CN117939631A - Self-adaptive object positioning method and device - Google Patents
Self-adaptive object positioning method and device Download PDFInfo
- Publication number
- CN117939631A CN117939631A CN202410146467.0A CN202410146467A CN117939631A CN 117939631 A CN117939631 A CN 117939631A CN 202410146467 A CN202410146467 A CN 202410146467A CN 117939631 A CN117939631 A CN 117939631A
- Authority
- CN
- China
- Prior art keywords
- preset
- information
- model
- signal intensity
- communication device
- 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
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
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/391—Modelling the propagation channel
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/391—Modelling the propagation channel
- H04B17/3912—Simulation models, e.g. distribution of spectral power density or received signal strength indicator [RSSI] for a given geographic region
-
- 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
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Electromagnetism (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention relates to the technical field of wireless sensing, and discloses a self-adaptive object positioning method and device, wherein the method comprises the following steps: acquiring first signal intensity information of communication between a measured object and at least one first communication device; inputting all the first signal intensity information into a preset information processing model set to obtain first attribute information of the measured object, wherein the first attribute information comprises position information, the preset information processing model set meets preset model training convergence conditions and comprises a preset signal intensity filtering model, a preset channel calculation model and a preset regression model, the preset signal intensity filtering model is used for executing preset filtering processing operation on all the first signal intensity information, the preset channel calculation model is used for simulating a channel environment of communication between the measured object and each first communication device, and the preset regression model is used for simulating the environment of the position of each first communication device. Therefore, the invention can improve the accuracy of object positioning.
Description
Technical Field
The invention relates to the technical field of wireless sensing, in particular to a self-adaptive object positioning method and device.
Background
With the continuous development of technology, more and more points of objects without positioning devices can be perceived through the radio frequency identification technology, and the flexibility of user perception of everything is improved.
In the existing radio frequency identification technology, three-point positioning methods are mostly adopted to position the point position of the measured object, namely, the point position of the measured object is determined through the point positions of three known points, however, for the three-point positioning methods, the solution space is often an area instead of an accurate point position, if the accurate point position is further determined, the point position of the measured object is determined, the centroid in the area is usually taken as the point position of the measured object, namely, the contribution degree of the three known points in the implicit three-point positioning method to the point position positioning of the measured object is the same, the difference between different known points is ignored, and the point position determination accuracy of the measured object is reduced.
It is important to provide a technical scheme for improving the positioning accuracy of the object.
Disclosure of Invention
The invention provides a self-adaptive object positioning method and device, which can be beneficial to object positioning accuracy.
In order to solve the technical problem, a first aspect of the present invention discloses a self-adaptive object positioning method, which includes:
acquiring first signal intensity information of communication between a measured object and at least one first communication device;
Inputting all the first signal intensity information into a preset information processing model set to obtain first attribute information of the measured object, wherein the first attribute information comprises position information, the preset information processing model set meets preset model training convergence conditions, the preset information processing model set comprises a preset signal intensity filtering model, a preset channel calculation model and a preset regression model, the preset signal intensity filtering model is used for executing preset filtering processing operation on all the first signal intensity information, the preset channel calculation model is used for simulating channel environments of communication between the measured object and each first communication device, and the preset regression model is used for simulating environments of positions of each first communication device.
In a first aspect of the present invention, the inputting all the first signal strength information into a preset information processing model set to obtain first attribute information of the measured object includes:
Inputting all the first signal intensity information into the preset signal intensity filtering model to obtain target signal intensity information;
inputting the target signal intensity information into the preset channel calculation model to obtain target distance information between the measured object and each first communication device;
And inputting the target signal intensity information and the target distance information into the preset regression model to obtain first attribute information of the measured object.
As an optional implementation manner, in the first aspect of the present invention, the preset signal strength filtering model is:
Wherein RSSI out is used to represent the target signal strength information, maxpooling is used to represent a max-pooling operation, A convolution kernel for representing the preset signal strength filtering model, b CNN for representing the bias of the convolution kernel, and RSSI in for representing a first matrix including a second matrix composed of the first signal strength information obtained by communication between the measured object and each of the first communication devices, anΗ is used to represent the total number of the first communication devices, andThe second matrix representing the ith of the first communication devices, anThe RSSI im is used to represent the mth first signal strength information of the communication between the measured object and the ith first communication device.
As an optional implementation manner, in the first aspect of the present invention, the preset channel calculation model is:
ym＝w2*tanh(w1*RSSIout+b1)+b2
Wherein y m is used to represent the target distance information, tanh () is used to represent a nonlinear activation function, the nonlinear activation function is used to perform a nonlinear transformation operation, w 1 is used to represent a first weight parameter of the preset channel calculation model, w 2 is used to represent a second weight parameter of the preset channel calculation model, b 1 is used to represent a first bias of the preset channel calculation model, and b 2 is used to represent a second bias of the preset channel calculation model.
As an optional implementation manner, in the first aspect of the present invention, the preset regression model is:
yout＝wout*x+bout
Wherein y out is used to represent first attribute information of the object under test, w out is used to represent an output weight parameter of the preset regression model, b out is used to represent an output bias of the preset regression model, x= [ RSSI out,ym,r1,...rη ], and r η＝(rxη,ryη) is used to represent a first real coordinate of an eta first communication device under a first preset coordinate system, rx η is used to represent an abscissa of the eta first communication device under the first preset coordinate system, and ry η is used to represent an ordinate of the eta first communication device under the first preset coordinate system.
As an optional implementation manner, in the first aspect of the present invention, the training step of the preset information processing model set includes:
for each target object in the target environment, determining a target identifier of the target object according to second attribute information of the target object; determining second signal strength information of communication between the target object and each second communication device according to the target identifier; determining the second signal strength information, the second attribute information of the target object and the third attribute information of each of the second communication devices as a first information set of the target object;
For each first information set, executing a preprocessing operation corresponding to the preset processing conditions on the first information set according to the preset processing conditions to obtain a second information set of the first information set;
dividing all the second information sets into a training sample data set and a test sample data set according to preset cross-validation conditions;
inputting each training sample data in the training sample data set into an original information processing model set according to a preset training condition to obtain first prediction attribute information of each training sample data and a preparation information processing model set corresponding to the original information processing model set;
Judging whether the preparation information processing model set meets a preset verification condition or not according to all the first prediction attribute information, and inputting each test sample data in the test sample data set into the preparation information processing model set according to the preset verification condition when judging that the preparation information processing model set meets the preset verification condition to obtain second prediction attribute information of each test sample data;
And judging whether the preparation information processing model set meets the preset model training convergence condition according to all the second prediction attribute information, and determining the preparation information processing model set as the preset information processing model set when judging that the preparation information processing model set meets the preset model training convergence condition.
As an optional implementation manner, in the first aspect of the present invention, the preset verification condition and the preset model training convergence condition include preset loss function convergence, where the preset loss function is:
Wherein y is used for representing a second real coordinate of the target object under a second preset coordinate system, d is used for representing a real distance between the target object and each second communication device, y my is used for representing predicted distance information between the target object and each second communication device, |w out|、|w2 |, Is a regularization parameter;
when the preset loss function is used for verifying whether the set of the preparation information processing models meets a preset verification condition, y outy is used for representing the first prediction attribute information;
And when the preset loss function is used for verifying whether the set of the preparation information processing models meets a preset model training convergence condition, y outy is used for representing the second prediction attribute information.
In a second aspect, the invention discloses an adaptive object positioning device, the device comprising:
the acquisition module is used for acquiring first signal intensity information of communication between the measured object and at least one first communication device;
The processing module is used for inputting all the first signal intensity information into a preset information processing model set to obtain first attribute information of the measured object, the first attribute information comprises position information, the preset information processing model set meets preset model training convergence conditions, the preset information processing model set comprises a preset signal intensity filtering model, a preset channel calculation model and a preset regression model, the preset signal intensity filtering model is used for executing preset filtering processing operation on all the first signal intensity information, the preset channel calculation model is used for simulating a channel environment of communication between the measured object and each first communication device, and the preset regression model is used for simulating the environment of the position where each first communication device is located.
In a second aspect of the present invention, as an optional implementation manner, the specific manner of obtaining the first attribute information of the measured object by the processing module inputting all the first signal strength information into a preset information processing model set includes:
Inputting all the first signal intensity information into the preset signal intensity filtering model to obtain target signal intensity information;
inputting the target signal intensity information into the preset channel calculation model to obtain target distance information between the measured object and each first communication device;
And inputting the target signal intensity information and the target distance information into the preset regression model to obtain first attribute information of the measured object.
As an optional implementation manner, in the second aspect of the present invention, the preset signal strength filtering model is:
Wherein RSSI out is used to represent the target signal strength information, maxpooling is used to represent a max-pooling operation, A convolution kernel for representing the preset signal strength filtering model, b CNN for representing the bias of the convolution kernel, and RSSI in for representing a first matrix including a second matrix composed of the first signal strength information obtained by communication between the measured object and each of the first communication devices, anΗ is used to represent the total number of the first communication devices, andThe second matrix representing the ith of the first communication devices, anThe RSSI im is used to represent the mth first signal strength information of the communication between the measured object and the ith first communication device.
As an optional implementation manner, in the second aspect of the present invention, the preset channel calculation model is:
ym＝w2*tanh(w1*RSSIout+b1)+b2
Wherein y m is used to represent the target distance information, tanh () is used to represent a nonlinear activation function, the nonlinear activation function is used to perform a nonlinear transformation operation, w 1 is used to represent a first weight parameter of the preset channel calculation model, w 2 is used to represent a second weight parameter of the preset channel calculation model, b 1 is used to represent a first bias of the preset channel calculation model, and b 2 is used to represent a second bias of the preset channel calculation model.
As an optional implementation manner, in the second aspect of the present invention, the preset regression model is:
yout＝wout*x+bout
Wherein y out is used to represent first attribute information of the object under test, w out is used to represent an output weight parameter of the preset regression model, b out is used to represent an output bias of the preset regression model, x= [ RSSI out,ym,r1,...rη ], and r η＝(rxη,ryη) is used to represent a first real coordinate of an eta first communication device under a first preset coordinate system, rx η is used to represent an abscissa of the eta first communication device under the first preset coordinate system, and ry η is used to represent an ordinate of the eta first communication device under the first preset coordinate system.
As an optional implementation manner, in the second aspect of the present invention, the training step of the preset information processing model set includes:
for each target object in the target environment, determining a target identifier of the target object according to second attribute information of the target object; determining second signal strength information of communication between the target object and each second communication device according to the target identifier; determining the second signal strength information, the second attribute information of the target object and the third attribute information of each of the second communication devices as a first information set of the target object;
For each first information set, executing a preprocessing operation corresponding to the preset processing conditions on the first information set according to the preset processing conditions to obtain a second information set of the first information set;
dividing all the second information sets into a training sample data set and a test sample data set according to preset cross-validation conditions;
inputting each training sample data in the training sample data set into an original information processing model set according to a preset training condition to obtain first prediction attribute information of each training sample data and a preparation information processing model set corresponding to the original information processing model set;
Judging whether the preparation information processing model set meets a preset verification condition or not according to all the first prediction attribute information, and inputting each test sample data in the test sample data set into the preparation information processing model set according to the preset verification condition when judging that the preparation information processing model set meets the preset verification condition to obtain second prediction attribute information of each test sample data;
And judging whether the preparation information processing model set meets the preset model training convergence condition according to all the second prediction attribute information, and determining the preparation information processing model set as the preset information processing model set when judging that the preparation information processing model set meets the preset model training convergence condition.
