CN116304654A - Training method of ambiguity confirming model, ambiguity confirming method and device - Google Patents
Training method of ambiguity confirming model, ambiguity confirming method and device Download PDFInfo
- Publication number
- CN116304654A CN116304654A CN202111572245.8A CN202111572245A CN116304654A CN 116304654 A CN116304654 A CN 116304654A CN 202111572245 A CN202111572245 A CN 202111572245A CN 116304654 A CN116304654 A CN 116304654A
- Authority
- CN
- China
- Prior art keywords
- ambiguity
- model
- training
- characteristic information
- difference
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
-
- 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
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0475—Generative networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Radar, Positioning & Navigation (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Automation & Control Theory (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Medical Informatics (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The application discloses a training method of an ambiguity confirming model, an ambiguity confirming method and an ambiguity confirming device, and belongs to the technical field of positioning. Firstly, acquiring sample positioning data; extracting characteristic information of sample positioning data; and training the neural network model according to the characteristic information of the sample positioning data to obtain an ambiguity confirming model. And then, inputting the characteristic information of the target positioning data into the ambiguity confirming model to obtain a confirming result of the ambiguity corresponding to the target positioning data. By the scheme disclosed by the application, the accuracy of the ambiguity confirmation can be improved.
Description
Technical Field
The application belongs to the technical field of positioning, and particularly relates to a training method of an ambiguity confirmation model, an ambiguity confirmation method and an ambiguity confirmation device.
Background
Along with the rapid development of lane-level navigation, automatic driving and other technologies, the high-precision rapid dynamic positioning application is more and more widespread. And ambiguity is the key to high accuracy positioning.
The ambiguity confirmation result affects the fixing rate and accuracy of the positioning result, for example, confirming the actual effective ambiguity as the unreal effective ambiguity may affect the fixing rate of positioning, and confirming the actual unreal effective ambiguity as the actual effective ambiguity may affect the positioning accuracy. Therefore, it is important to accurately confirm the degree of blurring.
In the related art, some observed quantity thresholds are set mainly through an empirical model, and the real-time observed quantity is compared with the set observed quantity thresholds to confirm the ambiguity. However, this approach relies heavily on empirical models and set observational thresholds, with low accuracy in ambiguity validation.
Disclosure of Invention
The embodiment of the application aims to provide a training method of an ambiguity confirming model, an ambiguity confirming method and a device, which can solve the problem of low ambiguity confirming accuracy.
In a first aspect, an embodiment of the present application provides a training method of an ambiguity confirmation model, including:
acquiring sample positioning data;
extracting characteristic information of sample positioning data, wherein the characteristic information comprises: at least one of a difference value between the widelane ambiguity and the ambiguity difference value, a position difference between a first position and a second position, and a position difference between the first position and a third position, wherein the ambiguity difference value is a difference value between ambiguities of two frequency points, the first position is a position obtained by performing positioning calculation according to the widelane ambiguity, the second position is a position obtained by performing positioning calculation according to the ambiguity of any one of the two frequency points, and the third position is a position obtained by performing positioning calculation according to the ultra-wide elane ambiguity;
And training the neural network model according to the characteristic information to obtain an ambiguity confirmation model.
In a second aspect, an embodiment of the present application provides an ambiguity confirming method, including:
acquiring target positioning data;
extracting characteristic information of target positioning data;
inputting the characteristic information into an ambiguity confirmation model obtained by training the ambiguity confirmation model by using the ambiguity confirmation model training method provided by the first aspect of the embodiment of the present application, so as to obtain a confirmation result of the ambiguity corresponding to the target positioning data.
In a third aspect, an embodiment of the present application provides a training apparatus for an ambiguity confirmation model, including:
the first acquisition module is used for acquiring sample positioning data;
the first extraction module is used for extracting characteristic information of the sample positioning data, wherein the characteristic information comprises: at least one of a difference value between the widelane ambiguity and the ambiguity difference value, a position difference between a first position and a second position, and a position difference between the first position and a third position, wherein the ambiguity difference value is a difference value between ambiguities of two frequency points, the first position is a position obtained by performing positioning calculation according to the widelane ambiguity, the second position is a position obtained by performing positioning calculation according to the ambiguity of any one of the two frequency points, and the third position is a position obtained by performing positioning calculation according to the ultra-wide elane ambiguity;
And the training module is used for training the neural network model according to the characteristic information to obtain an ambiguity confirmation model.
In a fourth aspect, an embodiment of the present application provides an ambiguity confirming apparatus, including:
the second acquisition module is used for acquiring target positioning data;
the second extraction module is used for extracting characteristic information of the target positioning data;
the confirming module is used for inputting the characteristic information into the ambiguity confirming model obtained by training by using the ambiguity confirming model training method provided by the first aspect of the embodiment of the application, and obtaining the ambiguity confirming result corresponding to the target positioning data.
In a fifth aspect, embodiments of the present application provide an electronic device comprising a processor and a memory storing a program or instructions executable on the processor, the program or instructions implementing the steps of the method according to the first or second aspect when executed by the processor.
In a sixth aspect, embodiments of the present application provide a readable storage medium having stored thereon a program or instructions which, when executed by a processor, implement the steps of the method according to the first or second aspect.
