CN115767411A - Self-learning wireless signal positioning method, system, equipment and storage medium - Google Patents
Self-learning wireless signal positioning method, system, equipment and storage medium Download PDFInfo
- Publication number
- CN115767411A CN115767411A CN202211035639.4A CN202211035639A CN115767411A CN 115767411 A CN115767411 A CN 115767411A CN 202211035639 A CN202211035639 A CN 202211035639A CN 115767411 A CN115767411 A CN 115767411A
- Authority
- CN
- China
- Prior art keywords
- terminal
- self
- training
- signal
- positioning
- 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
Images
Classifications
-
- 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
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The present application relates to artificial intelligence and wireless signal positioning technologies, including a self-learning wireless signal positioning method, system, computer device, and storage medium. Acquiring a periodic signal parameter set of a terminal to be positioned in a region to be identified for parameter identification to obtain a state characterization parameter; automatically and continuously generating a training signal parameter set which can be used for self-learning training by using the state characterization parameters and the signal parameter set; training a pre-constructed self-learning positioning model to be trained by utilizing the training signal parameter set; and calculating the coordinate position of the terminal to be positioned by using the trained self-learning wireless signal positioning model, and outputting the terminal coordinate. The invention provides a scheme which has the advantages that the system cost is not increased, the real-time engineering difficulty of the system is lower, the positioning precision of the wireless signal can be improved, and the time-varying characteristic of the wireless signal and the change of the field environment can be automatically adapted.
Description
Technical Field
The present application relates to the field of artificial intelligence and wireless signal positioning, and in particular, to a self-learning wireless signal positioning method, system, computer device, and storage medium.
Background
At present, the implementation of positioning services by using wireless signals is one of the common methods, but due to the instability of wireless signals and the influence of various factors such as shielding, reflection, multipath and the like, the accuracy of position estimation performed on positioning by simply using signal parameters cannot achieve a satisfactory effect. Although the cost is lowest, the method of calculating the position of the positioned article by utilizing the signal strength is most influenced by environmental change and has the worst precision; the method of positioning by using the arrival angle or the emission angle has relatively high positioning accuracy in an ideal environment, but has relatively high cost; the method has the limitations that a plurality of position fingerprint sampling points need to be set manually when a system is deployed each time, signal data of the sampling points are measured, implementation difficulty and workload are high, and a wireless signal has a time-varying characteristic, so that a signal intensity model measured in a certain time period may vary in another time period, and position fingerprints are invalid. Therefore, in order to solve the problems in the above methods, it is necessary to provide a scheme that can improve the accuracy of wireless signal positioning and automatically adapt to the time-varying characteristics of the wireless signal and the changes of the field environment without increasing the system cost and having low difficulty in real-time engineering of the system.
Disclosure of Invention
The embodiment of the application aims to provide a self-learning wireless signal positioning method, which is used for solving the problems that the training samples of a training model are difficult to sample and the signal positioning accuracy is low in the prior art.
In order to solve the above technical problem, the embodiment of the present application provides a self-learning wireless signal positioning method, which adopts the following technical solutions:
acquiring a periodic signal parameter set of a terminal to be positioned in a region to be identified for parameter identification to obtain a state characterization parameter, wherein the state characterization parameter is used for characterizing the motion state of the terminal to be positioned;
acquiring a signal parameter set of a terminal to be positioned in a region to be identified for parameter identification to obtain a state characterization parameter;
utilizing the state characterization parameters to automatically and continuously generate a training signal parameter set which can be used for self-learning training; training a pre-constructed self-learning positioning model to be trained by utilizing the training signal parameter set to obtain a training result set;
if the training result set does not exceed the training error interval, obtaining a trained self-learning wireless signal positioning model;
and calculating the coordinate position of the terminal to be positioned by utilizing the self-learning wireless signal positioning model, and outputting the terminal coordinate.
Further, the method further comprises:
acquiring position data sets of a plurality of deployed receiving terminals to construct an identification area;
performing geometric re-segmentation on the identification region by using the position data set based on a preset region division rule to obtain a plurality of sub-regions;
performing signal strength identification on the signal parameters of the terminal to be positioned received in each sub-area to obtain a signal strength value set;
and extracting the sub-region corresponding to the signal intensity value meeting the condition in the signal intensity value set to form a region to be identified.
Further, the method further comprises:
carrying out state judgment on the motion state of the terminal to be positioned;
when the terminal to be positioned is in a static state, extracting a signal parameter set of the terminal to be positioned in the area to be identified to perform probability accumulation calculation to obtain a probability accumulation value;
if the probability accumulated value exceeds a preset acceptable value, the state characterization parameters perform stable state characterization on the signal intensity of the terminal to be positioned to form stable state signal data;
if the probability accumulated value does not exceed a preset acceptable value and/or the terminal to be positioned is in a non-static state, performing unsteady state representation on the signal intensity of the terminal to be positioned by the state representation parameter to form unsteady state signal data;
and summarizing the steady-state signal parameters and/or the unsteady-state signal parameters to generate a training signal parameter set.
Further, the method also comprises the following steps:
calculating the position of the steady-state signal data by using any conventional signal intensity positioning algorithm to obtain a training coordinate comparison set;
calculating whether the training error of the training coordinate result set and the training coordinate comparison set exceeds the training error interval;
if the training error exceeds the preset training error interval, retraining the to-be-trained self-learning wireless signal positioning model until the training error is within the training error interval;
and if the wireless signal positioning model does not exceed the preset value, obtaining the trained self-learning wireless signal positioning model.
