CN107396312A - The accurate recognition methods of customer location based on neutral net - Google Patents
The accurate recognition methods of customer location based on neutral net Download PDFInfo
- Publication number
- CN107396312A CN107396312A CN201710585736.3A CN201710585736A CN107396312A CN 107396312 A CN107396312 A CN 107396312A CN 201710585736 A CN201710585736 A CN 201710585736A CN 107396312 A CN107396312 A CN 107396312A
- Authority
- CN
- China
- Prior art keywords
- user
- neutral net
- customer location
- recognition methods
- accurate recognition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000007935 neutral effect Effects 0.000 title claims abstract description 21
- 238000005259 measurement Methods 0.000 claims description 20
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000013439 planning Methods 0.000 abstract description 4
- 239000000463 material Substances 0.000 abstract description 2
- 230000008447 perception Effects 0.000 abstract description 2
- 238000012913 prioritisation Methods 0.000 abstract description 2
- 210000004027 cell Anatomy 0.000 description 25
- 238000003066 decision tree Methods 0.000 description 6
- 238000012549 training Methods 0.000 description 3
- 238000003909 pattern recognition Methods 0.000 description 2
- 238000013138 pruning Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000009966 trimming Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 210000003169 central nervous system Anatomy 0.000 description 1
- 238000010224 classification analysis Methods 0.000 description 1
- 238000000205 computational method Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/023—Services making use of location information using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
- H04W16/22—Traffic simulation tools or models
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/04—Arrangements for maintaining operational condition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/025—Services making use of location information using location based information parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
- H04W64/006—Locating users or terminals or network equipment for network management purposes, e.g. mobility management with additional information processing, e.g. for direction or speed determination
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention discloses the accurate recognition methods of the customer location based on neutral net, methods described establishes location fingerprint storehouse by using the customer location and the network environment of user that have been collected, and the elaborate position of user is then provided by the user network environment of no position.The present invention accurately can carry out precise positioning to different buildings and its internal different height, the true perception of user can accurately be reacted, so as to our the open-and-shut present situations for knowing network of energy, it is accurately positioned existing network problem, efficiently output prioritization scheme is matched based on multi-data source, network problem is found prior to client, reduces and complains.A large amount of manpower and materials are not only reduced, while to realize that overall, the comprehensive, scientifical planning of in-door covering lifting provides strong support, reduces the influence of various subjective factors in artificial planning, can realize and network exact is planned and optimized.
Description
Technical field
The present invention relates to data message technical field, and in particular to a kind of customer location based on neutral net precisely identifies
Method, it is exactly the mobile network environment using user, calculates a kind of method of user's elaborate position.
Background technology
The position that current telecommunications industry obtains user businessman can only be uploaded by user app, and base station location is found, and
Each map service provider POI.This several ways respectively has advantage and disadvantage.The active that this is user is uploaded by user app
Mode, user, which can pass, to be passed.And which positions generally by gps, typically in outdoor precision at 10 meters or so, certainly
Also there is inaccurate up to a hundred meters of the error of positioning, and it is substantially unavailable indoors;Base station location finds that this mode is operator's active
It was found that can solve the problems, such as user's not uploading position, but the precision positioned is inadequate, general 100 meters or so of precision.And ground
This is manually to gather to the poi information of figure service provider, and precision typically has no problem, but renewal speed is too slow, service fee
It is high.
Application and commercial value of the positional information for nowadays cybertimes are more and more important, and user uses mobile network
Also tend to generally, the purpose of the computational methods is in order to which by using mobile network's solution, positioning is not real-time at present, not enough precisely.
It is related to concept:
(1)Neutral net:Central nervous system of the computation model inspiration from animal of neutral net(Especially brain), and by
For estimating or may rely on substantial amounts of input and the unknown approximate function of in general.Artificial neural network typically appears as mutually
" neuron " of connection, it can from the calculated value of input, and can machine learning and pattern-recognition due to they from
The system of adaptive character.
(2)Bayesian network:Bayesian network is also known as belief network, is the extension of Bayes methods, is not know to know at present
Know one of expression and the maximally effective theoretical model in reasoning field.Bayesian network is the mathematical modeling based on probability inference, so-called
Probability inference is exactly that the process of other probabilistic informations is obtained by the information of some variables, the Bayes based on probability inference
Network (Bayesian network) proposes that it sets for solving complexity in order to solve the problems, such as ambiguity and imperfection
Failure caused by standby uncertain and relevance has very big advantage.
