CN111885702B - Positioning method, device, system and computer readable storage medium - Google Patents
Positioning method, device, system and computer readable storage medium Download PDFInfo
- Publication number
- CN111885702B CN111885702B CN202010702048.2A CN202010702048A CN111885702B CN 111885702 B CN111885702 B CN 111885702B CN 202010702048 A CN202010702048 A CN 202010702048A CN 111885702 B CN111885702 B CN 111885702B
- Authority
- CN
- China
- Prior art keywords
- determining
- acquisition
- characteristic value
- point
- value
- 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.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
- H04W64/003—Locating users or terminals or network equipment for network management purposes, e.g. mobility management locating network equipment
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention discloses a positioning method, which comprises the following steps: acquiring a time domain signal in a machine room, and performing frequency domain conversion on the time domain signal based on a preset conversion rule to obtain frequency domain information; determining a power value of each frequency point in the frequency domain information, and determining a frequency point characteristic value of each frequency point based on the power value; determining a target characteristic value based on the frequency point characteristic value and a preset characteristic value, wherein the preset characteristic value is a corresponding characteristic value when no target object exists in the machine room; and determining the target position of the target object in the machine room based on the target characteristic value. The invention also discloses a positioning device, a positioning system and a computer readable storage medium. The invention collects the signal characteristics when the target object exists in the machine room and the signal characteristics when the target object does not exist, and positions the target position of the target object by comparing the signal characteristics of the target object, thereby realizing the accurate positioning of the target object.
Description
Technical Field
The present invention relates to the field of information processing technologies, and in particular, to a positioning method, apparatus, system, and computer-readable storage medium.
Background
With the rapid development of social economy, the degree of informatization of various industries is higher and higher, and the places where infrastructure such as a data center machine room, a telecommunication machine room, an electric power machine room and the like are used for placing special equipment such as various data server cabinets, professional equipment cabinets and the like are also greatly increased, and the places are applied to the fields of telecommunication operators, government industries, internet enterprises, financial industries, electric power industries and the like which need a large amount of data aggregation, data storage and data processing. Because the computer lab not only has the data center of high confidentiality, but also has characteristics such as space is big, system complexity height, internal noise are big, if someone breaks into the computer lab privately and steals secret data, perhaps the staff takes place the accident when the computer lab is worked, for example the conflagration or because of the uncomfortable causes the circumstances such as faint, coma, if the specific position of staff in the computer lab is uncertain to external environment monitoring personnel, then can't in time take corresponding measure to guarantee the system data safety of computer lab or the personal safety of staff in the computer lab. Therefore, when someone enters the machine room, the external environment monitoring personnel need to determine the specific location of the personnel.
Environmental monitoring in the traditional sense especially confirms the position of personnel in above-mentioned all kinds of computer rooms, generally adopts modes such as camera collection, infrared collection, sound collection. If the camera is adopted to collect and determine the position of a person, the height of a cabinet in a machine room is generally higher than 2 meters and far higher than the height of the general person, and if a small number of cameras are adopted to collect, the problem of sight dead angles exists, so that the position information of the person cannot be effectively judged; if a large number of cameras are adopted for omnibearing monitoring, the monitoring cost can be increased; if the position of a person is determined by adopting infrared acquisition, the positioning accuracy of the infrared acquisition device can be seriously influenced because various electronic equipment in a machine room have a heating function; if adopt sound collection to come the definite personnel position, because all kinds of equipment noise interference in the computer lab is big, also can't carry out accurate positioning to personnel in the computer lab through the collection mode of sound intensity.
In the prior art, active positioning is performed by establishing a base station by using iBeacon (a low power consumption bluetooth positioning technology), UWB (Ultra Wide Band, Ultra Wide Band Wireless communication technology), WiFi (Wireless Fidelity ), and the like, but the problems of complicated engineering implementation, low reliability, low information security, and the like also exist.
Disclosure of Invention
The invention mainly aims to provide a positioning method, a positioning device, a positioning system and a computer readable storage medium, aiming at improving the accuracy of positioning a target object in a machine room.
In order to achieve the above object, the present invention provides a positioning method, including the steps of:
acquiring a time domain signal in a machine room, and performing frequency domain conversion on the time domain signal based on a preset conversion rule to obtain frequency domain information;
determining a power value of each frequency point in the frequency domain information, and determining a frequency point characteristic value of each frequency point based on the power value;
determining a target characteristic value based on the frequency point characteristic value and a preset characteristic value, wherein the preset characteristic value is a corresponding characteristic value when no target object exists in the machine room;
and determining the target position of the target object in the machine room based on the target characteristic value.
Optionally, the acquiring a time domain signal in the machine room, and performing frequency domain conversion on the time domain signal based on a preset conversion rule to obtain frequency domain information includes:
determining at least two preset acquisition points in the machine room, and determining a target frequency range corresponding to the machine room;
respectively collecting time domain signals corresponding to the target frequency range in the machine room based on the collection points;
and respectively converting the time domain signals acquired by each acquisition point based on a preset conversion rule to obtain frequency domain information corresponding to each acquisition point.