Further, the method further comprises:
calculating the position of the signal parameter set of the terminal to be positioned by utilizing any conventional signal intensity positioning algorithm to obtain a first positioning coordinate;
when the terminal to be positioned is in a stable state representation, outputting the first positioning coordinate as a terminal coordinate;
and/or calling the trained self-learning wireless signal positioning model to perform position calculation on the wireless signal parameter set of the terminal to be positioned to obtain a second positioning coordinate;
giving weights corresponding to the first positioning coordinate and the second positioning coordinate to perform coordinate calculation to obtain a third positioning coordinate;
and when the terminal to be positioned is in an unsteady state representation, outputting the third positioning coordinate as a terminal coordinate.
Further, the method further comprises:
extracting an error value corresponding to the training error;
correcting and calculating according to a preset learning rate by utilizing the error value to obtain a correction value;
and correcting the to-be-trained self-learning wireless signal positioning model by using the correction value to obtain the corrected to-be-trained self-learning wireless signal positioning model.
Further, the method further comprises:
retraining the corrected self-learning wireless signal positioning model to be trained until the corresponding error value is within the training error interval;
and stopping correcting the to-be-trained self-learning wireless signal positioning model.
In order to solve the above technical problem, an embodiment of the present application further provides a self-learning wireless signal positioning system, which adopts the following technical solutions:
a self-learning wireless signal locating system, the self-learning wireless signal locating system comprising:
the motion state detection and reporting module: the positioning terminal is arranged on the terminal to be positioned and used for detecting the motion state data of the positioning terminal and reporting the motion state data to the base station through wireless communication.
An identification module: the system comprises a signal parameter set used for acquiring a terminal to be positioned in a region to be identified and carrying out parameter identification to obtain a state characterization parameter;
a positioning training module: the self-learning positioning model to be trained is trained by utilizing the state characterization parameters and the signal parameter set to obtain a training result;
a correction module: the training error interval is used for obtaining a trained self-learning wireless signal positioning model if the training result does not exceed the training error interval;
a positioning comprehensive module: and the self-learning wireless signal positioning model is used for calculating the coordinate position of the terminal to be positioned and outputting the terminal coordinate.
In order to solve the above technical problem, an embodiment of the present application further provides a computer device, which adopts the following technical solutions:
a computer device comprising a memory having computer readable instructions stored therein and a processor that when executed implements the steps of the self-learning wireless signal location method as described above.
In order to solve the above technical problem, an embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solutions:
a computer readable storage medium having computer readable instructions stored thereon which, when executed by a processor, implement the steps of the self-learning wireless signal location method as described above.
Compared with the prior art, the embodiment of the application mainly has the following beneficial effects:
according to the method, a certain number of terminal base stations are deployed in an area, whether the signal parameters of the terminal to be positioned are in a stable state or not is judged by the terminal base stations, the signal parameters in the stable state are used for continuous training of the self-learning signal positioning model to be trained, the anti-locking work of generating training samples through manual measurement is replaced by the method, the deployment cost is reduced, meanwhile, the self-learning signal positioning model to be trained is further corrected and trained through correction values, the more self-learning training data accumulated according to the method can greatly improve the positioning accuracy, and the rules of environmental change and wireless signal fluctuation can be adapted.
Drawings
In order to more clearly illustrate the solution of the present application, the drawings needed for describing the embodiments of the present application will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and that other drawings can be obtained by those skilled in the art without inventive effort.
FIG. 1 is a flow chart of one embodiment of a self-learning wireless signal location method according to the present application;
FIG. 2 is a flowchart according to one embodiment of step S130 in the present application;
FIG. 3 is a block diagram of one embodiment of a self-learning wireless signal location system according to the present application
FIG. 4 is a schematic block diagram of one embodiment of a computer device according to the present application.
Detailed Description
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "including" and "having," and any variations thereof, in the description and claims of this application and the description of the above figures are intended to cover non-exclusive inclusions. The terms "first," "second," and the like in the description and claims of this application or in the foregoing drawings are used for distinguishing between different objects and not for describing a particular sequential order.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase 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. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.
With continued reference to fig. 1, a flow diagram of one embodiment of self-learning wireless signal location as proposed by the present application is shown. The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like. The self-learning wireless signal positioning method comprises the following steps:
s100: acquiring a periodic signal parameter set of a terminal to be positioned in a region to be identified for parameter identification to obtain a state characterization parameter, wherein the state characterization parameter is used for characterizing the motion state of the terminal to be positioned;
in the present embodiment, it should be noted that, for simplicity of description, most applications are also considered to be plane positioning, and the present application mainly takes two-dimensional plane positioning as an example for description. The scheme provided by the application can also aim at three-dimensional stereotaxic positioning, only corresponding dimensionality needs to be expanded, and the essence of the application is not affected.
Furthermore, any motion state sensor is further installed on the terminal to be positioned, and an acceleration sensor is taken as an example in the application. The motion state of the terminal to be positioned is measured through the acceleration sensor, and the motion state data are periodically sent to the terminal base station in a wireless communication mode. The motion sensor installed on the terminal to be positioned periodically measures motion data, and then reports the motion data to the base station through wireless communication.
Further, in a preferred embodiment, before the acquiring the signal parameter set of the terminal to be positioned in the area to be identified for parameter identification, acquiring an identification area is further included, and first acquiring location data sets of a plurality of deployed receiving terminals to construct the identification area; performing geometric re-segmentation on the identification region by using a position data set based on a preset region division rule to obtain a plurality of sub-regions; identifying signal strength of the received signal parameters of the terminal to be positioned in each sub-area to obtain a signal strength value set; and finally, extracting sub-regions corresponding to the signal intensity values meeting the conditions in the signal intensity value set to form the region to be identified.
Specifically, in this embodiment, the identification region is constructed by a receiving terminal capable of receiving a signal parameter sent by a terminal to be positioned, the receiving terminal includes a terminal base station, and after a plurality of terminal base stations are deployed, a position connection in any form is performed by acquiring position data of the terminal base stations, so as to obtain a geometric identification region. The method comprises the steps of subdividing a to-be-identified area in an identification area in a connection mode of preset terminal base stations, wherein the divided to-be-identified area at least comprises 3 terminal base stations, receiving signal parameters sent by a terminal to be positioned by utilizing a plurality of terminal base stations in the identification area to form an initial signal parameter set, analyzing the initial signal parameter set to obtain an initial strength value set, extracting receiving terminals meeting conditions in the initial strength value set according to a preset signal strength interval, and extracting the corresponding to-be-identified area by utilizing the receiving terminals meeting the conditions.
