CN111694901A - User equipment state judgment method, device, terminal and medium suitable for near field communication - Google Patents
User equipment state judgment method, device, terminal and medium suitable for near field communication Download PDFInfo
- Publication number
- CN111694901A CN111694901A CN201910196719.XA CN201910196719A CN111694901A CN 111694901 A CN111694901 A CN 111694901A CN 201910196719 A CN201910196719 A CN 201910196719A CN 111694901 A CN111694901 A CN 111694901A
- Authority
- CN
- China
- Prior art keywords
- data
- dimensional data
- dimensional
- low
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000004891 communication Methods 0.000 title claims abstract description 33
- 238000012706 support-vector machine Methods 0.000 claims abstract description 25
- 238000012545 processing Methods 0.000 claims abstract description 24
- 230000009467 reduction Effects 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000002123 temporal effect Effects 0.000 claims description 2
- 230000002159 abnormal effect Effects 0.000 abstract description 14
- 238000004422 calculation algorithm Methods 0.000 abstract description 9
- 230000011218 segmentation Effects 0.000 abstract description 9
- 230000008569 process Effects 0.000 abstract description 8
- 230000006870 function Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000012360 testing method Methods 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 5
- 238000012549 training Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000033001 locomotion Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000004931 aggregating effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005562 fading Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000029305 taxis Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
- G01S5/08—Position of single direction-finder fixed by determining direction of a plurality of spaced sources of known location
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
- H04W64/006—Locating users or terminals or network equipment for network management purposes, e.g. mobility management with additional information processing, e.g. for direction or speed determination
Abstract
The application provides a method, a device, a terminal and a medium for judging the state of user equipment suitable for near field communication, only 1 AP is needed, universally applicable data segmentation is carried out in a short time and a short distance according to RSS data, and then processing of selecting a plurality of dimensions in a plurality of dimensions is carried out according to a special rule of the data in the short time and the short distance; after new low-dimensional data are formed, removing abnormal values, performing special permutation and combination under the condition of lower dimension by using a support vector machine algorithm (SVM), and summing a plurality of obtained probability values; through the setting of the threshold, the new data in the online positioning stage is specially restricted. Thereby achieving the purpose of improving the system performance. The invention directly applies the time sequence to directly segment the data, provides a novel multi-dimensional selection, removes abnormal values and processes the SVM by a method of special combination with lower dimension. The method improves the distinguishing accuracy rate of the user states in a short distance in a short time.
Description
Technical Field
The present application relates to the field of mobile positioning technologies, and in particular, to a method, an apparatus, a terminal, and a medium for determining a state of a user equipment suitable for near field communication.
Background
The WiFi positioning technology refers to that WiFi simultaneously realizes a positioning function in addition to a communication function. WiFi is widely used in various large or small buildings such as homes, hotels, cafes, airports, markets and the like, and can also be used in public transportation means such as private cars, taxis, buses, special cars, trains, travel buses, cruise ships and the like, so that WiFi becomes the most attractive wireless technology (including positioning distinguishing and mobile positioning in a static state) in the positioning field.
Rss (received Signal Strength indication) belongs to an optional part of the radio transmission layer and is used to determine the link quality and whether to increase the broadcast transmission Strength. RSS is required for the normal operation of most wireless communication devices, and many communication systems require RSS information for the functions of sensing the quality of a link, implementing handover, adapting transmission rate, and the like. And almost all commercial wireless devices, including smart phones, wireless sensors, RFID readers, bluetooth, LTE, etc., support the collection of RSS data. The acquisition of the RSS of a WiFi signal is simple, the RSS depending on the location of the receiver. RSS is not affected by signal bandwidth and does not require high bandwidth, so RSS is a very popular signal feature and is widely used in positioning.
In a patent No. cn201610539286.x, a method for determining the moving and staying states of a user by using mobile phone positioning data is disclosed. The method for identifying the moving or staying state based on the naive Bayes classifier is established by using continuous track data generated by the positioning of the mobile phone of the user, and specifically comprises the following steps: firstly, establishing a naive Bayes classifier, classifying users by utilizing a certain amount of training samples, and calculating the probability of movement and stay states and the probability of occurrence of characteristic parameter values (direction included angle and minimum covering circle diameter) when stay or movement occurs; and secondly, judging the moving or staying state of the mobile phone positioning data by using a naive Bayes classifier, filtering abnormal data, aggregating and filling according to the sparsity of the data, classifying users, calculating the direction included angle of the characteristic parameters and the diameter value of the minimum coverage circle, and finally calculating the conditional probability of the category by using the established naive Bayes classifier to judge the category attribution of the user state.
However, the method is complex in structure and cannot solve the problem of how to accurately judge the state within a distance of less than 10m, the shorter the distance is, the more difficult the state is to distinguish, and the reference value range of each section is 5 to 30 minutes, so that the actual processing time is too long.
Content of application
In view of the above-mentioned shortcomings of the prior art, the present application aims to provide a method, an apparatus, a terminal, and a medium for determining a status of a user equipment suitable for near field communication, so as to solve the problems in the prior art.
