CN114252892A - Training method of machine learning model, interference detection method and device - Google Patents
Training method of machine learning model, interference detection method and device Download PDFInfo
- Publication number
- CN114252892A CN114252892A CN202010947378.8A CN202010947378A CN114252892A CN 114252892 A CN114252892 A CN 114252892A CN 202010947378 A CN202010947378 A CN 202010947378A CN 114252892 A CN114252892 A CN 114252892A
- Authority
- CN
- China
- Prior art keywords
- gnss
- interference
- historical
- positioning
- point
- 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 93
- 238000012549 training Methods 0.000 title claims abstract description 73
- 238000010801 machine learning Methods 0.000 title claims abstract description 49
- 238000001514 detection method Methods 0.000 title claims abstract description 32
- 230000008569 process Effects 0.000 claims description 17
- 230000008859 change Effects 0.000 claims description 16
- 238000004891 communication Methods 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 abstract 1
- 230000015654 memory Effects 0.000 description 13
- 238000005516 engineering process Methods 0.000 description 8
- 230000004807 localization Effects 0.000 description 7
- 238000004590 computer program Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 230000009191 jumping Effects 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008054 signal transmission 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
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/01—Satellite radio beacon positioning systems transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/13—Receivers
- G01S19/21—Interference related issues ; Issues related to cross-correlation, spoofing or other methods of denial of service
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Software Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The application discloses a training method of a machine learning model, an interference detection method and an interference detection device. The training method of the machine learning model comprises the following steps: obtaining a training sample set, wherein the sample set comprises interference samples and normal samples, one interference sample corresponds to a historical GNSS positioning point generated when equipment is interfered by GNSS, and one normal sample corresponds to a historical GNSS positioning point generated when the equipment is not interfered by the GNSS; determining a characteristic value of the sample according to the positioning parameters of the historical GNSS positioning points corresponding to the sample; and training the set machine learning model by using the training sample set with the determined characteristic value to obtain the machine learning model for detecting the GNSS signal interference. The signal interference detection model can be obtained quickly and efficiently, the accuracy of model detection is high, and the cost of model training and monitoring is low.
Description
Technical Field
The application relates to the technical field of satellite navigation signal positioning, in particular to a training method, an interference detection method and an interference detection device of a machine learning model.
Background
With the development of the civilization of a Satellite Navigation System (GNSS), the GNSS brings great convenience to the life of people, and particularly in the field of travel, the GNSS can provide various location-related services such as map Navigation and network car booking for users by combining with an electronic map.
Meanwhile, new problems occur in civil scenes, for example, GNSS interference, which may affect positioning based on GNSS, such as a problem that accuracy of a positioning location is lowered or the location cannot be positioned, thereby affecting implementation of a related location service. Therefore, the detection of GNSS interference becomes a problem to be solved by providers of relevant location services.
The existing GNSS interference detection technology mainly includes:
1. signal feature detection techniques. The technology detects the original signal characteristics of the GNSS to judge whether the GNSS receiver is interfered, and the detection of the original signal characteristics needs to modify the hardware or software part of the GNSS receiver.
2. Secondary information spoofing detection techniques. The technology compares data output by auxiliary equipment (an inertia/magnetic sensor, a log, a high-precision clock and the like) with data output by a GNSS receiver to realize interference detection, but the method can increase the cost of equipment for carrying the GNSS receiver and is only suitable for local scenes.
3. Direction of arrival detection techniques. The technology utilizes the antenna array to track the incident direction of the signal, when all satellites are detected to be incident from the same direction, the interference signal exists, the technology needs the antenna array, and the technology is difficult to be applied to consumer electronic products such as mobile phones and the like which carry GNSS receivers.
In summary, the above-mentioned technologies generally need to involve hardware modification, but the hardware modification of the consumer electronic product with the GNSS receiver has a cost problem on one hand, and on the other hand, the consumer electronic product has various models, has hardware differences and software limitations, and is difficult to implement GNSS interference detection through hardware and software modification.
Disclosure of Invention
In view of the above, the present application is proposed to provide a training method of a machine learning model, an interference detection method and apparatus that overcome or at least partially solve the above problems.
In a first aspect, an embodiment of the present application provides a method for training a machine learning model, where the model is used for detecting GNSS signal interference, and the method includes:
obtaining a training sample set, wherein the sample set comprises interference samples and normal samples, one interference sample corresponds to a historical GNSS positioning point generated when equipment is interfered by GNSS, and one normal sample corresponds to a historical GNSS positioning point generated when the equipment is not interfered by the GNSS;
determining a characteristic value of the sample according to the positioning parameters of the historical GNSS positioning points corresponding to the sample;
and training the set machine learning model by using the training sample set with the determined characteristic value to obtain the machine learning model for detecting the GNSS signal interference.
In some optional embodiments, the characteristic values of the sample include at least: determining a characteristic value of the sample according to the positioning parameter of the historical GNSS positioning point corresponding to the sample by using the pseudo-range residual error, wherein the determination comprises the following steps:
determining a pseudo-range residual error between equipment and an effective satellite according to positioning parameters of a historical GNSS positioning point corresponding to a sample, wherein the equipment is equipment for generating the historical positioning point corresponding to the sample, and the effective satellite is a GNSS satellite participating in resolving the positioning position of the historical GNSS positioning point;
and determining the mean value of the pseudo-range residuals meeting the set conditions in the pseudo-range residuals of the equipment and the effective satellites as the pseudo-range residuals of the sample.
In some optional embodiments, the characteristic values of the sample further comprise at least one of the following parameters:
the device calculating height, the obtained device height difference, the difference between the calculating angular velocity and the IMU measuring angular velocity and the calculating clock difference of the receiver loaded by the device.
In some optional embodiments, the characteristic value of the sample further comprises the number of valid satellites.
In some optional embodiments, the characteristic value of the sample further comprises a frequency drift of the device, the frequency drift of the device of the sample is determined by:
and determining the frequency drift of the equipment through Doppler frequency shift according to the change rate of the pseudo range between the equipment and the effective satellite, the position of the equipment and the position of the effective satellite.
In some optional embodiments, the characteristic values of the sample further comprise:
a signal-to-noise ratio of the active satellite, and/or an uncertainty in a rate of change of pseudorange between the device and the active satellite, the method further comprising:
the signal-to-noise ratio of the active satellite and/or the uncertainty in the rate of change of pseudorange between the device and the active satellite is obtained from data output by the operating system of the device.
In some optional embodiments, the method further comprises:
determining historical GNSS positioning points generated when the equipment is interfered by GNSS based on the historical GNSS positioning point data; correspondingly, the acquiring of the training sample set specifically includes:
interference samples are determined from historical GNSS positioning points generated when the equipment is interfered by GNSS, normal samples are determined from other historical GNSS positioning points in the historical GNSS positioning point data, and a training sample set is obtained.
In some optional embodiments, the method further comprises:
determining a GNSS positioning point generated when the equipment is interfered by GNSS based on historical GNSS positioning point data, and determining an interference hop geofence area according to the GNSS positioning point generated when the equipment is interfered by GNSS; correspondingly, the acquiring of the training sample set specifically includes:
and determining an interference sample from GNSS positioning points generated when equipment in the interference hop point geo-fence area is interfered by GNSS, and determining a normal sample from other historical GNSS positioning points in the interference hop point geo-fence area to obtain a training sample set.
In some optional embodiments, the determining, based on the historical GNSS positioning point data, a historical GNSS positioning point generated when the device is subjected to GNSS interference specifically includes:
aiming at historical GNSS positioning point data which belong to historical GNSS positioning points generated in the same driving process of the same equipment, the following steps are executed:
determining a GNSS interference positioning head point and a GNSS interference positioning tail point from historical GNSS positioning points generated in the same driving process of the same device;
and judging whether the area or the track of a geographic area formed by the GNSS interference positioning head point, the GNSS interference positioning tail point and the historical GNSS positioning points positioned between the head point and the tail point meets the rule of occurrence of GNSS interference, and if so, determining the head point, the tail point and the historical GNSS positioning points between the head point and the tail point as the GNSS positioning points generated when the GNSS interference occurs.
In some optional embodiments, the determining whether a trajectory formed by the GNSS interference positioning start point, the GNSS interference positioning end point, and the historical GNSS positioning point located between the start point and the end point satisfies a rule of occurrence of GNSS interference specifically includes:
map matching is carried out on historical GNSS positioning points, and if the continuous historical GNSS positioning points exceeding the preset number do not have matched road sections, the rule of GNSS interference is met; or the like, or, alternatively,
map matching is carried out on historical GNSS positioning points to obtain more than two matched road sections, and if the road sections are not communicated with other road sections, the rule of GNSS interference is met; accordingly, the method can be used for solving the problems that,
the determining of the head point, the tail point and the historical GNSS positioning points therebetween as the GNSS positioning points generated when GNSS interference occurs specifically includes:
setting the historical GNSS positioning points corresponding to the disconnected road sections as GNSS positioning points generated when GNSS interference occurs;
if the road sections are communicated, determining whether the path formed by the communication has a path section which does not accord with the driving rule, if so, meeting the rule of GNSS interference; accordingly, the method can be used for solving the problems that,
the determining of the head point, the tail point and the historical GNSS positioning points therebetween as the GNSS positioning points generated when GNSS interference occurs specifically includes: and determining the historical GNSS positioning point corresponding to the road section of the road end which does not conform to the driving rule as the GNSS positioning point generated when the GNSS interference occurs.
In a second aspect, an embodiment of the present application provides an interference detection method, including:
determining a characteristic value according to positioning parameters of the GNSS positioning point;
and inputting the characteristic value into a machine learning model obtained by training by adopting the method, and determining whether the GNSS positioning point is a positioning point generated when the equipment is interfered by GNSS signals according to an output result of the model.
In a third aspect, an embodiment of the present application provides a training apparatus for a machine learning model, where the model is used for detecting GNSS signal interference, and the apparatus includes:
the acquisition module is used for acquiring a training sample set, wherein the sample set comprises interference samples and normal samples, one interference sample corresponds to a historical GNSS positioning point generated when equipment is interfered by GNSS, and one normal sample corresponds to a historical GNSS positioning point generated when the equipment is not interfered by the GNSS;
the determining module is used for determining a characteristic value of the sample according to the positioning parameters of the sample corresponding to the GNSS historical positioning points obtained by the obtaining module;
and the training module is used for training the set machine learning model by using the training sample set of the characteristic value determined by the determining module so as to obtain the machine learning model for detecting the GNSS signal interference.
In a fourth aspect, an embodiment of the present application provides an interference detection apparatus, including:
the determining module is used for determining a characteristic value according to the positioning parameters of the GNSS positioning point;
and the detection module is used for inputting the characteristic value determined by the determination module into the machine learning model obtained by training by adopting the training method of the machine learning model, and determining whether the GNSS positioning point is a positioning point generated when the equipment is interfered by the GNSS signal according to the output result of the model.
In a fifth aspect, embodiments of the present application provide a computer-readable storage medium, on which computer instructions are stored, and when the instructions are executed by a processor, the method for training a machine learning model described above is implemented, or the method for detecting interference described above is implemented.
In a sixth aspect, an embodiment of the present application provides a server, including: the computer program comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the training method of the machine learning model or the interference detection method when executing the program.
The beneficial effects of the above technical scheme provided by the embodiment of the application at least include:
according to the training method of the machine learning model, a training sample set is obtained, wherein the sample set comprises interference samples and normal samples, one interference sample corresponds to a historical GNSS locating point generated when equipment is interfered by GNSS, and one normal sample corresponds to a historical GNSS locating point generated when the equipment is not interfered by the GNSS; determining a characteristic value of the sample according to the positioning parameters of the historical GNSS positioning points corresponding to the sample; and training the set machine learning model by using the training sample set with the determined characteristic value to obtain the machine learning model for detecting the GNSS signal interference. The method has the advantages that the historical GNSS locating points and the locating parameters which can be directly obtained from a satellite navigation locating system by the equipment are utilized, a sample set is obtained by resolving, a specified machine learning model is trained, the original signal characteristics of the satellite navigation signals do not need to be obtained, the improvement of hardware or software is not needed, the obtaining cost of the sample set is low, the process is simple, and the interference of recognizing the satellite navigation locating signals in the locating process of terminal equipment such as a mobile phone or a vehicle-mounted locator is realized.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present application is further described in detail by the accompanying drawings and examples.