Further, performing parameter identification on the received signal parameter set, and firstly, performing state judgment on the motion state of the terminal to be positioned; the signal parameter set further comprises a motion state signal parameter, when the terminal to be positioned is in a static state within a preset time, static state data are generated, when the base station terminal judges that the terminal to be positioned is in the static state through the static state data, the signal parameter set of the terminal to be positioned in the region to be identified is extracted for probability accumulation calculation, and a probability accumulated value is obtained; if the probability accumulated value exceeds a preset acceptable value, performing stable state representation on the signal strength of the terminal to be positioned by the state representation parameters to form stable state signal data;
if the probability accumulated value does not exceed a preset acceptable value and/or the terminal to be positioned is in a non-static state, performing non-stable state representation on the signal intensity of the terminal to be positioned by the state representation parameter to form non-stable state signal data, wherein it needs to be stated that when the static state data of the terminal to be positioned is not received, determining that the terminal to be positioned is in a motion state, and performing non-stable state representation on the terminal to be positioned in the motion state.
Specifically, in this embodiment, a motion state of a terminal to be positioned is determined first, when the terminal is in a stationary state, a signal strength parameter of the terminal to be positioned is continuously received, a mean value E and a standard deviation σ of the signal strength are calculated, occurrence probabilities of all wireless signal strengths between [ E- σ, E + σ ] in accumulated data are extracted, a probability accumulated value P is obtained, when the probability accumulated value P is greater than a receivable value, it is considered that the terminal has entered a steady state, steady-state characterization data is embedded in the signal parameter, and steady-state characterization signal data is formed, where an acceptable value in this embodiment is 68%. And carrying out time length statistics on the accumulated data which does not exceed the acceptable value, and emptying the accumulated statistical data when the preset statistical time length is exceeded and the acceptable value is not reached.
In detail, in this embodiment, non-steady-state characterization data is added to the signal parameters that do not exceed the preset statistical duration and do not reach the acceptable value and the signal parameters sent by the terminal to be positioned in the moving state, so as to form non-steady-state characterization signal data.
S110, automatically and continuously generating a training signal parameter set for self-learning training by using the state characterization parameters;
specifically, in this embodiment, the terminal base station receives state characterizing parameters and a signal strength set of all terminals to be located. When the state characterization parameters indicate that the terminal to be positioned has the stable state characterization, the signal intensity set corresponding to the terminal to be positioned can be used as a training sample to form a training signal parameter set; in the system operation process, the terminal to be positioned continuously generates state characterization parameters and a signal intensity set. As long as the state characterization parameters of the positioning terminal indicate that the positioning terminal has steady state characterization, the corresponding signal intensity set can be used as a training signal parameter set all the time and is continuously used for training the self-learning positioning model.
S120: training a pre-constructed self-learning positioning model to be trained by utilizing the training signal parameter set to obtain a training result;
in this embodiment, a learning training of the to-be-trained self-learning wireless signal positioning model is described by taking a BP neural network method as an example. The to-be-trained self-learning wireless signal positioning model comprises the following steps: an input layer, a hidden layer and an output layer;
using the signal strength parameter received by the terminal base station as the input of the input layer, denoted by R, where Ri represents the signal strength received by the terminal at base station i as the input of the ith neuron of the input layer, i = (1, \8230;, i).
Vih represents the weight from the ith neuron of the input layer to the H neuron of the hidden layer, wherein H =1, \8230, and H α H is the input of the H neuron of the hidden layer, so the input formula of the hidden layer comprises the following steps:
the activation function of the hidden layer adopts a Sigmod function:
and γ h is used to represent the threshold of the h-th neuron of the hidden layer, and bh is used to represent the output of the h-th neuron of the hidden layer, so that the output formula of the hidden layer includes:
using Whj to represent the weight from the h-th neuron of the hidden layer to the j-th neuron of the output layer, and using β j as the input of the j-th neuron of the output layer, the input formula of the output layer includes:
by using X 1 ，X 2 Respectively representing the output of the output layer, [ theta ] j Threshold value of j-th neuron of output layer, activation function of output layerThe purelin function is used for the data: f2 (x) = x;
then the training result is obtained as: xj = F2 (β j- θ) j )＝βj-θj。
In detail, in this embodiment, the to-be-trained self-learning signal localization model further includes: for weight parameter Vi h And Wh j And a threshold parameter gamma h And theta j The initial value of (2) is obtained. It should be noted that the weight initialization mainly adopts Xavier initialization method, and the initial value adopts variance as
The values of the distributions are averaged, where n represents the number of inputs.
In the above embodiment, the weight Vi h First taking [ -1,1]The number of input neurons and the number of output neurons are set to 3, and the activation function SigMod is set to 0.25 in the derivative around 0, since the initial value is variance
Uniformly distributed values, then weight Vi h Is in the range of [ -4,4]Are uniformly distributed.
Weight Wh j Setting the number of input neurons to be 3, the number of output neurons to be 2, setting the derivative of the activation function purelin near 0 to be 1, and setting the initial value to be the variance
Of evenly distributed values, the weight Wh j Is in the range of [ -1.095,1.095]Are uniformly distributed.
Threshold value theta j (wherein J =1, \ 8230;, J) is set to an initial value of [ -1,1]The random number in the middle of the random number,
threshold value gamma h(h＝1，…，h) The initial value is obtained by the following formula:
wherein M is a random number between [ -1,1 ].