To achieve the above and other related objects, a first aspect of the present application provides a method for determining a status of a user equipment for near field communication, comprising: obtaining a plurality of signal strength data of a plurality of user equipment within a near field range; slicing the acquired plurality of signal strength data into a plurality of data sets of the same number of signal strength data based on the time series; performing dimensionality reduction on each data set to obtain multiple groups of low-dimensional data of each data set; classifying the multiple groups of low-dimensional data of each data set by using a classifier model to obtain probability data of each group of low-dimensional data; and judging the classification value which is used for judging the state of the user equipment and corresponds to the data set to which the low-dimensional data of each group belongs according to the comparison result information between the sum of the probability data of the low-dimensional data of each group and a preset threshold value.
In some embodiments of the first aspect of the present application, each of the data sets is M-dimensional data, and the low-dimensional data is obtained by: k-dimensional data are extracted from the M-dimensional data in each data set, the content of the k-dimensional data is that k signal intensity values in the M-dimensional data are selected from large to small in sequence, and the sequence of the k-dimensional data is sequentially ordered according to the time sequence of the M-dimensional data; (ii) a Based on the first k data captured, (k-1) sets of (k-1) -dimensional data are formed ordered in the k-dimensional data chronologically.
In some embodiments of the first aspect of the present application, let the largest data of the k-dimensional data be kmax(ii) a The acquisition mode of the (k-1) -dimensional data of the (k-1) group ordered according to the original time sequence of the k-dimensional data comprises the following steps: forming k groups of (k-1) -dimensional data which are sorted according to the original time sequence of the k-dimensional data on the basis of the first k pieces of captured data; eliminating k data not including data kmaxTo form said (k-1) sets of (k-1) -dimensional data ordered by signal strength value from large to small.
In some embodiments of the first aspect of the present application, the method further comprises: the k-dimensional data extracted from the M-dimensional data is preprocessed to remove outlier data prior to forming (k-1) sets of (k-1) dimensional data sorted in the original temporal order of the k-dimensional data.
In some embodiments of the first aspect of the present application, the determining, according to the comparison result information between the sum of the probability data of each group of low-dimensional data and a preset threshold, a classification value used for determining a state of the ue and corresponding to a data set to which the group of low-dimensional data belongs includes: if the sum of the probability data of each group of low-dimensional data is greater than or equal to a first preset threshold value, judging that the classification value corresponding to the corresponding data set is a first value; if the sum of the probability data of each group of low-dimensional data is smaller than a second preset threshold value, judging that the classification value corresponding to the corresponding data set is a second value; the sum of the first preset threshold and the second preset threshold is the dimension value of the low-dimensional data; the first and second values represent that the user equipment is in one and the other of a stopped state and a moving state, respectively.
In some embodiments of the first aspect of the present application, the first predetermined threshold is (k-1) · λ; the second preset threshold value is (k-1) · (1- λ); wherein (k-1) represents a dimension value of the low-dimensional data, λ ∈ (0.5, 1).
In some embodiments of the first aspect of the present application, the classifier model comprises an SVM support vector machine model.
In some embodiments of the first aspect of the present application, the near field range comprises a distance range of 10 meters.
To achieve the above and other related objects, a second aspect of the present application provides a user equipment state determination apparatus for near field communication, comprising: the data acquisition module is used for acquiring a plurality of signal intensity data of a plurality of user equipment in a near field range; a data dividing module for dividing the acquired plurality of signal strength data into a plurality of data sets having the same number of signal strength data based on the time series; the data dimension reduction module is used for performing dimension reduction processing on each data set to obtain a plurality of groups of low-dimensional data of each data set; the probability calculation module is used for carrying out classification processing on a plurality of groups of low-dimensional data of each data set by utilizing a classifier model so as to obtain probability data of each group of low-dimensional data; and the threshold comparison module is used for judging the classification value which is used for judging the state of the user equipment and corresponds to the data set to which each group of low-dimensional data belongs according to the comparison result information between the sum of the probability data of each group of low-dimensional data and a preset threshold value.
To achieve the above and other related objects, a third aspect of the present application provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method.
To achieve the above and other related objects, a fourth aspect of the present application provides an electronic terminal comprising: a processor and a memory; the memory is for storing a computer program and the processor is for executing the computer program stored by the memory to cause the terminal to perform the method.
As described above, the method, the apparatus, the terminal, and the medium for determining the state of the user equipment suitable for near field communication according to the present application have the following beneficial effects: according to the technical scheme provided by the application, only 1 AP is needed, universally applicable data segmentation is carried out in a short time and a short distance according to RSS data, and then processing of selecting a plurality of dimensions in a plurality of dimensions is carried out according to a special rule of the data in the short time and the short distance; after new low-dimensional data are formed, removing abnormal values, performing special permutation and combination under the condition of lower dimension by using a support vector machine algorithm (SVM), and summing a plurality of obtained probability values; through the setting of the threshold, the new data in the online positioning stage is specially restricted. Thereby achieving the purpose of improving the system performance. The invention directly applies the time sequence to directly segment the data, provides a novel multi-dimensional selection, removes abnormal values and processes the SVM by a method of special combination with lower dimension. The method improves the distinguishing accuracy rate of the user states in a short distance in a short time.