In a seventh aspect, embodiments of the present application provide a chip comprising a processor and a communication interface, the communication interface and the processor being coupled, the processor being configured to execute programs or instructions to implement the steps of the method according to the first or second aspect.
In an eighth aspect, embodiments of the present application provide a computer program product stored in a storage medium, the program product being executable by at least one processor to implement the method according to the first or second aspect.
In the embodiment of the application, the sample positioning data are acquired; extracting characteristic information of sample positioning data, wherein the characteristic information comprises: at least one of a difference value between the widelane ambiguity and the ambiguity difference value, a position difference between a first position and a second position, and a position difference between the first position and a third position, wherein the ambiguity difference value is a difference value between ambiguities of two frequency points, the first position is a position obtained by performing positioning calculation according to the widelane ambiguity, the second position is a position obtained by performing positioning calculation according to the ambiguity of any one of the two frequency points, and the third position is a position obtained by performing positioning calculation according to the ultra-wide elane ambiguity; and training the neural network model according to the characteristic information to obtain an ambiguity confirmation model. And further, confirming the ambiguity corresponding to the acquired target positioning data by using the ambiguity confirming model, so as to obtain a confirming result of the ambiguity corresponding to the target positioning data. On the one hand, some observed quantity thresholds are not required to be set through an empirical model, namely the accuracy of the ambiguity confirmation can be improved without depending on the empirical model and the set observed quantity thresholds during the ambiguity confirmation. On the other hand, the ambiguity confirmation model is trained based on at least one of the difference between the widelane ambiguity and the ambiguity difference, the difference between the first position and the second position, and the difference between the first position and the third position, and the difference between the widelane ambiguity and the ambiguity difference, the difference between the first position and the second position, and the difference between the first position and the third position are important features among features related to ambiguity confirmation.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments of the present application will be briefly described, and it is possible for a person skilled in the art to obtain other drawings according to these drawings without inventive effort.
FIG. 1 is a flowchart of a training method of an ambiguity confirmation model according to an embodiment of the present application;
fig. 2 is a flowchart of an ambiguity confirming method according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a process of ambiguity validation provided by an embodiment of the present application;
FIG. 4 is a schematic structural diagram of a training device for an ambiguity confirmation model according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an ambiguity confirming apparatus according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application;
fig. 7 is a schematic diagram of a hardware structure of an electronic device implementing an embodiment of the present application.
Detailed Description
Technical solutions in the embodiments of the present application will be clearly described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application are within the scope of the protection of the present application.
The terms first, second and the like in the description and in the claims, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged, as appropriate, such that embodiments of the present application may be implemented in sequences other than those illustrated or described herein, and that the objects identified by "first," "second," etc. are generally of a type and not limited to the number of objects, e.g., the first object may be one or more. Furthermore, in the description and claims, "and/or" means at least one of the connected objects, and the character "/", generally means that the associated object is an "or" relationship.
The training method, the ambiguity confirming method and the device of the ambiguity confirming model provided by the embodiment of the application are described in detail below through specific embodiments and application scenes thereof with reference to the accompanying drawings.
Fig. 1 is a flowchart of a training method of an ambiguity confirmation model according to an embodiment of the present application. As shown in fig. 1, the training method of the ambiguity confirmation model may include:
s101: acquiring sample positioning data;
S102: extracting characteristic information of sample positioning data, wherein the characteristic information comprises: at least one of a difference value between the widelane ambiguity and the ambiguity difference value, a position difference between a first position and a second position, and a position difference between the first position and a third position, wherein the ambiguity difference value is a difference value between ambiguities of two frequency points, the first position is a position obtained by performing positioning calculation according to the widelane ambiguity, the second position is a position obtained by performing positioning calculation according to the ambiguity of any one of the two frequency points, and the third position is a position obtained by performing positioning calculation according to the ultra-wide elane ambiguity;
s103: and training the neural network model according to the characteristic information to obtain an ambiguity confirmation model.
The specific implementation of each of the above steps will be described in detail below.
In the embodiment of the application, the sample positioning data are acquired; extracting characteristic information of sample positioning data, wherein the characteristic information comprises: at least one of a difference value between the widelane ambiguity and the ambiguity difference value, a position difference between a first position and a second position, and a position difference between the first position and a third position, wherein the ambiguity difference value is a difference value between ambiguities of two frequency points, the first position is a position obtained by performing positioning calculation according to the widelane ambiguity, the second position is a position obtained by performing positioning calculation according to the ambiguity of any one of the two frequency points, and the third position is a position obtained by performing positioning calculation according to the ultra-wide elane ambiguity; and training the neural network model according to the characteristic information to obtain an ambiguity confirmation model. And further, confirming the ambiguity corresponding to the acquired target positioning data by using the ambiguity confirming model, so as to obtain a confirming result of the ambiguity corresponding to the target positioning data. On the one hand, some observed quantity thresholds are not required to be set through an empirical model, namely the accuracy of the ambiguity confirmation can be improved without depending on the empirical model and the set observed quantity thresholds during the ambiguity confirmation. On the other hand, the ambiguity confirmation model is trained based on at least one of the difference between the widelane ambiguity and the ambiguity difference, the difference between the first position and the second position, and the difference between the first position and the third position, and the difference between the widelane ambiguity and the ambiguity difference, the difference between the first position and the second position, and the difference between the first position and the third position are important features among features related to ambiguity confirmation.
In some possible implementations of the embodiments of the present application, the two frequency points in the embodiments of the present application may be any two frequency points that satisfy the conditions of composing the wide lane.
In some possible implementations of the embodiments of the present application, the widelane ambiguity in the embodiments of the present application may be ambiguity obtained by combining carrier phase observations corresponding to the two frequency points to obtain a carrier phase combination observation value, and fixing the carrier phase combination observation value according to the carrier phase combination observation value.
In some possible implementations of the embodiments of the present application, the ultra-wideband ambiguity in the embodiments of the present application may be an ambiguity that combines carrier-phase observations of at least two frequency points that satisfy a condition of forming an ultra-wideband, to obtain a carrier-phase combined observation, and is fixed according to the carrier-phase combined observation.
In some possible implementations of embodiments of the present application, ambiguities in sample positioning data may be pre-marked. In S103, the feature information and the corresponding ambiguity actual mark thereof may be input to the neural network model, to obtain a prediction result of the ambiguity of the sample positioning data corresponding to the feature information, and training the neural network model according to the ambiguity actual mark and the prediction result, to obtain an ambiguity confirmation model, where the ambiguity actual mark is used as the expected output of the feature information of the sample positioning data corresponding to the ambiguity actual mark when training the network model.
In some possible implementations of the embodiments of the present application, a threshold number of loop iteration training times may be set when training the neural network model, and training is stopped when the number of times the neural network model is trained reaches the set threshold number of loop iteration training times, to obtain the ambiguity confirmation model.
In some possible implementations of the embodiments of the present application, when training the neural network model, a loss value of the neural network model may also be calculated, and when the loss value of the neural network model reaches a minimum, training is stopped, so as to obtain the ambiguity confirmation model.
In some possible implementations of the embodiments of the present application, when training the neural network model, the accuracy of the neural network model prediction may also be calculated according to the ambiguity actual label and the prediction result, and when the accuracy of the neural network model prediction is greater than the accuracy threshold, training is stopped to obtain the ambiguity confirmation model.
In particular, a portion of the sample positioning data may be selected from the sample positioning data as a test sample. After training the neural network model for a period of time, inputting the characteristic information of the test sample into the neural network model at the moment to obtain a prediction result of the ambiguity of the test sample, calculating the accuracy of the prediction of the neural network model at the moment according to the prediction result of the ambiguity and an actual mark of the ambiguity of the test sample, when the accuracy of the prediction of the neural network model is not more than an accuracy threshold, continuing training the neural network model by utilizing the characteristic information of the sample positioning data, inputting the characteristic information of the test sample into the neural network model at the moment after a period of time, calculating the accuracy of the prediction of the neural network model at the moment until the accuracy of the prediction of the neural network model is more than an accuracy threshold, and taking the neural network model at the moment as an ambiguity confirmation model.
The embodiment of the present application does not limit a specific process of training a neural network model according to feature information to obtain an ambiguity confirmation model, and according to the feature information, the training of the neural network model may refer to a process of training the neural network model in a related technology, which is not described herein in detail.
In some possible implementations of embodiments of the present application, the feature information in embodiments of the present application may further include at least three of the following:
the method comprises the steps of fixing the number of ambiguities, detecting errors in unit weights, precision factor values, the number of reference satellite changes, quality marks of single-point solution positioning results, the number of valid pseudo-ranges, pseudo-range residual errors, the number of satellites, the ratio of minimum unit weight variance to secondary unit weight variance obtained according to alternative ambiguities, the mean value of fixed solution carrier double-difference residual errors and the average carrier-to-noise ratio.
In some possible implementations of embodiments of the present application, there are only two cases of ambiguity validation results, one case where the ambiguity is truly valid (i.e., the ambiguity validation passes) and the other case where the ambiguity is not truly valid (i.e., the ambiguity validation does not pass). Thus, the neural network model in the embodiment of the present application is a classification model. When classification is performed using the two classification models, the result of the prediction is one of the two cases, not the other.
In some possible implementations of embodiments of the present application, the classification model in embodiments of the present application may be: a binary regression-based binary model, a K nearest neighbor algorithm-based binary model, a binary decision tree-based binary model, a support vector machine-based binary model, and a naive Bayes-based binary model.
In the embodiment of the present application, the classification model in the embodiment of the present application is preferably: a logistic regression-based classification model.
In some possible implementations of the embodiments of the present application, the classification function of the logistic regression-based classification model in the embodiments of the present application is a Sigmoid function, where the Sigmoid function is shown in the following formula (1):
the assumed function of the logistic regression-based classification model in the embodiment of the present application is shown in the following formula (2):
in the formula (2), x is a vector corresponding to the feature information, and θ is a weight vector to be fitted.
In some possible implementations of embodiments of the present application, θ may be solved by maximum likelihood estimation. The method comprises the steps of obtaining a maximum likelihood function of a logistic regression-based binary model, wherein the maximum likelihood estimation is used for solving theta, and the theta obtained by solving is the optimal parameter of the logistic regression-based binary model at the moment when the log likelihood function of the logistic regression-based binary model is maximized.
In some possible implementations of embodiments of the present application, a gradient-increasing method may be employed to solve for θ 。
Fig. 2 is a flowchart of an ambiguity confirming method according to an embodiment of the present application. As shown in fig. 2, the ambiguity confirmation method may include:
s201: acquiring target positioning data;
s202: extracting characteristic information of target positioning data;
s203: and inputting the characteristic information into an ambiguity confirmation model obtained by training by using the ambiguity confirmation model training method provided by the embodiment of the application, so as to obtain an ambiguity confirmation result corresponding to the target positioning data.
In the embodiment of the application, the ambiguity corresponding to the acquired target positioning data can be confirmed through the ambiguity confirming model, and a confirming result of the ambiguity corresponding to the target positioning data is obtained. On the one hand, some observed quantity thresholds are not required to be set through an empirical model, namely the accuracy of the ambiguity confirmation can be improved without depending on the empirical model and the set observed quantity thresholds during the ambiguity confirmation. On the other hand, the ambiguity confirmation model is trained according to at least one of the difference between the widelane ambiguity and the ambiguity difference, the difference between the first position and the second position, and the difference between the first position and the third position, wherein the ambiguity difference is the difference between the ambiguities of the two frequency points, the first position is the position obtained by positioning calculation according to the widelane ambiguity, the second position is the position obtained by positioning calculation according to the ambiguity of any one of the two frequency points, the third position is the position obtained by positioning calculation according to the ultra-wide lane ambiguity, and the difference between the widelane ambiguity and the ambiguity difference, the difference between the first position and the second position, and the difference between the first position and the third position are important features in the features related to the ambiguity confirmation.
In extracting feature information from target positioning data, the extracted feature information is information of the same features as those in training a neural network model.
In some possible implementations of embodiments of the present application, the validation results of the ambiguity include: the ambiguity is true valid (i.e., the ambiguity is correct, with confirmation), the ambiguity is not true valid (i.e., the ambiguity is incorrect, without confirmation).
In some possible implementations of embodiments of the present application, the ambiguity identified in embodiments of the present application may be a whole-cycle ambiguity (ambiguity of whole cycles). The integer ambiguity is also called integer unknowns, and is an integer unknowns corresponding to a first observed value of a phase difference between a carrier phase and a reference phase in carrier phase measurement of the global positioning system technology.
Fig. 3 is a schematic diagram of a procedure for ambiguity confirmation provided in an embodiment of the present application. The ambiguity confirming process comprises two stages, namely an offline training stage and an online confirming stage.
In the off-line training stage, the characteristic information of the sample positioning data and the corresponding actual ambiguity mark are input into a machine learning-based classification model (namely a neural network model) to train the classification model so as to obtain an ambiguity confirmation model for ambiguity confirmation.
And in the online confirmation stage, extracting characteristic information of the actual positioning data, and inputting the characteristic information into an ambiguity confirmation model obtained through offline training stage training, so as to obtain a confirmation result of the ambiguity corresponding to the actual positioning data.
It should be noted that, in the training method of the ambiguity confirming model provided in the embodiment of the present application, the execution subject may be a training device of the ambiguity confirming model. In the embodiment of the present application, a training device for an ambiguity confirmation model is described by taking a training method for executing the ambiguity confirmation model by using a training device for an ambiguity confirmation model as an example.
Fig. 4 is a schematic structural diagram of a training device of an ambiguity confirmation model according to an embodiment of the present application. As shown in fig. 4, the training apparatus 400 of the ambiguity confirmation model may include:
a first obtaining module 401, configured to obtain sample positioning data;
a first extraction module 402, configured to extract feature information of the sample positioning data, where the feature information includes: at least one of a difference value between the widelane ambiguity and the ambiguity difference value, a position difference between a first position and a second position, and a position difference between the first position and a third position, wherein the ambiguity difference value is a difference value between ambiguities of two frequency points, the first position is a position obtained by performing positioning calculation according to the widelane ambiguity, the second position is a position obtained by performing positioning calculation according to the ambiguity of any one of the two frequency points, and the third position is a position obtained by performing positioning calculation according to the ultra-wide elane ambiguity;
And the training module 403 is configured to train the neural network model according to the feature information, and obtain an ambiguity confirmation model.
In the embodiment of the application, the sample positioning data are acquired; extracting characteristic information of sample positioning data, wherein the characteristic information comprises: at least one of a difference value between the widelane ambiguity and the ambiguity difference value, a position difference between a first position and a second position, and a position difference between the first position and a third position, wherein the ambiguity difference value is a difference value between ambiguities of two frequency points, the first position is a position obtained by performing positioning calculation according to the widelane ambiguity, the second position is a position obtained by performing positioning calculation according to the ambiguity of any one of the two frequency points, and the third position is a position obtained by performing positioning calculation according to the ultra-wide elane ambiguity; and training the neural network model according to the characteristic information to obtain an ambiguity confirmation model. And further, confirming the ambiguity corresponding to the acquired target positioning data by using the ambiguity confirming model, so as to obtain a confirming result of the ambiguity corresponding to the target positioning data. On the one hand, some observed quantity thresholds are not required to be set through an empirical model, namely the accuracy of the ambiguity confirmation can be improved without depending on the empirical model and the set observed quantity thresholds during the ambiguity confirmation. On the other hand, the ambiguity confirmation model is trained based on at least one of the difference between the widelane ambiguity and the ambiguity difference, the difference between the first position and the second position, and the difference between the first position and the third position, and the difference between the widelane ambiguity and the ambiguity difference, the difference between the first position and the second position, and the difference between the first position and the third position are important features among features related to ambiguity confirmation.
In some possible implementations of embodiments of the present application, the characteristic information further includes at least three of the following:
the method comprises the steps of fixing the number of ambiguities, detecting errors in unit weights, precision factor values, the number of reference satellite changes, quality marks of single-point solution positioning results, the number of valid pseudo-ranges, pseudo-range residual errors, the number of satellites, the ratio of minimum unit weight variance to secondary unit weight variance obtained according to alternative ambiguities, the mean value of fixed solution carrier double-difference residual errors and the average carrier-to-noise ratio.
In some possible implementations of embodiments of the present application, a neural network model includes:
and (5) classifying the models.
In some possible implementations of embodiments of the present application, the classification model includes:
a logistic regression-based classification model.
It should be noted that, in the ambiguity confirming method provided in the embodiment of the present application, the execution subject may be an ambiguity confirming device. In the embodiment of the present application, an example of an ambiguity confirming method performed by an ambiguity confirming apparatus is described as an ambiguity confirming apparatus provided in the embodiment of the present application.
Fig. 5 is a schematic structural diagram of an ambiguity confirming apparatus according to an embodiment of the present application. As shown in fig. 5, the ambiguity confirming apparatus 500 may include:
A second obtaining module 501, configured to obtain target positioning data;
a second extracting module 502, configured to extract feature information of the target positioning data;
and the confirmation module 503 is configured to input the feature information into the ambiguity confirmation model obtained by training using the ambiguity confirmation model training method provided by the embodiment of the present application, and obtain a confirmation result of the ambiguity corresponding to the target positioning data.
In the embodiment of the application, the ambiguity corresponding to the acquired target positioning data can be confirmed through the ambiguity confirming model, and a confirming result of the ambiguity corresponding to the target positioning data is obtained. On the one hand, some observed quantity thresholds are not required to be set through an empirical model, namely the accuracy of the ambiguity confirmation can be improved without depending on the empirical model and the set observed quantity thresholds during the ambiguity confirmation. On the other hand, the ambiguity confirmation model is trained according to at least one of the difference between the widelane ambiguity and the ambiguity difference, the difference between the first position and the second position, and the difference between the first position and the third position, wherein the ambiguity difference is the difference between the ambiguities of the two frequency points, the first position is the position obtained by positioning calculation according to the widelane ambiguity, the second position is the position obtained by positioning calculation according to the ambiguity of any one of the two frequency points, the third position is the position obtained by positioning calculation according to the ultra-wide lane ambiguity, and the difference between the widelane ambiguity and the ambiguity difference, the difference between the first position and the second position, and the difference between the first position and the third position are important features in the features related to the ambiguity confirmation.
The training device or the ambiguity confirming device of the ambiguity confirming model in the embodiment of the application may be an electronic device, or may be a component in the electronic device, such as an integrated circuit, or a chip. The electronic device may be a terminal, or may be other devices than a terminal. By way of example, the electronic device may be a mobile phone, tablet computer, notebook computer, palm computer, vehicle-mounted electronic device, mobile internet appliance (Mobile Internet Device, MID), augmented reality (augmented reality, AR)/Virtual Reality (VR) device, robot, wearable device, ultra-mobile personal computer, UMPC, netbook or personal digital assistant (personal digital assistant, PDA), etc., but may also be a server, network attached storage (Network Attached Storage, NAS), personal computer (personal computer, PC), television (TV), teller machine or self-service machine, etc., and the embodiments of the present application are not limited in particular.
The training device or the ambiguity confirming device of the ambiguity confirming model in the embodiment of the present application may be a device with an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiments of the present application.
The training device for the ambiguity confirming model provided by the embodiment of the application can realize each process in the training method embodiment of the ambiguity confirming model provided by the embodiment of the application, and in order to avoid repetition, the description is omitted here.
The ambiguity confirming device provided in the embodiment of the present application can implement each process in the embodiment of the ambiguity confirming method provided in the embodiment of the present application, and in order to avoid repetition, a detailed description is omitted here.
Optionally, as shown in fig. 6, the embodiment of the present application further provides an electronic device 600, including a processor 601 and a memory 602, where the memory 602 stores a program or instructions that can be executed on the processor 601, and the program or instructions implement the steps of the training method of the ambiguity confirmation model or the ambiguity confirmation method embodiment when executed by the processor 601, and achieve the same technical effects, so that repetition is avoided and redundant description is omitted herein.
In some possible implementations of embodiments of the present application, the processor 601 may include a Central Processing Unit (CPU), or an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or may be configured to implement one or more integrated circuits of embodiments of the present application.
In some possible implementations of embodiments of the present application, memory 602 may include Read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), magnetic disk storage media devices, optical storage media devices, flash Memory devices, electrical, optical, or other physical/tangible Memory storage devices. Thus, in general, the memory 602 includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software comprising computer-executable instructions and when the software is executed (e.g., by one or more processors) it is operable to perform the operations described with reference to the training method or the ambiguity validation method of the ambiguity validation model provided in accordance with embodiments of the present application.
Fig. 7 is a schematic diagram of a hardware structure of an electronic device implementing an embodiment of the present application.
The electronic device 700 includes, but is not limited to: radio frequency unit 701, network module 702, audio output unit 703, input unit 704, sensor 705, display unit 706, user input unit 707, interface unit 708, memory 709, and processor 710.
Those skilled in the art will appreciate that the electronic device 700 may also include a power source (e.g., a battery) for powering the various components, which may be logically connected to the processor 710 via a power management system so as to perform functions such as managing charge, discharge, and power consumption via the power management system. The electronic device structure shown in fig. 7 does not constitute a limitation of the electronic device, and the electronic device may include more or less components than shown, or may combine certain components, or may be arranged in different components, which are not described in detail herein.
Wherein the processor 710 is configured to: acquiring sample positioning data; extracting characteristic information of sample positioning data, wherein the characteristic information comprises: at least one of a difference value between the widelane ambiguity and the ambiguity difference value, a position difference between a first position and a second position, and a position difference between the first position and a third position, wherein the ambiguity difference value is a difference value between ambiguities of two frequency points, the first position is a position obtained by performing positioning calculation according to the widelane ambiguity, the second position is a position obtained by performing positioning calculation according to the ambiguity of any one of the two frequency points, and the third position is a position obtained by performing positioning calculation according to the ultra-wide elane ambiguity; and training the neural network model according to the characteristic information to obtain an ambiguity confirmation model.
In some possible implementations of embodiments of the present application, the characteristic information further includes at least three of the following:
the method comprises the steps of fixing the number of ambiguities, detecting errors in unit weights, precision factor values, the number of reference satellite changes, quality marks of single-point solution positioning results, the number of valid pseudo-ranges, pseudo-range residual errors, the number of satellites, the ratio of minimum unit weight variance to secondary unit weight variance obtained according to alternative ambiguities, the mean value of fixed solution carrier double-difference residual errors and the average carrier-to-noise ratio.
In some possible implementations of embodiments of the present application, a neural network model includes:
and (5) classifying the models.
In some possible implementations of embodiments of the present application, the classification model includes:
a logistic regression-based classification model.
In some possible implementations of embodiments of the present application, processor 710 may also be configured to: acquiring target positioning data; extracting characteristic information of target positioning data; and inputting the characteristic information into the ambiguity confirming model to obtain a confirming result of the ambiguity corresponding to the target positioning data.
In the embodiment of the application, the ambiguity corresponding to the acquired target positioning data can be confirmed through the ambiguity confirming model, and a confirming result of the ambiguity corresponding to the target positioning data is obtained. On the one hand, some observed quantity thresholds are not required to be set through an empirical model, namely the accuracy of the ambiguity confirmation can be improved without depending on the empirical model and the set observed quantity thresholds during the ambiguity confirmation. On the other hand, the ambiguity confirmation model is trained according to at least one of the difference between the widelane ambiguity and the ambiguity difference, the difference between the first position and the second position, and the difference between the first position and the third position, wherein the ambiguity difference is the difference between the ambiguities of the two frequency points, the first position is the position obtained by positioning calculation according to the widelane ambiguity, the second position is the position obtained by positioning calculation according to the ambiguity of any one of the two frequency points, the third position is the position obtained by positioning calculation according to the ultra-wide lane ambiguity, and the difference between the widelane ambiguity and the ambiguity difference, the difference between the first position and the second position, and the difference between the first position and the third position are important features in the features related to the ambiguity confirmation.
It should be appreciated that in embodiments of the present application, the input unit 704 may include a graphics processor (Graphics Processing Unit, GPU) 7041 and a microphone 7042, with the graphics processor 7041 processing image data of still pictures or video obtained by an image capturing device (e.g., a camera) in a video capturing mode or an image capturing mode. The display unit 706 may include a display panel 7061, and the display panel 7061 may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like. The user input unit 707 includes at least one of a touch panel 7071 and other input devices 7072. The touch panel 7071 is also referred to as a touch screen. The touch panel 7071 may include two parts, a touch detection device and a touch controller. Other input devices 7072 may include, but are not limited to, a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and so forth, which are not described in detail herein.
The memory 709 may be used to store software programs as well as various data. The memory 709 may mainly include a first storage area storing programs or instructions and a second storage area storing data, wherein the first storage area may store an operating system, application programs or instructions (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like. Further, the memory 709 may include volatile memory or nonvolatile memory, or the memory 709 may include both volatile and nonvolatile memory. The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable EPROM (EEPROM), or a flash Memory. The volatile memory may be random access memory (Random Access Memory, RAM), static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (ddr SDRAM), enhanced SDRAM (Enhanced SDRAM), synchronous DRAM (SLDRAM), and Direct RAM (DRRAM). Memory 709 in embodiments of the present application includes, but is not limited to, these and any other suitable types of memory.
The embodiment of the present application further provides a readable storage medium, where a program or an instruction is stored, where the program or the instruction implements each process of the training method or the embodiment of the ambiguity confirmation method of the ambiguity confirmation model when executed by a processor, and the same technical effect can be achieved, so that repetition is avoided, and no redundant description is given here.
The processor is a processor in the electronic device in the above embodiment. The readable storage medium includes a computer readable storage medium, and examples of the computer readable storage medium include a non-transitory computer readable storage medium such as ROM, RAM, magnetic disk, or optical disk.
The embodiment of the application further provides a chip, which comprises a processor and a communication interface, wherein the communication interface is coupled with the processor, and the processor is used for running a program or instructions, so that the training method of the ambiguity confirming model or each process of the ambiguity confirming method embodiment can be realized, the same technical effect can be achieved, and the repetition is avoided, and the repeated description is omitted.
It should be understood that the chips referred to in the embodiments of the present application may also be referred to as system-on-chip chips, chip systems, or system-on-chip chips, etc.
The embodiments of the present application provide a computer program product stored in a storage medium, where the program product is executed by at least one processor to implement the respective processes of the training method or the embodiment of the ambiguity confirmation method of the ambiguity confirmation model, and achieve the same technical effects, so that repetition is avoided, and no further description is given here.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. Furthermore, it should be noted that the scope of the methods and apparatus in the embodiments of the present application is not limited to performing the functions in the order shown or discussed, but may also include performing the functions in a substantially simultaneous manner or in an opposite order depending on the functions involved, e.g., the described methods may be performed in an order different from that described, and various steps may also be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the related art in the form of a computer software product stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk), including several instructions for causing a terminal (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method described in the embodiments of the present application.
The embodiments of the present application have been described above with reference to the accompanying drawings, but the present application is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many forms may be made by those of ordinary skill in the art without departing from the spirit of the present application and the scope of the claims, which are also within the protection of the present application.
Claims (12)
1. A method of training an ambiguity validation model, the method comprising:
acquiring sample positioning data;
extracting characteristic information of the sample positioning data, wherein the characteristic information comprises: at least one of a difference value between the widelane ambiguity and the ambiguity difference value, a position difference between a first position and a second position, and a position difference between the first position and a third position, wherein the ambiguity difference value is a difference value between ambiguities of two frequency points, the first position is a position obtained by performing positioning calculation according to the widelane ambiguity, the second position is a position obtained by performing positioning calculation according to the ambiguity of any one of the two frequency points, and the third position is a position obtained by performing positioning calculation according to the ultra-wide elane ambiguity;
and training a neural network model according to the characteristic information to obtain an ambiguity confirming model.
2. The method of claim 1, wherein the characteristic information further comprises at least three of the following:
the method comprises the steps of fixing the number of ambiguities, detecting errors in unit weights, precision factor values, the number of reference satellite changes, quality marks of single-point solution positioning results, the number of valid pseudo-ranges, pseudo-range residual errors, the number of satellites, the ratio of minimum unit weight variance to secondary unit weight variance obtained according to alternative ambiguities, the mean value of fixed solution carrier double-difference residual errors and the average carrier-to-noise ratio.
3. The method of claim 1, wherein the neural network model comprises:
and (5) classifying the models.
4. A method according to claim 3, wherein the classification model comprises:
a logistic regression-based classification model.
5. A method of ambiguity validation, the method comprising:
acquiring target positioning data;
extracting characteristic information of the target positioning data;
inputting the characteristic information into an ambiguity confirmation model obtained by training the ambiguity confirmation model according to any one of claims 1 to 4, and obtaining a confirmation result of the ambiguity corresponding to the target positioning data.
6. A training apparatus for an ambiguity validation model, the apparatus comprising:
the first acquisition module is used for acquiring sample positioning data;
the first extraction module is used for extracting characteristic information of the sample positioning data, wherein the characteristic information comprises: at least one of a difference value between the widelane ambiguity and the ambiguity difference value, a position difference between a first position and a second position, and a position difference between the first position and a third position, wherein the ambiguity difference value is a difference value between ambiguities of two frequency points, the first position is a position obtained by performing positioning calculation according to the widelane ambiguity, the second position is a position obtained by performing positioning calculation according to the ambiguity of any one of the two frequency points, and the third position is a position obtained by performing positioning calculation according to the ultra-wide elane ambiguity;
And the training module is used for training the neural network model according to the characteristic information to obtain an ambiguity confirmation model.
7. The apparatus of claim 6, wherein the characteristic information further comprises at least three of the following:
the method comprises the steps of fixing the number of ambiguities, detecting errors in unit weights, precision factor values, the number of reference satellite changes, quality marks of single-point solution positioning results, the number of valid pseudo-ranges, pseudo-range residual errors, the number of satellites, the ratio of minimum unit weight variance to secondary unit weight variance obtained according to alternative ambiguities, the mean value of fixed solution carrier double-difference residual errors and the average carrier-to-noise ratio.
8. The apparatus of claim 6, wherein the neural network model comprises:
and (5) classifying the models.
9. The apparatus of claim 8, wherein the classification model comprises:
a logistic regression-based classification model.
10. An ambiguity confirming apparatus, the apparatus comprising:
the second acquisition module is used for acquiring target positioning data;
the second extraction module is used for extracting the characteristic information of the target positioning data;
and the confirmation module is used for inputting the characteristic information into the ambiguity confirmation model obtained by training by using the ambiguity confirmation model training method according to any one of claims 1 to 4 to obtain a confirmation result of the ambiguity corresponding to the target positioning data.
11. An electronic device, the electronic device comprising: a processor and a memory storing a program or instructions executable on the processor, which when executed by the processor, implement the method of training an ambiguity validation model according to any one of claims 1 to 4 or the steps of an ambiguity validation method according to claim 5.
12. A readable storage medium, wherein a program or instructions is stored on the readable storage medium, which when executed by a processor, implements the method of training an ambiguity validation model according to any one of claims 1 to 4 or the steps of an ambiguity validation method according to claim 5.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111572245.8A CN116304654A (en) | 2021-12-21 | 2021-12-21 | Training method of ambiguity confirming model, ambiguity confirming method and device |
| PCT/CN2022/116375 WO2023116043A1 (en) | 2021-12-21 | 2022-08-31 | Training method for ambiguity validation model, method for ambiguity validation, and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111572245.8A CN116304654A (en) | 2021-12-21 | 2021-12-21 | Training method of ambiguity confirming model, ambiguity confirming method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116304654A true CN116304654A (en) | 2023-06-23 |
Family
ID=86822680
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111572245.8A Pending CN116304654A (en) | 2021-12-21 | 2021-12-21 | Training method of ambiguity confirming model, ambiguity confirming method and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN116304654A (en) |
| WO (1) | WO2023116043A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117092679A (en) * | 2023-10-19 | 2023-11-21 | 北京凯芯微科技有限公司 | Training method of artificial neural network for RTK ambiguity fixing judgment |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10338233B2 (en) * | 2017-04-12 | 2019-07-02 | Coherent Technical Services, Inc. | Assured validation of carrier-phase integer ambiguities for safety-of-life applications |
| CN110907973B (en) * | 2018-09-14 | 2021-11-19 | 千寻位置网络有限公司 | Network RTK baseline double-difference ambiguity checking method, device and positioning method |
| CN109191457B (en) * | 2018-09-21 | 2022-07-01 | 中国人民解放军总医院 | Pathological image quality validity identification method |
| CN112083463B (en) * | 2019-06-13 | 2024-03-29 | 千寻位置网络有限公司 | Method and device for detecting whether ambiguity is fixed correctly and positioning terminal |
| US11474263B2 (en) * | 2020-02-13 | 2022-10-18 | Mitsubishi Electric Research Laboratories, Inc. | System and method for GNSS ambiguity resolution |
-
2021
- 2021-12-21 CN CN202111572245.8A patent/CN116304654A/en active Pending
-
2022
- 2022-08-31 WO PCT/CN2022/116375 patent/WO2023116043A1/en unknown
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117092679A (en) * | 2023-10-19 | 2023-11-21 | 北京凯芯微科技有限公司 | Training method of artificial neural network for RTK ambiguity fixing judgment |
| CN117092679B (en) * | 2023-10-19 | 2024-01-30 | 北京凯芯微科技有限公司 | Training method of artificial neural network for RTK ambiguity fixing judgment |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023116043A1 (en) | 2023-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10572798B2 (en) | Dueling deep neural networks | |
| CN107784671A (en) | A kind of method and system positioned immediately for vision with building figure | |
| Luo et al. | Kayak and sailboat detection based on the improved YOLO with Transformer | |
| CN116304654A (en) | Training method of ambiguity confirming model, ambiguity confirming method and device | |
| CN112907671B (en) | Point cloud data generation method and device, electronic equipment and storage medium | |
| CN110728172B (en) | Point cloud-based face key point detection method, device and system and storage medium | |
| CN110673099A (en) | Multi-radar point trace correlation method and device | |
| CN114648556A (en) | Visual tracking method and device and electronic equipment | |
| CN113344994B (en) | Image registration method, device, electronic equipment and storage medium | |
| CN114565777A (en) | Data processing method and device | |
| CN114527456A (en) | UWB-based motion trajectory identification method and electronic equipment | |
| Lin | Automatic recognition and detection of building targets in urban remote sensing images using an improved regional convolutional neural network algorithm | |
| CN113155136B (en) | Training method and device of GNSS satellite orbit prediction deviation analysis model | |
| Guo et al. | Change detection for high resolution remote sensing image based on co-saliency strategy | |
| CN117788863A (en) | Local template generation method and local template generation device | |
| CN115965856B (en) | Image detection model construction method, device, computer equipment and storage medium | |
| Yu et al. | Gesture tracking and locating algorithm based on federated tracking filter | |
| Zeng et al. | DFPC-SLAM: A dynamic feature point constraints-based SLAM using stereo vision for dynamic environment | |
| US20220292878A1 (en) | Apparatus and method for detecting facial pose, image processing system, and storage medium | |
| Yang | Enhancing the Precision of Smartphone GNSS Positioning Using Machine Learning | |
| Li et al. | A Few-shot Dynamic Obstacle Avoidance Strategy in Unknown Environments | |
| CN115902958A (en) | Method, device and equipment for calibrating phase-frequency deviation between receivers | |
| CN117908053A (en) | Ionosphere data extraction method and device, storage medium and electronic equipment | |
| Li et al. | A Kinematic GNSS Positioning Method Based on Unscented Kalman Filter | |
| CN116412809A (en) | Method and device for real-time positioning and mapping under dynamic environment and electronic equipment |
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 |