With reference to fig. 2, S130: and if the training result does not exceed the training error interval, obtaining a trained self-learning wireless signal positioning model.
S131: performing position calculation on the steady-state signal data by using any conventional signal intensity positioning algorithm to obtain a training coordinate comparison set;
the method can select a signal intensity positioning algorithm to perform position calculation on stable signal data, respectively calculate the distances from a terminal to three nearest terminal base stations by using a wireless signal intensity and distance formula according to the signal intensity of a terminal to be detected received by the terminal base stations, and then calculate the position coordinates of the terminal to be positioned by using a trilateration method, namely, the three terminal base stations are respectively used as the circle centers, the distance from the terminal to be positioned to the terminal base station is used as a radius to draw a circle, and the intersection point of the three circles is the position of the terminal to be positioned.
Wherein, the intensity and distance calculation formula is as follows:
d is the distance from the terminal to the base station, d 0 For a reference distance, typically 1 meter; p T Is the transmit power; p L(d0) The signal strength received by the base station when the terminal is located at the reference distance; p L(d0) The signal strength received by the base station when the terminal is located at a distance d from the base station; eta is a path loss exponent, and is usually 2 to 4.
S132: calculating whether the training error of the training coordinate result set and the training coordinate comparison set exceeds the training error interval;
specifically, in this embodiment, any training sample K in the training sample set is extracted, and the terminal base station uses the training coordinate reference set measured in the conventional manner
The training result is
The signal strength value of the training samples is,
the error value is expressed as the following equation using the least square method:
s133: if the training error is within the training error interval, retraining the to-be-trained self-learning wireless signal positioning model until the training error is within the training error interval;
specifically, in this embodiment, an error value corresponding to the training error is extracted; correcting and calculating according to a preset learning rate by using the error value to obtain a correction value; according to E k And calculating the correction value of the weight and the threshold value of each self-learning signal positioning model to be trained by setting a learning rate eta between 0.01 and 0.1, wherein the formula for calculating the correction value of each weight sum and the threshold value is as follows:
Δ Whj is the corrected magnitude of Whj,
delta theta j is the correction value of theta j,
specifically, in this embodiment, if the Sigmod function is used as the activation function of the hidden layer, F1' (x) = F1 (x) (1-F1 (x));
wherein, make
Δ Vih is the corrected magnitude of Vih,
Δ γ h is a modified measure of γ h, Δ γ h = η × eh.
Further, the calculated correction quantity value is used for correcting the to-be-trained self-learning wireless signal positioning model to obtain a corrected to-be-trained self-learning wireless signal positioning model; retraining the corrected self-learning wireless signal positioning model to be trained by using the corrected weight and threshold until the corresponding error value E k Within the training error interval; and stopping correcting the self-learning wireless signal positioning model to be trained.
S134: and if the wireless signal is not beyond the preset range, obtaining a trained self-learning wireless signal positioning model.
S140: calculating the coordinate position of the terminal to be positioned by utilizing the self-learning wireless signal positioning model, and outputting the terminal coordinate
Specifically, in this embodiment, a signal parameter set of the terminal to be located is subjected to position calculation by using any conventional signal strength location algorithm, so as to obtain a first location coordinate; and when the terminal to be positioned is in a stable state representation, outputting a first positioning coordinate as a terminal coordinate of the terminal to be positioned.
Further, in this embodiment, positioning the unstable terminal to be positioned is also included. Carrying out position calculation on a wireless signal parameter set of a terminal to be positioned by calling a trained self-learning wireless signal positioning model to obtain a second positioning coordinate; and giving weights corresponding to the first positioning coordinate and the second positioning coordinate to perform coordinate calculation.
Specifically, whether a self-learning wireless signal positioning model in a current to-be-identified area is in an available state or not is judged, if the self-learning wireless signal positioning model is in the available state, a first positioning coordinate is endowed with low weight, a second positioning coordinate is endowed with high weight, the final coordinates of the first positioning coordinate and the second positioning coordinate are calculated by using the weights, a third positioning coordinate is obtained, and the third positioning coordinate is output as a terminal coordinate of the to-be-positioned terminal;
and if the terminal is in a non-available state, giving high weight to the first positioning coordinate, giving low weight to the second positioning coordinate, calculating the final coordinates of the first positioning coordinate and the second positioning coordinate by using the weights to obtain a third positioning coordinate, and outputting the third positioning coordinate as the terminal coordinate of the terminal to be positioned.
Compared with the prior art, the embodiment of the application mainly has the following beneficial effects: according to the method, a certain number of terminal base stations are deployed in an area, whether the signal parameters of the terminal to be positioned are in a stable state or not is judged by the terminal base stations, the signal parameters in the stable state are used for continuous training of the self-learning signal positioning model to be trained, the anti-locking work of generating training samples through manual measurement is replaced by the method, the deployment cost is reduced, meanwhile, the self-learning signal positioning model to be trained is further corrected and trained through correction values, the more self-learning training data accumulated according to the method can greatly improve the positioning accuracy, and the rules of environmental change and wireless signal fluctuation can be adapted.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the computer program is executed. The storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a Random Access Memory (RAM).
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of execution is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
With further reference to FIG. 3, as an implementation of the method shown in FIG. 1, the present application provides an embodiment of a self-learning wireless signal positioning system 200, which corresponds to the embodiment of the method shown in FIG. 2, and which is particularly applicable to various electronic devices.
The motion detection and reporting module 201: the system comprises a base station, a terminal to be positioned and a wireless communication module, wherein the base station is used for measuring the motion state of the terminal to be positioned and reporting the motion state to the base station in a wireless communication mode;
the motion detection and reporting module comprises a motion monitoring sub-module and a wireless communication sub-module. The motion monitoring submodule can be any device for monitoring the motion state of the terminal, and the application uses the acceleration sensor for explanation, and when the terminal to be positioned is in a static state, the acceleration value measured by the acceleration sensor is lower than a specific threshold value; when the terminal to be positioned is in a motion state, the acceleration value measured by the acceleration sensor is higher than a specific threshold value. The motion detection and reporting module can directly report the measured acceleration value to the base station, can also directly judge the motion state according to the acceleration value, and only reports the indicator of whether the motion state is in a static state to the base station.
