CN117278150B - Indoor wireless network signal measurement and calculation method, equipment and medium - Google Patents
Indoor wireless network signal measurement and calculation method, equipment and medium Download PDFInfo
- Publication number
- CN117278150B CN117278150B CN202311566437.7A CN202311566437A CN117278150B CN 117278150 B CN117278150 B CN 117278150B CN 202311566437 A CN202311566437 A CN 202311566437A CN 117278150 B CN117278150 B CN 117278150B
- Authority
- CN
- China
- Prior art keywords
- signal
- sample
- vector
- determining
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004364 calculation method Methods 0.000 title claims description 15
- 238000000691 measurement method Methods 0.000 title claims description 3
- 239000013598 vector Substances 0.000 claims abstract description 68
- 238000000034 method Methods 0.000 claims abstract description 28
- 230000002159 abnormal effect Effects 0.000 claims abstract description 27
- 230000009131 signaling function Effects 0.000 claims abstract description 19
- 238000005070 sampling Methods 0.000 claims abstract description 16
- 230000008859 change Effects 0.000 claims abstract description 15
- 230000007246 mechanism Effects 0.000 claims abstract description 8
- 238000005259 measurement Methods 0.000 claims description 32
- 239000011159 matrix material Substances 0.000 claims description 22
- 230000006870 function Effects 0.000 claims description 20
- 238000010606 normalization Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 abstract description 13
- 230000004913 activation Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 108010076504 Protein Sorting Signals Proteins 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/309—Measuring or estimating channel quality parameters
- H04B17/318—Received signal strength
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/33—Services specially adapted for particular environments, situations or purposes for indoor environments, e.g. buildings
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Monitoring And Testing Of Transmission In General (AREA)
Abstract
The invention discloses a method, equipment and medium for measuring and calculating indoor wireless network signals, which comprises the following specific steps: constructing an indoor space signal intensity data set; selecting sample data from the signal strength dataset, creating an embedded vector based on the sample data; constructing an encoder, and determining a signal characteristic vector based on the embedded vector; determining a plurality of signal semantical data based on the encoder and the signal feature vector; determining a signal change trend according to the plurality of signal semantical data, and calculating an offset value from each moment of each sample point to a signal function curve; and determining an abnormal sample according to the offset value, correcting the abnormal sample, and outputting the corrected signal strength. The sampled sample sequence is semantically represented and learned through an attention mechanism, and the offset of the sample is corrected according to the signal change trend, so that the influence of local optimum or local worst, overfitting, signal fluctuation and signal detection abnormal value caused by sampling errors on a detection result is effectively avoided, and the accuracy of signal detection is improved.
Description
Technical Field
The invention relates to the technical field of wireless signal processing, in particular to a method, equipment and medium for measuring and calculating indoor wireless network signals.
Background
The wireless communication technology is widely applied to various indoor environments of families, hotels, cafes, airports and shops, and brings convenience to the work and life of people. In recent years, with the popularity of smart devices, wi-Fi networks have become one of the most convenient and popular ways to access the internet. The wireless network signal influencing factors of the indoor environment become complex, wherein the material and distribution of the barriers, the flow of personnel and the mutual interference of the AP equipment can influence the stability of the indoor signals. Even under the condition that the indoor environment is not changed, the signals at the same position can be subjected to fluctuation and attenuation instability. This presents difficulties in the measurement of wireless signals. In order to ensure the quality and reliability of the wireless network, the indoor coverage range of Wi-Fi signals and the signal strength of different positions need to be accurately mastered. In general, people divide an indoor space into a plurality of small grids, and then measure the signal intensity of each grid point, and if the condition that the signal quality is poor or unstable is found, the wireless network can be optimized and adjusted in time. Because of many signal interference factors, in order to avoid inaccuracy of single-point signal measurement values, a manner of measuring and averaging multiple times is generally adopted for indoor signal measurement. However, the signal values measured in a single pass do not reflect the true signal intensity, which has mainly the following drawbacks: (1) All measured values are calculated each time, so that local optimum or local worst is easily brought, and fitting is performed; (2) The indoor signal strength may change along with time, such as the change of personnel concentration, the interference between the AP devices and the number of connecting terminals, and the mean value obtaining mode cannot correctly reflect the change rule of the device signals, and even covers the change rule of the device signals; (3) If some measured values are abnormal, inaccurate effects on the result are likely to occur.