(3)SVM:Support vector machines (Support Vector Machine) are a learning models for having supervision,
Commonly used to carry out pattern-recognition, classification and regression analysis.SVM methods are by a Nonlinear Mapping p, sample sky
Between be mapped in a higher-dimension or even infinite dimensional feature space(Hilbert spaces)So that it is non-in original sample space
The problem of linear separability, is converted into the problem of linear separability in feature space.Briefly, peacekeeping linearisation is exactly risen.
(4)C&R:Post-class processing (Classification and regression trees, CART) is decision tree
One kind, it is the method based on lucky Buddhist nun (Gini) index (and being most simplified lucky Buddhist nun's index).The core of decision tree growth
It is to determine the branching criteria of decision tree:
A. how a current best branch variable is selected from numerous attribute variables;
Namely selection can make the most fast variable of heterogeneous decline.
Heterogeneous measurement:GINI、TWOING、least squared deviation.
First two is directed to continuous variable mainly for classifying type variable, LSD.
Agency's division, weighting division, prior probability
B. how a current optimal partition point is found from numerous values of branching variable(Segmentation threshold);
A, numeric type variable --- the value of record is sorted from small to large, calculating is each worth as child node caused by critical point
Heterogeneous statistic.It is optimal division points that the maximum critical value of heterogeneous reduction degree, which can be made,.
B, classifying type variable --- list being divided into two subsets and be possible to combine, calculate son is generated under every kind of combination
The heterogeneity of node.Equally, the combination for making heterogeneous reduction degree maximum is found as optimum division point.
3. the dormant condition of decision tree
Meet to stop growing with next.
A, node has reached holomorphy;
B, the depth of number tree reaches the depth that user specifies;
C, the number of sample is less than the number that user specifies in node;
D, the amplitude peak that heterogeneous index declines is less than the amplitude that user specifies.
Beta pruning:Description of the complete decision tree to training sample feature is possible " excessively accurate "(By the shadow of noise data
Ring), lacked general representative and can not occur preferably with classification prediction is done to new data " overfitting ".
--- remove influences little division to the precision of tree.Use cost complexity method, i.e., measuring mistake divides wind simultaneously
Danger and the complexity of tree, make the two the smaller the better.
Prune approach:
A, pre- trimming(prepruning):Stop growing strategy
B, rear trimming(postpruning):On the basis of allowing decision tree to obtain most fully growing, further according to certain rule
Then, beta pruning is successively carried out from bottom to top.
Prediction:
Regression tree --- predicted value is the weighted mean of leaf node target variable
Classification tree --- the classification value of certain leaf segment point prediction should be the classification value for causing Misjudgement Loss minimum.
The content of the invention
The technical assignment of the present invention is to be directed to above weak point, there is provided a kind of customer location based on neutral net is accurate
Recognition methods.
The accurate recognition methods of customer location based on neutral net, methods described is by using the user position being collected
Put and the network environment of user establishes location fingerprint storehouse, then provide user's by the user network environment of no position
Elaborate position.
Methods described obtains its mobile phone latitude and longitude information to the smart phone user comprising GPS functions by APP, passes through shifting
Dynamic data network is reported to server;By the latitude and longitude information for parsing reporting of user, you can accurately obtain the fixed point position of user
Put.
Methods described is closed by using time slip scan mode to the MR of the user and the longitude and latitude degrees of data reported
Connection, recalls and user's MR wireless coverages situation and geographical position relation, and then as the learning sample of neutral net, establish position
Learning database.
The network environment parameters of the user include:
1)Main plot and adjacent cell MR.RSRP, it is the leading indicator for reflecting serving cell covering, represents in OMC-R measurement periods
Meet the number of samples that UE Reference Signal Received Power is counted according to by stages of span;
2)Main plot and adjacent cell MR.RSRQ, represent to meet counting down according to by stages for span in OMC-R measurement periods
The number of samples of row Reference Signal Received Quality;
3)MR.TADV, reflection UE arrive the signal propagation time of serving BS, are referring mainly to for reflection UE and serving BS distance
Mark;
4)AOA, reflect the reference azimuth of UE corresponding service cells, reference direction;
5)The physical area identification code of the defined neighboring BS relationship of NcPci, LTE and undefined neighboring BS relationship;
6)The up signal to noise ratio of SinrUL, TD-LTE serving cell, the signal to noise ratio for the upward signal that serving cell receives.
Main plot and adjacent cell MR.RSRP are defined as on the frequency band for considering measurement, carrying cell own reference signal
The linear average of the power of resource unit, it is the leading indicator for reflecting serving cell covering.
Main plot and adjacent cell MR.RSRQ are defined as ratio N × RSRP/(E-UTRA carrier RSSI), wherein N
The quantity molecule and denominator of resource block RB in expression E-UTRA carrier RSSI Measurement bandwidths is on the same resource block
Obtain.
The E-UTRA Carrier RSSI are the instruction of E-UTRA carrier received signals field strength, are UE from all resource blocks
The linear averaging for the total received power observed on source, including common signal channel service and non-service cell signal, adjacent channel are done
Disturb, thermal noise.
Methods described is learnt by the way that the network environment parameters of user and customer position information are put into model, is obtained
Location fingerprint storehouse, the user is positioned according to the user's measurement data subsequently obtained.
The precision of methods described positioning can adjust according to model grid.
Compared to the prior art the present invention, has the advantages that:
The mro measurement sample datas of accurate location known to the inventive method utilization carry out model training, the whole illustraton of model of training
Spectrum is shown in(Figure one, model topology figure), location fingerprint storehouse is then obtained, and the measurement data for subsequently obtaining user just can be quickly to this
User is positioned, and the precision of the positioning can adjust according to model grid, and positioning precision can reach within 5 meters.
The localization method rely on operator's MR measurement data, therefore can accurately to different buildings and its it is internal not
Precise positioning is carried out with height, can accurately react the true perception of user, so as to which we open-and-shut can know network
Present situation, be accurately positioned existing network problem, based on multi-data source match efficiently output prioritization scheme, prior to client find network ask
Topic, reduce and complain.A large amount of manpower and materials are not only reduced, while to realize overall, the comprehensive, scientifical planning of in-door covering lifting
Strong support is provided, reduces the influence of various subjective factors in artificial planning, can realize and network exact is planned and optimized.
Brief description of the drawings
Accompanying drawing 1 is model topology figure of the present invention.
Embodiment
Below in conjunction with the accompanying drawings and specific embodiment the invention will be further described.
The accurate recognition methods of customer location based on neutral net, methods described is by using the user position being collected
Put and the network environment of user establishes location fingerprint storehouse, then provide user's by the user network environment of no position
Elaborate position.
Methods described obtains its mobile phone latitude and longitude information to the smart phone user comprising GPS functions by APP, passes through shifting
Dynamic data network is reported to server;By the latitude and longitude information for parsing reporting of user, you can accurately obtain the fixed point position of user
Put.
Methods described is closed by using time slip scan mode to the MR of the user and the longitude and latitude degrees of data reported
Connection, recalls and user's MR wireless coverages situation and geographical position relation, and then as the learning sample of neutral net, establish position
Learning database.
The network environment parameters of the user include:
1)Main plot and adjacent cell MR.RSRP (reference signal receives power), it is to reflect the leading indicator that serving cell covers, table
Show the number of samples that UE Reference Signal Received Power is counted according to by stages for meeting span in OMC-R measurement periods;
2)Main plot and adjacent cell MR.RSRQ (Reference Signal Received Quality), represent to meet span in OMC-R measurement periods
According to by stages count the downlink reference signal quality of reception number of samples;
3)MR.TADV (Timing Advance), reflection UE arrive serving BS signal propagation time, be reflection UE and serving BS away from
From leading indicator;
4)AOA (eNB angle of arrival), reflect the reference azimuth of UE corresponding service cells, reference direction;Serving BS position relationship
Leading indicator;
5)The physical area identification code of the defined neighboring BS relationship of NcPci, LTE and undefined neighboring BS relationship, UE carry out intra-system handoff
The LTE adjacent cells of defined neighboring BS relationship and undefined neighboring BS relationship are measured when changing, in the defined neighboring BS relationship of LTE and
The defined neighboring BS relationship of LTE demodulated when being measured on the adjacent area carrier wave of undefined neighboring BS relationship and undefined neighboring BS relationship
Adjacent area carrier wave physical area identification code (PCI), undefined adjacent area is the adjacent area that does not configure in OMC neighbor cell configuration lists;
6)The up signal to noise ratio of SinrUL, TD-LTE serving cell, the signal to noise ratio for the upward signal that serving cell receives, it is that reflection is small
The leading indicator of area's quality of uplink signal, represent the original measurement value of the up signal to noise ratio of TD-LTE serving cells received.
Main plot and adjacent cell MR.RSRP are defined as on the frequency band for considering measurement, carrying cell own reference signal
Resource unit(RE)Power(W)Linear average, be reflect serving cell covering leading indicator.
Main plot and adjacent cell MR.RSRQ are defined as ratio N × RSRP/(E-UTRA carrier RSSI), wherein N
The quantity molecule and denominator of resource block RB in expression E-UTRA carrier RSSI Measurement bandwidths is on the same resource block
Obtain.
The E-UTRA Carrier RSSI are the instruction of E-UTRA carrier received signals field strength, are UE from all resource blocks
The total received power observed on source(W)Linear averaging, including common signal channel service and non-service cell signal, adjacent channel
Interference, thermal noise.
As shown in figure 1, methods described by the network environment parameters of user and customer position information by being put into model
Row study, obtains location fingerprint storehouse, just quickly the user can be positioned according to the user's measurement data subsequently obtained.Wherein
It is neural network model figure including Neural NET, Bayesian_MKV is Bayesian model, SVM models, C&R models.
The precision of methods described positioning can adjust according to model grid, and positioning precision can reach within 5 meters.
By embodiment above, the those skilled in the art can readily realize the present invention.But should
Work as understanding, the present invention is not limited to above-mentioned embodiment.On the basis of disclosed embodiment, the technical field
Technical staff can be combined different technical characteristics, so as to realize different technical schemes.
It is the known technology of those skilled in the art in addition to the technical characteristic described in specification.
Claims (9)
1. the accurate recognition methods of customer location based on neutral net, it is characterised in that methods described is by using acquired
Good customer location and the network environment of user establish location fingerprint storehouse, then by the user network environment of no position come
Provide the elaborate position of user.
2. the accurate recognition methods of the customer location according to claim 1 based on neutral net, it is characterised in that the side
Method obtains its mobile phone latitude and longitude information to the smart phone user comprising GPS functions by APP, is reported by mobile data network
To server;By the latitude and longitude information for parsing reporting of user, you can accurately obtain the fixed position of user.
3. the accurate recognition methods of the customer location according to claim 2 based on neutral net, it is characterised in that the side
Method is associated by using time slip scan mode to the MR of the user and the longitude and latitude degrees of data reported, is recalled and user MR
Wireless coverage situation and geographical position relation, and then as the learning sample of neutral net, establish position learning database.
4. the accurate recognition methods of the customer location according to claim 3 based on neutral net, it is characterised in that the use
The network environment parameters at family include:
1)Main plot and adjacent cell MR.RSRP, it is the leading indicator for reflecting serving cell covering, represents in OMC-R measurement periods
Meet the number of samples that UE Reference Signal Received Power is counted according to by stages of span;
2)Main plot and adjacent cell MR.RSRQ, represent to meet counting down according to by stages for span in OMC-R measurement periods
The number of samples of row Reference Signal Received Quality;
3)MR.TADV, reflection UE arrive the signal propagation time of serving BS, are referring mainly to for reflection UE and serving BS distance
Mark;
4)AOA, reflect the reference azimuth of UE corresponding service cells, reference direction;
5)The physical area identification code of the defined neighboring BS relationship of NcPci, LTE and undefined neighboring BS relationship;
6)The up signal to noise ratio of SinrUL, TD-LTE serving cell, the signal to noise ratio for the upward signal that serving cell receives.
5. the accurate recognition methods of the customer location according to claim 4 based on neutral net, it is characterised in that main plot
And adjacent cell MR.RSRP is defined as on the frequency band for considering measurement, the power of the resource unit of cell own reference signal is carried
Linear average, be reflect serving cell covering leading indicator.
6. the accurate recognition methods of the customer location according to claim 4 based on neutral net, it is characterised in that main plot
And adjacent cell MR.RSRQ is defined as ratio N × RSRP/(E-UTRA carrier RSSI), wherein N represents E-UTRA
The quantity molecule and denominator of resource block RB in carrier RSSI Measurement bandwidths obtains on the same resource block.
7. the accurate recognition methods of the customer location according to claim 6 based on neutral net, it is characterised in that the E-
UTRA Carrier RSSI indicate for E-UTRA carrier received signals field strength, are observed for UE from all resource block sources total
The linear averaging of receiving power, including common signal channel service and non-service cell signal, adjacent-channel interference, thermal noise.
8. according to any described accurate recognition methods of the customer location based on neutral net of claim 4-7, it is characterised in that
Methods described is learnt by the way that the network environment parameters of user and customer position information are put into model, obtains location fingerprint
Storehouse, the user is positioned according to the user's measurement data subsequently obtained.
9. the accurate recognition methods of the customer location according to claim 8 based on neutral net, it is characterised in that the side
The precision of method positioning can adjust according to model grid.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710585736.3A CN107396312A (en) | 2017-07-18 | 2017-07-18 | The accurate recognition methods of customer location based on neutral net |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710585736.3A CN107396312A (en) | 2017-07-18 | 2017-07-18 | The accurate recognition methods of customer location based on neutral net |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107396312A true CN107396312A (en) | 2017-11-24 |
Family
ID=60340117
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710585736.3A Pending CN107396312A (en) | 2017-07-18 | 2017-07-18 | The accurate recognition methods of customer location based on neutral net |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107396312A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107949054A (en) * | 2017-12-29 | 2018-04-20 | 清华大学 | Based on high-precision fingerprint positioning method in deep learning visible ray room |
CN108307427A (en) * | 2018-02-09 | 2018-07-20 | 北京天元创新科技有限公司 | A kind of LTE network covering analyzing, prediction technique and system |
CN108303672A (en) * | 2017-12-26 | 2018-07-20 | 武汉创驰蓝天信息科技有限公司 | WLAN indoor positionings error correcting method based on location fingerprint and system |
CN108513251A (en) * | 2018-02-13 | 2018-09-07 | 北京天元创新科技有限公司 | A kind of localization method and system based on MR data |
CN111836358A (en) * | 2019-12-24 | 2020-10-27 | 北京嘀嘀无限科技发展有限公司 | Positioning method, electronic device, and computer-readable storage medium |
WO2022089031A1 (en) * | 2020-10-27 | 2022-05-05 | 浪潮天元通信信息***有限公司 | Network optimization method based on big data and artificial intelligence |
WO2023184952A1 (en) * | 2022-03-30 | 2023-10-05 | 中兴通讯股份有限公司 | Method and apparatus for distinguishing indoor and outdoor terminals, and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102421188A (en) * | 2011-11-15 | 2012-04-18 | 上海百林通信网络科技有限公司 | Method for rapidly and accurately positioning mobile terminal |
CN103024673A (en) * | 2013-01-14 | 2013-04-03 | 北京中创信测科技股份有限公司 | Terminal positioning method and device for GSM (global system for mobile communication) networks |
CN106535133A (en) * | 2016-11-11 | 2017-03-22 | 天津大学 | Indoor telephone traffic accurate location method based on machine learning in cellular network |
CN106912103A (en) * | 2015-12-23 | 2017-06-30 | ***通信集团上海有限公司 | A kind of method of locating terminal and device |
-
2017
- 2017-07-18 CN CN201710585736.3A patent/CN107396312A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102421188A (en) * | 2011-11-15 | 2012-04-18 | 上海百林通信网络科技有限公司 | Method for rapidly and accurately positioning mobile terminal |
CN103024673A (en) * | 2013-01-14 | 2013-04-03 | 北京中创信测科技股份有限公司 | Terminal positioning method and device for GSM (global system for mobile communication) networks |
CN106912103A (en) * | 2015-12-23 | 2017-06-30 | ***通信集团上海有限公司 | A kind of method of locating terminal and device |
CN106535133A (en) * | 2016-11-11 | 2017-03-22 | 天津大学 | Indoor telephone traffic accurate location method based on machine learning in cellular network |
Non-Patent Citations (1)
Title |
---|
郝会娟: "《中国优秀硕士学位论文全文数据库(电子期刊)》", 15 November 2013 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108303672A (en) * | 2017-12-26 | 2018-07-20 | 武汉创驰蓝天信息科技有限公司 | WLAN indoor positionings error correcting method based on location fingerprint and system |
CN108303672B (en) * | 2017-12-26 | 2021-12-24 | 武汉创驰蓝天信息科技有限公司 | WLAN indoor positioning error correction method and system based on position fingerprint |
CN107949054A (en) * | 2017-12-29 | 2018-04-20 | 清华大学 | Based on high-precision fingerprint positioning method in deep learning visible ray room |
CN108307427A (en) * | 2018-02-09 | 2018-07-20 | 北京天元创新科技有限公司 | A kind of LTE network covering analyzing, prediction technique and system |
CN108513251A (en) * | 2018-02-13 | 2018-09-07 | 北京天元创新科技有限公司 | A kind of localization method and system based on MR data |
CN108513251B (en) * | 2018-02-13 | 2020-08-04 | 北京天元创新科技有限公司 | Positioning method and system based on MR data |
CN111836358A (en) * | 2019-12-24 | 2020-10-27 | 北京嘀嘀无限科技发展有限公司 | Positioning method, electronic device, and computer-readable storage medium |
CN111836358B (en) * | 2019-12-24 | 2021-09-14 | 北京嘀嘀无限科技发展有限公司 | Positioning method, electronic device, and computer-readable storage medium |
WO2022089031A1 (en) * | 2020-10-27 | 2022-05-05 | 浪潮天元通信信息***有限公司 | Network optimization method based on big data and artificial intelligence |
WO2023184952A1 (en) * | 2022-03-30 | 2023-10-05 | 中兴通讯股份有限公司 | Method and apparatus for distinguishing indoor and outdoor terminals, and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107396312A (en) | The accurate recognition methods of customer location based on neutral net | |
CN111277947B (en) | Cell longitude and latitude prediction method, device, server, base station and storage medium | |
CN107807346A (en) | Adaptive WKNN outdoor positionings method based on OTT Yu MR data | |
CN102036254B (en) | Quick automatic neighbor planning method for related networks | |
CN103428726B (en) | Antenna angle optimization method and system | |
Alimpertis et al. | City-wide signal strength maps: Prediction with random forests | |
CN109963287A (en) | Antenna directional angle optimization method, device, equipment and medium | |
CN108307339B (en) | User terminal positioning method, system, electronic equipment and storage medium | |
CN103997783B (en) | A kind of outdoor cluster match localization method and device | |
CN108901029B (en) | Deep learning-based indoor and outdoor user distinguishing method | |
CN109495897B (en) | Regional aggregation method and device for LTE network problems | |
CN110012418A (en) | Recognition methods, device, equipment and the medium of wireless network covering problem | |
CN109548074A (en) | Uplink interference source waveform localization method, device, equipment and medium based on MR | |
CN103458434B (en) | Method and device for determining antenna feeder parameters | |
CN103067927A (en) | Optimization method and device of inter-cell interference | |
CN109526019A (en) | Wireless private network base station range propagation model revision method based on measured data | |
CN113873532B (en) | Intelligent park 5G network planning method | |
CN112867147B (en) | Positioning method and positioning device | |
CN114449649B (en) | Interference source positioning method and device based on MRO data | |
CN114520997A (en) | Method, device, equipment and storage medium for positioning 5G network interference source | |
CN108924732B (en) | High-speed rail user equipment positioning method and device | |
CN109982368B (en) | Method, device, equipment and medium for checking cell azimuth | |
CN109239656A (en) | A kind of radio frequency map method for building up in location fingerprint positioning | |
US20210041525A1 (en) | Similarity Metric Customized to Radio Measurement in Heterogeneous Wireless Networks and Use Thereof | |
CN107682864A (en) | A kind of base station construction method assessed based on coverage rate |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171124 |