The identification module 202: the system comprises a signal parameter set used for acquiring a terminal to be positioned in a region to be identified and carrying out parameter identification to obtain a state representation parameter;
in this embodiment, the identification module further includes a region deployment sub-module, and the identification module further includes, before acquiring a signal parameter set of a terminal to be located in the region to be identified and performing parameter identification, acquiring the identification region by using the region deployment sub-module, where first the region deployment sub-module acquires position data sets of a plurality of deployed receiving terminals to construct the identification region; performing geometric recutting on the identification region by using the position data set based on a preset region division rule to obtain a plurality of sub-regions; identifying signal intensity of the signal parameters of the terminal to be positioned received in each sub-area to obtain a signal intensity value set; and finally, extracting sub-regions corresponding to the signal intensity values meeting the conditions in the signal intensity value set to form the region to be identified.
Specifically, in this embodiment, the area deployment submodule constructs the identification area through a receiving terminal capable of receiving a signal parameter sent by a terminal to be positioned, the receiving terminal includes a terminal base station, and after a plurality of terminal base stations are deployed, a position connection line of any form is performed by acquiring position data of the terminal base station, so as to obtain the identification area of a geometric shape. The method comprises the steps of subdividing a to-be-identified area in an identification area in a connection mode of preset terminal base stations, wherein the divided to-be-identified area at least comprises 3 terminal base stations, receiving signal parameters sent by a terminal to be positioned by utilizing a plurality of terminal base stations in the identification area to form an initial signal parameter set, analyzing the initial signal parameter set to obtain an initial strength value set, extracting receiving terminals meeting conditions in the initial strength value set according to a preset signal strength interval, and extracting the corresponding to-be-identified area by utilizing the receiving terminals meeting the conditions.
Furthermore, the identification module performs parameter identification on the received signal parameter set, and firstly performs state judgment on the motion state of the terminal to be positioned according to the motion state data reported by the motion detection and reporting module; the signal parameter set further comprises a motion state signal parameter, when the terminal to be positioned is in a static state within preset time, static state data are generated, the identification module judges that the terminal to be positioned is in the static state through the static state data, and the signal parameter set of the terminal to be positioned in the region to be identified is extracted for probability accumulation calculation to obtain a probability accumulated value; if the probability accumulated value exceeds a preset acceptable value, performing stable state representation on the signal strength of the terminal to be positioned by the state representation parameters to form stable state signal data; and if the probability accumulated value does not exceed a preset acceptable value and/or the terminal to be positioned is in a non-static state, performing non-stable state representation on the signal intensity of the terminal to be positioned by the state representation parameter to form non-stable state signal data, wherein it needs to be stated that when the identification module does not receive the static state data sent by the motion monitoring submodule, the terminal to be positioned is judged to be in a motion state, and the terminal to be positioned in the motion state is also subjected to non-stable state representation.
Specifically, in this embodiment, a motion state of the terminal to be positioned is determined first, when the terminal is in a stationary state, the signal strength parameter of the terminal to be positioned, the mean value E and the standard deviation σ of the line signal strength are continuously received, the occurrence probability of all wireless signal strengths between [ E- σ, E + σ ] in the accumulated data is extracted, a probability accumulated value P is obtained, when the probability accumulated value P is greater than a receivable value, it is considered that the terminal has entered a steady state, and steady-state characterization data is added to the signal parameter, so as to form steady-state characterization signal data, where an optional acceptable value in this embodiment is 68%. And carrying out time length statistics on the accumulated data which do not exceed the acceptable value, and emptying the accumulated statistical data when the preset statistical time length is exceeded and the accumulated statistical data does not reach the acceptable value.
In detail, in this embodiment, non-steady-state characterization data is embedded into the signal parameters whose preset statistical duration has not exceeded the preset statistical duration and whose acceptable value has not been reached, and the signal parameters sent by the terminal to be positioned in the moving state, so as to form non-steady-state characterization signal data.
The positioning training module 203: the self-learning positioning model to be trained is trained by utilizing the state characterization parameters and the signal parameter set to obtain a training result;
specifically, in this embodiment, the positioning training module receives a signal intensity set of a signal parameter set of the terminal to be positioned through the terminal base station, performs training of the to-be-trained self-learning wireless signal positioning model by using the signal intensity set with the stable-state representation signal data and the corresponding signal intensity as training samples, and extracts a training result to obtain a training coordinate result set.
In another preferred embodiment, the positioning training module, taking the BP neural network as an example to perform the learning training of the to-be-trained self-learning wireless signal positioning model, includes: an input layer, a hidden layer and an output layer;
using the signal strength parameter received by the terminal base station as the input of the input layer, denoted by R, where Ri represents the signal strength received by the terminal at base station i as the input of the ith neuron of the input layer, i = (1, \8230;, i).
Vih represents the weight from the ith neuron of the input layer to the H neuron of the hidden layer, wherein H =1, \ 8230, H α H is the input of the H neuron of the hidden layer, and the input formula of the hidden layer comprises:
the activation function of the hidden layer adopts a Sigmod function:
using γ h to represent the threshold of the h-th neuron of the hidden layer, and bh to represent the output of the h-th neuron of the hidden layer, the output formula of the hidden layer includes:
using Whj to represent the weight from the h-th neuron of the hidden layer to the j-th neuron of the output layer, and using β j as the input of the j-th neuron of the output layer, the input formula of the output layer includes:
by using X 1 ，X 2 Respectively representing the output of the output layer, [ theta ] j For the threshold value of the jth neuron of the output layer, the activation function of the output layer adopts a purelin function: f2 (x) = x;
the training result is obtained as follows: xj = F2 (β j- θ) j )＝βj-θj。
In detail, in this embodiment, the to-be-trained self-learning signal localization model further includes: for weight parameter Vi h And Wh j And a threshold parameter gamma h And theta j The initial value of (2) is obtained. In the following, the right isThe re-initialization mainly adopts an Xavier initialization method, and the initial value adopts variance of
The average distribution value, where n represents the number of inputs.