Disclosure of Invention
The invention aims to provide a method, equipment and medium for measuring and calculating signal values of indoor wireless network signals, which are used for measuring the signal values of grid points, wherein the signal values of the grid points cannot be effectively reflected due to signal fluctuation or abnormal value measurement in a traditional sampling mode for taking an average value of a plurality of measurement results.
The invention is realized by the following technical scheme:
the first aspect of the present invention provides a method for measuring and calculating indoor wireless network signals, comprising the following specific steps:
acquiring target measurement grid points, periodically measuring grid signal intensity, and constructing an indoor space signal intensity data set;
selecting sample data from the signal strength dataset, creating an embedded vector based on the sample data;
constructing an encoder, and determining a signal characteristic vector based on the embedded vector;
determining a plurality of signal semantical data based on the encoder and the signal feature vector;
determining a signal change trend according to the plurality of signal semantical data, and calculating an offset value from each moment of each sample point to a signal function curve;
and determining an abnormal sample according to the offset value, correcting the abnormal sample, and outputting the corrected signal strength.
According to the invention, the signal value measurement is carried out on the grid points, the samples are extracted by adopting a random sampling method, the semanteme representation and the learning are carried out on the sampled sample sequence through a attention mechanism, the change trend of the signal represented by the signal function is calculated, and finally the deviation of the samples is corrected to obtain the signal intensity of each grid point, so that the local optimum or the local worst caused by the sampling error is effectively avoided, the overfitting is avoided to a certain extent, the influence of the signal fluctuation and the abnormal value of the signal detection on the detection result is also effectively avoided, and the accuracy of the signal detection is improved.
Further, the constructing the indoor space signal intensity data set specifically includes:
obtaining a target measurement space, and equally dividing the target measurement space intoThe grid points;
periodically measuring the signal intensity of the grid points to obtain a grid signal measured value;
an indoor spatial signal strength dataset is constructed based on the grid signal measurements.
Further, the selecting sample data from the signal strength dataset specifically includes:
randomly selecting a fixed number of samples from the signal intensity data set, and randomly sampling the samples;
in the sampling process, after each time of sample collection, the collected sample is put back into the original data set.
Further, the determining the signal feature vector based on the embedded vector specifically includes:
creating an embedded vector according to token embedding, segment embedding and position embedding;
inputting the embedded vector into a LayerNorm function, and carrying out subsequent normalization operation on the vector;
inputting the embedded vector subjected to normalization operation into a dropout function, and performing anti-overfitting operation on the embedded vector;
and constructing an encoder, and inputting the embedded vector after the anti-overfitting operation into the encoder to obtain the characteristic vector of the signal.
Further, the determining the plurality of signal semantical data specifically includes:
creating a plurality of encoders using a multi-headed attention mechanism, traversing the attention score of each encoder layer in turn;
constructing a multi-head attention matrix, and combining the feature vectors of the signals to obtain attention vectors;
sending the attention vector into residual connection, and determining a residual value;
and inputting the attention to a feedforward neural network, acquiring network weights and learning parameters, and outputting a plurality of signal semanteme data by combining residual values.
Further, the specific attention vector calculating step includes:
；
；
in the method, in the process of the invention,for the multi-headed attention vector, concat () is a join function, head represents a single attention vector, +.>Representing a weight matrix, softmax () representing a normalization function, Q representing a query matrix, K representing a key matrix, V representing a value matrix, T representing a transpose operation, +.>Representing the dimensions of the key matrix.
Further, the calculating the offset value from each time point of each sample point to the signal function curve includes:
constructing a fitting curve of probability distribution of a plurality of data based on offset values of the signal function curve;
and solving the fitting curve based on the Taylor formula to obtain a signal function curve.