Drawings
Fig. 1 is a flowchart illustrating a method for determining a status of a ue suitable for nfc according to an embodiment of the present application.
FIG. 2 is a diagram illustrating a set of data sets according to an embodiment of the present application.
Fig. 3 is a schematic diagram illustrating an application scenario of the method for determining a status of a ue in an embodiment of the present application.
Fig. 4 is a schematic diagram of a ue status determination apparatus suitable for nfc according to an embodiment of the present invention.
Fig. 5 is a schematic structural diagram of an electronic terminal according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application is provided by way of specific examples, and other advantages and effects of the present application will be readily apparent to those skilled in the art from the disclosure herein. The present application is capable of other and different embodiments and its several details are capable of modifications and/or changes in various respects, all without departing from the spirit of the present application. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It is noted that in the following description, reference is made to the accompanying drawings which illustrate several embodiments of the present application. It is to be understood that other embodiments may be utilized and that mechanical, structural, electrical, and operational changes may be made without departing from the spirit and scope of the present application. The following detailed description is not to be taken in a limiting sense, and the scope of embodiments of the present application is defined only by the claims of the issued patent. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. Spatially relative terms, such as "upper," "lower," "left," "right," "lower," "below," "lower," "above," "upper," and the like, may be used herein to facilitate describing one element or feature's relationship to another element or feature as illustrated in the figures.
In this application, unless expressly stated or limited otherwise, the terms "mounted," "connected," "secured," "retained," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art as appropriate.
Also, as used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context indicates otherwise. It will be further understood that the terms "comprises," "comprising," and/or "comprising," when used in this specification, specify the presence of stated features, operations, elements, components, items, species, and/or groups, but do not preclude the presence, or addition of one or more other features, operations, elements, components, items, species, and/or groups thereof. The terms "or" and/or "as used herein are to be construed as inclusive or meaning any one or any combination. Thus, "A, B or C" or "A, B and/or C" means "any of the following: a; b; c; a and B; a and C; b and C; A. b and C ". An exception to this definition will occur only when a combination of elements, functions or operations are inherently mutually exclusive in some way.
The judgment of the moving and staying states of the user is an important problem to be solved urgently in the communication field. In the prior art, there is a method for judging the moving and staying states of a user through mobile phone positioning data, and particularly, a moving or staying state identification method based on a naive Bayes classifier is established according to continuous track data generated by the positioning of the mobile phone of the user. However, the method in the prior art has a complicated structure and cannot solve the determination of the moving and staying states of the user in the near field range, for example, the method cannot accurately determine the user state in a distance less than 10 m. It is known that it is difficult to determine the moving and staying states of the user as the distance is shorter.
In view of the defects of long time period, long distance, complex structure and the like of the existing mobile positioning judgment method, the application provides the user equipment state judgment method, the device, the terminal and the medium which are suitable for near field communication, and is used for solving the problems in the prior art. According to the technical scheme provided by the application, only 1 AP is needed, universally applicable data segmentation is carried out in a short time and a short distance according to RSS data, and then processing of selecting a plurality of dimensions in a plurality of dimensions is carried out according to a special rule of the data in the short time and the short distance; after new low-dimensional data are formed, removing abnormal values, performing special permutation and combination under the condition of lower dimension by using a support vector machine algorithm (SVM), and summing a plurality of obtained probability values; through the setting of the threshold, the new data in the online positioning stage is specially restricted. Thereby achieving the purpose of improving the system performance. The invention directly applies the time sequence to directly segment the data, provides a novel multi-dimensional selection, removes abnormal values and processes the SVM by a method of special combination with lower dimension. The method improves the distinguishing accuracy rate of the user states in a short distance in a short time.
An SVM (support Vector machine) support Vector machine is a generalized linear classifier for binary classification of data according to a supervised learning mode, and a decision boundary of the generalized linear classifier is a maximum edge distance hyperplane for solving learning samples. The SVM uses a hinge loss function to calculate empirical risks and adds a regularization term in a solution system to optimize structural risks, and the classifier has sparsity and robustness. SVMs can perform nonlinear classification by a kernel method, which is one of the common kernel learning methods.
Machine learning is a method that can give the machine the ability to learn and thus make it perform functions that cannot be done by direct programming. In a practical sense, machine learning is a method of training a model by using data and then using the model to predict.
Fig. 1 shows a schematic flow chart of a method for determining a state of a ue suitable for nfc according to an embodiment of the present application. In the present embodiment, the method includes step S11, step S12, step S13, step S14, and step S15.
In some embodiments, the method is applicable to a controller, for example: an ARM controller, an FPGA controller, an SoC controller, a DSP controller, or an MCU controller, etc. In some embodiments, the methods are also applicable to computers including components such as memory, memory controllers, one or more processing units (CPUs), peripheral interfaces, RF circuits, audio circuits, speakers, microphones, input/output (I/O) subsystems, display screens, other output or control devices, and external ports; the computer includes, but is not limited to, Personal computers such as desktop computers, notebook computers, tablet computers, smart phones, smart televisions, Personal Digital Assistants (PDAs), and the like. In other embodiments, the method may also be applied to a server, which may be arranged on one or more physical servers according to various factors such as functions, loads, and the like, or may be formed by a distributed or centralized server cluster, which is not limited in this application.
The near field communication described in this embodiment is a communication mode with a short transmission distance, and generally, as long as both communication parties transmit information through electromagnetic waves (infrared, radio microwave, etc.), and the transmission distance is limited to a short range, usually within several tens of meters, it is called short-range wireless communication. To further highlight the advantage of the solution of the present application that the status differentiation is achieved within a short distance and a short time, the following embodiments are explained by taking a communication distance as short as 10m as an example.
In step S11, a plurality of signal strength data of a plurality of user devices within a near field range is acquired. Specifically, a plurality of user equipments in the near field range may be intercepted by one wireless access node AP to acquire and store signal strength data of the user equipments over a period of time.
In step S12, the acquired plurality of signal strength data are divided into a plurality of data sets of the same number of signal strength data on the basis of time series.
In an embodiment, a wireless access node AP listens to a plurality of user equipments in a near field range to obtain signal strength data of the plurality of user equipments in a period of time, and the obtained signal strength data are segmented into a plurality of groups, that is, into a plurality of data sets, according to a time sequence and with every M signal strength data as one group. The number M of the signal strength data in each data set may be, for example, 20, 15, or 10 signal strength data per group, and the like, which is not limited in this application.
It should be noted that in the prior art, the signal strength data usually takes time periods as slicing points, but such slicing manner may cause data loss in some time periods after slicing and data excess in some time periods. The data segmentation mode adopted by the embodiment abandons the concept of an accurate time period, but directly segments the data according to the number of the data based on the time sequence, so that the number of the data in each group of data sets is equal, the problems that some groups of data are incomplete and some groups of data are excessive are avoided, and the accuracy of the state judgment of the user equipment in near field communication is more facilitated.
In step S13, dimension reduction is performed on each of the data sets to obtain multiple sets of low-dimensional data for each data set.
Specifically, each of the data sets is M-dimensional data, that is, M signal intensity data are present in each data set. The low-dimensional data is obtained by the following steps: extracting k-dimensional data from the M-dimensional data in each data set, which are sorted from large to small according to the signal intensity value; and constructing a model H by using an SVM algorithm, and forming (k-1) groups of (k-1) dimensional data which are sorted from large to small according to the signal intensity values on the basis of the first k pieces of data which are acquired.
Wherein, let the maximum data in the k-dimensional data be kmax(ii) a The acquisition mode of the (k-1) group of (k-1) dimensional data which is sorted from large to small according to the signal intensity value comprises the following steps: forming k groups of (k-1) -dimensional data which are sorted from large to small according to the signal intensity value on the basis of the first k pieces of the acquired data; eliminating k data not including data kmaxTo form said (k-1) sets of (k-1) -dimensional data ordered by signal strength value from large to small.
For the understanding of those skilled in the art, the data dimension reduction will be further explained and illustrated with reference to fig. 2. In a certain set of data shown in fig. 2, M signal intensity data are included in common, and the first 5 larger values of the M signal intensity data are selected based on the sequence of the signal intensity values from large to small to form five-dimensional data, i.e., D1, D2, D3, D4 and D5, D1, D2, D3, D4 and D5 are sorted in chronological order of the M signal intensity data, where D3 is the maximum value, D1 is the earliest acquired data, and D5 is the latest.
Based on the extracted D1, D2, D3, D4 and D5, 5 sets of chronologically ordered four-dimensional data are formed as shown on the right side of fig. 2, respectively: a first group (D1, D2, D3, D4), a second group (D1, D2, D3, D5), a third group (D1, D2, D4, D5), a fourth group (D1, D3, D4, D5), a fifth group (D2, D3, D4, D5). One or more sets of data not including the maximum data D3 are removed from the above 5 sets, i.e., a third set (D1, D2, D4, D5) is removed from the above 5 sets, thereby finally forming 4 sets of four-dimensional data.
It should be noted that the selection of the first k larger values from the M signal strength data employed in the present embodiment is due to the fact that the RSS varies greatly in the actual data acquisition, far exceeding the expected increase or decrease of the signal caused by the distance alone. According to the technical scheme, k maximum values are selected from each group of M data after segmentation, namely the maximum k values are selected due to the influence of RSS such as position change of shadow fading and the like, even if the minimum value is selected from a pure expected angle in theory, the discrimination can be maximized, and the minimum value actually has a minimum information amount to the result.
In one embodiment, k-dimensional data extracted from M-dimensional data is preprocessed to remove outlier data prior to forming a (k-1) set of chronologically ordered (k-1) dimensional data. Specifically, k-dimensional data is normalized first, and then abnormal value clearing processing is performed on the normalized data, namely, multidimensional data of offline training is substituted into an offline training set, N points with the shortest Euclidean distance are searched, and direct judgment is performed by the Euclidean distance. When detecting whether the current dimension data is an abnormal value, judging whether more than half of the N points with the nearest Euclidean distance are consistent with the moving state or the staying state of the corresponding user equipment, if so, determining that the dimension data is not an abnormal value, otherwise, determining that the dimension data is an abnormal value and needing to be removed.
In step S14, a classifier model is used to classify the sets of low-dimensional data of each data set to obtain probability data of each set of low-dimensional data.
Specifically, in the above embodiment, the probabilities that the predicted values output based on the preset SVM model algorithm are 0 are P for the (k-1) -dimensional data of the (k-1) group after the low-dimensional processing are taken as an example, respectively1、P2…、Pk-1Then the probability corresponding to the predicted value of 1 is (1-P)1)、(1-P2)…(1-Pk-1)。
In step S15, a classification value used for determining the state of the ue corresponding to the data set to which each group of low-dimensional data belongs is determined according to the comparison result information between the sum of the probability data of each group of low-dimensional data and a preset threshold.
If the k-dimensional time series points satisfy the following formula 1), the corresponding M-dimensional time series point decision value takes 0.
P1+P2+...+Pk-1More than or equal to (k-1) lambda; formula 1)
If the k-dimensional time series points satisfy the following formula 2), the corresponding M-dimensional time series point decision value takes 1.
P1+P2+...+Pk-1< (k-1) (1- λ); formula 2)
Wherein, λ ∈ (0.5,1), and if the sum of the probabilities of the k-dimensional data satisfies formula 1) and formula 2), the predicted value of the original SVM is considered to be correct, so as to improve the accuracy of the user state judgment.
Fig. 3 is a schematic diagram illustrating an application scenario of the method for determining a status of a ue in an embodiment of the present application. In this scenario, the testing area as the near field communication range is a building channel, which includes a fixed area with a size of 0.5 × 1m, a buffer area with a size of 0.5 × 1m, and a continuously moving area with a size of 8 × 1 m.
Three different types of mobile phones (such as A-type mobile phones, B-type mobile phones and C-type mobile phones) are selected as the equipment to be tested, WiFi receiving modules are arranged in all the 3 pieces of equipment to be tested, and 2 pieces of equipment to be tested are arranged in the fixed area. A trolley which is not shown in the drawing is arranged in the building channel, 1 AP and 1 device to be tested are placed in the trolley, and the trolley is connected with a personal computer through an HL-340USB serial port. The three areas of the building passage selected by the embodiment are unobstructed, and except the trolley and the environment around the passage, no other shelters in the passage exist, so that the signal intensity difference between different areas is smaller, and the state discrimination is more difficult.
Before testing, writing a program into the AP kernel to ensure that the AP can receive RSS information sent by 3 devices to be tested, the MAC address of the devices and the time when the AP receives a response signal, and fully debugging the AP, so that the AP outputs the RSS information, the MAC address of the mobile phone and the time when the AP receives the response signal in the reverse direction of the mobile phone to a personal computer through a serial port to store, record and integrate related information of the 3 devices to be tested in the testing process.
In the testing phase, the test can be performed by the following individual steps.
Step a: and moving the trolley from the boundary of the buffer area and the fixed area to the position farthest from the fixed area in the continuous moving area, moving the trolley from the position to the direction close to the fixed area until the trolley is towards the boundary of the buffer area and the fixed area, and repeating the actions for multiple times.
Preferably, in order to ensure the randomness of movement, the trolley can move in a continuous moving area in an accelerating, decelerating or uniform speed mode, a route can randomly select a straight line or a curve and the like, the trolley can randomly stay in a buffer area for a few seconds, and different tests are carried out for multiple times in multiple time periods and corresponding signal intensity data acquisition is carried out.
Step b: the collected signal intensity data is subjected to segmentation and dimension reduction, wherein the processes and principles of data segmentation and dimension reduction are described above, and thus are not described in detail.
Step c: the process and principle of removing the outlier are described above, and thus are not described in detail.
Step d: and (3) constructing a model H for the data subjected to abnormal value processing by using an SVM algorithm, arranging and combining 5 maximum values, dividing into 5 groups, and reducing one dimension for each group to form 5 groups of four-dimensional data. And performing SVM algorithm on the 5 groups of four-dimensional data, and removing one or more groups without the maximum value to finally form 4 groups of four-dimensional data.
Step e: respectively obtaining the probability P with the predicted value of 0 output by the practical application algorithm1、P2、P3、P4Summing the 4 probabilities, and taking lambda as 0.8, judging whether P is satisfied1+P2+P3+P4Not less than 3.2; or a probability P with a prediction value of 11、P2、P3、P4Summing the 4 probabilities, and taking lambda as 0.8, judging whether P is satisfied1+P2+P3+P4Is less than 0.8. If both are satisfied, the sum of the ranges between these still applies to the SVM model.
Those of ordinary skill in the art will understand that: all or part of the steps for implementing the above method embodiments may be performed by hardware associated with a computer program. The aforementioned computer program may be stored in a computer readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Fig. 4 is a schematic diagram of a user equipment state determination apparatus suitable for near field communication according to an embodiment of the present application. The user equipment state judgment device comprises a data acquisition module 41, a data segmentation module 42, a data dimension reduction module 43, a probability calculation module 44 and a threshold comparison module 45.
The data obtaining module 41 is configured to obtain a plurality of signal strength data of a plurality of user equipments in a near field range; the data dividing module 42 is configured to divide the acquired plurality of signal strength data into a plurality of data sets with the same number of signal strength data based on the time series; the data dimension reduction module 43 is configured to perform dimension reduction processing on each data set to obtain multiple sets of low-dimensional data of each data set; the probability calculation module 44 is configured to perform classification processing on the multiple sets of low-dimensional data of each data set by using a classifier model to obtain probability data of each set of low-dimensional data; the threshold comparison module 45 is configured to determine, according to comparison result information between a sum of probability data of each group of low-dimensional data and a preset threshold, a classification value used for determining a state of the user equipment, which corresponds to a data set to which each group of low-dimensional data belongs.
It should be noted that, the embodiment of the apparatus for determining a status of a ue in nfc according to this embodiment is similar to the embodiment of the method for determining a status of a ue in nfc according to the foregoing description, and therefore, no further description is given. It should be noted that the division of the modules of the above apparatus is only a logical division, and the actual implementation may be wholly or partially integrated into one physical entity, or may be physically separated. And these modules can be realized in the form of software called by processing element; or may be implemented entirely in hardware; and part of the modules can be realized in the form of calling software by the processing element, and part of the modules can be realized in the form of hardware. For example, the threshold comparison module may be a processing element separately set up, or may be implemented by being integrated in a chip of the apparatus, or may be stored in a memory of the apparatus in the form of program code, and a processing element of the apparatus calls and executes the function of the threshold comparison module. Other modules are implemented similarly. In addition, all or part of the modules can be integrated together or can be independently realized. The processing element described herein may be an integrated circuit having signal processing capabilities. In implementation, each step of the above method or each module above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in the form of software.
For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), or one or more microprocessors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), among others. For another example, when one of the above modules is implemented in the form of a Processing element scheduler code, the Processing element may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).
Fig. 5 is a schematic structural diagram of another electronic terminal according to an embodiment of the present application. This example provides an electronic terminal, includes: a processor 51, a memory 52, a transceiver 53, a communication interface 54, and a system bus 55; the memory 52 and the communication interface 54 are connected to the processor 51 and the transceiver 53 via the system bus 55 and perform communication with each other, the memory 52 is used for storing computer programs, the communication interface 54 and the transceiver 53 are used for communicating with other devices, and the processor 51 is used for running the computer programs, so that the electronic terminal executes the steps of the user equipment state judgment method suitable for near field communication as described above.
The above-mentioned system bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The system bus may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus. The communication interface is used for realizing communication between the database access device and other equipment (such as a client, a read-write library and a read-only library). The Memory may include a Random Access Memory (RAM), and may further include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory.
The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the device can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.
In summary, the present application provides a method, an apparatus, a terminal, and a medium for determining a state of a user equipment suitable for near field communication, and the technical scheme provided by the present application only requires 1 AP, performs a universally applicable data segmentation in a short time and a short distance according to RSS data, and then performs a process of selecting a plurality of dimensions from a plurality of dimensions according to a special rule of the data in the short time and the short distance; after new low-dimensional data are formed, removing abnormal values, performing special permutation and combination under the condition of lower dimension by using a support vector machine algorithm (SVM), and summing a plurality of obtained probability values; through the setting of the threshold, the new data in the online positioning stage is specially restricted. Thereby achieving the purpose of improving the system performance. The invention directly applies the time sequence to directly segment the data, provides a novel multi-dimensional selection, removes abnormal values and processes the SVM by a method of special combination with lower dimension. The method improves the distinguishing accuracy rate of the user states in a short distance in a short time. Therefore, the application effectively overcomes various defects in the prior art and has high industrial utilization value.
The above embodiments are merely illustrative of the principles and utilities of the present application and are not intended to limit the application. Any person skilled in the art can modify or change the above-described embodiments without departing from the spirit and scope of the present application. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical concepts disclosed in the present application shall be covered by the claims of the present application.
Claims (18)
1. A method for judging the state of user equipment suitable for near field communication is characterized by comprising the following steps:
obtaining a plurality of signal strength data of a plurality of user equipment within a near field range;
slicing the acquired plurality of signal strength data into a plurality of data sets of the same number of signal strength data based on the time series;
performing dimensionality reduction on each data set to obtain multiple groups of low-dimensional data of each data set;
classifying the multiple groups of low-dimensional data of each data set by using a classifier model to obtain probability data of each group of low-dimensional data;
and judging the classification value which is used for judging the state of the user equipment and corresponds to the data set to which the low-dimensional data of each group belongs according to the comparison result information between the sum of the probability data of the low-dimensional data of each group and a preset threshold value.
2. The method of claim 1, wherein each of the data sets is an M-dimensional data, and the low-dimensional data is obtained by:
selecting and extracting k-dimensional data from the M-dimensional data in each data set, wherein the content of the k-dimensional data is that k signal intensity values in the M-dimensional data are selected from large to small in sequence, and the sequence of the k-dimensional data is sequentially ordered according to the time sequence of the M-dimensional data;
based on the first k data captured, (k-1) sets of (k-1) -dimensional data are formed ordered in the k-dimensional data chronologically.
3. According to the rightThe method of claim 2, wherein the largest data of the k-dimensional data is kmax(ii) a The acquisition mode of the (k-1) group of (k-1) dimensional data which is sorted from large to small according to the signal intensity value comprises the following steps:
forming k groups of (k-1) -dimensional data which are sorted according to the original time sequence of the k-dimensional data on the basis of the first k pieces of captured data;
eliminating k data not including data kmaxTo form said (k-1) set of (k-1) -dimensional data sorted in k-dimensional data-in-time order.
4. The method of claim 2, further comprising:
the k-dimensional data extracted from the M-dimensional data is preprocessed to remove outlier data prior to forming (k-1) sets of (k-1) dimensional data sorted in the original temporal order of the k-dimensional data.
5. The method of claim 1, wherein the determining the classification value for determining the ue status corresponding to the data set to which each group of low-dimensional data belongs according to the comparison result information between the sum of the probability data of each group of low-dimensional data and a preset threshold comprises:
if the sum of the probability data of each group of low-dimensional data is greater than or equal to a first preset threshold value, judging that the classification value corresponding to the corresponding data set is a first value;
if the sum of the probability data of each group of low-dimensional data is smaller than a second preset threshold value, judging that the classification value corresponding to the corresponding data set is a second value;
the sum of the first preset threshold and the second preset threshold is the dimension value of the low-dimensional data; the first and second values represent that the user equipment is in one and the other of a stopped state and a moving state, respectively.
6. The method of claim 4, wherein the first preset threshold is (k-1) · λ; the second preset threshold value is (k-1) · (1- λ); wherein (k-1) represents a dimension value of the low-dimensional data, λ ∈ (0.5, 1).
7. The method of claim 1, wherein the classifier model comprises an SVM support vector machine model.
8. The method of claim 1, wherein the near field range comprises a distance range of 10 meters.
9. A device for determining a status of a user equipment suitable for near field communication, comprising:
the data acquisition module is used for acquiring a plurality of signal intensity data of a plurality of user equipment in a near field range;
a data dividing module for dividing the acquired plurality of signal strength data into a plurality of data sets having the same number of signal strength data based on the time series;
the data dimension reduction module is used for performing dimension reduction processing on each data set to obtain a plurality of groups of low-dimensional data of each data set;
the probability calculation module is used for carrying out classification processing on a plurality of groups of low-dimensional data of each data set by utilizing a classifier model so as to obtain probability data of each group of low-dimensional data;
and the threshold comparison module is used for judging the classification value which is used for judging the state of the user equipment and corresponds to the data set to which each group of low-dimensional data belongs according to the comparison result information between the sum of the probability data of each group of low-dimensional data and a preset threshold value.
10. The apparatus of claim 9, wherein the data sets are M-dimensional data, and the data dimension reduction module obtains the sets of low-dimensional data for each data set by:
extracting k-dimensional data from the M-dimensional data in each data set, wherein the content of the k-dimensional data is that k signal intensity values in the M-dimensional data are selected from large to small in sequence, and the sequence of the k-dimensional data is sequentially ordered according to the time sequence of the M-dimensional data;
based on the first k pieces of data extracted, (k-1) -dimensional data in which the (k-1) -dimensional data is sorted in the original time order of the k-dimensional data is formed.
11. The apparatus of claim 10, wherein the largest data of the k-dimensional data is kmax(ii) a The mode of obtaining the (k-1) -dimensional data of the (k-1) group according to the original time sequence of the k-dimensional data by the data dimension reduction module comprises the following steps:
forming k groups of (k-1) -dimensional data which are sorted according to the original time sequence of the k-dimensional data on the basis of the first k pieces of captured data;
eliminating k data not including data kmaxTo form said (k-1) set of (k-1) -dimensional data sorted in k-dimensional data chronological order.
12. The apparatus of claim 10, wherein the data dimension reduction module preprocesses k-dimensional data extracted from the M-dimensional data to remove outlier data prior to forming (k-1) sets of (k-1) dimensional data sorted in chronological order of the k-dimensional data.
13. The apparatus of claim 9, wherein the threshold comparison module performs the threshold comparison by:
if the sum of the probability data of each group of low-dimensional data is greater than or equal to a first preset threshold value, judging that the classification value corresponding to the corresponding data set is a first value;
if the sum of the probability data of each group of low-dimensional data is smaller than a second preset threshold value, judging that the classification value corresponding to the corresponding data set is a second value;
the sum of the first preset threshold and the second preset threshold is the dimension value of the low-dimensional data; the first and second values represent that the user equipment is in one and the other of a stopped state and a moving state, respectively.
14. The apparatus of claim 13, wherein the first preset threshold is (k-1) · λ; the second preset threshold value is (k-1) · (1- λ); wherein (k-1) represents a dimension value of the low-dimensional data, λ ∈ (0.5, 1).
15. The apparatus of claim 9, wherein the classifier model comprises an SVM support vector machine model.
16. The apparatus of claim 9, wherein the near field range comprises a distance range of 10 meters.
17. A computer-readable storage medium, on which a computer program is stored, wherein the computer program, when being executed by a processor, implements the method for determining a status of a user equipment adapted for near field communication according to any one of claims 1 to 8.
18. An electronic terminal, comprising: a processor and a memory;
the memory is used for storing a computer program;
the processor is configured to execute the computer program stored in the memory to enable the electronic terminal to execute the method for determining the status of the user equipment suitable for near field communication according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910196719.XA CN111694901A (en) | 2019-03-15 | 2019-03-15 | User equipment state judgment method, device, terminal and medium suitable for near field communication |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910196719.XA CN111694901A (en) | 2019-03-15 | 2019-03-15 | User equipment state judgment method, device, terminal and medium suitable for near field communication |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111694901A true CN111694901A (en) | 2020-09-22 |
Family
ID=72475828
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910196719.XA Pending CN111694901A (en) | 2019-03-15 | 2019-03-15 | User equipment state judgment method, device, terminal and medium suitable for near field communication |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111694901A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140358835A1 (en) * | 2013-05-30 | 2014-12-04 | Apple Inc. | Range class estimation for radio frequency devices |
| CN104703215A (en) * | 2015-03-27 | 2015-06-10 | 佛山络思讯环保科技有限公司 | Method and system for diagnosing indoor signal strength abnormality |
| US20170064490A1 (en) * | 2015-08-25 | 2017-03-02 | Yahoo! Inc. | System and method for device positioning with bluetooth low energy distributions |
| US20180338330A1 (en) * | 2017-05-22 | 2018-11-22 | Apple Inc. | Proximity pairing based on signal strength |
-
2019
- 2019-03-15 CN CN201910196719.XA patent/CN111694901A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140358835A1 (en) * | 2013-05-30 | 2014-12-04 | Apple Inc. | Range class estimation for radio frequency devices |
| CN104703215A (en) * | 2015-03-27 | 2015-06-10 | 佛山络思讯环保科技有限公司 | Method and system for diagnosing indoor signal strength abnormality |
| US20170064490A1 (en) * | 2015-08-25 | 2017-03-02 | Yahoo! Inc. | System and method for device positioning with bluetooth low energy distributions |
| US20180338330A1 (en) * | 2017-05-22 | 2018-11-22 | Apple Inc. | Proximity pairing based on signal strength |
Non-Patent Citations (1)
| Title |
|---|
| 徐晓苏;吴晓飞;张涛;闫琳宇;: "基于SALDE-UKF-SVM算法的WLAN室内定位方法" * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10964006B2 (en) | Identification of neural-network-generated fake images | |
| CN111867049B (en) | Positioning method, positioning device and storage medium | |
| US20190354509A1 (en) | Techniques for information ranking and retrieval | |
| US9681270B2 (en) | Device localization based on a learning model | |
| CN111860872B (en) | System and method for anomaly detection | |
| US11356537B2 (en) | Self-learning connected-device network | |
| Samek et al. | The convergence of machine learning and communications | |
| CN111796957B (en) | Transaction abnormal root cause analysis method and system based on application log | |
| Haseeb et al. | Wisture: Rnn-based learning of wireless signals for gesture recognition in unmodified smartphones | |
| US20210182595A1 (en) | Methods, systems and apparatus to improve image classification with boundary-bitmaps | |
| CN115905450B (en) | Water quality anomaly tracing method and system based on unmanned aerial vehicle monitoring | |
| Wu et al. | Self-adaptive SVDD integrated with AP clustering for one-class classification | |
| CN111694901A (en) | User equipment state judgment method, device, terminal and medium suitable for near field communication | |
| CN111127481A (en) | Image identification method and device based on TOF image communication area | |
| De Vita et al. | A deep learning approach for indoor user localization in smart environments | |
| CN111798237B (en) | Abnormal transaction diagnosis method and system based on application log | |
| CN111726861B (en) | Indoor positioning method, device and system for heterogeneous equipment and storage medium | |
| CN114430530A (en) | Space division method, apparatus, device, medium, and program product | |
| CN114662580A (en) | Training method, classification method, device, equipment and medium of data classification model | |
| Barnes-Cook et al. | Scalable wireless anomaly detection with generative-lstms on rf post-detection metadata | |
| US20230258772A1 (en) | Cfar adaptive processing for real-time prioritization | |
| CN111693939A (en) | Method, device, equipment and medium for improving positioning accuracy of indoor adjacent grids | |
| CN111882003B (en) | Data classification method, device and equipment | |
| CN116541252B (en) | Computer room fault log data processing method and device | |
| US20240089757A1 (en) | Systems and methods for selecting a machine learning model that predicts a subscriber network experience in a geographic area |
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 | ||
| AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20240119 |
|
| AD01 | Patent right deemed abandoned |