In the above embodiment, the weight Vi h Firstly get [ -1,1 [ ]]The number of input neurons and the number of output neurons are set to 3, and the activation function SigMod is set to 0.25 in the derivative around 0, since the initial value is variance
Uniformly distributed values, then weight Vi h Is in the range of [ -4,4]Are uniformly distributed.
Weight Wh j Setting the number of input neurons to be 3, the number of output neurons to be 2, and the derivative of the activation function purelin near 0 to be 1, since the initial value is the variance
Uniformly distributed value of (2), the weight Wh j In the range of [ -1.095,1.095]Are uniformly distributed.
Threshold value theta j (wherein J =1, \ 8230;, J) is set to an initial value of [ -1,1]The random number in the middle of the random number,
threshold value gamma h(h＝1，…，h) The initial value is obtained by the following formula:
wherein M is a random number between [ -1,1 ].
The correction module 204: the training error interval is used for obtaining a trained self-learning wireless signal positioning model if the training result does not exceed the training error interval;
specifically, in this embodiment, any conventional signal strength positioning algorithm is used to perform position calculation on the steady-state signal data to obtain a training coordinate comparison set; the method comprises the steps of selecting a signal intensity positioning algorithm to carry out position calculation on stable signal data, calculating the distances from a terminal to three nearest terminal base stations by utilizing a wireless signal intensity and distance formula according to the signal intensity of a terminal to be detected received by the terminal base stations, calculating the position coordinates of the terminal to be positioned by using a trilateration method, namely, drawing a circle by taking the three terminal base stations as the circle centers and the distance from the terminal to be positioned to the terminal base station as a radius, wherein the intersection point of the three circles is the position of the terminal to be positioned. Wherein, the intensity and distance calculation formula is as follows:
d is the distance from the terminal to the base station, d 0 For a reference distance, typically 1 meter; p is T The power for the hair to be sent; p L(d0) The signal strength received by the base station when the terminal is located at the reference distance; p L(d0) The signal strength received by the base station when the terminal is located at a distance d from the base station; eta is a path loss exponent, and is usually 2 to 4.
Further, the correction module calculates whether the training error of the training coordinate result set and the training coordinate comparison set exceeds the training error interval;
specifically, in this embodiment, any training sample K in the training sample set is extracted, and the terminal base station uses the training coordinate comparison set measured in the conventional manner
The training result is
The signal strength value of the training samples is,
the error value is expressed as the following equation using the least squares method:
further, in this embodiment, if the training error exceeds the preset error interval, the to-be-trained self-learning wireless signal positioning model is retrained until the training error is within the training error interval.
Specifically, the correction module extracts an error value corresponding to the training error; correcting and calculating according to a preset learning rate by using the error value to obtain a correction value; according to E k And calculating the correction value of the weight and the threshold value of each self-learning signal positioning model to be trained by setting a learning rate eta between 0.01 and 0.1, wherein the formula for calculating the correction value of each weight sum and the threshold value is as follows:
Δ Whj is the corrected magnitude of Whj,
delta theta j is the correction value of theta j,
specifically, in this embodiment, the activation function of the hidden layer is a Sigmod function, and then F1' (x) = F1 (x) (1-F1 (x));
wherein, it is made
Δ Vih is the correction value for Vih,
Δ γ h is the corrected magnitude of γ h, Δ γ h = η × eh.
Further, the correction module corrects the to-be-trained self-learning wireless signal positioning model by using the obtained correction quantity value to obtain a corrected to-be-trained self-learning wireless signal positioning model; by usingThe corrected self-learning wireless signal positioning model to be trained is retrained by the corrected weight and the threshold until the corresponding error value E k Within a training error interval; and stopping correcting the to-be-trained self-learning wireless signal positioning model.
Further, if the preset error interval is not exceeded, the trained self-learning wireless signal positioning model is obtained.
The positioning integration module 205: and the self-learning wireless signal positioning model is used for calculating the coordinate position of the terminal to be positioned and outputting the terminal coordinate.
Specifically, in this embodiment, the positioning integration module performs position calculation on the signal parameter set of the terminal to be positioned by using any conventional signal strength positioning algorithm to obtain a first positioning coordinate;
and when the terminal to be positioned is in a stable state representation, outputting a first positioning coordinate as a terminal coordinate of the terminal to be positioned.
Furthermore, the positioning comprehensive module also comprises a step of positioning the unstable terminal to be positioned. Carrying out position calculation on a wireless signal parameter set of a terminal to be positioned by calling a trained self-learning wireless signal positioning model to obtain a second positioning coordinate; and giving weights corresponding to the first positioning coordinate and the second positioning coordinate to calculate the coordinates.
Specifically, the positioning integration module judges whether a self-learning wireless signal positioning model in a current to-be-identified area is in an available state, if so, the self-learning wireless signal positioning model is endowed with low weight of a first positioning coordinate and high weight of a second positioning coordinate, the final coordinates of the first positioning coordinate and the second positioning coordinate are calculated by using the weights to obtain a third positioning coordinate, and the third positioning coordinate is output as a terminal coordinate of the to-be-positioned terminal;
and if the terminal is in a non-available state, giving high weight to the first positioning coordinate, giving low weight to the second positioning coordinate, calculating the final coordinates of the first positioning coordinate and the second positioning coordinate by using the weights to obtain a third positioning coordinate, and outputting the third positioning coordinate as the terminal coordinate of the terminal to be positioned.