As an optional implementation manner, in the second aspect of the present invention, the preset verification condition and the preset model training convergence condition include preset loss function convergence, where the preset loss function is:
Wherein y is used for representing a second real coordinate of the target object under a second preset coordinate system, d is used for representing a real distance between the target object and each second communication device, y my is used for representing predicted distance information between the target object and each second communication device, |w out|、|w2 |, Is a regularization parameter;
when the preset loss function is used for verifying whether the set of the preparation information processing models meets a preset verification condition, y outy is used for representing the first prediction attribute information;
And when the preset loss function is used for verifying whether the set of the preparation information processing models meets a preset model training convergence condition, y outy is used for representing the second prediction attribute information.
In a third aspect, the invention discloses another adaptive object positioning device, said device comprising:
A memory storing executable program code;
A processor coupled to the memory;
the processor invokes the executable program code stored in the memory to perform the adaptive object positioning method disclosed in the first aspect of the present invention.
A fourth aspect of the invention discloses a computer storage medium storing computer instructions which, when invoked, are adapted to carry out the adaptive object positioning method disclosed in the first aspect of the invention.
Compared with the prior art, the embodiment of the invention has the following beneficial effects:
In the embodiment of the invention, first signal intensity information of communication between a measured object and at least one first communication device is obtained; inputting all the first signal intensity information into a preset information processing model set to obtain first attribute information of the measured object, wherein the first attribute information comprises position information, the preset information processing model set meets preset model training convergence conditions, the preset information processing model set comprises a preset signal intensity filtering model, a preset channel calculation model and a preset regression model, the preset signal intensity filtering model is used for executing preset filtering processing operation on all the first signal intensity information, the preset channel calculation model is used for simulating a channel environment of communication between the measured object and each first communication device, and the preset regression model is used for simulating an environment of a position where each first communication device is located. Therefore, the method and the device can determine the position information of the measured object based on the acquired first signal intensity information communicated between the measured object and at least one first communication device and the preset signal intensity filtering model, the preset channel calculation model and the preset regression model in the preset information model set meeting the preset model training convergence condition, can fully combine the channel environment communicated between the measured object and each first communication device and the environment where each first communication device is located, and improve the positioning accuracy of the measured object.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an adaptive object positioning method according to an embodiment of the present invention;
FIG. 2 is a schematic structural view of an adaptive object positioning apparatus according to an embodiment of the present invention;
FIG. 3 is a schematic structural view of yet another adaptive object positioning apparatus according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a configuration of a set of preset information processing models according to an embodiment of the present invention;
fig. 5 is a schematic view of a deployment scenario of a preset information processing model set according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terms first, second and the like in the description and in the claims and in the above-described figures are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, apparatus, article, or article that comprises a list of steps or elements is not limited to only those listed but may optionally include other steps or elements not listed or inherent to such process, method, article, or article.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the invention. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
The invention discloses a self-adaptive object positioning method and a self-adaptive object positioning device, which can determine the position information of an object to be measured based on acquired first signal intensity information communicated between the object to be measured and at least one first communication device and a preset signal intensity filtering model, a preset channel calculation model and a preset regression model in a preset information model set which meet preset model training convergence conditions, can fully combine the channel environment communicated between the object to be measured and each first communication device and the environment where each first communication device is located, and improve the positioning accuracy of the object to be measured. The following will describe in detail.
Example 1
Referring to fig. 1, fig. 1 is a flow chart of a method for positioning an adaptive object according to an embodiment of the invention. The adaptive object positioning method described in fig. 1 may be applied to a positioning device, or may be applied to a satellite device, or may be applied to an intelligent device associated with the positioning device and/or the satellite device, where the association may refer to an electrical connection, a wireless connection, an indirect connection, an attachment, etc., and the intelligent device may include, but is not limited to, one or more of a cloud device, an edge computing device, a relay device, a base station device, an intelligent home device, a city management device, and an intelligent networking device. As shown in fig. 1, the adaptive object positioning method may include the following operations:
101. first signal strength information of communication between the object to be measured and at least one first communication device is acquired.
In an embodiment of the present invention, optionally, the obtaining the first signal strength information of the communication between the measured object and the at least one first communication device may include the following operations:
For each first communication device, determining identification information of the object to be tested; determining a first sensing signal according to the identification information, sending the first sensing signal to the azimuth of the identification information, and receiving a second sensing signal, wherein the second sensing signal is a feedback signal of the first sensing signal; first signal strength information of communication between the object to be measured and the first communication device is determined according to the first sensing signal and the second sensing signal.
In this optional embodiment, optionally, the identification information may be at least one of an electronic tag, a trademark of a measured object, a size, a shape, a material, a weight, a color, a smoothness, a transmittance, a radiance, and the like.
In this optional embodiment, optionally, the azimuth of the identification information may or may not include the azimuth of the measured object relative to the first communication device.
Therefore, by implementing the alternative embodiment, the first sensing signal can be determined according to the identification information of the detected object, so that the first sensing signal is sent to the direction where the identification information is located, the second sensing signal is received, and further, the first signal intensity information between the detected object and the first communication equipment is determined according to the first sensing signal and the second sensing signal, and the determination flexibility of the first signal intensity information can be further improved on the basis of improving the determination accuracy of the first signal intensity information.
102. Inputting all the first signal intensity information into a preset information processing model set to obtain first attribute information of the measured object, wherein the first attribute information comprises position information, the preset information processing model set meets preset model training convergence conditions, the preset information processing model set comprises a preset signal intensity filtering model, a preset channel calculation model and a preset regression model, the preset signal intensity filtering model is used for executing preset filtering processing operation on all the first signal intensity information, the preset channel calculation model is used for simulating a channel environment of communication between the measured object and each first communication device, and the preset regression model is used for simulating an environment of a position where each first communication device is located.
In the embodiment of the present invention, the first attribute information may further include the identification information.
In an embodiment of the present invention, optionally, the preset signal strength filtering model may include a convolution layer and a maximum pooling layer as shown in fig. 4. In fig. 4, the first communication device is limited to a base station device, and may include, but not limited to, a mobile phone, a PC, a game machine, a vehicle-mounted intelligent network device, and the like. And, in fig. 4, all the first signal strength information in the embodiment of the present invention corresponds to the "preprocessed positioning data set" in fig. 4, the preset signal strength filtering model in the embodiment of the present invention corresponds to the RSSI filtering network in fig. 4, the preset channel calculation model in the embodiment of the present invention corresponds to the channel transmission calculation model in fig. 4, and the preset regression model in the embodiment of the present invention corresponds to the linear regression model in fig. 4.
Therefore, by implementing the embodiment of the invention, the position information of the measured object can be determined based on the acquired first signal intensity information communicated between the measured object and at least one first communication device and the preset signal intensity filtering model, the preset channel calculation model and the preset regression model which meet the preset model training convergence condition in the preset information model set, the channel environment communicated between the measured object and each first communication device and the environment where each first communication device is located can be fully combined, and the positioning accuracy of the measured object is improved.
In an embodiment of the present invention, as an optional implementation manner, the inputting all the first signal strength information into the preset information processing model set to obtain the first attribute information of the measured object may include the following operations:
and inputting all the first signal intensity information into a preset signal intensity filtering model to obtain target signal intensity information.
And inputting the target signal intensity information into a preset channel calculation model to obtain target distance information between the measured object and each first communication device.
And inputting the target signal intensity information and the target distance information into a preset regression model to obtain first attribute information of the measured object.
It can be seen that implementing the alternative embodiment discloses a model architecture of a preset information processing model set, by inputting all the first signal intensity information into a preset signal intensity filtering model, target signal intensity information can be obtained, so that the target signal intensity information is input into a preset channel calculation model, target distance information between a measured object and each first communication device is obtained, and then the target signal intensity information and the target distance information are input into a preset regression model, so that first attribute information of the measured object is obtained, and different functions of the preset signal intensity filtering model, the preset channel calculation model and the preset regression model can be combined through a specific model architecture, so that object positioning accuracy is further improved.
In this optional embodiment, as an optional implementation manner, the preset signal strength filtering model is:
Wherein RSSI out is used to represent target signal strength information, maxpooling is used to represent maximum pooling operations, Convolution kernel for representing a preset signal strength filtering model, b CNN for representing bias of the convolution kernel, RSSI in for representing a first matrix comprising a second matrix composed of first signal strength information obtained by communication between the measured object and each first communication device, andΗ is used to denote the total number of first communication devices,A second matrix for representing the ith first communication device, anThe RSSI im is used to represent the mth first signal strength information of the communication between the measured object and the ith first communication device.
Therefore, the implementation of the alternative embodiment discloses a model framework of a preset signal strength filtering model, which can improve the accuracy of determining the target signal strength information by specifically carrying out convolution processing and maximum pooling operation processing on the signal strength information, and is beneficial to improving the accuracy of determining the subsequent target distance information and the accuracy of determining the position information of the measured object.
In this optional embodiment, as another optional implementation manner, the preset channel calculation model is:
ym＝w2*tanh(w1*RSSIout+b1)+b2
Wherein y m is used to represent target distance information, tanh () is used to represent a nonlinear activation function, the nonlinear activation function is used to perform nonlinear transformation operation, w 1 is used to represent a first weight parameter of a preset channel calculation model, w 2 is used to represent a second weight parameter of the preset channel calculation model, b 1 is used to represent a first bias of the preset channel calculation model, and b 2 is used to represent a second bias of the preset channel calculation model.
It can be seen that implementing the alternative embodiment discloses a model architecture of a preset channel calculation model, and the channel environment of communication between the measured object and each first communication device can be simulated through the trained preset channel calculation model, so that the influence of channel interference on the positioning of the measured object is synthesized, the accuracy of determining the target distance information is improved, and further the combination of the target signal intensity information and the preset regression model is facilitated, and the accuracy of determining the position information of the measured object is improved.
In this alternative embodiment, as a further alternative implementation manner, the preset regression model is:
yout＝wout*x+bout
Wherein y out is used for representing first attribute information of the object to be measured, w out is used for representing output weight parameters of a preset regression model, b out is used for representing output bias of the preset regression model, x= [ RSSI out,ym,r1,...rη ], and r η＝(rxη,ryη) is used for representing first real coordinates of an eta first communication device in a first preset coordinate system, rx η is used for representing abscissa coordinates of the eta first communication device in the first preset coordinate system, and ry η is used for representing ordinate coordinates of the eta first communication device in the first preset coordinate system.
It can be seen that implementing the alternative embodiment discloses a model architecture of a preset regression model, and the environment where each first communication device is located can be simulated through the trained preset regression model, so that the contribution weights of different first communication devices to the measured object can be determined adaptively, and the accuracy of determining the position information of the measured object can be improved by combining the target signal intensity information and the target distance information.
In an optional embodiment, the training step of the preset information processing model set includes:
for each target object in the target environment, determining a target identifier of the target object according to second attribute information of the target object; determining second signal strength information of communication between the target object and each second communication device according to the target identification; the second signal strength information, the second attribute information of the target object, and the third attribute information of each second communication device are determined as the first information set of the target object.
And for each first information set, executing a preprocessing operation corresponding to the preset processing condition on the first information set according to the preset processing condition to obtain a second information set of the first information set.
And dividing all the second information sets into a training sample data set and a test sample data set according to preset cross-validation conditions.
According to preset training conditions, each training sample data in the training sample data set is input into the original information processing model set, and first prediction attribute information of each training sample data and a preparation information processing model set corresponding to the original information processing model set are obtained.
Judging whether the preparation information processing model set meets the preset verification conditions or not according to all the first prediction attribute information, and inputting each test sample data in the test sample data set into the preparation information processing model set according to the preset verification conditions when judging that the preparation information processing model set meets the preset verification conditions to obtain second prediction attribute information of each test sample data.
And judging whether the set of the preparation information processing models meets the preset model training convergence condition according to all the second prediction attribute information, and determining the set of the preparation information processing models as the set of the preset information processing models when judging that the set of the preparation information processing models meets the preset model training convergence condition.
In this alternative embodiment, the first set of information includes, but is not limited to, location information of the second communication device, location information of the target object relative to the second communication device, target identification, and second signal strength information. Specifically, the method can be obtained by performing a preset calculation processing operation on the second signal strength information, the second attribute information of the target object and the third attribute information of each second communication device.
Optionally, the preprocessing operation may include, but is not limited to, at least one of data normalization, deletion of missing values, and the like.
Further optionally, the preset cross-validation conditions may include, but are not limited to, at least one of 5-fold cross-validation and 10-fold cross-validation, and specifically, the number of cross-validation may be determined according to an actual application scenario, which is not specifically limited in the embodiment of the present invention.
It can be seen that implementing the optional embodiment discloses a training step of a preset information processing model set, so that accuracy of implementing corresponding application functions of a preset signal strength filtering model, a preset channel calculation model and a preset regression model in the preset information processing model set can be improved, and accuracy of positioning a measured object is improved.
In another optional embodiment, the preset verification condition and the preset model training convergence condition include preset loss function convergence, where the preset loss function is:
Wherein y is used for representing second real coordinates of the target object under a second preset coordinate system, d is used for representing real distance of communication between the target object and each second communication device, y my is used to represent the predicted distance information of the target object from each second communication device, |w out|、|w2 |, Is a regularization parameter.
When the preset loss function is used for verifying whether the set of preliminary information processing models satisfies the preset verification condition, y outy is used for representing the first prediction attribute information.
When the preset loss function is used for verifying whether the set of the preparation information processing models meets the preset model training convergence condition, y outy is used for representing the second prediction attribute information.
Therefore, the implementation of the optional embodiment can determine the preset loss function through the preset information processing model set, so as to verify whether the preset verification condition is met by the preset information processing model set and whether the preset model training convergence condition is met by the preset information processing model set, thereby further improving the accuracy of realizing the corresponding application function by the preset signal intensity filtering model, the preset channel calculation model and the preset regression model in the preset information processing model set and improving the accuracy of positioning the measured object.
In yet another alternative embodiment, as shown in fig. 5, the preset information processing model set in the embodiment of the present invention corresponds to the positioning model of the server in fig. 5, that is, the preset information processing model set may be deployed on the server, and optionally, the server is electrically connected to the first communication device in a wired manner or wirelessly connected to the first communication device, so that wireless channel communication is implemented through the identification information, where the identification information corresponds to the RFID tag in fig. 5.
Example two
Referring to fig. 2, fig. 2 is a schematic structural diagram of an adaptive object positioning device according to an embodiment of the invention. The adaptive object positioning apparatus described in fig. 2 may be applied to a positioning device, or may be applied to a satellite device, or may be applied to an intelligent device associated with the positioning device and/or the satellite device, where the association may refer to an electrical connection, a wireless connection, an indirect connection, an attachment, etc., and the intelligent device may include, but is not limited to, one or more of a cloud device, an edge computing device, a relay device, a base station device, an intelligent home device, a city management device, and an intelligent networking device. As shown in fig. 2, the adaptive object positioning apparatus may include:
an acquisition module 201 is configured to acquire first signal strength information of communication between the object to be measured and at least one first communication device.
The processing module 202 is configured to input all the first signal strength information into a preset information processing model set, to obtain first attribute information of the object to be measured, where the first attribute information includes location information, and the preset information processing model set satisfies a preset model training convergence condition, and the preset information processing model set includes a preset signal strength filtering model, a preset channel computing model, and a preset regression model, where the preset signal strength filtering model is used to perform a preset filtering operation on all the first signal strength information, and the preset channel computing model is used to simulate a channel environment of communication between the object to be measured and each first communication device, and the preset regression model is used to simulate an environment where each first communication device is located.
Therefore, by implementing the embodiment of the invention, the position information of the measured object can be determined based on the acquired first signal intensity information communicated between the measured object and at least one first communication device and the preset signal intensity filtering model, the preset channel calculation model and the preset regression model which meet the preset model training convergence condition in the preset information model set, the channel environment communicated between the measured object and each first communication device and the environment where each first communication device is located can be fully combined, and the positioning accuracy of the measured object is improved.
In this embodiment of the present invention, as an optional implementation manner, the specific manner in which the processing module 202 inputs all the first signal intensity information into the preset information processing model set to obtain the first attribute information of the measured object includes:
and inputting all the first signal intensity information into a preset signal intensity filtering model to obtain target signal intensity information.
And inputting the target signal intensity information into a preset channel calculation model to obtain target distance information between the measured object and each first communication device.
And inputting the target signal intensity information and the target distance information into a preset regression model to obtain first attribute information of the measured object.
It can be seen that implementing the alternative embodiment discloses a model architecture of a preset information processing model set, by inputting all the first signal intensity information into a preset signal intensity filtering model, target signal intensity information can be obtained, so that the target signal intensity information is input into a preset channel calculation model, target distance information between a measured object and each first communication device is obtained, and then the target signal intensity information and the target distance information are input into a preset regression model, so that first attribute information of the measured object is obtained, and different functions of the preset signal intensity filtering model, the preset channel calculation model and the preset regression model can be combined through a specific model architecture, so that object positioning accuracy is further improved.
In this optional embodiment, as an optional implementation manner, the preset signal strength filtering model is:
Wherein RSSI out is used to represent target signal strength information, maxpooling is used to represent maximum pooling operations, Convolution kernel for representing a preset signal strength filtering model, b CNN for representing bias of the convolution kernel, RSSI in for representing a first matrix comprising a second matrix composed of first signal strength information obtained by communication between the measured object and each first communication device, andΗ is used to denote the total number of first communication devices,A second matrix for representing the ith first communication device, anThe RSSI im is used to represent the mth first signal strength information of the communication between the measured object and the ith first communication device.
Therefore, the implementation of the alternative embodiment discloses a model framework of a preset signal strength filtering model, which can improve the accuracy of determining the target signal strength information by specifically carrying out convolution processing and maximum pooling operation processing on the signal strength information, and is beneficial to improving the accuracy of determining the subsequent target distance information and the accuracy of determining the position information of the measured object.
In this optional embodiment, as another optional implementation manner, the preset channel calculation model is:
ym＝w2*tanh(w1*RSSIout+b1)+b2
Wherein y m is used to represent target distance information, tanh () is used to represent a nonlinear activation function, the nonlinear activation function is used to perform nonlinear transformation operation, w 1 is used to represent a first weight parameter of a preset channel calculation model, w 2 is used to represent a second weight parameter of the preset channel calculation model, b 1 is used to represent a first bias of the preset channel calculation model, and b 2 is used to represent a second bias of the preset channel calculation model.
It can be seen that implementing the alternative embodiment discloses a model architecture of a preset channel calculation model, and the channel environment of communication between the measured object and each first communication device can be simulated through the trained preset channel calculation model, so that the influence of channel interference on the positioning of the measured object is synthesized, the accuracy of determining the target distance information is improved, and further the combination of the target signal intensity information and the preset regression model is facilitated, and the accuracy of determining the position information of the measured object is improved.
In this alternative embodiment, as a further alternative implementation manner, the preset regression model is:
yout＝wout*x+bout
Wherein y out is used for representing first attribute information of the object to be measured, w out is used for representing output weight parameters of a preset regression model, b out is used for representing output bias of the preset regression model, x= [ RSSI out,ym,r1,...rη ], and r η＝(rxη,ryη) is used for representing first real coordinates of an eta first communication device in a first preset coordinate system, rx η is used for representing abscissa coordinates of the eta first communication device in the first preset coordinate system, and ry η is used for representing ordinate coordinates of the eta first communication device in the first preset coordinate system.
It can be seen that implementing the alternative embodiment discloses a model architecture of a preset regression model, and the environment where each first communication device is located can be simulated through the trained preset regression model, so that the contribution weights of different first communication devices to the measured object can be determined adaptively, and the accuracy of determining the position information of the measured object can be improved by combining the target signal intensity information and the target distance information.
In an optional embodiment, the training step of the preset information processing model set includes:
for each target object in the target environment, determining a target identifier of the target object according to second attribute information of the target object; determining second signal strength information of communication between the target object and each second communication device according to the target identification; the second signal strength information, the second attribute information of the target object, and the third attribute information of each second communication device are determined as the first information set of the target object.
And for each first information set, executing a preprocessing operation corresponding to the preset processing condition on the first information set according to the preset processing condition to obtain a second information set of the first information set.
And dividing all the second information sets into a training sample data set and a test sample data set according to preset cross-validation conditions.
According to preset training conditions, each training sample data in the training sample data set is input into the original information processing model set, and first prediction attribute information of each training sample data and a preparation information processing model set corresponding to the original information processing model set are obtained.
Judging whether the preparation information processing model set meets the preset verification conditions or not according to all the first prediction attribute information, and inputting each test sample data in the test sample data set into the preparation information processing model set according to the preset verification conditions when judging that the preparation information processing model set meets the preset verification conditions to obtain second prediction attribute information of each test sample data.
And judging whether the set of the preparation information processing models meets the preset model training convergence condition according to all the second prediction attribute information, and determining the set of the preparation information processing models as the set of the preset information processing models when judging that the set of the preparation information processing models meets the preset model training convergence condition.
It can be seen that implementing the optional embodiment discloses a training step of a preset information processing model set, so that accuracy of implementing corresponding application functions of a preset signal strength filtering model, a preset channel calculation model and a preset regression model in the preset information processing model set can be improved, and accuracy of positioning a measured object is improved.
In another optional embodiment, the preset verification condition and the preset model training convergence condition include preset loss function convergence, where the preset loss function is:
Wherein y is used for representing second real coordinates of the target object under a second preset coordinate system, d is used for representing real distance of communication between the target object and each second communication device, y my is used to represent the predicted distance information of the target object from each second communication device, |w out|、|w2 |, Is a regularization parameter.
When the preset loss function is used for verifying whether the set of preliminary information processing models satisfies the preset verification condition, y outy is used for representing the first prediction attribute information.
When the preset loss function is used for verifying whether the set of the preparation information processing models meets the preset model training convergence condition, y outy is used for representing the second prediction attribute information.
Therefore, the implementation of the optional embodiment can determine the preset loss function through the preset information processing model set, so as to verify whether the preset verification condition is met by the preset information processing model set and whether the preset model training convergence condition is met by the preset information processing model set, thereby further improving the accuracy of realizing the corresponding application function by the preset signal intensity filtering model, the preset channel calculation model and the preset regression model in the preset information processing model set and improving the accuracy of positioning the measured object.
Example III
Referring to fig. 3, fig. 3 is a schematic structural diagram of another adaptive object positioning device according to an embodiment of the present invention. As shown in fig. 3, the adaptive object positioning apparatus may include:
a memory 301 storing executable program code.
A processor 302 coupled with the memory 301.
The processor 302 invokes the executable program code stored in the memory 301 to perform the steps in the adaptive object positioning method described in the first embodiment of the present invention.
Example IV
The embodiment of the invention discloses a computer storage medium which stores computer instructions for executing the steps in the adaptive object positioning method described in the first embodiment of the invention when the computer instructions are called.
Example five
An embodiment of the present invention discloses a computer program product comprising a non-transitory computer storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps of the adaptive object positioning method described in embodiment one.
The apparatus embodiments described above are merely illustrative, wherein the modules illustrated as separate components may or may not be physically separate, and the components shown as modules may or may not be physical, i.e., may be located in one place, or may be distributed over a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above detailed description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course by means of hardware. Based on such understanding, the foregoing technical solutions may be embodied essentially or in part in the form of a software product that may be stored in a computer-readable storage medium including Read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), erasable programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), one-time programmable Read-Only Memory (OTPROM), electrically erasable programmable Read-Only Memory (EEPROM), compact disc Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM) or other optical disc Memory, magnetic disc Memory, tape Memory, or any other medium that can be used for computer-readable carrying or storing data.
Finally, it should be noted that: the embodiment of the invention discloses a self-adaptive object positioning method and device, which are disclosed as preferred embodiments of the invention, and are only used for illustrating the technical scheme of the invention, but not limiting the technical scheme; although the invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art will understand that; the technical scheme recorded in the various embodiments can be modified or part of technical features in the technical scheme can be replaced equivalently; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (10)
1. A method of adaptive object positioning, the method comprising:
acquiring first signal intensity information of communication between a measured object and at least one first communication device;
Inputting all the first signal intensity information into a preset information processing model set to obtain first attribute information of the measured object, wherein the first attribute information comprises position information, the preset information processing model set meets preset model training convergence conditions, the preset information processing model set comprises a preset signal intensity filtering model, a preset channel calculation model and a preset regression model, the preset signal intensity filtering model is used for executing preset filtering processing operation on all the first signal intensity information, the preset channel calculation model is used for simulating channel environments of communication between the measured object and each first communication device, and the preset regression model is used for simulating environments of positions of each first communication device.
2. The adaptive object locating method according to claim 1, wherein the inputting all the first signal strength information into a preset information processing model set, to obtain the first attribute information of the measured object, includes:
Inputting all the first signal intensity information into the preset signal intensity filtering model to obtain target signal intensity information;
inputting the target signal intensity information into the preset channel calculation model to obtain target distance information between the measured object and each first communication device;
And inputting the target signal intensity information and the target distance information into the preset regression model to obtain first attribute information of the measured object.
3. The adaptive object locating method according to claim 2, wherein the preset signal strength filtering model is:
Wherein RSSI out is used to represent the target signal strength information, maxpooling is used to represent a max-pooling operation, A convolution kernel for representing the preset signal strength filtering model, b CNN for representing the bias of the convolution kernel, and RSSI in for representing a first matrix including a second matrix composed of the first signal strength information obtained by communication between the measured object and each of the first communication devices, anΗ is used to represent the total number of the first communication devices, andThe second matrix representing the ith of the first communication devices, anThe RSSI im is used to represent the mth first signal strength information of the communication between the measured object and the ith first communication device.
4. The adaptive object locating method according to claim 3, wherein the preset channel calculation model is:
ym＝w2*tanh(w1*RSSIout+b1)+b2
Wherein y m is used to represent the target distance information, tanh () is used to represent a nonlinear activation function, the nonlinear activation function is used to perform a nonlinear transformation operation, w 1 is used to represent a first weight parameter of the preset channel calculation model, w 2 is used to represent a second weight parameter of the preset channel calculation model, b 1 is used to represent a first bias of the preset channel calculation model, and b 2 is used to represent a second bias of the preset channel calculation model.
5. The adaptive object locating method according to claim 4, wherein the preset regression model is:
yout＝wout*x+bout
Wherein y out is used to represent first attribute information of the object under test, w out is used to represent an output weight parameter of the preset regression model, b out is used to represent an output bias of the preset regression model, x= [ RSSI out,ym,r1,...rη ], and r η＝(rxη,ryη) is used to represent a first real coordinate of an eta first communication device under a first preset coordinate system, rx η is used to represent an abscissa of the eta first communication device under the first preset coordinate system, and ry η is used to represent an ordinate of the eta first communication device under the first preset coordinate system.
6. The method for adaptive object localization as claimed in any one of claims 1 to 5, wherein the training step of the set of predetermined information processing models comprises:
for each target object in the target environment, determining a target identifier of the target object according to second attribute information of the target object; determining second signal strength information of communication between the target object and each second communication device according to the target identifier; determining the second signal strength information, the second attribute information of the target object and the third attribute information of each of the second communication devices as a first information set of the target object;
For each first information set, executing a preprocessing operation corresponding to the preset processing conditions on the first information set according to the preset processing conditions to obtain a second information set of the first information set;
dividing all the second information sets into a training sample data set and a test sample data set according to preset cross-validation conditions;
inputting each training sample data in the training sample data set into an original information processing model set according to a preset training condition to obtain first prediction attribute information of each training sample data and a preparation information processing model set corresponding to the original information processing model set;
Judging whether the preparation information processing model set meets a preset verification condition or not according to all the first prediction attribute information, and inputting each test sample data in the test sample data set into the preparation information processing model set according to the preset verification condition when judging that the preparation information processing model set meets the preset verification condition to obtain second prediction attribute information of each test sample data;
And judging whether the preparation information processing model set meets the preset model training convergence condition according to all the second prediction attribute information, and determining the preparation information processing model set as the preset information processing model set when judging that the preparation information processing model set meets the preset model training convergence condition.
7. The adaptive object locating method according to claim 6, wherein the preset verification condition and the preset model training convergence condition include a preset loss function convergence, the preset loss function being:
Wherein y is used for representing a second real coordinate of the target object under a second preset coordinate system, d is used for representing a real distance between the target object and each second communication device, y my is used for representing predicted distance information between the target object and each second communication device, |w out|、|w2 |, Is a regularization parameter;
when the preset loss function is used for verifying whether the set of the preparation information processing models meets a preset verification condition, y outy is used for representing the first prediction attribute information;
And when the preset loss function is used for verifying whether the set of the preparation information processing models meets a preset model training convergence condition, y outy is used for representing the second prediction attribute information.