Optionally, the step of determining the power value of each frequency point in the frequency domain information, and determining the frequency point characteristic value of each frequency point based on the power value includes:
sequentially determining the power value of each frequency point in the frequency domain information corresponding to each acquisition point, and determining the power sum of each acquisition point based on the power value of each frequency point;
and respectively calculating the ratio of the power value of the frequency point corresponding to each acquisition point to the sum of the power of each acquisition point to obtain the characteristic value of the frequency point corresponding to each acquisition point.
Optionally, the step of sequentially determining the power value of each frequency point in the frequency domain information corresponding to each acquisition point, and determining the power sum of each acquisition point based on the power value of each frequency point includes:
determining the acquisition time of the frequency point corresponding to each acquisition point, and respectively integrating the instantaneous power of the frequency point of each acquisition point based on the acquisition time;
calculating integral results of the frequency points of the acquisition points, and determining power values of the frequency points of the acquisition points based on the integral results and the acquisition time;
and adding the power values of the frequency points of the acquisition points to obtain the power sum of the acquisition points.
Optionally, the step of determining a target characteristic value based on the frequency point characteristic value and a preset characteristic value includes:
respectively determining the difference value between the frequency point characteristic value corresponding to each acquisition point and a preset characteristic value to obtain the difference value characteristic value of each acquisition point;
and determining a target characteristic value corresponding to each acquisition point based on the signal intensity of the difference characteristic value of each acquisition point.
Optionally, the step of determining a target feature value corresponding to each of the acquisition points based on the signal strength of the difference feature value of each of the acquisition points includes:
sequentially determining the signal intensity of the frequency point corresponding to the difference characteristic value of each acquisition point and the total signal intensity corresponding to the difference characteristic value of each acquisition point;
respectively determining classification characteristic values of the acquisition points based on the signal intensity and the total signal intensity;
and screening out classification characteristic values with the same characteristic value in all the acquisition points to obtain a target characteristic value.
Optionally, the step of determining a target position of a target object in the machine room based on the target feature value includes:
inputting the target characteristic value into a preset algorithm, so as to obtain a target coordinate value corresponding to the target characteristic value;
and determining the target position of the target object in the machine room based on the target coordinate value.
In addition, to achieve the above object, the present invention also provides a positioning apparatus, comprising:
the acquisition conversion module is used for acquiring time domain signals in the machine room and carrying out frequency domain conversion on the time domain signals based on a preset conversion rule to obtain frequency domain information;
the first determining module is used for determining a power value of each frequency point in the frequency domain information and determining a frequency point characteristic value of each frequency point based on the power value;
a second determining module, configured to determine a target feature value based on the frequency point feature value and a preset feature value, where the preset feature value is a corresponding feature value when there is no target object in the machine room;
and the third determining module is used for determining the target position of the target object in the machine room based on the target characteristic value.
Optionally, the acquisition conversion module is further configured to:
determining at least two preset acquisition points in the machine room, and determining a target frequency range corresponding to the machine room;
respectively acquiring time domain signals corresponding to the target frequency range in the machine room based on the acquisition points;
and respectively converting the time domain signals acquired by each acquisition point based on a preset conversion rule to obtain frequency domain information corresponding to each acquisition point.
Optionally, the first determining module is further configured to:
sequentially determining the power value of each frequency point in the frequency domain information corresponding to each acquisition point, and determining the power sum of each acquisition point based on the power value of each frequency point;
and respectively calculating the ratio of the power value of the frequency point corresponding to each acquisition point to the sum of the power of each acquisition point to obtain the characteristic value of the frequency point corresponding to each acquisition point.
Optionally, the step of sequentially determining the power value of each frequency point in the frequency domain information corresponding to each acquisition point, and determining the power sum of each acquisition point based on the power value of each frequency point includes:
determining the acquisition time of the frequency point corresponding to each acquisition point, and respectively integrating the instantaneous power of the frequency point of each acquisition point based on the acquisition time;
calculating an integral result of the frequency point of each acquisition point, and determining a power value of the frequency point of each acquisition point based on the integral result and the acquisition time;
and adding the power values of the frequency points of the acquisition points to obtain the power sum of the acquisition points.
Optionally, the second determining module is further configured to:
respectively determining the difference value between the frequency point characteristic value corresponding to each acquisition point and a preset characteristic value to obtain the difference value characteristic value of each acquisition point;
and determining a target characteristic value corresponding to each acquisition point based on the signal intensity of the difference characteristic value of each acquisition point.
Optionally, the second determining module is further configured to:
sequentially determining the signal intensity of the frequency point corresponding to the difference characteristic value of each acquisition point and the total signal intensity corresponding to the difference characteristic value of each acquisition point;
respectively determining classification characteristic values of the acquisition points based on the signal intensity and the total signal intensity;
and screening out classification characteristic values with the same characteristic value in all the acquisition points to obtain a target characteristic value.
Optionally, the third determining module is further configured to:
inputting the target characteristic value into a preset algorithm, so as to obtain a target coordinate value corresponding to the target characteristic value;
and determining the target position of the target object in the machine room based on the target coordinate value.
In addition, to achieve the above object, the present invention also provides a positioning system, including: a memory, a processor and a positioning program stored on the memory and executable on the processor, the positioning program when executed by the processor implementing the steps of the positioning method as described above.