Drawings
The accompanying drawings are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiment(s) of the application and together with the description serve to explain the application and not limit the application. In the drawings:
FIG. 1 is a flowchart illustrating a method for training a machine learning model according to an embodiment of the present disclosure;
FIG. 2 is a flowchart illustrating an embodiment of determining a sample parameter value according to an embodiment of the present disclosure;
FIG. 3 is a flowchart illustrating an implementation of step S24 in FIG. 2;
fig. 4 is a flowchart of an interference localization point identification method in the second embodiment of the present application;
fig. 5 is an exemplary diagram of an interference localization point in the second embodiment of the present application;
fig. 6 is a flowchart of another method for identifying an interference localization point in the third embodiment of the present application;
FIG. 7 is a schematic structural diagram of a training apparatus for machine learning model according to an embodiment of the present application;
fig. 8 is a schematic structural diagram of an interference detection apparatus in an embodiment of the present application.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
In order to solve the problems that the satellite navigation signal interference detection of a mobile terminal in the prior art is high in cost and difficult to implement, embodiments of the present application provide a training method, an interference detection method, and an apparatus for a machine learning model, which can quickly and efficiently detect whether a positioning point obtained by a satellite navigation positioning method is a positioning point generated when the satellite navigation signal interference is received, and are high in accuracy and low in cost.
GNSS spoofing, which typically spoofs a GNSS receiver to lock onto a spoofed signal and produce a false position, typically by GNSS signal forwarding or signal generator, etc.; in the narrow GNSS interference, a GNSS receiver is generally prevented from locking a real signal by emitting a suppressed signal in the same frequency band of the GNSS signal, so that the GNSS receiver cannot be positioned or the positioning accuracy is reduced. These phenomena may be collectively referred to as GNSS interference in a broad sense, and the interference in the embodiment of the present application is GNSS interference in a broad sense.
Example one
An embodiment of the present application provides a training method for a machine learning model, where the model is used for detecting GNSS signal interference, and a training process of the training method is shown in fig. 1, and includes the following steps:
step S11: a training sample set is obtained.
The sample set comprises interference samples and normal samples, wherein one interference sample corresponds to a historical GNSS positioning point generated when the equipment is interfered by GNSS, and one normal sample corresponds to a historical GNSS positioning point generated when the equipment is not interfered by GNSS.
Specifically, the GNSS positioning points described above and in the following description are positioning points obtained by using a satellite navigation positioning method. Taking the device as a mobile phone, for example, the positioning points determined in different manners may be obtained from different network positioning interfaces, for example, GNSS positioning points obtained by a satellite navigation positioning manner are obtained from a satellite navigation positioning interface.
In one embodiment, the method may include determining historical GNSS fix generated when the device is subject to GNSS interference based on historical GNSS fix data; interference samples are determined from historical GNSS positioning points generated when the equipment is subjected to GNSS interference, normal samples are determined from other historical GNSS positioning points (historical GNSS positioning points generated when the equipment is not subjected to GNSS interference) in historical GNSS positioning point data, and a training sample set is obtained.
In one embodiment, the method may further include determining a GNSS positioning point generated when the device is subjected to GNSS interference based on historical GNSS positioning point data, and determining an interference hop geofence region according to the GNSS positioning point generated when the device is subjected to GNSS interference; an interference sample is determined from GNSS positioning points generated when equipment in the interference hop geofence area is interfered by GNSS, and a normal sample is determined from other historical GNSS positioning points (historical GNSS positioning points generated when the equipment is not interfered by GNSS) in the interference hop geofence area, so as to obtain a training sample set.
The interference hop geofenced area is an area defined based on an interference localization point determined by a GNSS localization point generated when the device identified in the historical GNSS localization points is interfered by GNSS, i.e., a localization point generated according to the GNSS signal positioning that is interfered.
Specifically, at least one interference hop geofence area may be obtained through manual interaction according to the location information of the GNSS interference point; or, the GNSS interference points with the close positions are clustered into one type, and an interference hop point geo-fence area is determined according to the position information of each type of interference points; other methods may be used to determine the interfering hop geofence region based on the location information of the GNSS interfering points.
Interference samples and normal samples are determined only from historical positioning points in the interference skip point geo-fence area, so that the labeling information (interference or normal) of each sample is more accurate, the interference of other factors is eliminated, and the accuracy of the model obtained by final training is higher.
Step S12: and determining the characteristic value of the sample according to the positioning parameters of the historical GNSS positioning points corresponding to the sample.
The characteristic values of the sample comprise at least one of the following parameters:
(1) and (5) pseudo-range residual errors.
Determining pseudo-range residual errors between the equipment and effective satellites according to positioning parameters of historical GNSS positioning points corresponding to the samples; and determining the mean value of the pseudo-range residuals meeting the set conditions in the pseudo-range residuals of the equipment and the effective satellites as the pseudo-range residuals of the sample. For example, the mean of a preset number of maximum pseudorange residuals among the pseudorange residuals of the device and the valid satellites may be used as the pseudorange residual of the sample.
The equipment is equipment for generating historical positioning points corresponding to the samples; the effective satellite is a GNSS satellite which participates in resolving the positioning position of the historical GNSS positioning point, not all the satellite information received by the equipment participates in resolving the positioning position, but only the effective satellite information participates in resolving the positioning position.
The distance between the device and the effective satellite can be determined according to the position of the device and the position of the effective satellite; the range residuals (i.e., pseudorange residuals) between the device and the active satellites are determined based on the distances between the device and the active satellites, the pseudoranges between the device and the active satellites, and the clock error of the device.
The narrow clock difference is a clock difference between a clock of the device receiver and a standard clock of the satellite, and the clock difference is a generalized clock difference and includes errors caused by the narrow clock difference, frequency offset, random error and the like.
The pseudorange between the satellite and the device may be determined from the speed of light, the time of signal reception and the time of signal transmission in the satellite navigation signal information.
(2) The number of valid satellites.
In the process of resolving the positioning position by the satellite navigation positioning system according to the satellite navigation positioning information, effective satellites need to be screened from a plurality of satellites capable of receiving satellite signals, and the positioning position is determined according to the received signals of the effective satellites. The effective satellite can be determined by determining the pitch angle between the device and the satellite according to the position of the device receiver, namely the device, and the position of the satellite, and screening the satellite with the pitch angle larger than a set angle as the effective satellite.