Compared with the prior art, the embodiment of the application mainly has the following beneficial effects: according to the method, a certain number of terminal base stations are deployed in an area, whether the signal parameters of the terminal to be positioned are in a stable state or not is judged by the terminal base stations, the signal parameters in the stable state are used for continuous training of the self-learning signal positioning model to be trained, the anti-locking work of generating training samples through manual measurement is replaced by the method, the deployment cost is reduced, meanwhile, the self-learning signal positioning model to be trained is further corrected and trained through correction values, the more self-learning training data accumulated according to the method can greatly improve the positioning accuracy, and the rules of environmental change and wireless signal fluctuation can be adapted.
In order to solve the technical problem, the embodiment of the application further provides computer equipment. Referring to fig. 4 in particular, fig. 4 is a block diagram of a basic structure of a computer device according to the embodiment.
The computer device 4 comprises a memory 31, a processor 32, a network interface 33 communicatively connected to each other via a system bus. It is noted that only the computer device 3 having the components 31-33 is shown in the figure, but it is to be understood that not all of the shown components are required to be implemented, and that more or less components may be implemented instead. As will be understood by those skilled in the art, the computer device is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and the hardware includes, but is not limited to, a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like.
The computer device can be a desktop computer, a notebook, a palm computer, a cloud server and other computing devices. The computer equipment can carry out man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch panel or voice control equipment and the like.
The memory 31 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 31 may be an internal storage unit of the computer device 3, such as a hard disk or a memory of the computer device 3. In other embodiments, the memory 31 may also be an external storage device of the computer device 3, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the computer device 3. Of course, the memory 31 may also comprise both an internal storage unit of the computer device 3 and an external storage device thereof. In this embodiment, the memory 31 is generally used for storing an operating system and various application software installed in the computer device 3, such as program codes of the X method. Further, the memory 31 may also be used to temporarily store various types of data that have been output or are to be output.
The processor 32 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 32 is typically used to control the overall operation of the computer device 3. In this embodiment, the processor 32 is configured to execute the program code stored in the memory 31 or process data, for example, execute the program code of the X method.
The network interface 33 may comprise a wireless network interface or a wired network interface, and the network interface 33 is generally used for establishing a communication connection between the computer device 3 and other electronic devices.
The present application further provides another embodiment, which is to provide a computer readable storage medium storing the online platform modification program, wherein the online platform modification program is executable by at least one processor to cause the at least one processor to perform the steps of the self-learning wireless signal positioning method as described above.
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 online platform, and certainly can also be implemented by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as 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 application.
The application is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
It is to be understood that the above-described embodiments are merely illustrative of some, but not restrictive, of the broad invention, and that the appended drawings illustrate preferred embodiments of the invention and do not limit the scope of the invention. This application is capable of embodiments in many different forms and is provided for the purpose of enabling a thorough understanding of the disclosure of the application. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to one skilled in the art that the present application may be practiced without modification or with equivalents of some of the features described in the foregoing embodiments. All equivalent structures made by using the contents of the specification and the drawings of the present application are directly or indirectly applied to other related technical fields, and all the equivalent structures are within the protection scope of the present application.
Claims (10)
1. A method of self-learning wireless signal location, the method comprising:
acquiring a periodic signal parameter set of a terminal to be positioned in a region to be identified for parameter identification to obtain a state characterization parameter, wherein the state characterization parameter is used for characterizing the motion state of the terminal to be positioned;
automatically and continuously generating a training signal parameter set which can be used for self-learning training by using the state characterization parameters and the signal parameter set;
training a pre-constructed self-learning positioning model to be trained by utilizing the training signal parameter set to obtain a training result set;
if the training result set does not exceed the training error interval, obtaining a trained self-learning wireless signal positioning model;
and calculating the coordinate position of the terminal to be positioned by utilizing the self-learning wireless signal positioning model, and outputting the terminal coordinate.
2. The self-learning wireless signal positioning method of claim 1, wherein before obtaining the signal parameter set of the terminal to be positioned in the area to be identified for parameter identification, the method further comprises:
acquiring position data sets of a plurality of deployed receiving terminals to construct an identification area;
performing geometric re-segmentation on the identification region by using the position data set based on a preset region division rule to obtain a plurality of sub-regions;
performing signal intensity identification on the signal parameters of the terminal to be positioned received in each sub-area to obtain a signal intensity value set;
and extracting the sub-region corresponding to the signal intensity value meeting the condition in the signal intensity value set to form a region to be identified.
3. The self-learning wireless signal positioning method of claim 2, wherein the obtained periodic signal parameter set of the terminal to be positioned in the area to be identified is used for performing parameter identification to obtain a state characterizing parameter, wherein the state characterizing parameter is used for characterizing the motion state of the terminal to be positioned, and the method specifically comprises:
performing data processing on the signal parameter set by using the motion characterization parameter corresponding to the terminal to be positioned;
when the terminal to be positioned is in a static state, extracting a signal parameter set of the terminal to be positioned in the area to be identified, and performing probability accumulation calculation to obtain a probability accumulation value;
if the probability accumulated value exceeds a preset acceptable value, the state characterization parameters perform stable state characterization on the signal intensity of the terminal to be positioned to form stable state signal data;
and if the probability accumulated value does not exceed a preset acceptable value and/or the terminal to be positioned is in a non-static state, performing non-steady state characterization on the signal strength of the terminal to be positioned by the state characterization parameters to form non-steady state signal data.
4. The method as claimed in claim 3, wherein the obtaining of the trained self-learning wireless signal positioning model if the training result set does not exceed the training error interval specifically comprises:
calculating the position of the steady-state signal data by using any conventional signal intensity positioning algorithm to obtain a training coordinate reference set;
calculating whether the training errors of the training coordinate result set and the training coordinate comparison set exceed the training error interval;
if the training error is within the training error interval, retraining the to-be-trained self-learning wireless signal positioning model until the training error is within the training error interval;
and if the wireless signal is not beyond the preset range, obtaining a trained self-learning wireless signal positioning model.
5. The self-learning wireless signal positioning method of claim 4, wherein the calculating the coordinate position of the terminal to be positioned using the self-learning wireless signal positioning model and outputting terminal coordinates further comprises;
calculating the position of the signal parameter set of the terminal to be positioned by utilizing any conventional signal intensity positioning algorithm to obtain a first positioning coordinate;
when the terminal to be positioned is in a stable state representation, outputting the first positioning coordinate as a terminal coordinate;
and/or calling the trained self-learning wireless signal positioning model to perform position calculation on the wireless signal parameter set of the terminal to be positioned to obtain a second positioning coordinate;
giving weights corresponding to the first positioning coordinate and the second positioning coordinate to perform coordinate calculation to obtain a third positioning coordinate;
and when the terminal to be positioned is the unsteady state representation, outputting the third positioning coordinate as a terminal coordinate.
6. The method as claimed in claim 5, wherein the retraining the to-be-trained self-learning wireless signal positioning model until the training error is within the training error interval comprises:
extracting an error value corresponding to the training error;
correcting and calculating according to a preset learning rate by utilizing the error value to obtain a correction value;
and correcting the to-be-trained self-learning wireless signal positioning model by using the correction value to obtain the corrected to-be-trained self-learning wireless signal positioning model.
7. The method as claimed in claim 6, wherein after obtaining the corrected self-learning wireless signal positioning model to be trained, the method further comprises:
retraining the corrected self-learning wireless signal positioning model to be trained until the corresponding error value is within the training error interval;
and stopping correcting the to-be-trained self-learning wireless signal positioning model.
8. A self-learning wireless signal location system, the system comprising:
a motion detection and reporting module: the system is used for measuring the motion state of the positioning terminal and reporting the motion state to a base station in a wireless communication mode;
an identification module: the system comprises a signal parameter set used for acquiring a terminal to be positioned in a region to be identified and carrying out parameter identification to obtain a state representation parameter;
a positioning training module: the self-learning positioning model to be trained is trained by utilizing the state characterization parameters and the signal parameter set to obtain a training result;
a correction module: the training error interval is used for obtaining a trained self-learning wireless signal positioning model if the training result does not exceed the training error interval;
a positioning comprehensive module: and the self-learning wireless signal positioning model is used for calculating the coordinate position of the terminal to be positioned and outputting the terminal coordinate.
9. A computer device comprising a memory having computer readable instructions stored therein and a processor which when executed implements the steps of the self-learning wireless signal location method of any one of claims 1 to 7.
10. A computer readable storage medium having computer readable instructions stored thereon which, when executed by a processor, implement the steps of the self-learning wireless signal location method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211035639.4A CN115767411A (en) | 2022-08-26 | 2022-08-26 | Self-learning wireless signal positioning method, system, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211035639.4A CN115767411A (en) | 2022-08-26 | 2022-08-26 | Self-learning wireless signal positioning method, system, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115767411A true CN115767411A (en) | 2023-03-07 |
Family
ID=85349355
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211035639.4A Pending CN115767411A (en) | 2022-08-26 | 2022-08-26 | Self-learning wireless signal positioning method, system, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115767411A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116763298A (en) * | 2023-05-12 | 2023-09-19 | 嘉兴温芯智能科技有限公司 | State monitoring method and system |
-
2022
- 2022-08-26 CN CN202211035639.4A patent/CN115767411A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116763298A (en) * | 2023-05-12 | 2023-09-19 | 嘉兴温芯智能科技有限公司 | State monitoring method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109397703A (en) | A kind of fault detection method and device | |
| US11161244B2 (en) | System and method for automatic error recovery in robotic assembly | |
| CN106529079A (en) | Chemical process failure detection method based on failure-dependent principal component space | |
| CN109359665B (en) | Household appliance load identification method and device based on support vector machine | |
| CN108615050B (en) | Human body posture distinguishing method based on support vector machine | |
| CN111367777B (en) | Alarm processing method, device, equipment and computer readable storage medium | |
| CN114022847A (en) | Intelligent agent trajectory prediction method, system, equipment and storage medium | |
| CN115767411A (en) | Self-learning wireless signal positioning method, system, equipment and storage medium | |
| CN111414586A (en) | Environment monitoring method and system | |
| Cho et al. | Hierarchical anomaly detection using a multioutput Gaussian process | |
| CN109766905B (en) | Target grouping method based on self-organizing feature mapping network | |
| CN108171271B (en) | Early warning method and system for equipment degradation | |
| CN116993060B (en) | Intelligent building site safety management method and system based on Internet of things | |
| CN115958609B (en) | Instruction data safety early warning method based on intelligent robot automatic control system | |
| Ren et al. | Improved shape-based distance method for correlation analysis of multi-radar data fusion in self-driving vehicle | |
| CN111814523A (en) | Human body activity recognition method and device | |
| EP2889724B1 (en) | System and method for selecting features for identifying human activities in a human-computer interacting environment | |
| CN106156470B (en) | Time series abnormity detection and labeling method and system | |
| CN107122767A (en) | A kind of physical activity end-point detecting method based on comentropy | |
| CN116467102B (en) | Fault detection method and device based on edge algorithm | |
| CN113361932A (en) | Early warning method, device, equipment and medium for calibration assembly line of metering equipment | |
| CN109993182B (en) | Pattern recognition method and device based on Fuzzy ART | |
| CN113233270A (en) | Elevator internal and external judgment method based on robot running safety and related equipment | |
| CN115438452B (en) | Reliable transmission detection method for time sequence network signals | |
| WO2014073366A1 (en) | Information processing system, recognition dictionary learning method, and recognition dictionary learning program |
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 |