In addition, to achieve the above object, the present invention further provides a computer readable storage medium, having a positioning program stored thereon, where the positioning program, when executed by a processor, implements the steps of the positioning method as described above.
The positioning method provided by the invention comprises the steps of collecting time domain signals in a machine room, and carrying out frequency domain conversion on the time domain signals based on a preset conversion rule to obtain frequency domain information; determining a power value of each frequency point in the frequency domain information, and determining a frequency point characteristic value of each frequency point based on the power value; determining a target characteristic value based on the frequency point characteristic value and a preset characteristic value, wherein the preset characteristic value is a corresponding characteristic value when no target object exists in the machine room; and determining the target position of the target object in the machine room based on the target characteristic value. The invention collects the signal characteristics when the target object exists in the machine room and the signal characteristics when the target object does not exist, and positions the target position of the target object by comparing the signal characteristics when the target object exists or does not exist, thereby realizing the accurate positioning of the target object.
Drawings
Fig. 1 is a schematic diagram of a system architecture of a hardware operating environment according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a positioning method according to a first embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, fig. 1 is a system structural diagram of a hardware operating environment according to an embodiment of the present invention.
The system comprises a wireless signal acquisition module, a wireless signal conversion module, a multipoint feature matching module, a position information calculation module, a data correction module and the like.
As shown in fig. 1, the system may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. The communication bus 1002 is used to implement connection communication among these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., a WiFi interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the system architecture shown in FIG. 1 is not intended to be limiting of the system, and may include more or fewer components than shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, the memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and a positioning program.
The operating system is a program for managing and controlling the positioning system and software resources, and supports the running of a network communication module, a user interface module, a positioning program and other programs or software; the network communication module is used for managing and controlling the network interface 1002; the user interface module is used to manage and control the user interface 1003.
In the positioning system shown in fig. 1, the positioning system calls a positioning program stored in a memory 1005 through a processor 1001 and performs operations in various embodiments of the positioning method described below.
Based on the hardware structure, the embodiment of the positioning method is provided.
Referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of the positioning method of the present invention, where the method includes:
step S10, collecting time domain signals in a machine room, and performing frequency domain conversion on the time domain signals based on a preset conversion rule to obtain frequency domain information;
step S20, determining the power value of each frequency point in the frequency domain information, and determining the frequency point characteristic value of each frequency point based on the power value;
step S30, determining a target characteristic value based on the frequency point characteristic value and a preset characteristic value, wherein the preset characteristic value is a corresponding characteristic value when no target object exists in the machine room;
and step S40, determining the target position of the target object in the machine room based on the target characteristic value.
The positioning method is applied to positioning systems of machine rooms such as data center machine rooms, telecommunication machine rooms and electric power machine rooms. In order to realize accurate positioning of a target object in a machine room, a plurality of signal acquisition points are uniformly distributed in a positioning system of the machine room, and in addition, the positioning system also comprises a wireless signal acquisition module, a wireless signal conversion module, a multi-point feature matching module, a position information calculation module, a data correction module and the like, wherein the wireless signal acquisition module is used for acquiring wireless time domain signals in the machine room through acquisition points; the wireless signal conversion module is used for carrying out frequency domain conversion on the acquired time domain signals, separating frequency points in a preset signal frequency range through the converted frequency domain information, and determining a characteristic value of each frequency point; the multipoint feature matching module is used for comparing feature values obtained by a plurality of signal acquisition points and classifying signals with the same feature values into one class; the position information calculation module is used for calculating the target position of the target object through a supervised learning algorithm; the data correction module is used for receiving correction parameters input by a user and improving the positioning accuracy.
Because the environment inside the machine room is complex, wireless signals such as bluetooth, WiFi, wireless mobile communication and other signals exist, and propagation characteristics such as refraction, reflection, diffraction and the like exist in the machine room, a large error occurs when a traditional method based on space wireless Signal attenuation is adopted to determine the distance, and further various algorithms based on the RSSI (Received Signal Strength Indication) Signal Strength, such as a triangular space positioning algorithm, an angle difference algorithm under a direction finding condition and the like, are greatly reduced in performance in the machine room, or even the basic positioning function of the machine room cannot be effectively realized. It can be understood that, under normal conditions, that is, when no target object is in the machine room, the signal characteristics inside the machine room are stable, if a target object enters the machine room and the target object itself emits a signal, then the signal inside the machine room changes, and therefore, the position of the target object causing the signal change can be analyzed by monitoring the signal change in the machine room.
It should be noted that the target object may be a person, and the person carries a device such as a mobile phone which transmits a signal to the outside; the target object may also be an object, and the object itself emits a signal to the outside, such as a robot or other robotic device.
The positioning system of the embodiment positions the target position of the target object by acquiring the signal characteristics when the target object exists in the machine room and the signal characteristics when the target object does not exist and comparing the signal characteristics when the target object exists or does not exist, thereby realizing the accurate positioning of the target object.
The respective steps will be described in detail below:
step S10, collecting time domain signals in a machine room, and performing frequency domain conversion on the time domain signals based on a preset conversion rule to obtain frequency domain information;
in this embodiment, the collection points are uniformly arranged inside the machine room in advance, the positioning system collects the time domain signals in the machine room through the collection points, and then converts the collected time domain signals into frequency domain signals according to a preset conversion rule, wherein the preset conversion rule may be fourier conversion.
It can be understood that the time domain signal can visually observe the shape of the signal, but the signal cannot be accurately described by using limited parameters, and the frequency domain analysis can decompose a complex signal into the superposition of simple signals (sinusoidal signals), so that the "construction" of the signal can be more accurately known. Therefore, after the time domain signal in the machine room is collected, the time domain signal needs to be converted into a frequency domain signal for subsequent positioning analysis.
It should be noted that, the acquisition point may acquire a wireless signal within 6G, and in the process of acquiring a time domain signal, the acquisition of the time domain may be specifically performed according to actual requirements, for example, full-band coarse granularity acquisition within a period of time, or bandwidth acquisition within a period of time, so as to obtain a wireless signal with time domain characteristics, that is, a time domain signal.
Specifically, the step of collecting time domain signals in the machine room and performing frequency domain conversion on the time domain signals based on a preset conversion rule to obtain frequency domain information comprises:
a1, determining at least two preset acquisition points in the machine room, and determining a target frequency range corresponding to the machine room;
in the embodiment, the collection points preset in the machine room are uniformly distributed and at least comprise two collection points. It can be understood that, because the inside self environment of computer lab is comparatively complicated, radio signal is like signals such as bluetooth, wiFi, wireless mobile communication, propagation characteristics such as refraction, reflection, diffraction exist for it is complicated to lead to the signal in the computer lab is complicated, if carry out single-point collection, the complicated computer lab environment can lead to gathering the data that the point gathered at every turn and great deviation appears, has seriously influenced the accuracy nature to target object location in the computer lab.
A2, respectively acquiring time domain signals corresponding to the target frequency range in the machine room based on the acquisition points;
in this embodiment, the signal that the target object emanates can be wireless signals such as bluetooth, WiFi, wireless mobile communication, and different signals correspond different frequency range, for example, the target frequency range of known bluetooth signal is 2.4-2.485 GHz, when gathering the bluetooth signal in the computer lab, require each acquisition point to gather the signal in 2.4-2.485 GHz frequency range.
Step a3, respectively converting the time domain signals collected by each collection point based on a preset conversion rule to obtain frequency domain information corresponding to each collection point.
In this embodiment, the acquired time domain signal is subjected to frequency domain conversion based on a preset conversion rule, such as fourier transform, to obtain frequency domain information corresponding to the signal, where the frequency domain information is preferably information such as frequency, amplitude, and phase in specific implementation.
Step S20, determining the power value of each frequency point in the frequency domain information, and determining the frequency point characteristic value of each frequency point based on the power value;
in this embodiment, after obtaining the frequency domain information of the signal, each acquisition point calculates the power value of each frequency point in each acquisition point by combining the time domain information of the signal, that is, based on the frequency, time, voltage, current, and other information of the signal, and calculates the power sum of each acquisition point, and then calculates the ratio of the power value of the frequency point corresponding to each acquisition point to the power sum respectively, so as to obtain the frequency point characteristic value of the frequency point corresponding to each acquisition point. The obtained frequency point characteristic values are subjected to normalization processing on the power values of the frequency points in the acquisition points, so that subsequent positioning analysis is facilitated.
It should be noted that the time of the signal includes a certain time of signal acquisition and a time length from the beginning to the end of signal acquisition, i.e., an acquisition time.
Specifically, in this embodiment, the step of determining the power value of each frequency point in the frequency domain information and determining the frequency point characteristic value of each frequency point based on the power value includes:
b1, sequentially determining the power value of each frequency point in the frequency domain information corresponding to each acquisition point, and determining the power sum of each acquisition point based on the power value of each frequency point;
in this embodiment, the power value is a representation of the signal strength. The power value of the frequency point refers to the average value of the instantaneous power of the frequency point in one acquisition time, and the power sum refers to the power sum of the frequency points in a single acquisition point.
Further, in the present embodiment, step b1 includes:
b11, determining the collection time of the frequency point corresponding to each collection point, and respectively integrating the instantaneous power of the frequency point of each collection point based on the collection time;
in this embodiment, the acquisition time of each acquisition point is determined, the voltage and current information of the corresponding frequency point is acquired at the same time, and the instantaneous power corresponding to each frequency point is integrated in any acquisition time interval.
It should be noted that the instantaneous power of a frequency point is the product of the corresponding instantaneous voltage and instantaneous current of the frequency point, and the instantaneous voltage and instantaneous current of the frequency point can be obtained from time domain information.
Step b12, calculating the integral result of the frequency point of each acquisition point, and determining the power value of the frequency point of each acquisition point based on the integral result and the acquisition time;
in this embodiment, the power value of the frequency point at each acquisition point is obtained by multiplying the reciprocal of the acquisition time by the integration result.
That is, the specific formula of the power value of the frequency point of each acquisition point is as follows:
wherein, P is the power value of each frequency point;
t: any period of acquisition time of the periodic signal or the non-periodic signal is acquired;
t: a certain moment of signal acquisition;
u (t): the voltage value of the signal at a certain moment;
i (t): the current value of the signal at a certain moment;
step b13, adding the power values of the frequency points of each acquisition point to obtain the power sum of each acquisition point.
Specifically, the power sum of each acquisition point has a specific formula as follows:
wherein, Ptotal: the power sum of all frequency points of a single acquisition point;
n: the number of the frequency points acquired by a single acquisition point;
pn: and the power value of the nth frequency point on a single acquisition point.
Step b2, respectively calculating the ratio of the power value of the frequency point corresponding to each acquisition point to the sum of the power of each acquisition point, and obtaining the characteristic value of the frequency point corresponding to each acquisition point.
In this embodiment, the frequency point characteristic value is a ratio of the power value of the frequency point corresponding to each acquisition point to the sum of the powers of the acquisition points.
Therefore, the calculation formula of the frequency point characteristic value of the frequency point corresponding to each acquisition point is as follows:
w is P/Ptotal
Wherein, w: and the frequency point characteristic value of the frequency point corresponding to the single acquisition point.
Step S30, determining a target characteristic value based on the frequency point characteristic value and a preset characteristic value, wherein the preset characteristic value is a corresponding characteristic value when no target object exists in the machine room;
in this embodiment, each acquisition point in the machine room acquires signals when there is a target object. When no target object exists in the machine room, a signal within the target frequency range also exists, so that the preset characteristic value can be acquired and calculated through the acquisition point under the condition of no target object. And respectively calculating the difference value between the frequency point characteristic value and the preset characteristic value of each acquisition point signal based on the frequency point characteristic value and the preset characteristic value, namely the target characteristic value.
And step S40, determining the target position of the target object in the machine room based on the target characteristic value.
In this embodiment, the target characteristic value of the signal is input into a preset algorithm to obtain a target coordinate value corresponding to the target characteristic value, so as to determine a target position of the target object in the machine room.
The preset algorithm mainly adopts an algorithm with supervised learning, such as Naive bayes (Naive Bayesian), K-Nearest Neighbors (KNN), Decision Trees (Decision Trees), neural networks, and the like, and for convenience of description, the K-Nearest Neighbors algorithm is taken as an example for description in this embodiment.
The training process of the K-nearest neighbor algorithm model comprises the following steps:
the positioning system collects various wireless signals in the machine room through the collection points, determines the training characteristic value of each collection point and the training position corresponding to the training characteristic value according to the steps of collecting the signals, then takes the training characteristic value as the input of the model, takes the training position as the output of the model, and trains the K-nearest neighbor algorithm model. In the training process, the training position is a real position and is determined in advance, and the accuracy of the model is adjusted by changing the value of K in the K-nearest neighbor algorithm, so that the K-nearest neighbor algorithm model is determined.
Therefore, when the target position of the target object is positioned, the corresponding target position can be obtained only by inputting the determined target characteristic value into a preset algorithm.
In the positioning method of the embodiment, corresponding frequency domain information is obtained by collecting time domain signals in a machine room and performing frequency domain conversion on the time domain signals based on a preset conversion rule; determining the power value of each frequency point in the frequency domain information, and determining the frequency point characteristic value of each frequency point; determining a target characteristic value based on the frequency point characteristic value and the preset characteristic value of each frequency point; and determining the target position of the target object in the machine room based on the target characteristic value. The invention collects the signal characteristics when the target object exists in the machine room and the signal characteristics when the target object does not exist, and positions the target position of the target object by comparing the signal characteristics when the target object exists or does not exist, thereby realizing the accurate positioning of the target object.
Further, based on the first embodiment of the positioning method of the present invention, a second embodiment of the positioning method of the present invention is provided.
The second embodiment of the positioning method is different from the first embodiment of the positioning method in that step S30 includes:
step c, respectively determining the difference value between the frequency point characteristic value corresponding to each acquisition point and a preset characteristic value to obtain the difference value characteristic value of each acquisition point;
and d, determining a target characteristic value corresponding to each acquisition point based on the signal intensity of the difference characteristic value of each acquisition point.
In order to further improve the positioning accuracy, the positioning method of this embodiment obtains the difference characteristic value of each acquisition point by respectively determining the difference between the frequency point characteristic value corresponding to each acquisition point and the preset characteristic value, and determines the target characteristic value corresponding to each acquisition point based on the signal strength of the difference characteristic value of each acquisition point.
The respective steps will be described in detail below:
and c, respectively determining the difference value between the frequency point characteristic value corresponding to each acquisition point and a preset characteristic value to obtain the difference value characteristic value of each acquisition point.
In this embodiment, the determined frequency point characteristic value is subtracted from the preset characteristic value to obtain a difference characteristic value, and the specific process is not described herein again.
And d, determining a target characteristic value corresponding to each acquisition point based on the signal intensity of the difference characteristic value of each acquisition point.
In this embodiment, to further obtain a more ideal target characteristic value, which is convenient for accurate positioning of a subsequent target position, after obtaining the difference characteristic value, normalization processing is performed on the difference characteristic value, specifically, by calculating the signal intensity of the difference characteristic value of each frequency point in each acquisition point and the total signal intensity corresponding to each acquisition point, a classification characteristic value of each frequency point is obtained, so as to determine the target characteristic value.
Specifically, step d includes:
d1, sequentially determining the signal intensity of the frequency point corresponding to the difference characteristic value of each acquisition point and the total signal intensity corresponding to the difference characteristic value of each acquisition point;
in this embodiment, the RSSI of the frequency point corresponding to each acquisition point is defined as follows:
RSSI＝10logP
step d2, respectively determining classification characteristic values of the acquisition points based on the signal intensity and the total signal intensity;
in this embodiment, the classification characteristic value of each frequency point in each acquisition point is a ratio of the signal intensity corresponding to each frequency point to the total signal intensity of the acquisition point where the frequency point is located.
After the signal intensity of each frequency point is calculated, similarly, the total signal intensity of each acquisition point has the following specific formula:
RSSIgeneral assembly＝10logPGeneral assembly
Therefore, the calculation formula of the classification characteristic value of the frequency point of each acquisition point is as follows:
w1 RSSI/RSSI total
Wherein, RSSI always: the total signal intensity of the frequency points of a single acquisition point;
w 1: and (4) classifying characteristic values of the frequency points of the single acquisition point.
And d3, screening classification characteristic values with the same characteristic values in all the collection points to obtain a target characteristic value.
In this embodiment, because signals in the machine room are complicated, if only the classification characteristic values acquired by a single acquisition point are analyzed, the target object cannot be accurately positioned effectively, and therefore, classification characteristic values with the same characteristic value need to be screened out by comparing a plurality of acquisition points, and the same classification characteristic value is used as the target characteristic value.
And finally, determining the target position of the target object based on the target characteristic value through a preset algorithm. It should be noted that, as the difference characteristic value is further normalized, the finally obtained target characteristic value is more converged, and when the target characteristic value is input into the preset algorithm, a more accurate target position can be obtained.
In this embodiment, after obtaining the difference between the frequency point characteristic value corresponding to each acquisition point and the preset characteristic value, that is, the difference characteristic value, the classification characteristic value corresponding to the frequency point is obtained by analyzing the frequency point signal intensity corresponding to the difference characteristic value and the total signal intensity of the acquisition point where the frequency point is located, so as to determine the target characteristic value of the frequency point, perform more deep processing and analysis on the acquired data, and further improve the accuracy of positioning the target object in the machine room.
Further, based on the first and second embodiments of the positioning method of the present invention, a third embodiment of the positioning method of the present invention is provided.
The third embodiment of the positioning method differs from the first and second embodiments of the positioning method in that step S40 includes:
and e, receiving the input correction parameters, and correcting the preset algorithm.
In this embodiment, although the preset algorithm is obtained through training of a large amount of data, there still exists a case that the coordinates of the target position obtained through the preset algorithm are not matched with the real target position, that is, the accuracy of the preset algorithm is not enough, and therefore, the preset algorithm needs to be corrected, and the target object is accurately positioned by continuously perfecting the algorithm model. The preset algorithm is corrected, the correction parameters input by a user can be received, and the value of K can be artificially changed by the K-nearest neighbor algorithm, so that the accuracy of positioning the target object is improved.
In the positioning method of this embodiment, under the condition that the target position coordinates obtained through the algorithm model are not matched with the real target position, correction parameters input by a user, such as target position coordinates output by an artificial change algorithm model, are received, further accurate positioning of the target position is realized in the implementation process, and the accuracy of positioning the target object in the machine room is improved.
The invention also provides a positioning device. The positioning device of the present invention comprises:
the acquisition conversion module is used for acquiring time domain signals in the machine room and carrying out frequency domain conversion on the time domain signals based on a preset conversion rule to obtain frequency domain information;
the first determining module is used for determining a power value of each frequency point in the frequency domain information and determining a frequency point characteristic value of each frequency point based on the power value;
a second determining module, configured to determine a target feature value based on the frequency point feature value and a preset feature value, where the preset feature value is a corresponding feature value when there is no target object in the machine room;
and the third determining module is used for determining the target position of the target object in the machine room based on the target characteristic value.
Further, the acquisition conversion module is further configured to:
determining at least two preset acquisition points in the machine room, and determining a target frequency range corresponding to the machine room;
respectively collecting time domain signals corresponding to the target frequency range in the machine room based on the collection points;
and respectively converting the time domain signals acquired by each acquisition point based on a preset conversion rule to obtain frequency domain information corresponding to each acquisition point.
Further, the first determining module is further configured to:
sequentially determining the power value of each frequency point in the frequency domain information corresponding to each acquisition point, and determining the power sum of each acquisition point based on the power value of each frequency point;
and respectively calculating the ratio of the power value of the frequency point corresponding to each acquisition point to the sum of the power of each acquisition point to obtain the characteristic value of the frequency point corresponding to each acquisition point.
Further, the step of sequentially determining the power value of each frequency point in the frequency domain information corresponding to each acquisition point, and determining the power sum of each acquisition point based on the power value of each frequency point includes:
determining the acquisition time of the frequency point corresponding to each acquisition point, and respectively integrating the instantaneous power of the frequency point of each acquisition point based on the acquisition time;
calculating an integral result of the frequency point of each acquisition point, and determining a power value of the frequency point of each acquisition point based on the integral result and the acquisition time;
and adding the power values of the frequency points of the acquisition points to obtain the power sum of the acquisition points.
Further, the second determining module is further configured to:
respectively determining the difference value between the frequency point characteristic value corresponding to each acquisition point and a preset characteristic value to obtain the difference value characteristic value of each acquisition point;
and determining a target characteristic value corresponding to each acquisition point based on the signal intensity of the difference characteristic value of each acquisition point.
Further, the second determining module is further configured to:
sequentially determining the signal intensity of the frequency point corresponding to the difference characteristic value of each acquisition point and the total signal intensity corresponding to the difference characteristic value of each acquisition point;
respectively determining classification characteristic values of the acquisition points based on the signal intensity and the total signal intensity;
and screening out classification characteristic values with the same characteristic value in all the acquisition points to obtain a target characteristic value.
Further, the third determining module is further configured to:
inputting the target characteristic value into a preset algorithm, so as to obtain a target coordinate value corresponding to the target characteristic value;
and determining the target position of the target object in the machine room based on the target coordinate value.
The invention also provides a computer readable storage medium.
The computer-readable storage medium of the present invention has stored thereon a positioning program, which when executed by a processor, implements the steps of the positioning method as described above.
The method implemented when the positioning program running on the processor is executed may refer to each embodiment of the positioning method of the present invention, and details are not described here.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system 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 system. 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 system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only an alternative embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes performed by the present specification and drawings, or applied directly or indirectly to other related technical fields, are included in the scope of the present invention.
Claims (8)
1. A positioning method, characterized in that the positioning method comprises the steps of:
collecting time domain signals in a machine room, and performing frequency domain conversion on the time domain signals based on a preset conversion rule to obtain frequency domain information;
determining a power value of each frequency point in the frequency domain information, and determining a frequency point characteristic value of each frequency point based on the power value;
determining a target characteristic value based on the frequency point characteristic value and a preset characteristic value, wherein the preset characteristic value is a corresponding characteristic value when no target object exists in the machine room;
determining a target position of a target object in the machine room based on the target characteristic value;
wherein the step of determining a target characteristic value based on the frequency point characteristic value and a preset characteristic value comprises:
respectively determining the difference value between the frequency point characteristic value corresponding to each acquisition point and a preset characteristic value to obtain the difference value characteristic value of each acquisition point;
sequentially determining the signal intensity of the frequency point corresponding to the difference characteristic value of each acquisition point and the total signal intensity corresponding to the difference characteristic value of each acquisition point;
respectively determining classification characteristic values of the acquisition points based on the signal intensity and the total signal intensity;
and screening out classification characteristic values with the same characteristic value in all the acquisition points to obtain a target characteristic value.
2. The positioning method according to claim 1, wherein the step of acquiring the time domain signal in the machine room and performing frequency domain conversion on the time domain signal based on a preset conversion rule to obtain frequency domain information comprises:
determining at least two preset acquisition points in the machine room, and determining a target frequency range corresponding to the machine room;
respectively acquiring time domain signals corresponding to the target frequency range in the machine room based on the acquisition points;
and respectively converting the time domain signals acquired by each acquisition point based on a preset conversion rule to obtain frequency domain information corresponding to each acquisition point.
3. The method according to claim 2, wherein the step of determining the power value of each frequency point in the frequency domain information and determining the frequency point characteristic value of each frequency point based on the power value comprises:
sequentially determining the power value of each frequency point in the frequency domain information corresponding to each acquisition point, and determining the power sum of each acquisition point based on the power value of each frequency point;
and respectively calculating the ratio of the power value of the frequency point corresponding to each acquisition point to the sum of the power of each acquisition point to obtain the characteristic value of the frequency point corresponding to each acquisition point.
4. The method according to claim 3, wherein the step of sequentially determining the power value of each frequency point in the frequency domain information corresponding to each acquisition point, and determining the power sum of each acquisition point based on the power value of each frequency point comprises:
determining the acquisition time of the frequency point corresponding to each acquisition point, and respectively integrating the instantaneous power of the frequency point of each acquisition point based on the acquisition time;
calculating an integral result of the frequency point of each acquisition point, and determining a power value of the frequency point of each acquisition point based on the integral result and the acquisition time;
and adding the power values of the frequency points of the acquisition points to obtain the power sum of the acquisition points.
5. The positioning method according to claim 1, wherein the step of determining the target position of the target object in the machine room based on the target feature value comprises:
inputting the target characteristic value into a preset algorithm, so as to obtain a target coordinate value corresponding to the target characteristic value;
and determining the target position of the target object in the machine room based on the target coordinate value.
6. A positioning device, comprising:
the acquisition conversion module is used for acquiring time domain signals in the machine room and carrying out frequency domain conversion on the time domain signals based on a preset conversion rule to obtain frequency domain information;
the first determining module is used for determining a power value of each frequency point in the frequency domain information and determining a frequency point characteristic value of each frequency point based on the power value;
a second determining module, configured to determine a target feature value based on the frequency point feature value and a preset feature value, where the preset feature value is a corresponding feature value when there is no target object in the machine room;
the third determining module is used for determining the target position of the target object in the machine room based on the target characteristic value;
the second determining module is further configured to determine difference values between the frequency point characteristic values corresponding to the acquisition points and preset characteristic values respectively to obtain difference value characteristic values of the acquisition points;
sequentially determining the signal intensity of the frequency point corresponding to the difference characteristic value of each acquisition point and the total signal intensity corresponding to the difference characteristic value of each acquisition point;
respectively determining classification characteristic values of the acquisition points based on the signal strength and the total signal strength;
and screening out classification characteristic values with the same characteristic value in all the acquisition points to obtain a target characteristic value.
7. A positioning system, characterized in that the positioning system comprises: memory, a processor and a positioning program stored on the memory and executable on the processor, the positioning program when executed by the processor implementing the steps of the positioning method according to any of claims 1 to 5.
8. A computer-readable storage medium, characterized in that a positioning program is stored on the computer-readable storage medium, which positioning program, when executed by a processor, carries out the steps of the positioning method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010702048.2A CN111885702B (en) | 2020-07-20 | 2020-07-20 | Positioning method, device, system and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010702048.2A CN111885702B (en) | 2020-07-20 | 2020-07-20 | Positioning method, device, system and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111885702A CN111885702A (en) | 2020-11-03 |
| CN111885702B true CN111885702B (en) | 2022-06-03 |
Family
ID=73155137
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010702048.2A Active CN111885702B (en) | 2020-07-20 | 2020-07-20 | Positioning method, device, system and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111885702B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104780606A (en) * | 2015-03-30 | 2015-07-15 | 南京邮电大学 | Indoor positioning system and method based on WLAN (wireless local area network) |
| CN110769370A (en) * | 2019-10-25 | 2020-02-07 | 中山大学 | Indoor positioning method based on signal fusion of directional antenna and omnidirectional antenna |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5999131A (en) * | 1997-07-01 | 1999-12-07 | Information Systems Laboratories, Inc. | Wireless geolocation system |
| CN101576616A (en) * | 2008-05-06 | 2009-11-11 | 广州香港科大研究开发有限公司 | Indoor positioning system based on RFID technology |
| CN104535962B (en) * | 2014-12-24 | 2017-07-11 | 北京奇虎科技有限公司 | Indoor orientation method and indoor locating system |
| CN107678051A (en) * | 2016-08-01 | 2018-02-09 | 华为技术服务有限公司 | The method and relevant device of a kind of positioning |
| CN108024328A (en) * | 2016-11-04 | 2018-05-11 | 中兴通讯股份有限公司 | A kind of wireless location method, device and base station |
| CN107346014A (en) * | 2017-06-09 | 2017-11-14 | 宇龙计算机通信科技(深圳)有限公司 | A kind of localization method, device and terminal |
| CN109901107A (en) * | 2019-03-07 | 2019-06-18 | 西安电子科技大学 | A kind of time difference positioning method, device, computer equipment and readable storage medium storing program for executing |
-
2020
- 2020-07-20 CN CN202010702048.2A patent/CN111885702B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104780606A (en) * | 2015-03-30 | 2015-07-15 | 南京邮电大学 | Indoor positioning system and method based on WLAN (wireless local area network) |
| CN110769370A (en) * | 2019-10-25 | 2020-02-07 | 中山大学 | Indoor positioning method based on signal fusion of directional antenna and omnidirectional antenna |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111885702A (en) | 2020-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hsieh et al. | Deep learning-based indoor localization using received signal strength and channel state information | |
| US11902857B2 (en) | Handling concept drift in Wi-Fi-based localization | |
| JP7154295B2 (en) | Motion detection based on machine learning of radio signal characteristics | |
| Kosba et al. | RASID: A robust WLAN device-free passive motion detection system | |
| Khan et al. | A deep learning framework using passive WiFi sensing for respiration monitoring | |
| US20240089740A1 (en) | System, method, and apparatus for providing dynamic, prioritized spectrum management and utilization | |
| US20210176120A1 (en) | Fine grained network management to edge device features | |
| US11849332B2 (en) | System, method, and apparatus for providing dynamic, prioritized spectrum management and utilization | |
| WO2020227806A1 (en) | Determining a confidence for a motion zone identified as a location of motion for motion detected by wireless signals | |
| CN111935820B (en) | Positioning implementation method based on wireless network and related equipment | |
| Samadh et al. | Indoor localization based on channel state information | |
| US20190302221A1 (en) | Fog-based internet of things (iot) platform for real time locating systems (rtls) | |
| Zhao et al. | Block-sparse coding-based machine learning approach for dependable device-free localization in IoT environment | |
| Liu et al. | A sensor-free crowd counting framework for indoor environments based on channel state information | |
| KR102469664B1 (en) | Anomaly detection method and system | |
| CN111885702B (en) | Positioning method, device, system and computer readable storage medium | |
| Xie et al. | Weight-aware sensor deployment in wireless sensor networks for smart cities | |
| CN115665852B (en) | Indoor positioning method, device, equipment and storage medium | |
| Careem et al. | Wirelessly indoor positioning system based on RSS Signal | |
| CN107798854A (en) | A kind of ammeter long-distance monitoring method based on image recognition | |
| CN115002703A (en) | Passive indoor people number detection method based on Wi-Fi channel state information | |
| Natarajan et al. | A machine learning approach to passive human motion detection using WiFi measurements from commodity IoT devices | |
| CN110991566B (en) | Method and device for diagnosing fault of wind driven generator in information fusion mode | |
| Han et al. | Device-free localization via sparse coding with log-regularizer | |
| Pipelidis et al. | Cross-device radio map generation via crowdsourcing |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |