CN110824514A - Fingerprint positioning method and device and computer readable storage medium - Google Patents
Fingerprint positioning method and device and computer readable storage medium Download PDFInfo
- Publication number
- CN110824514A CN110824514A CN201810920309.0A CN201810920309A CN110824514A CN 110824514 A CN110824514 A CN 110824514A CN 201810920309 A CN201810920309 A CN 201810920309A CN 110824514 A CN110824514 A CN 110824514A
- Authority
- CN
- China
- Prior art keywords
- cluster
- test data
- data
- determining
- joint probability
- 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
- 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
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
- G01S5/0252—Radio frequency fingerprinting
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
- G01S5/0278—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves involving statistical or probabilistic considerations
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Computer Networks & Wireless Communication (AREA)
- Collating Specific Patterns (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention discloses a fingerprint positioning method and device and a computer readable storage medium. The fingerprint positioning method comprises the following steps: clustering auxiliary global satellite positioning system data in the base station measurement report data, and determining at least one cluster and the longitude and latitude of the central point of each cluster; determining a joint probability density model corresponding to each cluster according to the characteristic data of each cluster; acquiring test data of a user terminal; bringing the test data into the joint probability density model of each cluster, and determining the cluster to which the test data belongs; and taking the longitude and latitude of the central point of the cluster to which the test data belongs as a positioning result of the user terminal. The method uses the probability density model prediction to replace the process of finding the optimal matching prediction according to the road test data in the grid, thereby saving the cost required by the road test.
Description
Technical Field
The invention relates to the field of big data positioning, in particular to a fingerprint positioning method and device and a computer readable storage medium.
Background
The fingerprint positioning is divided into outdoor fingerprint positioning and indoor fingerprint positioning, and the outdoor fingerprint positioning technology of the related technology needs to grid a map and carry out drive test on longitude and latitude information and signal strength information in each grid. Modeling the information collected for each grid. When the user is at any position on the map, the matching degree of the field intensity information of the user signal and each grid model is compared, and the user can be positioned in a certain grid, so that the position information of the user can be acquired.
Disclosure of Invention
The applicant found that: the traditional outdoor fingerprint positioning technology needs a large amount of road tests, the positioning precision is influenced by the size of grid division and whether test points in grids are uniform, and a large amount of time and energy are consumed in the rasterization process. Modeling requires drive test data under different weather conditions.
In view of the above technical problems, the present invention provides a fingerprint Positioning method and apparatus, and a computer-readable storage medium, which cluster samples according to an Assisted Global Positioning System (AGPS) to establish a prediction model, thereby saving the cost required for drive test.
According to an aspect of the present invention, there is provided a fingerprint positioning method, including:
clustering auxiliary global satellite positioning system data in the base station measurement report data, and determining at least one cluster and the longitude and latitude of the central point of each cluster;
determining a joint probability density model corresponding to each cluster according to the characteristic data of each cluster;
acquiring test data of a user terminal;
bringing the test data into the joint probability density model of each cluster, and determining the cluster to which the test data belongs;
and taking the longitude and latitude of the central point of the cluster to which the test data belongs as a positioning result of the user terminal.
In some embodiments of the present invention, the bringing the test data into the joint probability density model of each cluster, and the determining the cluster to which the test data belongs, includes:
bringing the test data into a joint probability density model of each cluster, and determining the joint probability of the test data belonging to each cluster;
and taking the cluster corresponding to the maximum joint probability as the cluster to which the test data belongs.
In some embodiments of the present invention, the determining, according to the feature data of each cluster, a probability density model corresponding to each cluster includes:
for each cluster, respectively fitting by adopting at least one characteristic data to obtain at least one model, wherein one characteristic data corresponds to one model;
and determining a joint probability density model corresponding to each cluster according to the at least one model and the weight value corresponding to each model.
In some embodiments of the invention, said separately fitting with at least one characteristic data comprises:
and according to different signal transmission scenes, performing curve or surface fitting by adopting at least one of Rayleigh distribution, Rice distribution and multidimensional Gaussian distribution.