Further, the determining and correcting the abnormal sample according to the offset value includes:
defining an offset threshold;
calculating the offset value from each moment to the signal function curve of each sample point for the signal intensity of each grid point at each moment;
judging whether the offset value exceeds a threshold value, if so, determining the sample as an abnormal sample;
acquiring a signal value of the abnormal sample point replaced by a value of the sample corresponding to the fitting curve;
and traversing all grid points to detect and correct abnormal values, and obtaining the corrected indoor signal intensity.
A second aspect of the present invention provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing a method of indoor wireless network signal measurement calculation when executing the program.
A third aspect of the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method of indoor wireless network signal measurement calculation.
Compared with the prior art, the invention has the following advantages and beneficial effects:
(1) By adopting a random sampling method, local optimum or local worst caused by sampling errors are avoided, and overfitting is avoided to a certain extent;
(2) The semantically representing and learning are carried out on the sampled signal sample sequence through an attention mechanism, the mode can find out the association relation among samples, the system can effectively reflect the change of the indoor signal strength along with time, such as the change of personnel concentration, the interference among AP equipment and the quantity of connecting terminals, and the change rule of the signal is better reflected;
(3) The signal intensity of each grid point is obtained by correcting the offset of the sample, so that the influence of signal fluctuation and signal detection abnormal value on a detection result is effectively avoided, and the accuracy of signal detection is improved.
Drawings
In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the drawings that are needed in the examples will be briefly described below, it being understood that the following drawings only illustrate some examples of the present invention and therefore should not be considered as limiting the scope, and that other related drawings may be obtained from these drawings without inventive effort for a person skilled in the art. In the drawings:
fig. 1 is a specific calculation method for signal measurement in an embodiment of the present invention.
Detailed Description
For the purpose of making apparent the objects, technical solutions and advantages of the present invention, the present invention will be further described in detail with reference to the following examples and the accompanying drawings, wherein the exemplary embodiments of the present invention and the descriptions thereof are for illustrating the present invention only and are not to be construed as limiting the present invention.
As a possible embodiment, as shown in fig. 1, the first aspect of the present embodiment provides a method for calculating signal measurement of an indoor wireless network, by performing signal value cycle measurement on grid points to obtain signal strength, constructing an indoor spatial signal strength dataset, selecting sample data from the signal strength dataset, creating an embedded vector based on the sample data, constructing an encoder, determining a signal feature vector based on the embedded vector, determining a plurality of signal semantical data, extracting samples in the process by adopting a random sampling method, performing semantical representation and learning on a sampled sample sequence by using an attention mechanism, determining a signal change trend according to the plurality of signal semantical data, calculating an offset value from each moment of each sample point to a signal function curve, calculating a signal function to represent the signal change trend, and finally correcting the offset of the samples to obtain the signal strength of each grid point, thereby effectively avoiding local optimization or local worst caused by signal sampling errors, avoiding overfitting of signal fluctuation and signal detection abnormal values to a certain extent, and improving the accuracy of signal detection.
In some possible embodiments, the method includes obtaining a target measurement grid point, periodically measuring grid signal strength, and constructing an indoor space signal strength dataset, specifically including:
creating a grid: dividing the indoor space into a plurality of grid points, assuming that the indoor space is L meters long and W meters wide, dividing the indoor space into 1 meter unitsThe grid points;
periodically measuring grid signal strength: for each grid pointWherein: />The signal values were measured every 15 minutes with the detection device, Z times in total, and the signal values measured each time were noted as: />Wherein: i represents the number of measurements, ">The method comprises the steps of carrying out a first treatment on the surface of the j represents the serial number of the indoor grid point, < >>；
Creating a measurement sample: after Z measurements, grid pointsThe signal strength dataset of (2) is:；
acquiring grid signal strength: after Z times of measurement are carried out on all grid points in the room, an indoor space signal intensity data set is obtained; the change in signal strength of the grid points with time is expressed as follows:
；
；
…；
。
in some possible embodiments, sample data is selected from the signal strength dataset, and an embedded vector is created based on the sample data, specifically comprising:
signal characteristic learning: first, a fixed number of samples are randomly selected from a signal strength data set RSSIAfter each sample is collected, the sample needs to be put back into the original data set, that is, the collected sample is guaranteed to be possibly selected again after being put back. By adopting the method for sampling, the sub-sample set may have repeatability, so that the local optimum or the local worst caused by sampling errors are avoided, and the overfitting is avoided to a certain extent; then, for learning sample->Semantic representation of (2) learning signal features through an attention mechanism and association relationships between signals;
random sampling: randomly extracting m samples from the signal intensity data set D to form a sub-sample setThe number of samples of the obtained sampling set and the training set is the same, but the content of the samples is different. If we do R random samples for m sample training sets, R sample sets are different due to randomness;
creating an embedded vector: to capture an effective fitted curve, the signal data is mapped to a fixed dimensional vector. The method comprises token embedding, segment embedding and position embedding, and the three vectors are connected, and the corresponding formulas are as follows:
；
wherein X is an embedded vector, T is token embedding, S is segment embedding, and P is position embedding;
LayerNorm operation is performed: the embedded vector is input into the LayerNorm function for the normalization operation of the vector. The corresponding formula is:
；
performing a dropout operation: the embedded vector is input into a dropout function for vector overfitting prevention. The corresponding formula is:
。
in some possible embodiments, constructing an encoder, determining a signal feature vector based on the embedded vector, and determining a plurality of signal semantically data based on the encoder and the signal feature vector specifically includes:
obtaining signal characteristic vectors: inputting the obtained embedded vector into an encoder to obtain a characteristic vector of a signal;
initializing an encoder: using a multi-headed attention mechanism, the relationship between multiple network device signals can be captured well. This embodiment creates 12 encoders in which attention scores in signal features are calculated using multi-headed attention. It consists of eight attention heads and calculates the attention score in turn;
traversing the encoder layer: each encoder consists of a multi-headed attention and a feed forward, traversing each encoder layer in turn to obtain an attention score;
creating a multi-headed attention matrix: creating 3 attention calculation vectors for the embedded vectors acquired in S204 in turnAnd divide it into a plurality of groups;
calculating an attention score: to enhance the fitting ability of the signal features, three matrices are used in the multi-headed note. Multiplying the weight matrix by X2、/>And->Forming intoThree matrices: query matrix Q, key matrix K, and value matrix V. For each attention head, a self-attention function is performed by input X2 to obtain an attention vector. The weight of the attention value is obtained using a softmax function. The corresponding formula is:；
；
in the method, in the process of the invention,for the multi-headed attention vector, concat () is a join function, head represents a single attention vector, +.>Representing a weight matrix, softmax () representing a normalization function, Q representing a query matrix, K representing a key matrix, V representing a value matrix, T representing a transpose operation, +.>Representing the dimensions of the key matrix;
attention was given to the LayerNorm procedure: the attention vector acquired in step S209 is fed into the residual connection. The residual may return our gradient directly to the initial layer. The corresponding formula is:
；
in the method, in the process of the invention,for residual value->Is a residual function;
input attention to the feed forward neural network: each layer in the encoder contains a fully connected feed forward network that is applied separately and identically to each location. This involves two linear transformations with one ReLU activation in between. When the attention of the signal feature is obtained, it is fed to a Feed Forward Network (FFN). The corresponding formula is:
；
where FFN () is the feed-forward neural network, max () is the activation function,for residual value->Weights for the first layer of the network, < >>Weights for the second layer of the network,>for the first layer learn parameters,/for>Learning parameters for the second time;
calculating an encoder layer output vector: the output vector of the last layer of the hidden layer is used as an attention representation of the signal features.
In some possible embodiments, determining a signal variation trend according to the plurality of signal semantical data, and calculating an offset value from each moment of each sample point to a signal function curve specifically includes: a signal strength fitting curve is obtained by calculating probability distribution of a plurality of signal semantical data, wherein,
defining the signal function includes: the number of normal signal intensity values of each grid point is far greater than that of abnormal values, a fitting curve can be obtained according to probability distribution of a plurality of data, and the fitting curve is expressed by the following functions:
；
representing grid points->Fitting signal intensity values at time t of day. />Samples representing time t, divided into one time period every 15 minutes per day, and 96 time periods in total per day;
the expansion polynomial includes: will be according to the Taylor formulaAnd expanding into a polynomial, wherein s is a Taylor expansion function, k is a Taylor expansion series, and the parameter is a super parameter of the model and needs to be preset. The formula is as follows:
；
further, the conversion into a general form is as follows:
；
wherein the method comprises the steps ofIs the polynomial coefficient we need to solve;
further, let theThen the following steps are obtained:
；
further, findSo that a given dataset +.>Carry to->I.e. minimizing the error value of the function, i.e. solving:
；
further, as the quadratic equation is a concave function with an upward opening, the equation is derived:
；
bringing the sample value into the above-mentioned state to obtainObtaining a signal function:。
in some possible embodiments, the abnormal sample is determined according to the offset value and corrected, the corrected signal strength is output, specifically including calculating the offset value from each time point of each sample point to the signal function curve, if the offset value exceeds the threshold value, the abnormal sample is considered, the abnormal sample is replaced by the value corresponding to the fitted curve,
defining the offset threshold includes: wherein the method comprises the steps ofFor a given anomaly threshold value, the signal value is considered valid if the offset value is below the anomaly threshold value. If the threshold value is exceeded, the point is considered to be an outlier;
calculating the offset value includes: calculating the offset value of the sample point to the signal function curve for the signal intensity of each grid point at each momentFinally, obtaining the sample bias of all grid pointsShifting the value;
；
；
…；
；
the abnormal sample correction includes: if it isThe signal value at that point is considered to be normal. Otherwise, consider that the point is acquired +.>For abnormal samples, we take the value of the fitted curve +.>A signal value for the point;
the obtaining of the corrected grid signal intensity comprises the following steps: after abnormal value detection and correction are carried out on the signal sequences of all grid points, corrected indoor signal intensity is obtained;
；
；
…；
。
a second aspect of the present embodiment provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements a method for measuring and calculating signals of an indoor wireless network when executing the program.
A third aspect of the present embodiment provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method of indoor wireless network signal measurement calculation.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (8)
1. The indoor wireless network signal measurement and calculation method is characterized by comprising the following specific steps:
acquiring target measurement grid points, periodically measuring grid signal intensity, and constructing an indoor space signal intensity data set;
selecting sample data from the signal strength dataset, creating an embedded vector based on the sample data;
constructing an encoder, and determining a signal characteristic vector based on the embedded vector;
the determining the signal characteristic vector based on the embedded vector specifically comprises:
creating an embedded vector according to token embedding, segment embedding and position embedding;
inputting the embedded vector into a LayerNorm function, and carrying out subsequent normalization operation on the vector;
inputting the embedded vector subjected to normalization operation into a dropout function, and performing anti-overfitting operation on the embedded vector;
constructing an encoder, and inputting an embedded vector after performing anti-overfitting operation into the encoder to obtain a characteristic vector of a signal;
determining a plurality of signal semantical data based on the encoder and the signal feature vector;
the determining the plurality of signal semantical data specifically comprises:
creating a plurality of encoders using a multi-headed attention mechanism, traversing the attention score of each encoder layer in turn;
constructing a multi-head attention matrix, and combining the feature vectors of the signals to obtain attention vectors;
sending the attention vector into residual connection, and determining a residual value;
inputting attention into a feedforward neural network, acquiring network weight and learning parameters, and outputting a plurality of signal semanteme data by combining residual values;
determining a signal change trend according to the plurality of signal semantical data, and calculating an offset value from each moment of each sample point to a signal function curve;
and determining an abnormal sample according to the offset value, correcting the abnormal sample, and outputting the corrected signal strength.
2. The indoor wireless network signal measurement computing method of claim 1, wherein the constructing an indoor space signal strength dataset specifically comprises:
acquiring a target measurement space, and equally dividing the target measurement space into L.W grid points;
periodically measuring the signal intensity of the grid points to obtain a grid signal measured value;
an indoor spatial signal strength dataset is constructed based on the grid signal measurements.
3. The indoor wireless network signal measurement computing method of claim 1, wherein the selecting sample data from a signal strength dataset specifically comprises:
randomly selecting a fixed number of samples from the signal intensity data set, and randomly sampling the samples;
in the sampling process, after each time of sample collection, the collected sample is put back into the original data set.
4. The indoor wireless network signal measurement computing method according to claim 1, wherein the attention vector specific computing step includes:
multihead＝concat(head 1 ,…,head h )W O
in the formula, multibead is a multi-head attention vector, concat () is a join function, head represents a single attention vector, W O Representing a weight matrix, softmax () representing a normalization function, Q representing a query matrix, K representing a key matrix, V representing a value matrix, T representing a transpose operation, d k Representing the dimensions of the key matrix.
5. The indoor wireless network signal measurement computing method of claim 1, wherein the computing an offset value of each time to signal function curve for each sample point comprises:
constructing a fitting curve of probability distribution of a plurality of data based on offset values of the signal function curve;
and solving the fitting curve based on the Taylor formula to obtain a signal function curve.
6. The indoor wireless network signal measurement computing method of claim 1, wherein the determining and correcting the abnormal samples according to the offset value comprises:
defining an offset threshold;
calculating the offset value from each moment to the signal function curve of each sample point for the signal intensity of each grid point at each moment;
judging whether the offset value exceeds a threshold value, if so, determining the sample as an abnormal sample;
acquiring a signal value of the abnormal sample point replaced by a value of the sample corresponding to the fitting curve;
and traversing all grid points to detect and correct abnormal values, and obtaining the corrected indoor signal intensity.
7. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the indoor wireless network signal measurement calculation method of any one of claims 1 to 6 when the program is executed by the processor.
8. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the indoor wireless network signal measurement calculation method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311566437.7A CN117278150B (en) | 2023-11-23 | 2023-11-23 | Indoor wireless network signal measurement and calculation method, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311566437.7A CN117278150B (en) | 2023-11-23 | 2023-11-23 | Indoor wireless network signal measurement and calculation method, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117278150A CN117278150A (en) | 2023-12-22 |
| CN117278150B true CN117278150B (en) | 2024-02-09 |
Family
ID=89220062
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311566437.7A Active CN117278150B (en) | 2023-11-23 | 2023-11-23 | Indoor wireless network signal measurement and calculation method, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117278150B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117598700B (en) * | 2024-01-23 | 2024-03-29 | 吉林大学 | Intelligent blood oxygen saturation detection system and method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113779361A (en) * | 2021-08-27 | 2021-12-10 | 华中科技大学 | Construction method and application of cross-modal retrieval model based on multi-layer attention mechanism |
| CN115177273A (en) * | 2022-06-30 | 2022-10-14 | 北京工业大学 | Movement intention identification method and system based on multi-head re-attention mechanism |
| CN115685060A (en) * | 2021-07-28 | 2023-02-03 | 华为技术有限公司 | Indoor fingerprint map construction method and related device |
| CN116109649A (en) * | 2023-02-01 | 2023-05-12 | 电子科技大学 | 3D point cloud instance segmentation method based on semantic error correction |
| KR20230096523A (en) * | 2021-12-23 | 2023-06-30 | 명지대학교 산학협력단 | Indoor positioning method and apparatus |
| CN116824143A (en) * | 2023-06-29 | 2023-09-29 | 合肥工业大学 | Point cloud segmentation method based on bilateral feature fusion and vector self-attention |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2677087A1 (en) * | 2007-02-05 | 2008-08-14 | Andrew Corporation | System and method for optimizing location estimate of mobile unit |
| US9408026B2 (en) * | 2011-10-04 | 2016-08-02 | Telefonaktiebolaget Lm Ericsson (Publ) | Methods and arrangements for positioning in wireless communications systems |
| US11580317B2 (en) * | 2019-03-16 | 2023-02-14 | Nec Corporation | Tracking RFID groups with spatio-temporal proximity |
-
2023
- 2023-11-23 CN CN202311566437.7A patent/CN117278150B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115685060A (en) * | 2021-07-28 | 2023-02-03 | 华为技术有限公司 | Indoor fingerprint map construction method and related device |
| CN113779361A (en) * | 2021-08-27 | 2021-12-10 | 华中科技大学 | Construction method and application of cross-modal retrieval model based on multi-layer attention mechanism |
| KR20230096523A (en) * | 2021-12-23 | 2023-06-30 | 명지대학교 산학협력단 | Indoor positioning method and apparatus |
| CN115177273A (en) * | 2022-06-30 | 2022-10-14 | 北京工业大学 | Movement intention identification method and system based on multi-head re-attention mechanism |
| CN116109649A (en) * | 2023-02-01 | 2023-05-12 | 电子科技大学 | 3D point cloud instance segmentation method based on semantic error correction |
| CN116824143A (en) * | 2023-06-29 | 2023-09-29 | 合肥工业大学 | Point cloud segmentation method based on bilateral feature fusion and vector self-attention |
Non-Patent Citations (2)
| Title |
|---|
| 室内定位方法综述;席瑞 等;计算机科学;20160415(第04期);全文 * |
| 普适环境室内定位***研究;梁韵基 等;计算机科学;20100315(第03期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117278150A (en) | 2023-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117278150B (en) | Indoor wireless network signal measurement and calculation method, equipment and medium | |
| CN115018021B (en) | Machine room abnormity detection method and device based on graph structure and abnormity attention mechanism | |
| CN107966638B (en) | Method and apparatus for correcting error, storage medium, and processor | |
| CN109151995B (en) | Deep learning regression fusion positioning method based on signal intensity | |
| CN112884056A (en) | Optimized LSTM neural network-based sewage quality prediction method | |
| CN109359665B (en) | Household appliance load identification method and device based on support vector machine | |
| CN111680725B (en) | Gas sensor array multi-fault isolation algorithm based on reconstruction contribution | |
| CN110297218B (en) | Method for detecting unknown modulation mode of radar signal based on generation countermeasure network | |
| CN113705809B (en) | Data prediction model training method, industrial index prediction method and device | |
| CN117056874A (en) | Unsupervised electricity larceny detection method based on deep twin autoregressive network | |
| CN117349664B (en) | On-line monitoring method and system for sprouting vegetable growth environment | |
| CN116522096B (en) | Three-dimensional digital twin content intelligent manufacturing method based on motion capture | |
| CN114584230B (en) | Predictive channel modeling method based on countermeasure network and long-term and short-term memory network | |
| CN109187898B (en) | Soft measurement method and device for ammonia nitrogen content of water in aquaculture environment | |
| CN110232221A (en) | Dam Crack influence factor dynamic Contribution Rate method | |
| CN111641471B (en) | Weight design method for prediction in atomic clock signal combination control | |
| CN112040408B (en) | Multi-target accurate intelligent positioning and tracking method suitable for supervision places | |
| CN110793920B (en) | Atmospheric remote measurement method combining chemical imaging and hyperspectral | |
| CN114896895A (en) | Gate-controlled cyclic neural network-based denitration system inlet nitrogen oxide emission prediction method and system | |
| CN113657520A (en) | Intrusion detection method based on deep confidence network and long-time and short-time memory network | |
| CN109521176B (en) | Virtual water quality monitoring method based on improved deep extreme learning machine | |
| CN116051555B (en) | Wafer temperature distribution detection system and method | |
| CN113779837B (en) | Structural modal sensitivity analysis method based on novel actual measurement normalization technology | |
| CN117556226A (en) | Electronic current transformer error prediction method and device based on neural network | |
| CN112230532A (en) | New atomic clock signal prediction method, device and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |