CN112911509A - Indoor positioning method and device of Internet of things, terminal equipment and storage medium - Google Patents
Indoor positioning method and device of Internet of things, terminal equipment and storage medium Download PDFInfo
- Publication number
- CN112911509A CN112911509A CN202110234160.2A CN202110234160A CN112911509A CN 112911509 A CN112911509 A CN 112911509A CN 202110234160 A CN202110234160 A CN 202110234160A CN 112911509 A CN112911509 A CN 112911509A
- Authority
- CN
- China
- Prior art keywords
- detected
- label
- tag
- determining
- closest
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000003860 storage Methods 0.000 title claims abstract description 12
- 239000013598 vector Substances 0.000 claims abstract description 52
- 238000003062 neural network model Methods 0.000 claims abstract description 8
- 238000012549 training Methods 0.000 claims abstract description 7
- 230000002068 genetic effect Effects 0.000 claims abstract description 5
- 238000004590 computer program Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000006855 networking Effects 0.000 claims 1
- 238000004422 calculation algorithm Methods 0.000 description 19
- 238000010586 diagram Methods 0.000 description 14
- 230000006870 function Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000001914 filtration Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000007175 bidirectional communication Effects 0.000 description 1
- 238000010170 biological method Methods 0.000 description 1
- 210000000349 chromosome Anatomy 0.000 description 1
- 230000006854 communication Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005672 electromagnetic field Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/023—Services making use of location information using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/025—Services making use of location information using location based information parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/33—Services specially adapted for particular environments, situations or purposes for indoor environments, e.g. buildings
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/80—Services using short range communication, e.g. near-field communication [NFC], radio-frequency identification [RFID] or low energy communication
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The embodiment of the invention discloses an indoor positioning method and device of the Internet of things, terminal equipment and a storage medium. The indoor positioning method of the Internet of things comprises the following steps: acquiring signal intensity vectors of a plurality of reference tags and a tag to be detected, and determining the reference tag closest to the position of the tag to be detected according to the signal intensity vectors; acquiring the actual position of the closest reference label, and determining the initial estimation positioning coordinate of the label to be detected according to the actual position; selecting a sample set with strongest correlation with the initial estimation positioning coordinate according to the correlation parameter; and training the sample set by adopting a genetic neural network model to determine the final positioning coordinate. According to the indoor positioning method of the Internet of things, under the condition that data information is less, the relation between the label signal strength value and the position coordinate is established, and therefore the positioning accuracy of the positioning method can be improved.
Description
Technical Field
The invention relates to the field of indoor positioning, in particular to an indoor positioning method and device of an internet of things, terminal equipment and a storage medium.
Background
Fifth generation communication technologies have begun to test success this year. As an indoor positioning technology of the Internet of things, the intelligent city intelligent positioning system has a strong effect in the development of intelligent cities. The indoor positioning technology of the existing internet of things adopts a radio frequency identification indoor positioning technology, a radio frequency mode is utilized, a fixed antenna modulates a radio signal into an electromagnetic field, a tag attached to an article generates induction current after passing through the magnetic field to transmit data, and the aims of identification and triangular positioning are achieved through a plurality of pairs of bidirectional communication interactive data. However, the radio frequency identification indoor positioning technology is easily interfered by external environment and has poor positioning accuracy. Therefore, there is a need for an improved indoor positioning technique that is not interfered by external environment and has improved positioning accuracy.
Disclosure of Invention
In view of the above technical problems, embodiments of the present invention provide an indoor positioning method and apparatus for an internet of things, a terminal device, and a storage medium, where a relationship between a tag signal strength value and a position coordinate is established under the condition of less data information, so that positioning accuracy of the positioning method can be improved.
A first aspect of an embodiment of the present invention provides an indoor positioning method for an internet of things, including:
acquiring signal intensity vectors of a plurality of reference tags and a tag to be detected, and determining the reference tag closest to the position of the tag to be detected according to the signal intensity vectors;
acquiring the actual position of the reference label which is closest to the reference label, and determining the initial estimation positioning coordinate of the label to be detected according to the actual position;
selecting a sample set with the strongest correlation with the initial estimation positioning coordinate according to the correlation parameter;
and training the sample set by adopting a neural network model to determine a final positioning coordinate.
Preferably, the acquiring signal strength vectors of a plurality of reference tags and a tag to be detected, and determining the reference tag closest to the tag to be detected according to the signal strength vectors specifically includes:
acquiring a first signal intensity vector of the reference label and acquiring a second signal intensity vector of the label to be detected;
calculating Euclidean distance according to the first signal vector and the second signal vector;
and determining the reference label closest to the position of the label to be detected according to the Euclidean distance.
The obtaining of the actual position of the closest reference tag and the determining of the initial estimated positioning coordinate of the tag to be detected according to the actual position specifically include:
acquiring the actual position of the closest reference label;
determining a weight value of the reference label according to the Euclidean distance;
and determining the initial estimation positioning coordinate of the label to be detected according to the weight value and the closest actual position of the reference label.
Preferably, the selecting, according to the correlation parameter, the sample set having the strongest correlation with the initial estimated location coordinate specifically includes:
acquiring the actual position of a label to be detected;
respectively calculating correlation coefficients according to the actual positions of the labels to be detected and the initial estimation positioning coordinates of a plurality of groups of the labels to be detected;
and selecting a group of sample sets of the signal intensity of the to-be-detected label corresponding to the minimum correlation coefficient.
A second aspect of the embodiments of the present invention provides an indoor positioning device for an internet of things, including:
the tag determining module is used for acquiring signal intensity vectors of a plurality of reference tags and a tag to be detected, and determining the reference tag closest to the position of the tag to be detected according to the signal intensity vectors;
the initial position determining module is used for acquiring the actual position of the reference label which is closest to the reference label and determining the initial estimation positioning coordinate of the label to be detected according to the actual position;
the sample set selection module is used for selecting a sample set with the strongest correlation with the initial estimation positioning coordinate according to the correlation parameter;
and the final position determining module is used for training the sample set by adopting a neural network model to determine a final positioning coordinate.
Preferably, the tag determination module includes:
the signal intensity acquisition unit is used for acquiring a first signal intensity vector of the reference label and acquiring a second signal intensity vector of the label to be detected;
a distance calculation unit for calculating a euclidean distance based on the first signal vector and the second signal vector;
and the reference label determining unit is used for determining the reference label closest to the position of the label to be detected according to the Euclidean distance.
Preferably, the initial position determining module includes:
a first position acquisition unit for acquiring an actual position of the reference tag closest to the reference tag;
a weight determining unit, configured to determine a weight value of the reference tag according to the euclidean distance;
and the initial coordinate determination unit is used for determining the initial estimated positioning coordinate of the to-be-detected label according to the weight value and the closest actual position of the reference label.
Preferably, the sample set determination module includes:
the second position acquisition unit is used for acquiring the actual position of the label to be detected;
the correlation coefficient calculation unit is used for respectively calculating correlation coefficients according to the actual positions of the labels to be detected and the initial estimation positioning coordinates of a plurality of groups of the labels to be detected;
and the sample set selection unit is used for selecting a sample set of the signal intensity of the label to be detected corresponding to the minimum correlation coefficient.
A third aspect of an embodiment of the present invention provides a terminal device, including: at least one processor and memory;
the memory stores a computer program; the at least one processor executes the computer program stored in the memory to implement the indoor positioning method of the internet of things.
A fourth aspect of the embodiments of the present invention provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed, the method for indoor positioning of an internet of things is implemented.
Compared with the prior art, the indoor positioning method of the Internet of things in the technical scheme provided by the embodiment of the invention has the advantages that the relation between the label signal strength value and the position coordinate is established under the condition of less data information, so that the positioning accuracy of the positioning method can be improved. Experimental research shows that the average positioning error of the indoor positioning method of the Internet of things is about 0.9m, is 64% lower than that of the traditional LANDMARC algorithm, and improves the indoor positioning accuracy of the positioning accuracy.
Drawings
Fig. 1 is a flowchart of an indoor positioning method of an internet of things in the embodiment of the present invention.
Fig. 2 is a diagram of a laboratory site deployment reference in an embodiment of the present invention.
Fig. 3 is a positioning error comparison diagram of four indoor positioning methods according to the embodiment of the present invention.
Fig. 4 is a distance error cumulative distribution function diagram of four indoor positioning methods according to the embodiment of the present invention.
Fig. 5 is a schematic structural diagram of an indoor positioning device of the internet of things in the embodiment of the invention.
Fig. 6 is a schematic structural diagram of a terminal device in an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides an indoor positioning method of the Internet of things, which is used for establishing the relation between the label signal strength value and the position coordinate under the condition of less data information, so that the positioning accuracy of a positioning algorithm can be improved. Referring to fig. 1, the specific steps of the indoor positioning method of the internet of things in the embodiment of the present invention are described in detail as follows:
s1, acquiring a plurality of reference labels and a signal intensity vector of a label to be detected, and determining the reference label closest to the position of the label to be detected according to the signal intensity vector;
s2, acquiring the actual position of the closest reference label, and determining the initial estimation positioning coordinate of the label to be detected according to the actual position;
step S3, selecting a sample set with the strongest correlation with the initial estimation positioning coordinate according to the correlation parameter;
and step S4, training the sample set by adopting a neural network model, and determining the final positioning coordinate.
Before step S1, positions of the reference tag and the card reader need to be set, and the card reader reads the signal strength vectors of the reference tag and the tag to be tested. The reference label, the label to be detected and the card reader are distributed in an indoor positioning range. Preferably, the reference tags are uniformly distributed, and more preferably, the reference tags are arranged in an array, but not limited thereto; the label to be detected is positioned at the adjacent position of the plurality of reference labels; the card reader is deployed at the edge of the indoor positioning range. The deployment site is described below in an experimental example: referring to fig. 1, four card readers are placed at four corners of a 10m by 10m laboratory, and 121 reference tags are disposed in the laboratory, forming an array arrangement of 11 by 11. Fig. 2 is only an example, and is not limited to this example.
And when the positions of the reference label, the label to be detected and the card reader in the indoor positioning range are determined, the related information is acquired. Specifically, step S1 is described in detail as follows:
and step S11, acquiring a first signal intensity vector of the reference label and acquiring a second signal intensity vector of the label to be detected. Suppose that the number of the arranged reference tags is M, the number of the tags to be tested is N, and the number of the card readers is k.
Then, the first signal strength vector observed in the ith reference tag is
The second signal intensity vector at the jth tag to be tested is:
wherein 0< i M, 0< j N, k is the number of card readers.
And step S12, calculating the Euclidean distance according to the first signal vector and the second signal vector. The euclidean distance between the ith reference tag and the jth tag to be tested can be obtained according to the above formulas (1) and (2), and the specific formula is as follows:
and step S13, determining the reference label closest to the position of the label to be detected according to the Euclidean distance. Then, M euclidean distance values, that is, the euclidean distance values between the M reference tags and the jth tag to be detected, can be obtained according to the formula (3), and the specific formula is as follows:
Ej＝(E1j,E2j,...,EMj) (4)
selection of EjMiddle minimum value, if EljAnd if the distance is minimum, the distance between the ith reference label and the jth label to be detected is closer.
In the signal intensity vector collection process, the collection values of the first signal intensity vector of the ith reference tag and the second signal intensity vector of the jth tag to be detected are not unique. Acquiring the first signal intensity vectors for n times, obtaining n first signal intensity vectors according to the formula (1), and obtaining an initial signal intensity sample set of the reference label
Filtering out the maximum value and the minimum value through a Gaussian filter algorithm, and removing noise points and boundary points by adopting a DBSCAN algorithm to obtain a final signal intensity sample set of the ith reference label
Wherein p is<n is the same as the formula (I). Acquiring the second signal intensity vectors for n times, obtaining n second signal intensity vectors by the formula (2), and obtaining an initial signal intensity sample set of the label to be detected
Filtering out the maximum value and the minimum value through a Gaussian filter algorithm, and removing noise points and boundary points by adopting a DBSCAN algorithm to obtain a final signal intensity sample set of the ith reference label
Wherein p is<n。
After the closest reference tag is determined, the position of the tag to be detected needs to be preliminarily estimated according to the position of the reference tag. Step S2 is described in detail below:
and step S21, acquiring the actual position of the closest reference label. The actual position of the ith reference tag is not unique when being acquired, the actual position of the ith reference tag needs to be acquired, p actual positions of the reference tags are left in the processing process of the sample set, and the coordinate of the actual position of each reference tag is (x)p,yp)。
And step S22, determining the weight value of the reference label according to the Euclidean distance. The associated weight values of the reference tags are defined by the following formula:
wherein l is the reference label closest to the label to be detected.
And step S23, obtaining the initial estimation positioning coordinate of the label to be detected according to the weight value and the actual position of the closest reference label.
The initial estimated location coordinates of the tag to be detected are (x, y), and the formula (5) is substituted, so that the specific calculation formula is as follows:
next, a sample set of the to-be-tested tags is further selected, and the specific step S3 is as follows:
and step S31, acquiring the actual position of the label to be detected.
According to the actual distance (x) that the card reader can read the label to be detected0,y0)。
And step S32, respectively calculating correlation coefficients according to the actual positions of the labels to be detected and the initial estimation positioning coordinates of a plurality of groups of labels to be detected.
The jth label to be detected can obtain q groups of sample sets, and then the initial estimation positioning coordinate (x) of the q groups of labels to be detected can be obtained according to the formula (x)j,yj) Is composed of (x)0,y0)、(xj,yj) The correlation coefficient d can be calculatedjThe formula is as follows:
and step S33, selecting a sample set of signal intensity of a group of labels to be tested corresponding to the minimum correlation coefficient. Q sets of correlation coefficients d are calculated by the above formula (7)j，djTaking d in q groups as the position correlation is stronger when the value is smallerjA set of minimum values corresponds to a sample set of signal strengths of the tags under test.
After the sample set of the signal intensity of the label to be detected is selected, the sample set of the signal intensity of the label to be detected is further trained on a neural network model, and therefore the more accurate final positioning coordinate of the label to be detected is obtained.
The RBF (Radial Basis Function) neural network is prior art and is not cumbersome here. The genetic algorithm is an efficient algorithm capable of realizing global search, has a biological method with a natural rule, can automatically acquire contents related to a search space, and obtains a new generation of colony and achieves a final expected result by taking all chromosomes in the colony as objects through methods such as mutation, intersection and the like. The invention adopts the genetic algorithm to optimize the RBF neural network, optimizes parameters such as output weight, width, Gaussian function center and the like of the RBF neural network, establishes a training model by using the RBF neural network optimized by the genetic algorithm, and can improve the accuracy of output results, thereby enabling the indoor positioning accuracy to be higher.
Through the indoor positioning method of the internet of things, advantages of positioning errors and positioning accuracy of the embodiment of the invention can be described through experimental data, please refer to fig. 3 and 4.
As shown in fig. 3, the average positioning error finally obtained by the indoor positioning method of the internet of things provided by the present invention is about 0.9m, 64% smaller than the average positioning error of the indoor positioning method of the LANDARC algorithm, 56% smaller than the average positioning error of the indoor positioning method of the RBF-LANDARC algorithm, and 18% smaller than the average positioning error of the indoor positioning method of the DBSCAN-RBF-LANDARC algorithm. The indoor positioning method of the Internet of things has the advantages that the positioning error fluctuates between 0.09 m and 3.45m, the fluctuation range is small, and the positioning accuracy is excellent.
As shown in fig. 4, the positioning accuracy of the indoor positioning method of the internet of things in the range of 1m is 80%, the positioning accuracy of the indoor positioning method of the LANDMARC algorithm is 15%, the positioning accuracy of the indoor positioning method of the RBF-LANDMARC algorithm is 25%, and the positioning accuracy of the indoor positioning method of the DBSCAN-RBF-LANDMARC algorithm is 60%. The positioning accuracy of the indoor positioning method of the Internet of things in the range of 2m is 85%, and the positioning accuracy of the indoor positioning method of the LANDMRC algorithm, the RBF-LANDMRC algorithm and the DBSCAN-RBF-LANDMRC algorithm is 60%, 40% and 75% respectively. Therefore, the improved indoor positioning method of the Internet of things has better positioning accuracy.
Based on the above indoor positioning method of the internet of things, the present invention further provides an indoor positioning device 100 of the internet of things, referring to fig. 5, the indoor positioning device 100 of the internet of things includes:
the tag determining module 110 is configured to obtain signal strength vectors of a plurality of reference tags and a tag to be detected, and determine, according to the signal strength vectors, a reference tag closest to the position of the tag to be detected;
an initial position determining module 120, configured to obtain an actual position of the closest reference tag, and determine an initial estimated positioning coordinate of the tag to be detected according to the actual position;
a sample set selecting module 130, configured to select, according to the correlation parameter, a sample set with the strongest correlation with the initial estimated location coordinate;
and a final position determining module 140, configured to train the sample set by using a neural network model, and determine a final positioning coordinate.
Wherein the tag determination module 110 includes:
a signal strength obtaining unit 111, configured to obtain a first signal strength vector of a reference tag, and obtain a second signal strength vector of a tag to be detected;
a distance calculation unit 112, configured to calculate a euclidean distance according to the first signal vector and the second signal vector;
and a reference tag determining unit 113, configured to determine, according to the euclidean distance, a reference tag closest to the position of the tag to be detected.
Wherein the initial position determining module 120 includes:
a first position acquisition unit 121 for acquiring an actual position of the closest reference tag;
a weight determining unit 122, configured to determine a weight value of the reference tag according to the euclidean distance;
and an initial coordinate determining unit 123, configured to determine an initial estimated positioning coordinate of the tag to be detected according to the weight value and the actual position of the closest reference tag.
Wherein the sample set determining module 130 comprises:
a second position obtaining unit 131, configured to obtain an actual position of the tag to be detected;
a correlation coefficient calculating unit 132, configured to calculate correlation coefficients according to the actual positions of the tags to be detected and the initial estimated positioning coordinates of the sets of tags to be detected, respectively;
the sample set selecting unit 133 is configured to select a sample set of signal strengths of a group of tags to be tested corresponding to the minimum correlation coefficient.
The functions of each module in each apparatus in the embodiment of the present application may refer to corresponding descriptions in the above method, and are not described herein again.
Still another embodiment of the present invention provides a terminal device, configured to execute the method for collecting product anomalies provided in the foregoing embodiment.
Fig. 6 is a schematic structural diagram of a terminal device of the present invention, and as shown in fig. 6, the terminal device includes: at least one processor 601 and memory 602;
the memory stores a computer program; the at least one processor executes the computer program stored in the memory to implement the method for collecting product exceptions provided by the above-described embodiments.
Still another embodiment of the present invention provides a computer-readable storage medium, in which a computer program is stored, and the computer program, when executed, implements the method for collecting product anomalies described above.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, electronic devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing electronic device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing electronic device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing electronic devices to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing electronic device to cause a series of operational steps to be performed on the computer or other programmable electronic device to produce a computer implemented process such that the instructions which execute on the computer or other programmable electronic device provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or electronic device that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or electronic device. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or electronic device that comprises the element.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. An indoor positioning method of the Internet of things is characterized by comprising the following steps:
acquiring signal intensity vectors of a plurality of reference tags and a tag to be detected, and determining the reference tag closest to the position of the tag to be detected according to the signal intensity vectors;
acquiring the actual position of the reference label which is closest to the reference label, and determining the initial estimation positioning coordinate of the label to be detected according to the actual position;
selecting a sample set with the strongest correlation with the initial estimation positioning coordinate according to the correlation parameter;
and training the sample set by adopting a genetic neural network model to determine a final positioning coordinate.
2. The internet of things indoor positioning method according to claim 1, wherein the obtaining of signal strength vectors of a plurality of reference tags and a tag to be detected and the determining of the reference tag closest to the tag to be detected according to the signal strength vectors specifically include:
acquiring a first signal intensity vector of the reference label and acquiring a second signal intensity vector of the label to be detected;
calculating Euclidean distance according to the first signal vector and the second signal vector;
and determining the reference label closest to the position of the label to be detected according to the Euclidean distance.
3. The internet of things indoor positioning method according to claim 1, wherein the obtaining of the actual position of the closest reference tag and the determining of the initial estimated positioning coordinates of the tag to be detected according to the actual position specifically include:
acquiring the actual position of the closest reference label;
determining a weight value of the reference label according to the Euclidean distance;
and determining the initial estimation positioning coordinate of the label to be detected according to the weight value and the closest actual position of the reference label.
4. The internet of things indoor positioning method according to claim 1, wherein the selecting a sample set having a strongest correlation with the initial estimated positioning coordinates according to the correlation parameters specifically comprises:
acquiring the actual position of a label to be detected;
respectively calculating correlation coefficients according to the actual positions of the labels to be detected and the initial estimation positioning coordinates of a plurality of groups of the labels to be detected;
and selecting a group of sample sets of the signal intensity of the to-be-detected label corresponding to the minimum correlation coefficient.
5. An indoor positioner of thing networking, its characterized in that includes:
the tag determining module is used for acquiring signal intensity vectors of a plurality of reference tags and a tag to be detected, and determining the reference tag closest to the position of the tag to be detected according to the signal intensity vectors;
the initial position determining module is used for acquiring the actual position of the reference label which is closest to the reference label and determining the initial estimation positioning coordinate of the label to be detected according to the actual position;
the sample set selection module is used for selecting a sample set with the strongest correlation with the initial estimation positioning coordinate according to the correlation parameter;
and the final position determining module is used for training the sample set by adopting a neural network model to determine a final positioning coordinate.
6. The indoor positioning device of the internet of things as claimed in claim 5, wherein the tag determination module comprises:
the signal intensity acquisition unit is used for acquiring a first signal intensity vector of the reference label and acquiring a second signal intensity vector of the label to be detected;
a distance calculation unit for calculating a euclidean distance based on the first signal vector and the second signal vector;
and the reference label determining unit is used for determining the reference label closest to the position of the label to be detected according to the Euclidean distance.
7. The indoor positioning device of the internet of things of claim 5, wherein the initial position determining module comprises:
a first position acquisition unit for acquiring an actual position of the reference tag closest to the reference tag;
a weight determining unit, configured to determine a weight value of the reference tag according to the euclidean distance;
and the initial coordinate determination unit is used for determining the initial estimated positioning coordinate of the to-be-detected label according to the weight value and the closest actual position of the reference label.
8. The internet of things indoor positioning device of claim 5, wherein the sample set determining module comprises:
the second position acquisition unit is used for acquiring the actual position of the label to be detected;
the correlation coefficient calculation unit is used for respectively calculating correlation coefficients according to the actual positions of the labels to be detected and the initial estimation positioning coordinates of a plurality of groups of the labels to be detected;
and the sample set selection unit is used for selecting a sample set of the signal intensity of the label to be detected corresponding to the minimum correlation coefficient.
9. A terminal device, comprising: at least one processor and memory;
the memory stores a computer program; the at least one processor executes the memory-stored computer program to implement the method of indoor positioning of the internet of things of any of claims 1-4.