(3) And (4) frequency drift of equipment.
The frequency drift of the device, that is, the time offset of the clock of the device receiver in unit time, may specifically be determined by doppler shift according to the pseudo-range change rate between the device and the effective satellite, the position of the device, and the position of the effective satellite.
(4) Signal-to-noise ratio of the active satellite.
The signal-to-noise ratio of the active satellite can be directly obtained from data output by the operating system of the device.
(5) The rate of change of pseudoranges between the device and the active satellite.
The rate of change of pseudoranges between the device and the active satellites may be obtained directly from data output by the operating system of the device.
Optionally, the characteristic value of the sample may further include at least one of the following parameters:
the method comprises the steps of calculating the height of equipment, obtaining the height difference of the equipment, calculating the difference value of angular velocity and IMU measured angular velocity, and calculating the clock difference value of a receiver loaded on the equipment.
The obtained device height difference is the difference between the device height at a certain moment and the device height at the previous moment directly obtained from data output by an operating system of the device; correspondingly, the clock difference value is solved as the difference value between the clock difference of the equipment receiver at a certain moment and the clock difference of the equipment receiver at the previous moment.
The parameters are acquired either in a positioning parameter calculation mode or directly acquired from data output by an operating system of the equipment. The most original satellite observation data acquired by the equipment is an encrypted message containing the parameters, for example, an encrypted message in a character string form consisting of 0 and 1; the operating system of the device decrypts and calculates the received information and outputs the information, so that parameters such as the signal-to-noise ratio of the effective satellite and the uncertainty of the pseudo-range change rate can be directly acquired from data output by the operating system of the device.
Step S13: and training the set machine learning model by using the training sample set with the determined characteristic value to obtain the machine learning model for detecting the GNSS signal interference.
The training method of the machine learning model, provided by the embodiment of the application, includes obtaining a training sample set, where the sample set includes interference samples and normal samples, where one interference sample corresponds to a historical GNSS positioning point generated when a device is interfered by GNSS, and one normal sample corresponds to a historical GNSS positioning point generated when a device is not interfered by GNSS; determining a characteristic value of the sample according to the positioning parameters of the historical GNSS positioning points corresponding to the sample; and training the set machine learning model by using the training sample set with the determined characteristic value to obtain the machine learning model for detecting the GNSS signal interference. The method comprises the steps of directly obtaining historical GNSS locating points and locating parameters from a satellite navigation locating system by utilizing equipment, resolving to obtain a sample set, training a specified machine learning model, obtaining original signal characteristics of satellite navigation signals without obtaining, and modifying hardware or software, obtaining the sample set with low cost and simple process, and realizing the identification of the interference of the satellite navigation locating signals in the locating process of the equipment such as a mobile phone or a vehicle-mounted locator.
One specific implementation of the characteristic value determination of the sample described above with reference to fig. 2 may specifically include the following steps:
step S21: and determining the position of the satellite according to the signal transmitting time and the ephemeris file in the satellite navigation signal information.
The ephemeris file records the change of the position of the satellite along with time, and the position of the satellite can be obtained by an interpolation method according to the signal transmitting time in the satellite navigation signal information and the ephemeris file.
Step S22: and determining the pseudo range between the equipment corresponding to the marked historical GNSS positioning point and the satellite according to the light speed, the signal receiving time and the signal transmitting time in the satellite navigation signal information.
The annotated historical GNSS fixes are samples in the sample set (historical GNSS fixes) that are annotated with interference or normal.
Step S21 and step S22 may be executed first, or may be executed simultaneously.
Step S23: and determining the pseudo-range change rate of the marked historical GNSS positioning points according to the pseudo-range of the marked historical GNSS positioning points before and after the marked historical GNSS positioning points are adjacent.
Step S24: and determining the position of the equipment, the clock error of the equipment and the effective satellite by an iterative method according to the position of the satellite, a preset initial value of the position of the equipment and the pseudo range between the satellite and the equipment.
Referring to FIG. 3, the determination of valid satellites may, in one embodiment, include the steps of:
step S241: and determining a first pitch angle of each satellite according to the position of each satellite and a preset initial position value of the equipment, and screening out the satellites of which the first pitch angle is greater than a preset angle threshold value.
Step S242: and determining the predicted position and the predicted clock error of the equipment according to the position of each satellite screened currently and the pseudo range between the equipment and each satellite screened currently.
Step S243: and determining a second pitch angle of each satellite according to the position of each satellite and the currently determined predicted position of the equipment, and screening out the satellites of which the second pitch angles are larger than a preset angle threshold value from all the satellites.
Step S244: and judging whether a preset iteration termination condition is met.
Specifically, the method may include determining whether an offset between a currently determined predicted position of the device and a last determined predicted position of the device is smaller than a preset distance threshold; or judging whether the current iteration times reach the preset times.
If the determination in step S244 is yes, go to step S245; otherwise, the process continues to step S242.
Step S245: and determining the predicted position and the predicted clock error of the currently determined equipment as the position and the clock error of the equipment, and determining the currently screened satellite as an effective satellite to obtain the number of the effective satellites.
Step S25: determining a distance between the device and the effective satellite according to the position of the device and the position of the effective satellite, and determining a pseudo-range residual error between the device and the effective satellite according to the distance between the device and the effective satellite, the pseudo-range between the device and the effective satellite and the clock error of the device.
For each valid satellite, the pseudorange between the device and the valid satellite is subtracted from the distance between the device and the valid satellite, and then the clock error of the device is subtracted to obtain a pseudorange residual between the device and the valid satellite.
Step S26: and determining the residual mean value of the maximum pseudo-range residual errors with the preset number.
Step S27: and determining the frequency drift of the equipment by a derivation method according to the change rate of the pseudo range between the equipment and the effective satellite, the position of the equipment and the position of the effective satellite.
Step S28: the signal-to-noise ratio of the active satellite and the uncertainty in the rate of change of pseudorange between the device and the active satellite are obtained from data output by the operating system of the device.
Step S29: and determining the number of the effective satellites, the residual mean value, the frequency drift of the equipment, the signal-to-noise ratio of the effective satellites and the uncertainty of the pseudo-range change rate between the effective satellites and the equipment as the characteristic values of the sample.
Example two
The second embodiment of the present application provides a method for identifying a GNSS positioning point generated when a device is interfered by GNSS based on historical GNSS positioning point data, that is, a GNSS interference point, a flow of which is shown in fig. 4, including the following steps:
step S41: and determining a GNSS interference positioning head point and a GNSS interference positioning tail point from historical GNSS positioning points generated in the same driving process of the same equipment.
Specifically, the method may include determining adjacent historical GNSS positioning points whose distance is greater than a set distance threshold, and obtaining at least two sets of positioning point pairs with position hopping; and determining the next historical GNSS positioning point of the previous positioning point pair in the two adjacent groups of positioning point pairs as the GNSS interference positioning head point, and determining the previous historical GNSS positioning point of the next positioning point pair as the GNSS interference positioning tail point.
Referring to fig. 5, when the distance between the historical GNSS positioning point 1 and the historical GNSS positioning point 2 is greater than a set distance threshold, determining that the historical GNSS positioning point 1 and the historical GNSS positioning point 2 are a group of positioning point pairs with hopping positions; the distance between the historical GNSS locating point 3 and the historical GNSS locating point 4 is larger than a set distance threshold value, and the historical GNSS locating point 3 and the historical GNSS locating point 4 are determined to be a group of locating point pairs with jumping positions; and determining the next historical GNSS positioning point 2 of the previous positioning point pair 12 in the two adjacent positioning point pairs as a GNSS interference positioning head point, and determining the previous historical GNSS positioning point 3 of the next positioning point pair 34 as a GNSS interference positioning tail point.
Step S42: and judging whether the area or the track of a geographic area formed by the GNSS interference positioning head point, the GNSS interference positioning tail point and the historical GNSS positioning points positioned between the head point and the tail point meets the rule of GNSS interference.
And/or judging whether the area of a geographical area formed by the GNSS interference positioning head point, the GNSS interference positioning tail point and the historical GNSS positioning points positioned between the head point and the tail point is smaller than a preset area threshold value or not, and/or judging whether a track formed by the GNSS interference positioning head point, the GNSS interference positioning tail point and the historical GNSS positioning points positioned between the head point and the tail point does not conform to the advancing rule of the track or not.
As a result of the interference to the satellite navigation positioning signal, generally, the positioning points of the device within the coverage of the interference signal are located in a specific area, so that the GNSS interference points between two adjacent positioning point pairs are concentrated in a predetermined area, and the GNSS interference points between two adjacent positioning point pairs can be determined as the interference positioning points.
The track formed by the historical GNSS locating points does not conform to the advancing rule of the track, and the track can comprise that a matching road of the historical GNSS locating points is not communicated with a matching road of the historical GNSS locating points in front of and/or behind; or the matching road of the historical GNSS positioning point is communicated with the matching road of the previous and/or subsequent historical GNSS positioning points, but the matching road is not in accordance with the theory, such as the round-trip circulation of the track segment.
In one embodiment, the determining whether a track formed by the GNSS interference positioning head point, the GNSS interference positioning tail point and the historical GNSS positioning points located between the head point and the tail point satisfies a rule of occurrence of GNSS interference may include performing map matching on the historical GNSS positioning points, and if there are no matching road segments for the consecutive historical GNSS positioning points exceeding a preset number, satisfying the rule of occurrence of GNSS interference, and determining that the historical GNSS positioning points of the non-matching road segments are GNSS positioning points generated when GNSS interference occurs; or the like, or, alternatively,
map matching is carried out on the historical GNSS positioning points to obtain more than two matched road sections, and if yes, the historical GNSS positioning points are matched with the two matched road sections; and if the road sections are communicated, determining whether a path section which is not in accordance with the driving rule exists in the path formed by the communication, and if so, satisfying the rule of the occurrence of the GNSS interference, and determining the historical GNSS positioning point which corresponds to the road section which is not in accordance with the driving rule as the GNSS positioning point which is generated when the GNSS interference occurs.
If the step S42 shows YES, go to step S43.
Step S43: and determining the head point, the tail point and the historical GNSS positioning points among the head point and the tail point as the GNSS positioning points generated when the GNSS interference occurs.
For example, the next historical GNSS positioning point 2 of the previous positioning point pair 12 in the two adjacent groups of jumping positioning point pairs in fig. 5 is determined as the GNSS interference positioning head point, the previous historical GNSS positioning point 3 of the next positioning point pair 34 is determined as the GNSS interference positioning tail point, and the GNSS positioning points 2 and 3 and the historical GNSS positioning point in between are determined as the GNSS positioning points generated when GNSS interference occurs.
EXAMPLE III
The third embodiment of the present application provides a method for identifying a GNSS positioning point generated when GNSS interference occurs, that is, a GNSS interference point, based on historical GNSS positioning point data, where a flow of the method is shown in fig. 6, and the method includes the following steps:
step S61: and matching the roads for the historical GNSS positioning points with the same track, and determining the historical GNSS positioning points with failed road matching as GNSS interference points if the continuous road matching of the historical GNSS positioning points with the number exceeding the preset number fails.
If the road matching fails without the historical GNSS positioning points, step S92 is executed.
Step S62: and judging whether a road section which is not communicated with other road sections exists in the obtained plurality of road sections.
If yes, go to step S63; if not, go to step S64.
Step S63: and taking the historical GNSS positioning points corresponding to the disconnected road sections as the GNSS positioning points generated when the GNSS interference occurs.
Step S64: and judging whether the path formed by the communication has a path section which does not accord with the driving rule.
If yes, go to step S65.
Step S65: and determining the historical GNSS positioning point corresponding to the road section of the road section which does not conform to the driving rule as the GNSS positioning point generated when the GNSS interference occurs.
Based on the inventive concept of the present application, an embodiment of the present application further provides an interference detection method, including:
determining a characteristic value according to positioning parameters of the GNSS positioning point;
and inputting the characteristic value into a machine learning model obtained by training by adopting the method, and determining whether the GNSS positioning point is a positioning point generated when the equipment is interfered by GNSS signals according to an output result of the model.
Based on the inventive concept of the present application, an embodiment of the present application further provides a training apparatus for a machine learning model, where the model is used for detecting GNSS signal interference, and a structure of the model is as shown in fig. 7, where the training apparatus includes:
an obtaining module 71, configured to obtain a training sample set, where the sample set includes an interference sample and a normal sample, where one interference sample corresponds to one historical GNSS positioning point generated when a device is subjected to GNSS interference, and one normal sample corresponds to one historical GNSS positioning point generated when the device is not subjected to GNSS interference;
a determining module 72, configured to determine a feature value of the sample according to the positioning parameter, obtained by the obtaining module 71, of the GNSS historical positioning point corresponding to the sample;
a training module 73, configured to train the set machine learning model using the training sample set of feature values determined by the determining module 72 to obtain a machine learning model for detecting GNSS signal interference.
In one embodiment, the determining module 72 is specifically configured to:
determining a pseudo-range residual error between equipment and an effective satellite according to positioning parameters of a historical GNSS positioning point corresponding to a sample, wherein the equipment is equipment for generating the historical positioning point corresponding to the sample, and the effective satellite is a GNSS satellite participating in resolving the positioning position of the historical GNSS positioning point; and determining the mean value of the pseudo-range residuals meeting the set conditions in the pseudo-range residuals of the equipment and the effective satellites as the pseudo-range residuals of the sample.
In one embodiment, the determining module 72 is specifically configured to:
and determining the frequency drift of the equipment through Doppler frequency shift according to the change rate of the pseudo range between the equipment and the effective satellite, the position of the equipment and the position of the effective satellite.
In an embodiment, the obtaining module 71 is specifically configured to:
determining historical GNSS positioning points generated when the equipment is interfered by GNSS based on the historical GNSS positioning point data; interference samples are determined from historical GNSS positioning points generated when the equipment is interfered by GNSS, normal samples are determined from other historical GNSS positioning points in the historical GNSS positioning point data, and a training sample set is obtained.
In an embodiment, the obtaining module 71 is specifically configured to, for historical GNSS positioning points belonging to the same device and generated in the same driving process in the historical GNSS positioning point data, perform the following steps:
determining a GNSS interference positioning head point and a GNSS interference positioning tail point from historical GNSS positioning points generated in the same driving process of the same device; and judging whether the area or the track of a geographic area formed by the GNSS interference positioning head point, the GNSS interference positioning tail point and the historical GNSS positioning points positioned between the head point and the tail point meets the rule of occurrence of GNSS interference, and if so, determining the head point, the tail point and the historical GNSS positioning points between the head point and the tail point as the GNSS positioning points generated when the GNSS interference occurs.
In an embodiment, the obtaining module 71 is specifically configured to:
map matching is carried out on historical GNSS positioning points, and if the continuous historical GNSS positioning points exceeding the preset number do not have matched road sections, the rule of GNSS interference is met; or the like, or, alternatively,
map matching is carried out on historical GNSS positioning points to obtain more than two matched road sections, and if the road sections are not communicated with other road sections, the rule of GNSS interference is met; setting the historical GNSS positioning points corresponding to the disconnected road sections as GNSS positioning points generated when GNSS interference occurs;
if the road sections are communicated, determining whether the path formed by the communication has a path section which does not accord with the driving rule, if so, meeting the rule of GNSS interference; the determining of the head point, the tail point and the historical GNSS positioning points therebetween as the GNSS positioning points generated when GNSS interference occurs specifically includes: and determining the historical GNSS positioning point corresponding to the road section of the road end which does not conform to the driving rule as the GNSS positioning point generated when the GNSS interference occurs.
Based on the inventive concept of the present application, an embodiment of the present application further provides an interference detection apparatus, which has a structure as shown in fig. 8, and includes:
the determining module 81 is configured to determine a feature value according to a positioning parameter of the GNSS positioning point;
the detection module 82 is configured to input the feature value determined by the determination module 81 into the machine learning model trained by the method, and determine whether the GNSS positioning point is a positioning point generated when the device is interfered by GNSS signals according to an output result of the model.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Based on the inventive concept of the present application, embodiments of the present application further provide a computer-readable storage medium, on which computer instructions are stored, and when the instructions are executed by a processor, the method for training the machine learning model or the method for detecting the interference is implemented.
Based on the inventive concept of the present application, an embodiment of the present application further provides a server, including: the computer program comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the training method of the machine learning model or the interference detection method when executing the program.
Unless specifically stated otherwise, terms such as processing, computing, calculating, determining, displaying, or the like, may refer to an action and/or process of one or more processing or computing systems or similar devices that manipulates and transforms data represented as physical (e.g., electronic) quantities within the processing system's registers and memories into other data similarly represented as physical quantities within the processing system's memories, registers or other such information storage, transmission or display devices. Information and signals may be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols, and chips that may be referenced throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.
It should be understood that the specific order or hierarchy of steps in the processes disclosed is an example of exemplary approaches. Based upon design preferences, it is understood that the specific order or hierarchy of steps in the processes may be rearranged without departing from the scope of the present disclosure. The accompanying method claims present elements of the various steps in a sample order, and are not intended to be limited to the specific order or hierarchy presented.
In the foregoing detailed description, various features are grouped together in a single embodiment for the purpose of streamlining the disclosure. This method of disclosure is not to be interpreted as reflecting an intention that the claimed embodiments of the subject matter require more features than are expressly recited in each claim. Rather, as the following claims reflect, this application is directed to less than all of the features of a single disclosed embodiment. Thus, the following claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the application.
Those of skill would further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal. Of course, the processor and the storage medium may reside as discrete components in a user terminal.
For a software implementation, the techniques described herein may be implemented with modules (e.g., procedures, functions, and so on) that perform the functions described herein. The software codes may be stored in memory units and executed by processors. The memory unit may be implemented within the processor or external to the processor, in which case it can be communicatively coupled to the processor via various means as is known in the art.
What has been described above includes examples of one or more embodiments. It is, of course, not possible to describe every conceivable combination of components or methodologies for purposes of describing the aforementioned embodiments, but one of ordinary skill in the art may recognize that many further combinations and permutations of various embodiments are possible. Accordingly, the embodiments described herein are intended to embrace all such alterations, modifications and variations that fall within the scope of the appended claims. Furthermore, to the extent that the term "includes" is used in either the detailed description or the claims, such term is intended to be inclusive in a manner similar to the term "comprising" as "comprising" is interpreted when employed as a transitional word in a claim. Furthermore, any use of the term "or" in the specification of the claims is intended to mean a "non-exclusive or". The terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
Claims (14)
1. A method of training a machine learning model for detecting GNSS signal interference, the method comprising:
obtaining a training sample set, wherein the sample set comprises interference samples and normal samples, one interference sample corresponds to a historical GNSS positioning point generated when equipment is interfered by GNSS, and one normal sample corresponds to a historical GNSS positioning point generated when the equipment is not interfered by the GNSS;
determining a characteristic value of the sample according to the positioning parameters of the historical GNSS positioning points corresponding to the sample;
and training the set machine learning model by using the training sample set with the determined characteristic value to obtain the machine learning model for detecting the GNSS signal interference.
2. The method of claim 1, the characteristic values of the sample comprising at least: determining a characteristic value of the sample according to the positioning parameter of the historical GNSS positioning point corresponding to the sample by using the pseudo-range residual error, wherein the determination comprises the following steps:
determining a pseudo-range residual error between equipment and an effective satellite according to positioning parameters of a historical GNSS positioning point corresponding to a sample, wherein the equipment is equipment for generating the historical positioning point corresponding to the sample, and the effective satellite is a GNSS satellite participating in resolving the positioning position of the historical GNSS positioning point;
and determining the mean value of the pseudo-range residuals meeting the set conditions in the pseudo-range residuals of the equipment and the effective satellites as the pseudo-range residuals of the sample.
3. The method of claim 2, wherein the sample feature values further comprise at least one of the following parameters:
the device calculating height, the obtained device height difference, the difference between the calculating angular velocity and the IMU measuring angular velocity and the calculating clock difference of the receiver loaded by the device.
4. The method of claim 2, wherein the characteristic value of the sample further comprises a number of valid satellites.
5. The method of claim 2, the characteristic values of the sample further comprising a frequency drift of the device, the frequency drift of the device of the sample determined by:
and determining the frequency drift of the equipment through Doppler frequency shift according to the change rate of the pseudo range between the equipment and the effective satellite, the position of the equipment and the position of the effective satellite.
6. The method of claim 2, the characteristic values of the sample further comprising:
a signal-to-noise ratio of the active satellite, and/or an uncertainty in a rate of change of pseudorange between the device and the active satellite, the method further comprising:
the signal-to-noise ratio of the active satellite and/or the uncertainty in the rate of change of pseudorange between the device and the active satellite is obtained from data output by the operating system of the device.
7. The method of claim 1, the method further comprising:
determining historical GNSS positioning points generated when the equipment is interfered by GNSS based on the historical GNSS positioning point data; correspondingly, the acquiring of the training sample set specifically includes:
interference samples are determined from historical GNSS positioning points generated when the equipment is interfered by GNSS, normal samples are determined from other historical GNSS positioning points in the historical GNSS positioning point data, and a training sample set is obtained.
8. The method of claim 1, the method further comprising:
determining a GNSS positioning point generated when the equipment is interfered by GNSS based on historical GNSS positioning point data, and determining an interference hop geofence area according to the GNSS positioning point generated when the equipment is interfered by GNSS; correspondingly, the acquiring of the training sample set specifically includes:
and determining an interference sample from GNSS positioning points generated when equipment in the interference hop point geo-fence area is interfered by GNSS, and determining a normal sample from other historical GNSS positioning points in the interference hop point geo-fence area to obtain a training sample set.
9. The method according to claim 7 or 8, wherein determining historical GNSS fix generated when a device is subjected to GNSS interference based on historical GNSS fix data comprises:
aiming at historical GNSS positioning point data which belong to historical GNSS positioning points generated in the same driving process of the same equipment, the following steps are executed:
determining a GNSS interference positioning head point and a GNSS interference positioning tail point from historical GNSS positioning points generated in the same driving process of the same device;
and judging whether the area or the track of a geographic area formed by the GNSS interference positioning head point, the GNSS interference positioning tail point and the historical GNSS positioning points positioned between the head point and the tail point meets the rule of occurrence of GNSS interference, and if so, determining the head point, the tail point and the historical GNSS positioning points between the head point and the tail point as the GNSS positioning points generated when the GNSS interference occurs.
10. The method of claim 9, wherein determining whether a trajectory formed by the GNSS interference positioning start point, the GNSS interference positioning end point, and the historical GNSS positioning points located between the start point and the end point satisfies a rule for GNSS interference, comprises:
map matching is carried out on historical GNSS positioning points, and if the continuous historical GNSS positioning points exceeding the preset number do not have matched road sections, the rule of GNSS interference is met; or the like, or, alternatively,
map matching is carried out on historical GNSS positioning points to obtain more than two matched road sections, and if the road sections are not communicated with other road sections, the rule of GNSS interference is met; accordingly, the method can be used for solving the problems that,
the determining of the head point, the tail point and the historical GNSS positioning points therebetween as the GNSS positioning points generated when GNSS interference occurs specifically includes:
setting the historical GNSS positioning points corresponding to the disconnected road sections as GNSS positioning points generated when GNSS interference occurs;
if the road sections are communicated, determining whether the path formed by the communication has a path section which does not accord with the driving rule, if so, meeting the rule of GNSS interference; accordingly, the method can be used for solving the problems that,
the determining of the head point, the tail point and the historical GNSS positioning points therebetween as the GNSS positioning points generated when GNSS interference occurs specifically includes: and determining the historical GNSS positioning point corresponding to the road section of the road end which does not conform to the driving rule as the GNSS positioning point generated when the GNSS interference occurs.
11. An interference detection method, comprising:
determining a characteristic value according to positioning parameters of the GNSS positioning point;
inputting the characteristic value into a machine learning model obtained by training by adopting the method of any one of claims 1 to 10, and determining whether the GNSS positioning point is a positioning point generated when the equipment is interfered by GNSS signals according to the output result of the model.
12. An apparatus for training a machine learning model, the model for detecting GNSS signal interference, the apparatus comprising:
the acquisition module is used for acquiring a training sample set, wherein the sample set comprises interference samples and normal samples, one interference sample corresponds to a historical GNSS positioning point generated when equipment is interfered by GNSS, and one normal sample corresponds to a historical GNSS positioning point generated when the equipment is not interfered by the GNSS;
the determining module is used for determining a characteristic value of the sample according to the positioning parameters of the sample corresponding to the GNSS historical positioning points obtained by the obtaining module;
and the training module is used for training the set machine learning model by using the training sample set of the characteristic value determined by the determining module so as to obtain the machine learning model for detecting the GNSS signal interference.
13. An interference detection apparatus comprising:
the determining module is used for determining a characteristic value according to the positioning parameters of the GNSS positioning point;
a detection module, configured to input the feature value determined by the determination module into a machine learning model trained by the method according to any one of claims 1 to 10, and determine whether the GNSS positioning point is a positioning point generated when the device is interfered by GNSS signals according to an output result of the model.
14. A computer readable storage medium having stored thereon computer instructions which, when executed by a processor, implement the machine learning model training method of any one of claims 1 to 10 or the interference detection method of claim 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010947378.8A CN114252892A (en) | 2020-09-10 | 2020-09-10 | Training method of machine learning model, interference detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010947378.8A CN114252892A (en) | 2020-09-10 | 2020-09-10 | Training method of machine learning model, interference detection method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114252892A true CN114252892A (en) | 2022-03-29 |
Family
ID=80788016
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010947378.8A Pending CN114252892A (en) | 2020-09-10 | 2020-09-10 | Training method of machine learning model, interference detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114252892A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105550702A (en) * | 2015-12-09 | 2016-05-04 | 哈尔滨工业大学 | GNSS deception jamming recognition method based on SVM |
| CN107238847A (en) * | 2017-04-21 | 2017-10-10 | 中国科学院光电研究院 | A kind of satellite navigation interferer signal detection method and system |
| CN109425883A (en) * | 2017-08-23 | 2019-03-05 | 阿里巴巴集团控股有限公司 | A kind of localization method, device, terminal, server and storage medium |
| CN109782304A (en) * | 2019-01-29 | 2019-05-21 | 西安交通大学 | A kind of the GNSS cheating interference detection method and system of signal acquisition phase |
| CN110109162A (en) * | 2019-03-26 | 2019-08-09 | 西安开阳微电子有限公司 | A kind of Kalman filtering positioning calculation method that GNSS receiver is adaptive |
| US20200049837A1 (en) * | 2018-08-09 | 2020-02-13 | Apple Inc. | Machine learning assisted satellite based positioning |
| CN111221011A (en) * | 2018-11-26 | 2020-06-02 | 千寻位置网络有限公司 | GNSS positioning method and device based on machine learning |
-
2020
- 2020-09-10 CN CN202010947378.8A patent/CN114252892A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105550702A (en) * | 2015-12-09 | 2016-05-04 | 哈尔滨工业大学 | GNSS deception jamming recognition method based on SVM |
| CN107238847A (en) * | 2017-04-21 | 2017-10-10 | 中国科学院光电研究院 | A kind of satellite navigation interferer signal detection method and system |
| CN109425883A (en) * | 2017-08-23 | 2019-03-05 | 阿里巴巴集团控股有限公司 | A kind of localization method, device, terminal, server and storage medium |
| US20200049837A1 (en) * | 2018-08-09 | 2020-02-13 | Apple Inc. | Machine learning assisted satellite based positioning |
| CN111221011A (en) * | 2018-11-26 | 2020-06-02 | 千寻位置网络有限公司 | GNSS positioning method and device based on machine learning |
| CN109782304A (en) * | 2019-01-29 | 2019-05-21 | 西安交通大学 | A kind of the GNSS cheating interference detection method and system of signal acquisition phase |
| CN110109162A (en) * | 2019-03-26 | 2019-08-09 | 西安开阳微电子有限公司 | A kind of Kalman filtering positioning calculation method that GNSS receiver is adaptive |
Non-Patent Citations (2)
| Title |
|---|
| 王强: "GPS_BD2双模接收机定位算法的设计与实现", 《中国优秀硕士学位论文全文数据库信息科技辑》, 15 March 2017 (2017-03-15), pages 5 - 14 * |
| 邢伟坡: "Android移动终端高精度导航定位技术研究", 《卫星导航定位与北斗系统应用2019》, 10 September 2019 (2019-09-10), pages 221 - 224 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107976697B (en) | Train safety positioning method and system based on Beidou/GPS combination | |
| US8374784B2 (en) | System and method for determining the geographic location of a device | |
| EP2876463B1 (en) | Method for determining location of vehicle | |
| CN111337953B (en) | Satellite navigation spoofing detection method, device, equipment and medium | |
| US7233864B2 (en) | Method for improving GPS integrity and detecting multipath interference using inertial navigation sensors and a network of mobile receivers | |
| KR101154079B1 (en) | Method for determining initial location of navigation apparatus | |
| US6574557B2 (en) | Positioning error range setting apparatus, method, and navigation apparatus | |
| US20090177382A1 (en) | Calibration of a Navigation System | |
| US20220236425A1 (en) | Detection of spoofing attacks on satellite navigation systems | |
| US11435482B2 (en) | Method for verifying the plausibility of GNSS position signals | |
| US20020042268A1 (en) | Systems and methods for determining signal coverage | |
| CN104880717B (en) | Satellite measured value multi-path error detection device and algorithm | |
| WO2016003262A1 (en) | A system and method for detecting global positioning system anomalies | |
| Beitler et al. | CMCD: multipath detection for mobile GNSS receivers | |
| Tang et al. | Improving performance of pedestrian positioning by using vehicular communication signals | |
| CN115685260A (en) | Identification deception jamming identification method, device, platform and medium for GLS reference station | |
| CN111194001A (en) | LTE fingerprint positioning correction method, device and system | |
| CN112219136A (en) | Reliable method for determining the position of a receiving device | |
| CN109525947B (en) | Unmanned aerial vehicle motion trail recording method and device | |
| CN114252892A (en) | Training method of machine learning model, interference detection method and device | |
| KR102584796B1 (en) | Method and apparatus for location estimating using gis information | |
| Yu | Improved positioning of land vehicle in ITS using digital map and other accessory information | |
| Takenga et al. | Robust positioning system based on fingerprint approach | |
| CN114167453A (en) | Interference detection method and device | |
| Niedermeier et al. | Detection and mitigation of GNSS deception by combination of odometric dead reckoning and GNSS observations for vehicles |
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 |