8. An adaptive object positioning device, the device comprising:
the acquisition module is used for acquiring first signal intensity information of communication between the measured object and at least one first communication device;
The processing module is used for inputting all the first signal intensity information into a preset information processing model set to obtain first attribute information of the measured object, the first attribute information comprises position information, the preset information processing model set meets preset model training convergence conditions, the preset information processing model set comprises a preset signal intensity filtering model, a preset channel calculation model and a preset regression model, the preset signal intensity filtering model is used for executing preset filtering processing operation on all the first signal intensity information, the preset channel calculation model is used for simulating a channel environment of communication between the measured object and each first communication device, and the preset regression model is used for simulating the environment of the position where each first communication device is located.
9. An adaptive object positioning device, the device comprising:
A memory storing executable program code;
A processor coupled to the memory;
The processor invokes the executable program code stored in the memory to perform the adaptive object positioning method of any of claims 1-7.
10. A computer storage medium storing computer instructions which, when invoked, are adapted to perform the adaptive object positioning method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410146467.0A CN117939631A (en) | 2024-02-01 | 2024-02-01 | Self-adaptive object positioning method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410146467.0A CN117939631A (en) | 2024-02-01 | 2024-02-01 | Self-adaptive object positioning method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117939631A true CN117939631A (en) | 2024-04-26 |
Family
ID=90770192
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410146467.0A Pending CN117939631A (en) | 2024-02-01 | 2024-02-01 | Self-adaptive object positioning method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117939631A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20010022558A1 (en) * | 1996-09-09 | 2001-09-20 | Tracbeam Llc | Wireless location using signal fingerprinting |
| CN110225460A (en) * | 2019-06-05 | 2019-09-10 | 三维通信股份有限公司 | A kind of indoor orientation method and device based on deep neural network |
| CN113740832A (en) * | 2020-10-26 | 2021-12-03 | 北京沃东天骏信息技术有限公司 | Positioning method, positioning device, positioning equipment and storage medium |
| CN113945215A (en) * | 2021-10-11 | 2022-01-18 | 浙江工业大学 | RFID indoor positioning method based on stacking model |
| CN115327478A (en) * | 2022-10-10 | 2022-11-11 | 广东省电信规划设计院有限公司 | Device positioning method and system based on DOA estimation of wireless access point |
| CN116170874A (en) * | 2023-02-24 | 2023-05-26 | 江苏亿通高科技股份有限公司 | Robust WiFi fingerprint indoor positioning method and system |
-
2024
- 2024-02-01 CN CN202410146467.0A patent/CN117939631A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20010022558A1 (en) * | 1996-09-09 | 2001-09-20 | Tracbeam Llc | Wireless location using signal fingerprinting |
| CN110225460A (en) * | 2019-06-05 | 2019-09-10 | 三维通信股份有限公司 | A kind of indoor orientation method and device based on deep neural network |
| CN113740832A (en) * | 2020-10-26 | 2021-12-03 | 北京沃东天骏信息技术有限公司 | Positioning method, positioning device, positioning equipment and storage medium |
| CN113945215A (en) * | 2021-10-11 | 2022-01-18 | 浙江工业大学 | RFID indoor positioning method based on stacking model |
| CN115327478A (en) * | 2022-10-10 | 2022-11-11 | 广东省电信规划设计院有限公司 | Device positioning method and system based on DOA estimation of wireless access point |
| CN116170874A (en) * | 2023-02-24 | 2023-05-26 | 江苏亿通高科技股份有限公司 | Robust WiFi fingerprint indoor positioning method and system |
Non-Patent Citations (1)
| Title |
|---|
| 李丽娜;梁德;马俊;涂志;: "基于灰色-RBF神经网络的传播损耗模型训练", 计算机应用与软件, no. 08, 15 August 2016 (2016-08-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6045747B2 (en) | Scalable real-time position detection based on overlapping neural networks | |
| CN112070807B (en) | Multi-target tracking method and electronic device | |
| CN112218330B (en) | Positioning method and communication device | |
| CN111541511A (en) | Communication jamming signal identification method based on target detection in complex electromagnetic environment | |
| CN108744516A (en) | Obtain method and apparatus, storage medium and the electronic device of location information | |
| CN111932451B (en) | Method and device for evaluating repositioning effect, electronic equipment and storage medium | |
| CN108427941A (en) | Method, method for detecting human face and device for generating Face datection model | |
| CN114543810B (en) | Unmanned aerial vehicle cluster passive positioning method and device under complex environment | |
| CN115712099A (en) | Radar interference countermeasure test method, device, equipment and storage medium | |
| CN113822892A (en) | Evaluation method, device and equipment of simulated radar and computer program product | |
| JP6696859B2 (en) | Quality estimation device and quality estimation method | |
| CN117506897A (en) | Robot calibration method and device | |
| CN117939631A (en) | Self-adaptive object positioning method and device | |
| CN119469151B (en) | Fusion localization methods, media, and devices based on reinforcement learning and particle filtering | |
| CN112052572B (en) | Digital twin industrial simulation system based on WLAN (wireless local area network) position awareness | |
| CN116321187A (en) | A training method and device for a signal path loss prediction model | |
| CN115550863A (en) | WIFI indoor positioning method based on convolutional neural network | |
| CN117938689A (en) | AI model configuration method, terminal and network equipment | |
| CN111461228B (en) | Image recommendation method and device and storage medium | |
| CN113435538A (en) | Wireless communication equipment deployment method and device | |
| CN116340802A (en) | A method, device and equipment for predicting received power | |
| CN120302235B (en) | Perception positioning method and electronic equipment | |
| CN116843304B (en) | Digital twin park management method, device, equipment and storage medium | |
| CN113313079B (en) | Training method and system of vehicle attribute recognition model and related equipment | |
| CN115226112B (en) | Network planning method, device, equipment and storage medium based on machine learning |
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 |