10. A computer-readable storage medium, in which a computer program is stored, which, when executed, implements the method for indoor positioning of the internet of things as claimed in any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110234160.2A CN112911509A (en) | 2021-03-03 | 2021-03-03 | Indoor positioning method and device of Internet of things, terminal equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110234160.2A CN112911509A (en) | 2021-03-03 | 2021-03-03 | Indoor positioning method and device of Internet of things, terminal equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112911509A true CN112911509A (en) | 2021-06-04 |
Family
ID=76107494
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110234160.2A Pending CN112911509A (en) | 2021-03-03 | 2021-03-03 | Indoor positioning method and device of Internet of things, terminal equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112911509A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102111876A (en) * | 2011-02-24 | 2011-06-29 | 华为技术有限公司 | Method and device for selecting reference labels used for location |
| CN108989976A (en) * | 2018-06-04 | 2018-12-11 | 华中师范大学 | Fingerprint positioning method and system in a kind of wisdom classroom |
| WO2019138225A1 (en) * | 2018-01-10 | 2019-07-18 | Oxford University Innovation Limited | Determining the location of a mobile device |
| CN111901747A (en) * | 2020-07-25 | 2020-11-06 | 福建工程学院 | Indoor accurate positioning method and system based on LANDMAC |
-
2021
- 2021-03-03 CN CN202110234160.2A patent/CN112911509A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102111876A (en) * | 2011-02-24 | 2011-06-29 | 华为技术有限公司 | Method and device for selecting reference labels used for location |
| WO2019138225A1 (en) * | 2018-01-10 | 2019-07-18 | Oxford University Innovation Limited | Determining the location of a mobile device |
| CN108989976A (en) * | 2018-06-04 | 2018-12-11 | 华中师范大学 | Fingerprint positioning method and system in a kind of wisdom classroom |
| CN111901747A (en) * | 2020-07-25 | 2020-11-06 | 福建工程学院 | Indoor accurate positioning method and system based on LANDMAC |
Non-Patent Citations (4)
| Title |
|---|
| JINGQIU REN等: "LANDMARC indoor positioning algorithm based on density-based spatial clustering of applications with noise-genetic algorithm-radial basis function neural network", 《INTERNATIONAL JOURNAL OF DISTRIBUTED SENSOR NETWORKS》, 29 February 2020 (2020-02-29), pages 4 - 7 * |
| 宋宁佳;崔英花;: "基于MEA-GRNN的RFID室内定位", 电讯技术, no. 10, 28 October 2020 (2020-10-28) * |
| 王晨;陈增强;: "基于连续蚁群算法融合的神经网络RFID信号分布模型", 东南大学学报(自然科学版), no. 1, 20 July 2013 (2013-07-20) * |
| 马翠红;徐天天;杨友良;: "基于AGA-GRNN的三维室内定位研究", 现代电子技术, no. 14, 14 July 2020 (2020-07-14) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108875776B (en) | Model training method and device, service recommendation method and device, and electronic device | |
| Gong et al. | Optimizing RFID network planning by using a particle swarm optimization algorithm with redundant reader elimination | |
| CN110942072A (en) | Quality evaluation-based quality scoring and detecting model training and detecting method and device | |
| CN111028016A (en) | Sales data prediction method and device and related equipment | |
| CN104537647A (en) | Target detection method and device | |
| CN112052813B (en) | Method and device for identifying translocation between chromosomes, electronic equipment and readable storage medium | |
| CN113298152B (en) | Model training method, device, terminal equipment and computer readable storage medium | |
| CN109886295A (en) | A kind of butterfly recognition methods neural network based and relevant device | |
| CN113901977A (en) | Deep learning-based power consumer electricity stealing identification method and system | |
| CN110942090A (en) | Model training method, image processing method, device, electronic equipment and storage medium | |
| CN115169809A (en) | Smart city evaluation method and device | |
| CN114972737A (en) | Remote sensing image target detection system and method based on prototype comparison learning | |
| CN113158084B (en) | Method, device, computer equipment and storage medium for processing movement track data | |
| CN110390096A (en) | A kind of park evaluation method and device | |
| CN116805387A (en) | Model training method, quality inspection method and related equipment based on knowledge distillation | |
| CN112911509A (en) | Indoor positioning method and device of Internet of things, terminal equipment and storage medium | |
| CN112200862A (en) | Training method of target detection model, target detection method and device | |
| CN114330450B (en) | Method and system for identifying submarine craft through multi-physical-field fusion detection | |
| CN114708307A (en) | Target tracking method, system, storage medium and device based on correlation filter | |
| CN111325242A (en) | Image classification method, terminal and computer storage medium | |
| CN114199992B (en) | Method and system for detecting corrosion of tank wall of oil storage tank | |
| CN109831737A (en) | A kind of bluetooth localization method, device, equipment and system based on confidence level | |
| Pei et al. | Multi-Level Feature Extraction and Autoregressive Prediction Based Wi-Fi Indoor Fingerprint Localization | |
| CN113313079B (en) | Training method and system of vehicle attribute recognition model and related equipment | |
| CN113724733B (en) | Biological sound event detection model training method and sound event detection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |