library to determine the predicted position of the terminal to be detected, thereby improving the accuracy of indoor positioning.

Description

Technical Field

[0001] The present invention relates to the field of wireless communication technology, and in particular to an indoor positioning method, device, electronic equipment and storage medium. Background Art

[0002] With the development of mobile communication technology, a large number of communication base stations have been established around the world. Using communication base stations as wireless positioning base stations has become a new way for mobile communication networks to provide LBS services.

[0003] Based on the positioning principle, base station positioning technology can be roughly divided into three types: Cell ID-based positioning technology, measurement-based positioning technology, and location fingerprint-based positioning technology. Cell ID-based positioning technology is currently the simplest positioning technology. It determines the user's location by obtaining the Cell ID in the mobile cellular communication network. Measurement-based positioning technology primarily uses geometric methods to calculate the position of the measured object based on measurement data. It is the most important and widely used positioning technology. First, the distance between a reference point with a known location and the measured object is measured. Then, triangulation is used to calculate the position of the measured object. Specifically, mainstream measurement data includes: measuring the distance between the reference point and the measured object directly through physical movement and motion; measuring the radio wave propagation time between the reference point and the measured object; and measuring the attenuation of radio wave energy between the reference point and the measured object. Location fingerprint-based positioning technology abstracts and formalizes the specific positioning environment, describing each location within the positioning environment with specific, quantitative parameters, and integrating this information into a database. First, signals are collected at various locations and features are extracted from them as the fingerprint of that location (the most commonly used features are RSSI sequence, mean, variance and other statistical features of the RSSI sequence); then a classification algorithm is used to match the received signals with the fingerprint of each location to achieve positioning.

[0004] Current base station positioning technology uses a field strength triangulation algorithm based on downlink RSRP, which relies on the longitude and latitude or coordinates of neighboring base stations. However, indoor locations often have distributed base stations, and the antennas can be very far from the base stations. Therefore, using the base station longitude and latitude as the basis for the triangulation algorithm can result in significant errors. Furthermore, since the number of neighboring cells that can be measured indoors is small (less than three at most locations), field strength-based triangulation positioning is not possible at most locations. Using a fingerprint algorithm based on downlink RSRP relies primarily on the distinct downlink RSRP signatures of the serving cell and neighboring cells at each location. However, since the number of neighboring cells that can be measured indoors is small, and the serving cell's signal is significantly affected by human traffic, using the downlink RSRP of the serving cell and neighboring cells as fingerprints results in minimal and unstable signatures between locations, leading to large positioning errors. Summary of the Invention

[0005] The present invention provides an indoor positioning method, device, electronic device and storage medium, which are used to solve the defects of the prior art that the characteristics of multiple locations are not very different and the positioning error is large, and achieve accurate indoor positioning.

[0006] The present invention provides an indoor positioning method, comprising:

[0007] Acquire received signal strength indicator RSSI data of the terminal to be detected, wherein the RSSI data includes an RSSI sequence obtained by measuring a signal of the terminal to be detected by multiple small remote radio frequency units (pRRUs), and the RSSI sequence includes multiple RSSI values;

[0008] Generate an RSSI difference sequence of the terminal to be detected according to the RSSI data;

[0009] The RSSI difference sequence of the terminal to be detected is matched with the RSSI difference sequence of the fingerprint data in the fingerprint library to determine the predicted position of the terminal to be detected.

[0010] According to the indoor positioning method provided by the present invention, generating the RSSI difference sequence of the terminal to be detected according to the RSSI data includes:

[0011] Calculating a first weight of the pRRU according to a probability of the pRRU appearing in the measurement report;

[0012] Normalizing the RSSI values ​​in the RSSI sequence, and determining second weights of the RSSI values ​​in the RSSI sequence according to probability values ​​in a standard normal distribution table;

[0013] Generate an RSSI difference sequence of the terminal to be detected according to the first weight, the second weight and the RSSI value.

[0014] According to the indoor positioning method provided by the present invention, generating the RSSI difference sequence of the terminal to be detected according to the first weight, the second weight and the RSSI value includes:

[0015] Calculating a difference between the set of RSSI values ​​using a difference calculation formula based on a set of RSSI values ​​in the RSSI data and a first weight and a second weight corresponding to the set of RSSI values, wherein the set of RSSI values ​​includes two RSSI values;

[0016] Continue calculating the difference of the next set of RSSI values ​​in the RSSI data until all RSSI differences in the RSSI data are obtained, and generate an RSSI difference sequence of the terminal to be detected;

[0017] The difference calculation formula is as follows:

[0018] R 1-2 =W p1 *W R1 *R1-W p2 *W R2 *R2

[0019] Among them, R 1-2 represents the difference between the first RSSI value and the second RSSI value, W p1 Represents the first weight corresponding to the first RSSI value, W R1 represents the second weight corresponding to the first RSSI value, R1 represents the first RSSI value, W p2 Represents the first weight corresponding to the second RSSI value, W R2 represents the second weight corresponding to the second RSSI value, and R2 represents the second RSSI value.

[0020] According to the indoor positioning method provided by the present invention, the RSSI difference sequence of the terminal to be detected is matched with the RSSI difference sequence of fingerprint data in the fingerprint library to determine the predicted position of the terminal to be detected, including:

[0021] Calculating the cosine similarity between the RSSI difference sequence of the terminal to be detected and the RSSI difference sequence of the fingerprint data in the fingerprint library;

[0022] determining candidate fingerprint data according to the cosine similarity, and determining a third weight of the candidate fingerprint data according to the cosine similarity;

[0023] A center of gravity fitting is performed based on the coordinates corresponding to the candidate fingerprint data and the third weight to obtain a predicted position of the terminal to be detected.

[0024] According to the indoor positioning method provided by the present invention, the calculating of the cosine similarity between the RSSI difference sequence of the terminal to be detected and the RSSI difference sequence of the fingerprint data in the fingerprint library includes:

[0025] The cosine similarity between the RSSI difference sequence of the terminal to be detected and the RSSI difference sequence of the fingerprint data in the fingerprint library is calculated according to the cosine similarity formula, wherein the cosine similarity formula is as follows:

[0026]

[0027] Among them, SQRT is the square root calculation, X i is the difference sequence of the RSSI value of the terminal to be detected, Y iis the difference sequence of the ith RSSI value of the fingerprint data, and n is the number of RSSI values.

[0028] According to the indoor positioning method provided by the present invention, determining candidate fingerprint data according to the cosine similarity includes:

[0029] Determining, based on the cosine similarity, three candidate fingerprint data with the largest cosine similarity;

[0030] The performing centroid fitting according to the coordinates of the candidate fingerprint data and the third weight to obtain the predicted position of the terminal to be detected includes:

[0031] Calculating weighted coordinates according to a barycenter fitting formula, coordinates of any two candidate fingerprint data, and a third weight of the any two candidate fingerprint data;

[0032] Determining the center of gravity of the triangle formed by the weighted coordinates to obtain the predicted position of the terminal to be detected;

[0033] The center of gravity fitting formula is as follows:

[0034]

[0035]

[0036] Among them, X 12 is the weighted horizontal coordinate, X1 is the horizontal coordinate of the first candidate fingerprint data, X2 is the horizontal coordinate of the second candidate fingerprint data, and Y 12 Weighted ordinate, Y1 is the ordinate of the first candidate fingerprint data, Y2 is the ordinate of the second candidate fingerprint data, cos1 is the third weight of the first candidate fingerprint data, and cos2 is the third weight of the second candidate fingerprint data.

[0037] The indoor positioning method provided by the present invention further includes:

[0038] Building the fingerprint library;

[0039] The constructing of the fingerprint library comprises:

[0040] Acquire received signal strength indicator RSSI data of each target point collected through dialing, wherein the RSSI data of the target point includes an RSSI sequence obtained by measuring a signal of a terminal at the target point by multiple pRRUs;

[0041] Generate an RSSI difference sequence of the target point according to the RSSI data;

[0042] The fingerprint library is constructed according to the coordinates corresponding to the target point and the RSSI difference sequence of the target point.

[0043] The present invention also provides an indoor positioning device, comprising:

[0044] a signal receiving unit, configured to obtain received signal strength indication RSSI data of a terminal to be detected, wherein the RSSI data comprises an RSSI sequence obtained by measuring a signal of the terminal to be detected by multiple small remote radio frequency units (pRRUs), and the RSSI sequence comprises multiple RSSI values;

[0045] A difference sequence generating unit, configured to generate an RSSI difference sequence of the terminal to be detected based on the RSSI data;

[0046] The position determination unit is configured to match the RSSI difference sequence of the terminal to be detected with the RSSI difference sequence of the fingerprint data in the fingerprint library to determine the predicted position of the terminal to be detected.

[0047] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any of the above-described indoor positioning methods are implemented.

[0048] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which implements the steps of any of the above-mentioned indoor positioning methods when executed by a processor.

[0049] The indoor positioning method, device, electronic device and storage medium provided by the present invention generate an RSSI difference sequence of a terminal to be detected based on RSSI data, use the RSSI difference to eliminate the influence of different uplink transmission powers of different terminals, and generate an RSSI difference sequence with obvious characteristics. The predicted position of the terminal to be detected is determined by matching the RSSI difference sequence, thereby improving the accuracy of indoor positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0051] Figure 1 A schematic diagram of the flow of the indoor positioning method provided by the present invention;

[0052] Figure 2A schematic diagram of a process for matching the RSSI difference sequence of the terminal to be detected with the RSSI difference sequence of fingerprint data in a fingerprint library to determine the predicted position of the terminal to be detected provided by the present invention;

[0053] Figure 3 A schematic diagram of the process of constructing the fingerprint library provided by the present invention;

[0054] Figure 4 It is a structural diagram of the indoor positioning device provided by the present invention;

[0055] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0056] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0057] Figure 1 A flow chart of the indoor positioning method provided by an embodiment of the present invention is shown as follows: Figure 1 As shown, the following steps are included:

[0058] Step 100: Acquire received signal strength indication RSSI data of the terminal to be detected, wherein the RSSI data includes an RSSI sequence obtained by measuring the signal of the terminal to be detected by multiple small remote radio frequency units (pRRUs), and the RSSI sequence includes multiple RSSI values.

[0059] Specifically, over a period of time, multiple small remote radio units (pRRUs) measure the uplink multipath signal strength of the terminal to be detected and obtain received signal strength indication (RSSI) data. Each pRRU measures multiple RSSI values, which form the RSSI sequence corresponding to the pRRU.

[0060] Step 101: Generate an RSSI difference sequence of the terminal to be detected according to the RSSI data.

[0061] Specifically, the acquired RSSI data includes multiple RSSI values. Each set of RSSI values ​​can derive an RSSI difference. According to the RSSI differences of all RSSI values ​​measured by the terminal to be detected within a period of time, an RSSI difference sequence of the terminal to be detected is generated.

[0062] Step 102: Match the RSSI difference sequence of the terminal to be detected with the RSSI difference sequence of the fingerprint data in the fingerprint library to determine the predicted position of the terminal to be detected.

[0063] The fingerprint database includes multiple pieces of fingerprint data, each piece of fingerprint data includes the position coordinates of a target point and an RSSI difference sequence corresponding to the position coordinates.

[0064] It can be understood that the RSSI difference sequence of the terminal to be detected is matched with the RSSI difference sequence in the fingerprint library. The higher the matching degree, the closer the position coordinates of the target point in the fingerprint library are to the position coordinates of the terminal to be detected. The predicted position of the terminal to be detected is determined based on the matching degree.

[0065] For example, the cosine similarity between the RSSI difference sequence of the terminal to be detected and the RSSI difference sequence of each target point in the fingerprint library is calculated. The higher the cosine similarity, the closer the target point is to the position of the terminal to be detected. The position of the terminal to be detected is determined based on the size of the cosine similarity.

[0066] In an embodiment of the present invention, an RSSI difference sequence of a terminal to be detected is generated based on RSSI data. The RSSI difference is used to eliminate the influence of different uplink transmission powers of different terminals. The generated RSSI difference sequence has obvious characteristics. The predicted position of the terminal to be detected is determined by matching the RSSI difference sequence, thereby improving the accuracy of indoor positioning.

[0067] In one embodiment, generating the RSSI difference sequence of the terminal to be detected according to the RSSI data includes the following steps:

[0068] Calculating a first weight of the pRRU according to a probability of the pRRU appearing in the measurement report;

[0069] Normalizing the RSSI values ​​in the RSSI sequence, and determining second weights of the RSSI values ​​in the RSSI sequence according to probability values ​​in a standard normal distribution table;

[0070] Generate an RSSI difference sequence of the terminal to be detected according to the first weight, the second weight and the RSSI value.

[0071] Specifically, some pRRUs may appear sporadically in the measurement report due to being far from the terminal to be detected, being severely obscured, or experiencing malfunctions. Therefore, the first weight of each pRRU needs to be calculated based on the probability of the pRRU appearing in the measurement report. The first weight of the pRRU is also the first weight of the RSSI value corresponding to the pRRU.

[0072] The RSSI values ​​in the RSSI sequence are normalized and a second weight of the RSSI values ​​in the RSSI sequence is determined based on a probability value in a standard normal distribution table. The RSSI sequence includes multiple RSSI values, and normalizing the multiple RSSI values ​​yields a standardized RSSI value. A probability value corresponding to the standardized RSSI value is determined based on the standard normal distribution table, and the probability value is used as the second weight of the RSSI value.

[0073] The standardization process is as follows:

[0074] Calculate the average value E of the RSSI values ​​in the RSSI sequence.

[0075] The standard deviation σ of the RSSI values ​​in the RSSI sequence is calculated based on the average value.

[0076] The RSSI values ​​in the RSSI sequence are standardized according to the mean value, standard deviation, and standardization formula, where the standardization formula is as follows:

[0077]

[0078] Where |RSSI'| is the RSSI value after normalization, |RSSI| is the RSSI value before normalization, E is the mean, and σ is the standard deviation.

[0079] Then, an RSSI difference sequence of the terminal to be detected is generated according to the first weight, the second weight and the RSSI value.

[0080] Specifically, the RSSI difference sequence of the terminal to be detected is generated according to the RSSI value and the first weight and the second weight of the RSSI value.

[0081] In the embodiment of the present invention, a first weight and a second weight are introduced when generating an RSSI difference sequence. The generated RSSI difference sequence has obvious characteristics, thereby improving the accuracy of indoor positioning.

[0082] In one embodiment, generating the RSSI difference sequence of the terminal to be detected according to the first weight, the second weight, and the RSSI value comprises the following steps:

[0083] According to a group of RSSI values ​​in the RSSI data and a first weight and a second weight corresponding to the group of RSSI values, a difference calculation formula is used to calculate a difference between the group of RSSI values, wherein the group of RSSI values ​​includes two RSSI values.

[0084] The difference calculation formula is as follows:

[0085] R 1-2 =W p1 *W R1 *R1-W p2 *W R2 *R2

[0086] Among them, R 1-2 represents the difference between the first RSSI value and the second RSSI value, W p1 Represents the first weight corresponding to the first RSSI value, W R1 represents the second weight corresponding to the first RSSI value, R1 represents the first RSSI value, W p2 Represents the first weight corresponding to the second RSSI value, W R2 represents the second weight corresponding to the second RSSI value, and R2 represents the second RSSI value.

[0087] Specifically, R1 and R2 are RSSI values ​​in an RSSI sequence measured by different pRRUs.

[0088] Continue to calculate the difference of the next group of RSSI values ​​in the RSSI data until all RSSI differences in the RSSI data are obtained, and generate an RSSI difference sequence of the terminal to be detected.

[0089] Specifically, the RSSI data of the terminal to be detected includes multiple groups of RSSI values, and the difference of each group of RSSI values ​​is calculated sequentially until all RSSI differences in the RSSI data are obtained, thereby generating an RSSI difference sequence of the terminal to be detected.

[0090] In the embodiment of the present invention, a first weight and a second weight are introduced when generating an RSSI difference sequence. The generated RSSI difference sequence has obvious characteristics. All RSSI differences in the RSSI data of the terminal to be detected are calculated to generate an RSSI difference sequence, thereby improving the accuracy of indoor positioning.

[0091] Figure 2 The embodiment of the present invention provides a flow chart of matching the RSSI difference sequence of the terminal to be detected with the RSSI difference sequence of the fingerprint data in the fingerprint library to determine the predicted position of the terminal to be detected, as shown in FIG. Figure 2As shown, in one embodiment, matching the RSSI difference sequence of the terminal to be detected with the RSSI difference sequence of fingerprint data in the fingerprint library to determine the predicted position of the terminal to be detected includes the following sub-steps:

[0092] Step 200: Calculate the cosine similarity between the RSSI difference sequence of the terminal to be detected and the RSSI difference sequence in the fingerprint database.

[0093] Specifically, the fingerprint database includes multiple RSSI difference sequences, and the cosine similarity between the RSSI difference sequence of the terminal to be detected and the multiple RSSI difference sequences in the fingerprint database is calculated.

[0094] Step 201: Determine candidate fingerprint data according to the cosine similarity, and determine a third weight of the candidate fingerprint data according to the cosine similarity.

[0095] Specifically, the greater the cosine similarity between the RSSI difference sequence of the terminal to be detected and the RSSI difference sequence in the fingerprint library, the closer the position coordinates corresponding to the RSSI difference sequence of the terminal to be detected and the RSSI difference sequence in the fingerprint library are, and a preset number of alternative fingerprint data with the largest cosine similarity with the RSSI difference sequence of the terminal to be detected are determined. The preset number can be one or more, and the third weight of the alternative fingerprint data is determined according to the cosine similarity.

[0096] Step 202: Perform centroid fitting based on the coordinates corresponding to the candidate fingerprint data and the third weight to obtain a predicted position of the terminal to be detected.

[0097] It should be noted that the greater the cosine similarity, the higher the weight, and the closer the predicted position of the terminal to be detected, which is finally determined after the center of gravity fitting, is to the position of the candidate fingerprint data.

[0098] In the embodiment of the present invention, cosine similarity is used to compare fingerprints, and centroid fitting is performed on the determined candidate fingerprint data to obtain the predicted position of the terminal to be detected, thereby improving the accuracy of the predicted result of the terminal position to be detected.

[0099] In one embodiment, calculating the cosine similarity between the RSSI difference sequence of the terminal to be detected and the RSSI difference sequence of the fingerprint data in the fingerprint library includes:

[0100] The cosine similarity between the RSSI difference sequence of the terminal to be detected and the RSSI difference sequence of the fingerprint data in the fingerprint library is calculated according to the cosine similarity formula, wherein the cosine similarity formula is as follows:

[0101]

[0102] Among them, SQRT is the square root calculation, X i is the difference sequence of the RSSI value of the terminal to be detected, Y i is the difference sequence of the ith RSSI value of the fingerprint data, and n is the number of RSSI values.

[0103] In the embodiment of the present invention, cosine similarity is used to compare fingerprints, and centroid fitting is performed on the determined candidate fingerprint data to obtain the predicted position of the terminal to be detected, thereby improving the accuracy of the predicted result of the terminal position to be detected.

[0104] In one embodiment, determining candidate fingerprint data according to the cosine similarity includes:

[0105] According to the cosine similarity, three candidate fingerprint data with the largest cosine similarity are determined.

[0106] The performing centroid fitting according to the coordinates of the candidate fingerprint data and the third weight to obtain the predicted position of the terminal to be detected includes:

[0107] The weighted coordinates are calculated according to the centroid fitting formula, the coordinates of any two candidate fingerprint data and the third weights of the any two candidate fingerprint data.

[0108] The center of gravity fitting formula is as follows:

[0109]

[0110]

[0111] Among them, X 12 is the weighted horizontal coordinate, X1 is the horizontal coordinate of the first candidate fingerprint data, X2 is the horizontal coordinate of the second candidate fingerprint data, and Y 12 Weighted ordinate, Y1 is the ordinate of the first candidate fingerprint data, Y2 is the ordinate of the second candidate fingerprint data, cos1 is the third weight of the first candidate fingerprint data, and cos2 is the third weight of the second candidate fingerprint data.

[0112] Specifically, the weighted coordinates are calculated according to the ratio of the third weight of the second candidate fingerprint data to the sum of the third weights of the second candidate fingerprint data and the first candidate fingerprint data.

[0113] Optionally, the weighted coordinates may be calculated based on the ratio of the third weight of the first candidate fingerprint data to the sum of the third weights of the second candidate fingerprint data and the first candidate fingerprint data, which can achieve the same technical effect. To avoid repetition, it will not be described here.

[0114] The center of gravity of the triangle formed by the weighted coordinates is determined to obtain the predicted position of the terminal to be detected.

[0115] Specifically, one weighted coordinate can be determined based on any two candidate fingerprint data, and three weighted coordinates can be determined based on three candidate fingerprint data. The center of gravity of the triangle formed by these three weighted coordinates is the predicted position of the terminal to be detected.

[0116] In the embodiment of the present invention, cosine similarity is used to compare fingerprints, and centroid fitting is performed on the determined candidate fingerprint data to obtain the predicted position of the terminal to be detected, thereby improving the accuracy of the predicted result of the terminal position to be detected.

[0117] Figure 3 The schematic diagram of the process of constructing the fingerprint library provided by the embodiment of the present invention is as follows: Figure 3 As shown, constructing the fingerprint library includes the following sub-steps:

[0118] Step 300: Acquire received signal strength indicator RSSI data of each target point collected through dialing, wherein the RSSI data of the target point includes RSSI sequences obtained by measuring signals of terminals at the target point by multiple pRRUs.

[0119] The dial test refers to measuring the signal of the terminal at each target point to obtain the RSSI data of each target point.

[0120] Specifically, an RSSI sequence is obtained by measuring uplink multipath signals of the terminal at each target point using multiple pRRUs collected through dialing.

[0121] Step 301: Generate an RSSI difference sequence of the target point according to the RSSI data.

[0122] Specifically, the process of generating the RSSI difference sequence of the target point according to the RSSI data corresponds to the process of generating the RSSI difference sequence of the terminal to be detected according to the RSSI data in step 101, and will not be repeated here to avoid repetition.

[0123] Step 302: Construct the fingerprint library according to the coordinates corresponding to the target point and the RSSI difference sequence of the target point.

[0124] Specifically, the RSSI difference sequence is used as the fingerprint of the target point, and the fingerprint library is constructed according to the coordinates corresponding to the target point and the fingerprint of the target point, that is, the RSSI difference sequence.

[0125] The embodiment of the present invention builds a fingerprint library according to RSSI data collected by dialing, and then locates the terminal to be detected based on the fingerprint library to determine the predicted position of the terminal to be detected, thereby improving the accuracy of indoor positioning.

[0126] The indoor positioning device provided by the present invention is described below. The indoor positioning device described below and the indoor positioning method described above can be referenced to each other.

[0127] Another embodiment of the present invention provides an indoor positioning device, such as Figure 4 As shown, it includes: a signal receiving unit 410, a difference sequence generating unit 420 and a position determining unit 430, wherein,

[0128] The signal receiving unit 410 is configured to obtain received signal strength indication RSSI data of the terminal to be detected, wherein the RSSI data includes an RSSI sequence obtained by measuring the signal of the terminal to be detected by multiple small radio remote units (pRRUs), and the RSSI sequence includes multiple RSSI values;

[0129] The difference sequence generating unit 420 is configured to generate an RSSI difference sequence of the terminal to be detected according to the RSSI data;

[0130] The position determination unit 430 is configured to match the RSSI difference sequence of the terminal to be detected with the RSSI difference sequence of the fingerprint data in the fingerprint library to determine the predicted position of the terminal to be detected.

[0131] Optionally, the difference sequence generating unit 420 is further configured to:

[0132] Calculating a first weight of the pRRU according to a probability of the pRRU appearing in the measurement report;

[0133] Normalizing the RSSI values ​​in the RSSI sequence, and determining second weights of the RSSI values ​​in the RSSI sequence according to probability values ​​in a standard normal distribution table;

[0134] Generate an RSSI difference sequence of the terminal to be detected according to the first weight, the second weight and the RSSI value.

[0135] Optionally, generating the RSSI difference sequence of the terminal to be detected according to the first weight, the second weight, and the RSSI value includes:

[0136] Calculating a difference between the set of RSSI values ​​using a difference calculation formula based on a set of RSSI values ​​in the RSSI data and a first weight and a second weight corresponding to the set of RSSI values, wherein the set of RSSI values ​​includes two RSSI values;

[0137] Continue calculating the difference of the next set of RSSI values ​​in the RSSI data until all RSSI differences in the RSSI data are obtained, and generate an RSSI difference sequence of the terminal to be detected;

[0138] The difference calculation formula is as follows:

[0139] R 1-2 =W p1 *W R1 *R1-W p2 *W R2 *R2

[0140] Among them, R 1-2 represents the difference between the first RSSI value and the second RSSI value, W p1 Represents the first weight corresponding to the first RSSI value, W R1 represents the second weight corresponding to the first RSSI value, R1 represents the first RSSI value, W p2 Represents the first weight corresponding to the second RSSI value, W R2 represents the second weight corresponding to the second RSSI value, and R2 represents the second RSSI value.

[0141] Optionally, the position determining unit 430 is further configured to:

[0142] Calculating the cosine similarity between the RSSI difference sequence of the terminal to be detected and the RSSI difference sequence of the fingerprint data in the fingerprint library;

[0143] determining candidate fingerprint data according to the cosine similarity, and determining a third weight of the candidate fingerprint data according to the cosine similarity;

[0144] A center of gravity fitting is performed based on the coordinates corresponding to the candidate fingerprint data and the third weight to obtain a predicted position of the terminal to be detected.

[0145] Optionally, calculating the cosine similarity between the RSSI difference sequence of the terminal to be detected and the RSSI difference sequence of fingerprint data in the fingerprint library includes:

[0146] The cosine similarity between the RSSI difference sequence of the terminal to be detected and the RSSI difference sequence of the fingerprint data in the fingerprint library is calculated according to the cosine similarity formula, wherein the cosine similarity formula is as follows:

[0147]

[0148] Among them, SQRT is the square root calculation, X i is the difference sequence of the RSSI value of the terminal to be detected, Y i is the difference sequence of the ith RSSI value of the fingerprint data, and n is the number of RSSI values.

[0149] Optionally, determining candidate fingerprint data according to the cosine similarity includes:

[0150] Determining, based on the cosine similarity, three candidate fingerprint data with the largest cosine similarity;

[0151] The performing centroid fitting according to the coordinates of the candidate fingerprint data and the third weight to obtain the predicted position of the terminal to be detected includes:

[0152] Calculating weighted coordinates according to a barycenter fitting formula, coordinates of any two candidate fingerprint data, and a third weight of the any two candidate fingerprint data;

[0153] Determining the center of gravity of the triangle formed by the weighted coordinates to obtain the predicted position of the terminal to be detected;

[0154] The center of gravity fitting formula is as follows:

[0155]

[0156]

[0157] Among them, X 12 is the weighted horizontal coordinate, X1 is the horizontal coordinate of the first candidate fingerprint data, X2 is the horizontal coordinate of the second candidate fingerprint data, and Y 12 Weighted ordinate, Y1 is the ordinate of the first candidate fingerprint data, Y2 is the ordinate of the second candidate fingerprint data, cos1 is the third weight of the first candidate fingerprint data, and cos2 is the third weight of the second candidate fingerprint data.

[0158] Optionally, the indoor positioning device provided by an embodiment of the present invention further includes a fingerprint library construction module, wherein the fingerprint library construction module is configured to:

[0159] Acquire received signal strength indicator RSSI data of each target point collected through dialing, wherein the RSSI data of the target point includes an RSSI sequence obtained by measuring a signal of a terminal at the target point by multiple pRRUs;

[0160] Generate an RSSI difference sequence of the target point according to the RSSI data;

[0161] The fingerprint library is constructed according to the coordinates corresponding to the target point and the RSSI difference sequence of the target point.

[0162] The indoor positioning device provided by the present invention can realize Figures 1 to 3 The various processes implemented by the method embodiment achieve the same technical effect and are not described here again to avoid repetition.

[0163] Figure 5 An example of a physical structure diagram of an electronic device is shown below. Figure 5 As shown, the electronic device may include: a processor 510, a communication interface 520, a memory 530, and a communication bus 540, wherein the processor 510, the communication interface 520, and the memory 530 communicate with each other via the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute the indoor positioning method, which includes:

[0164] Acquire received signal strength indicator RSSI data of the terminal to be detected, wherein the RSSI data includes an RSSI sequence obtained by measuring a signal of the terminal to be detected by multiple small remote radio frequency units (pRRUs), and the RSSI sequence includes multiple RSSI values;

[0165] Generate an RSSI difference sequence of the terminal to be detected according to the RSSI data;

[0166] The RSSI difference sequence of the terminal to be detected is matched with the RSSI difference sequence of the fingerprint data in the fingerprint library to determine the predicted position of the terminal to be detected.

[0167] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0168] On the other hand, the present invention further provides a computer program product, comprising a computer program stored on a non-transitory computer-readable storage medium, wherein the computer program comprises program instructions. When the program instructions are executed by a computer, the computer can perform the indoor positioning method provided by each of the above methods, the method comprising:

[0169] Acquire received signal strength indicator RSSI data of the terminal to be detected, wherein the RSSI data includes an RSSI sequence obtained by measuring a signal of the terminal to be detected by multiple small remote radio frequency units (pRRUs), and the RSSI sequence includes multiple RSSI values;

[0170] Generate an RSSI difference sequence of the terminal to be detected according to the RSSI data;

[0171] The RSSI difference sequence of the terminal to be detected is matched with the RSSI difference sequence of the fingerprint data in the fingerprint library to determine the predicted position of the terminal to be detected.

[0172] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the above-mentioned indoor positioning method, the method comprising:

[0173] Acquire received signal strength indicator RSSI data of the terminal to be detected, wherein the RSSI data includes an RSSI sequence obtained by measuring a signal of the terminal to be detected by multiple small remote radio frequency units (pRRUs), and the RSSI sequence includes multiple RSSI values;

[0174] Generate an RSSI difference sequence of the terminal to be detected according to the RSSI data;

[0175] The RSSI difference sequence of the terminal to be detected is matched with the RSSI difference sequence of the fingerprint data in the fingerprint library to determine the predicted position of the terminal to be detected.

[0176] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0177] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0178] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An indoor positioning method, characterized in that: include: Acquire received signal strength indicator RSSI data of the terminal to be detected, wherein the RSSI data includes an RSSI sequence obtained by measuring a signal of the terminal to be detected by multiple small remote radio frequency units (pRRUs), and the RSSI sequence includes multiple RSSI values; Generating an RSSI difference sequence of the terminal to be detected based on the RSSI data, including: calculating a first weight of the pRRU based on a probability of the pRRU appearing in a measurement report; normalizing RSSI values ​​in the RSSI sequence, and determining a second weight of the RSSI values ​​in the RSSI sequence based on probability values ​​in a standard normal distribution table; and generating an RSSI difference sequence of the terminal to be detected based on the first weight, the second weight, and the RSSI value; Matching the RSSI difference sequence of the terminal to be detected with the RSSI difference sequence of the fingerprint data in the fingerprint library to determine the predicted position of the terminal to be detected; Generating the RSSI difference sequence of the terminal to be detected according to the first weight, the second weight, and the RSSI value includes: According to a group of RSSI values ​​in the RSSI data and the first weight and the second weight corresponding to the group of RSSI values, a difference calculation formula is used to calculate the difference of the group of RSSI values, wherein the group of RSSI values ​​includes two RSSI values; the difference of the next group of RSSI values ​​in the RSSI data is continued to be calculated until all RSSI differences in the RSSI data are obtained, thereby generating an RSSI difference sequence for the terminal to be detected.

2. The indoor positioning method according to claim 1, characterized in that: The difference calculation formula is as follows: R 1-2 =In p1 *IN R1 *R1-W p2 *IN R2 *R2 Among them, R 1-2 represents the difference between the first RSSI value and the second RSSI value, W p1 Represents the first weight corresponding to the first RSSI value, W R1 represents the second weight corresponding to the first RSSI value, R1 represents the first RSSI value, W p2 Represents the first weight corresponding to the second RSSI value, W R2 represents the second weight corresponding to the second RSSI value, and R2 represents the second RSSI value.

3. The indoor positioning method according to claim 1, characterized in that: The matching of the RSSI difference sequence of the terminal to be detected with the RSSI difference sequence of fingerprint data in the fingerprint library to determine the predicted position of the terminal to be detected includes: Calculating the cosine similarity between the RSSI difference sequence of the terminal to be detected and the RSSI difference sequence of the fingerprint data in the fingerprint library; determining candidate fingerprint data according to the cosine similarity, and determining a third weight of the candidate fingerprint data according to the cosine similarity; A center of gravity fitting is performed based on the coordinates corresponding to the candidate fingerprint data and the third weight to obtain a predicted position of the terminal to be detected.

4. The indoor positioning method according to claim 3, characterized in that: The calculating of the cosine similarity between the RSSI difference sequence of the terminal to be detected and the RSSI difference sequence of the fingerprint data in the fingerprint library includes: The cosine similarity between the RSSI difference sequence of the terminal to be detected and the RSSI difference sequence of the fingerprint data in the fingerprint library is calculated according to the cosine similarity formula, wherein the cosine similarity formula is as follows: Among them, SQRT is the square root calculation, X i is the difference sequence of the RSSI value of the terminal to be detected, Y i is the difference sequence of the ith RSSI value of the fingerprint data, and n is the number of RSSI values.

5. The indoor positioning method according to claim 3, characterized in that: Determining candidate fingerprint data according to the cosine similarity includes: Determining, based on the cosine similarity, three candidate fingerprint data with the largest cosine similarity; The performing centroid fitting according to the coordinates of the candidate fingerprint data and the third weight to obtain the predicted position of the terminal to be detected includes: Calculating weighted coordinates according to a barycenter fitting formula, coordinates of any two candidate fingerprint data, and a third weight of the any two candidate fingerprint data; Determining the center of gravity of the triangle formed by the weighted coordinates to obtain the predicted position of the terminal to be detected; The center of gravity fitting formula is as follows: Among them, X 12 is the weighted horizontal coordinate, X1 is the horizontal coordinate of the first candidate fingerprint data, X2 is the horizontal coordinate of the second candidate fingerprint data, and Y 12 Weighted ordinate, Y1 is the ordinate of the first candidate fingerprint data, Y2 is the ordinate of the second candidate fingerprint data, cos1 is the third weight of the first candidate fingerprint data, and cos2 is the third weight of the second candidate fingerprint data.

6. The indoor positioning method according to claim 1, characterized in that: Also includes: Building the fingerprint library; The constructing of the fingerprint library comprises: Acquire received signal strength indicator RSSI data of each target point collected through dialing, wherein the RSSI data of the target point includes an RSSI sequence obtained by measuring a signal of a terminal at the target point by multiple pRRUs; Generate an RSSI difference sequence of the target point according to the RSSI data; The fingerprint library is constructed according to the coordinates corresponding to the target point and the RSSI difference sequence of the target point.

7. An indoor positioning device, characterized in that: include: a signal receiving unit, configured to obtain received signal strength indication RSSI data of a terminal to be detected, wherein the RSSI data comprises an RSSI sequence obtained by measuring a signal of the terminal to be detected by multiple small remote radio frequency units (pRRUs), and the RSSI sequence comprises multiple RSSI values; a difference sequence generating unit, configured to generate an RSSI difference sequence of the terminal to be detected based on the RSSI data, comprising: calculating a first weight of the pRRU based on a probability of the pRRU appearing in a measurement report; normalizing the RSSI values ​​in the RSSI sequence, and determining a second weight of the RSSI values ​​in the RSSI sequence based on a probability value in a standard normal distribution table; and generating an RSSI difference sequence of the terminal to be detected based on the first weight, the second weight, and the RSSI value; a position determination unit, configured to match the RSSI difference sequence of the terminal to be detected with the RSSI difference sequence of the fingerprint data in the fingerprint library to determine the predicted position of the terminal to be detected; Generating the RSSI difference sequence of the terminal to be detected according to the first weight, the second weight, and the RSSI value includes: According to a group of RSSI values ​​in the RSSI data and the first weight and the second weight corresponding to the group of RSSI values, a difference calculation formula is used to calculate the difference of the group of RSSI values, wherein the group of RSSI values ​​includes two RSSI values; the difference of the next group of RSSI values ​​in the RSSI data is continued to be calculated until all RSSI differences in the RSSI data are obtained, thereby generating an RSSI difference sequence for the terminal to be detected.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the indoor positioning method according to any one of claims 1 to 6 are implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the indoor positioning method according to any one of claims 1 to 6 are implemented.

Images