In some embodiments of the invention, the characteristic data comprises reference signal received power data.
According to another aspect of the present invention, there is provided a fingerprint positioning device comprising:
the cluster processing module is used for carrying out cluster processing on the auxiliary global satellite positioning system data in the base station measurement report data and determining at least one cluster and the longitude and latitude of the central point of each cluster;
the model establishing module is used for determining a joint probability density model corresponding to each cluster according to the characteristic data of each cluster;
the test data acquisition module is used for acquiring test data of the user terminal;
the cluster determining module is used for bringing the test data into the joint probability density model of each cluster and determining the cluster to which the test data belongs;
and the positioning module is used for taking the longitude and latitude of the central point of the cluster to which the test data belongs as the positioning result of the user terminal.
In some embodiments of the invention, the cluster determination module is configured to bring the test data into the joint probability density model of each cluster, and determine a joint probability that the test data belongs to each cluster; and taking the cluster corresponding to the maximum joint probability as the cluster to which the test data belongs.
In some embodiments of the present invention, the fingerprint positioning device is configured to perform operations for implementing the fingerprint positioning method according to any of the above embodiments.
According to another aspect of the present invention, there is provided a fingerprint positioning device comprising:
a memory to store instructions;
a processor configured to execute the instructions to cause the fingerprint positioning apparatus to perform operations for implementing the fingerprint positioning method according to any one of the above embodiments.
According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions which, when executed by a processor, implement a fingerprint location method as in any of the above embodiments.
The method uses the probability density model prediction to replace the process of finding the optimal matching prediction according to the road test data in the grid, thereby saving the cost required by the road test.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a diagram of a fingerprint location method according to some embodiments of the present invention.
FIG. 2 is a diagram of another embodiment of a fingerprint location method of the present invention.
FIG. 3 is a diagram of a fingerprint location method according to yet another embodiment of the present invention.
FIG. 4 is a graph illustrating the effect of clustering on grid construction in some embodiments of the present invention.
FIG. 5 is a graph illustrating the simulation effect of the probability density model in some embodiments of the invention.
FIG. 6 is a diagram illustrating a model effect test in some embodiments of the invention.
FIG. 7 is a diagram of a fingerprint locating device according to some embodiments of the present invention.
FIG. 8 is a schematic view of another embodiment of a fingerprint positioning device according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The relative arrangement of the components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.
Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
FIG. 1 is a diagram of a fingerprint location method according to some embodiments of the present invention. Preferably, this embodiment can be performed by the fingerprint positioning device of the present invention. The method comprises the following steps:
step 11, performing clustering processing on the assisted global positioning system data in the MR (Measurement Report) data of the base station, and determining at least one cluster and the longitude and latitude of the central point of each cluster.
In some embodiments of the invention, each cluster corresponds to a case, for example: each cluster corresponds to a different weather, different people stream density condition.
And step 12, determining a joint probability density model corresponding to each cluster according to the characteristic data of each cluster.
In some embodiments of the present invention, step 12 may comprise:
and step 121, for each cluster, respectively fitting by using at least one characteristic data to obtain at least one model, wherein one characteristic data corresponds to one model.
In some embodiments of the present invention, in step 121, the step of separately fitting with at least one feature data may include: and according to different signal transmission scenes, performing curve or surface fitting by adopting at least one of the Rayleigh distribution, the Rice distribution, the multidimensional Gaussian distribution and other distributions.
In some embodiments of the invention, the characteristic data may comprise RSRP (Reference signal receiving Power) data.
And step 122, determining a joint probability density model corresponding to each cluster according to the at least one model and the weight value corresponding to each model.
In some embodiments of the present invention, step 12 may comprise: and performing characteristic processing on each training characteristic under various types of data, considering a signal propagation model in an actual situation, performing fitting distribution on each characteristic of a received signal, converting the training characteristics into a probability form, and establishing a prediction model.
And step 13, acquiring the test data of the user terminal.
And step 14, bringing the test data into the joint probability density model of each cluster, and determining the cluster to which the test data belongs.
In some embodiments of the invention, step 14 may comprise:
step 141, the test data is brought into the joint probability density model of each cluster to determine the joint probability of the test data belonging to each cluster.
And 142, taking the cluster corresponding to the maximum joint probability as the cluster to which the test data belongs.
And step 15, taking the longitude and latitude of the central point of the cluster to which the test data belongs as a positioning result of the user terminal.
Based on the fingerprint positioning method provided by the embodiment of the invention, the samples are clustered according to the existing AGPS information, the training characteristics under various types of data are subjected to characteristic processing, a signal propagation model in the actual situation is considered, the fitting distribution is carried out on the characteristics of the received signals, the training characteristics are converted into a probability form, a prediction model is established, the drive test process of the related technology is replaced, and the cost required by the drive test is saved.
FIG. 2 is a diagram of another embodiment of a fingerprint location method of the present invention. FIG. 3 is a diagram of a fingerprint location method according to yet another embodiment of the present invention. Preferably, this embodiment can be performed by the fingerprint positioning device of the present invention. The fingerprint locating method as shown in fig. 2 comprises the following steps:
step 21, performing clustering processing on the assisted global positioning system data in the MR (Measurement Report) data of the base station, and determining a plurality of clusters (K1, K2.., Kn) and coordinates (longitude and latitude) of a center point of each cluster: (c11, c12), (c21, c22), …, (cn1, cn 2).
For example: in the fingerprint location method in the embodiment of fig. 3, the clustering process includes three clusters, K1, K2 and K3.
And step 22, establishing a joint probability density model (P1, P2.., Pn) according to the data characteristics under each cluster.
In the embodiment of the present invention shown in fig. 3, step 22 may include:
step 221, for each of three clusters of K1, K2, and K3, fitting n features respectively, and obtaining n models K1, K2.
For example: n models obtained by clustering the K1 in the embodiment of fig. 3 are K11, K12.
In step 222, each model corresponds to a probability density.
For example: n models of K1 in the embodiment of fig. 3 are K11, K12, and K1n respectively correspond to probability densities of P11, P12, P1 n.
Step 223, determining a joint probability density model corresponding to each cluster according to the probability density of the at least one model and the weight value corresponding to each model.
For example: in the embodiment of fig. 3, a joint probability density model P1 of K1 may be determined according to probability densities of n models of K1, P11, P12, ·, P1n, and weight values w11, w12, ·, w1n of the n models.
And step 23, determining the class of the test set according to the joint probability for the matching degree of the test data calculator domain cluster, and taking the longitude and latitude of the central point of the class of the test set as a positioning result.
In some embodiments of the present invention, step 23 may comprise:
231, substituting n characteristics of the test data into different models to obtain the joint probability P of the test data belonging to the kth classkTaking the class to which the maximum probability belongs: k is argmax (P)k)。
For example: in the embodiment of fig. 3, n features of the test data are substituted into different models K1, K2 and K3, a joint probability P1 that the test data belongs to K1, a joint probability P2 that the test data belongs to K2 and a joint probability P3 that the test data belongs to K3 are obtained, and a cluster corresponding to the maximum value among P1, P2 and P3 is used as a cluster to which the test data belongs.
Step 232, taking the longitude and latitude of the central point of the cluster to which the test data belongs as a positioning result.
The applicant found that: the related art fingerprint algorithm does not process the features when calling the user fingerprint for classification.
The method of the embodiment of the invention does not depend on the longitude and latitude of the base station, clusters the samples according to the existing AGPS information, processes the characteristics of each training characteristic under various data, considers the signal propagation model in the actual situation, fits the distribution of each characteristic of the received signals, converts the training characteristics into a probability form, establishes a prediction model, replaces the drive test process of the original method, and saves the cost required by drive test.
FIG. 4 is a graph illustrating the effect of clustering on grid construction in some embodiments of the present invention. The embodiment of fig. 4 is a graph showing the effect of 6 clusters of single base stations in sample data, and the maximum distance in a cluster does not exceed 80 meters. Unlike rasterization, the clustering method does not require drive tests, and positioning is more accurate when the user is in a dense urban area. Because the main clusters are all concentrated in dense urban areas, the more clusters are classified, the more accurate the positioning is.
Fig. 5 and 6 are graphs showing the effect of single feature fitting under single-class data according to some embodiments of the present invention. FIG. 5 is a graph illustrating the simulation effect of the probability density model in some embodiments of the invention. Specifically, Rayleigh distribution fitting is carried out on PSRP data distribution of a master station under an MR data training set to obtain a Rayleigh model, and the maximum error is not more than 8%. FIG. 6 is a diagram illustrating a model effect test in some embodiments of the invention. In fig. 5 and 6, "+" curves represent probability density models, and "diamond" plot points represent actual values in the test set. From fig. 5 and 6, it can be seen that the fitted probability density model has a good prediction level for the test set probability, with an average error of 11.5%.
The embodiment of the invention adopts a new fingerprint positioning model, the method of the embodiment of the invention changes the related fingerprint positioning process, and uses clustering to replace the rasterization and drive test process, and the clustering quantity can be adjusted according to the data set condition. The fingerprint positioning method according to the above embodiment of the present invention specifically performs clustering according to AGPS fields in MR data. Each type is independent to be a model, and different joint probability models, such as Rayleigh distribution, Gaussian distribution and the like, are fitted under different weathers according to various types of data. Then, the embodiment of the invention uses the joint probability density model to predict the user position, thereby saving the labor cost consumed in the rasterization and drive test processes. According to the embodiment of the invention, different probability density models can be fitted according to data characteristics under various conditions such as different weather conditions, different people stream densities and the like, and then the user position is predicted.
The embodiment of the invention is a fingerprint positioning method based on a probability density model, and a clustering method is used for replacing a rasterization process.
In the embodiment of the invention, the probability density model prediction is used to replace the process of finding the optimal matching prediction according to the road test data in the grid, so that the cost required by the road test is saved.
According to the embodiment of the invention, different probability models can be generated according to data under different conditions to position the user, so that the drive test data (different weather and different pedestrian volume) under different conditions can be replaced. The embodiment of the invention can be applied to the aspects of 5G user positioning, network optimization front-back comparison and the like.
The applicant found that: the data with AGPS information in the LTE-MR data accounts for about 4% of the total data, and the data source of the embodiment of the invention is stable. The above-described embodiments of the present invention are readily implemented.
FIG. 7 is a diagram of a fingerprint locating device according to some embodiments of the present invention. As shown in fig. 7, the fingerprint location device may include a cluster processing module 71, a model building module 72, a test data obtaining module 73, a cluster determining module 74 and a location module 75, wherein:
the cluster processing module 71 is configured to perform cluster processing on the assisted global positioning system data in the base station measurement report data, and determine at least one cluster and a longitude and latitude of a center point of each cluster.
In some embodiments of the invention, each cluster corresponds to a case, for example: each cluster corresponds to a different weather, different people stream density condition.
And the model establishing module 72 is configured to determine a joint probability density model corresponding to each cluster according to the feature data of each cluster.
In some embodiments of the invention, the characteristic data may comprise RSRP data.
In some embodiments of the present invention, the model establishing module 72 may be specifically configured to perform respective fitting on each cluster by using at least one feature data to obtain at least one model, where one feature data corresponds to one model; and determining a joint probability density model corresponding to each cluster according to the at least one model and the weight value corresponding to each model.
In some embodiments of the present invention, the model establishing module 72 may be specifically configured to perform curve or surface fitting according to different signal transmission scenarios by using at least one of rayleigh distribution, rice distribution, and multidimensional gaussian distribution to obtain at least one model.
In some embodiments of the present invention, the model building module 72 may be specifically configured to perform feature processing on each training feature under various types of data, consider a signal propagation model in an actual situation, perform fitting distribution on each feature of a received signal, convert the training features into a probability form, and build a prediction model.
A test data obtaining module 73, configured to obtain test data of the user terminal.
And a cluster determining module 74, configured to bring the test data into the joint probability density model of each cluster, and determine the cluster to which the test data belongs.
In some embodiments of the present invention, cluster determination module 74 may be configured to bring the test data into the joint probability density model for each cluster, determining the joint probability that the test data belongs to each cluster; and taking the cluster corresponding to the maximum joint probability as the cluster to which the test data belongs.
And a positioning module 75, configured to use the longitude and latitude of the central point of the cluster to which the test data belongs as a positioning result of the user terminal.
In some embodiments of the present invention, the fingerprint positioning device is configured to perform operations for implementing the fingerprint positioning method according to any of the embodiments described above (e.g., any of fig. 1-3).
Based on the fingerprint positioning device provided by the embodiment of the invention, the samples are clustered according to the existing AGPS information, the training characteristics under various types of data are subjected to characteristic processing, a signal propagation model in the actual situation is considered, the fitting distribution is carried out on the characteristics of the received signals, the training characteristics are converted into a probability form, a prediction model is established, the drive test process of the related technology is replaced, and the cost required by the drive test is saved.
FIG. 8 is a schematic view of another embodiment of a fingerprint positioning device according to the present invention. As shown in fig. 8, the fingerprint positioning device may comprise a memory 81 and a processor 82, wherein:
a memory 81 for storing instructions;
a processor 82 configured to execute the instructions to cause the fingerprint positioning device to perform operations for implementing the fingerprint positioning method according to any of the embodiments described above (e.g., any of the embodiments of fig. 1-3).
The embodiment of the invention adopts a new fingerprint positioning model, the method of the embodiment of the invention changes the related fingerprint positioning process, and uses clustering to replace the rasterization and drive test process, and the clustering quantity can be adjusted according to the data set condition. The fingerprint positioning method according to the above embodiment of the present invention specifically performs clustering according to AGPS fields in MR data. Each type is independent to be a model, and different joint probability models, such as Rayleigh distribution, Gaussian distribution and the like, are fitted under different weathers according to various types of data. Then, the embodiment of the invention uses the joint probability density model to predict the user position, thereby saving the labor cost consumed in the rasterization and drive test processes. According to the embodiment of the invention, different probability density models can be fitted according to data characteristics under various conditions such as different weather conditions, different people stream densities and the like, and then the user position is predicted.
According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions which, when executed by a processor, implement a fingerprint location method as in any of the above embodiments.
The computer-readable storage medium of the above-described embodiment of the present invention uses a clustering method instead of the rasterization process.
The computer-readable storage medium of the above embodiment of the present invention uses probability density model prediction to replace the process of finding the optimal matching prediction according to the road test data in the grid, thereby saving the cost required by the road test.
According to the computer-readable storage medium of the above embodiment of the present invention, different probability models can be generated according to data under different conditions to locate the user, so as to replace drive test data (different weather and different pedestrian volume) under different conditions. The embodiment of the invention can be applied to the aspects of 5G user positioning, network optimization front-back comparison and the like.
The fingerprint location device described above may be implemented as a general purpose processor, a Programmable Logic Controller (PLC), a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any suitable combination thereof, for performing the functions described herein.
Thus far, the present invention has been described in detail. Some details well known in the art have not been described in order to avoid obscuring the concepts of the present invention. It will be fully apparent to those skilled in the art from the foregoing description how to practice the presently disclosed embodiments.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The description of the present invention has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the invention in the form disclosed. Many modifications and variations will be apparent to practitioners skilled in this art. The embodiment was chosen and described in order to best explain the principles of the invention and the practical application, and to enable others of ordinary skill in the art to understand the invention for various embodiments with various modifications as are suited to the particular use contemplated.
Claims (10)
1. A fingerprint positioning method, comprising:
clustering auxiliary global satellite positioning system data in the base station measurement report data, and determining at least one cluster and the longitude and latitude of the central point of each cluster;
determining a joint probability density model corresponding to each cluster according to the characteristic data of each cluster;
acquiring test data of a user terminal;
bringing the test data into the joint probability density model of each cluster, and determining the cluster to which the test data belongs;
and taking the longitude and latitude of the central point of the cluster to which the test data belongs as a positioning result of the user terminal.
2. The fingerprint localization method of claim 1, wherein the fitting of the test data to the joint probability density model for each cluster, and the determining of the cluster to which the test data belongs comprises:
bringing the test data into a joint probability density model of each cluster, and determining the joint probability of the test data belonging to each cluster;
and taking the cluster corresponding to the maximum joint probability as the cluster to which the test data belongs.
3. The fingerprint positioning method according to claim 1 or 2, wherein the determining the probability density model corresponding to each cluster according to the feature data of each cluster comprises:
for each cluster, respectively fitting by adopting at least one characteristic data to obtain at least one model, wherein one characteristic data corresponds to one model;
and determining a joint probability density model corresponding to each cluster according to the at least one model and the weight value corresponding to each model.
4. The fingerprint localization method of claim 3, wherein the separately fitting with the at least one feature data comprises:
and according to different signal transmission scenes, performing curve or surface fitting by adopting at least one of Rayleigh distribution, Rice distribution and multidimensional Gaussian distribution.
5. The fingerprint location method of claim 3,
the characteristic data includes reference signal received power data.
6. A fingerprint positioning apparatus, comprising:
the cluster processing module is used for carrying out cluster processing on the auxiliary global satellite positioning system data in the base station measurement report data and determining at least one cluster and the longitude and latitude of the central point of each cluster;
the model establishing module is used for determining a joint probability density model corresponding to each cluster according to the characteristic data of each cluster;
the test data acquisition module is used for acquiring test data of the user terminal;
the cluster determining module is used for bringing the test data into the joint probability density model of each cluster and determining the cluster to which the test data belongs;
and the positioning module is used for taking the longitude and latitude of the central point of the cluster to which the test data belongs as the positioning result of the user terminal.
7. Fingerprint positioning device according to claim 6,
the cluster determining module is used for bringing the test data into the joint probability density model of each cluster and determining the joint probability of the test data belonging to each cluster; and taking the cluster corresponding to the maximum joint probability as the cluster to which the test data belongs.
8. Fingerprint positioning apparatus according to claim 6 or 7, characterized in that the apparatus is configured to perform operations for implementing the fingerprint positioning method according to any one of claims 1-5.
9. A fingerprint positioning apparatus, comprising:
a memory to store instructions;
a processor for executing the instructions to cause the fingerprint positioning device to perform operations to implement the fingerprint positioning method of any one of claims 1-5.
10. A computer-readable storage medium storing computer instructions which, when executed by a processor, implement the fingerprint location method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810920309.0A CN110824514A (en) | 2018-08-14 | 2018-08-14 | Fingerprint positioning method and device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810920309.0A CN110824514A (en) | 2018-08-14 | 2018-08-14 | Fingerprint positioning method and device and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110824514A true CN110824514A (en) | 2020-02-21 |
Family
ID=69547045
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810920309.0A Pending CN110824514A (en) | 2018-08-14 | 2018-08-14 | Fingerprint positioning method and device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110824514A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111417067A (en) * | 2020-03-13 | 2020-07-14 | 智慧足迹数据科技有限公司 | Method and device for positioning visited position of user |
| CN112543938A (en) * | 2020-09-29 | 2021-03-23 | 华为技术有限公司 | Generation method and device of grid occupation map |
| CN113409018A (en) * | 2021-06-25 | 2021-09-17 | 北京红山信息科技研究院有限公司 | People flow density determination method, device, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105764137A (en) * | 2016-02-02 | 2016-07-13 | 北京邮电大学 | Indoor location method and system |
| CN106102161A (en) * | 2016-05-30 | 2016-11-09 | 天津大学 | Based on the data-optimized indoor orientation method of focusing solutions analysis |
| CN106535283A (en) * | 2016-11-25 | 2017-03-22 | 南京科技职业学院 | Indoor positioning method based on beacon clustering |
| US20170188227A1 (en) * | 2015-12-29 | 2017-06-29 | Sk Planet Co., Ltd. | Service provision method using wireless fingerprint map, device performing the same, and recording medium recording computer program executing the same |
-
2018
- 2018-08-14 CN CN201810920309.0A patent/CN110824514A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170188227A1 (en) * | 2015-12-29 | 2017-06-29 | Sk Planet Co., Ltd. | Service provision method using wireless fingerprint map, device performing the same, and recording medium recording computer program executing the same |
| CN105764137A (en) * | 2016-02-02 | 2016-07-13 | 北京邮电大学 | Indoor location method and system |
| CN106102161A (en) * | 2016-05-30 | 2016-11-09 | 天津大学 | Based on the data-optimized indoor orientation method of focusing solutions analysis |
| CN106535283A (en) * | 2016-11-25 | 2017-03-22 | 南京科技职业学院 | Indoor positioning method based on beacon clustering |
Non-Patent Citations (2)
| Title |
|---|
| MA LIN等: "Accuracy Enhancement for Fingerprint-based WLAN Indoor Probability Positioning Algorithm", 《2010 FIRST INTERNATIONAL CONFERENCE ON PERVASIVE COMPUTING, SIGNAL PROCESSING AND APPLICATIONS》 * |
| 杨麒弘: "基于蜂窝网络的定位技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111417067A (en) * | 2020-03-13 | 2020-07-14 | 智慧足迹数据科技有限公司 | Method and device for positioning visited position of user |
| CN112543938A (en) * | 2020-09-29 | 2021-03-23 | 华为技术有限公司 | Generation method and device of grid occupation map |
| CN113409018A (en) * | 2021-06-25 | 2021-09-17 | 北京红山信息科技研究院有限公司 | People flow density determination method, device, equipment and storage medium |
| CN113409018B (en) * | 2021-06-25 | 2024-03-05 | 北京红山信息科技研究院有限公司 | People stream density determining method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105044662B (en) | A kind of fingerprint cluster multi-point joint indoor orientation method based on WIFI signal intensity | |
| CN109168177B (en) | Longitude and latitude backfill method based on soft mining signaling | |
| CN109389163B (en) | Unmanned aerial vehicle image classification system and method based on topographic map | |
| Jiao et al. | Analyzing the impacts of urban expansion on green fragmentation using constraint gradient analysis | |
| CN110824514A (en) | Fingerprint positioning method and device and computer readable storage medium | |
| CN105430032A (en) | Method of pushing information by combining geographic position of terminal, and server | |
| CN109947881B (en) | POI weight judging method and device, mobile terminal and computer readable storage medium | |
| CN103336894B (en) | A kind of city plot ratio automatic Mesh Partition Method | |
| CN109033170B (en) | Data repairing method, device and equipment for parking lot and storage medium | |
| CN110443810A (en) | Point cloud plane dividing method based on quick adjacent voxel inquiry | |
| CN110717619A (en) | Multi-scale space-time load prediction method and system for bottom-up power distribution network | |
| CN110020224A (en) | Correlating method, device, equipment and the medium of map interest point data | |
| CN114374449A (en) | Interference source determination method, device, equipment and medium | |
| CN110047072A (en) | A kind of gravel size identification processing system and processing method based on mobile interchange | |
| CN112328728A (en) | Clustering method and device for mining traveler track, electronic device and storage medium | |
| CN109991591A (en) | Localization method, device, computer equipment and storage medium based on deep learning | |
| CN113133007B (en) | Method, device and equipment for selecting address of communication station | |
| CN109961129A (en) | A kind of Ocean stationary targets search scheme generation method based on improvement population | |
| CN101599142A (en) | Land evaluation index classification quantitative method based on spatial data field | |
| CN110719602A (en) | Fingerprint positioning method and device | |
| CN113141570B (en) | Underground scene positioning method, device, computing equipment and computer storage medium | |
| CN113689226A (en) | Method and device for selecting address of commercial complex, electronic equipment and storage medium | |
| CN117114371A (en) | Modern water network flood prevention monitoring and scheduling method and system based on satellite remote sensing | |
| CN112613530A (en) | Cell resident identification method and system based on adaptive density clustering algorithm | |
| CN108427742B (en) | Power distribution network reliability data restoration method and system based on low-rank matrix |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200221 |
|
| RJ01 | Rejection of invention patent application after publication |