CN109429264A - A kind of data processing method, device, equipment and computer readable storage medium - Google Patents
A kind of data processing method, device, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN109429264A CN109429264A CN201710751113.9A CN201710751113A CN109429264A CN 109429264 A CN109429264 A CN 109429264A CN 201710751113 A CN201710751113 A CN 201710751113A CN 109429264 A CN109429264 A CN 109429264A
- Authority
- CN
- China
- Prior art keywords
- sorted
- data
- serving cell
- indoor
- sample
- 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.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/10—Scheduling measurement reports ; Arrangements for measurement reports
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Abstract
The present invention provides a kind of data processing method, device, equipment and computer readable storage medium, is related to field of communication technology, is being covered in indoor region to improve by macro station, distinguishes the accuracy that MR is house data or outdoor data.Data processing method of the invention includes: to obtain measurement report MR to be sorted；The MR to be sorted is pre-processed；Using pretreated MR as input data, it is input in SAE indoor and outdoor data classification model and is run the model, obtains the corresponding indoor and outdoor data classification result of the MR to be sorted.The accuracy for distinguishing that MR is house data or outdoor data can be improved in the present invention.
Description
Technical field
The present invention relates to field of communication technology more particularly to a kind of data processing method, device, equipment and computer-readable
Storage medium.
Background technique
Currently, existing network optimization personnel mainly pass through DT (Drive Test, drive test) CQT (Call Quality Test, it is fixed
Point test) test data for obtaining particular course and region is tested, to be used to assess network quality, but the above method is mainly concentrated
In outdoor test.Discovery for internal home network quality problems often relies on customer complaint and completes to the repetition measurement of complaint.Together
When, it is limited to the accuracy for the time and location description that matter difference occurs during customer complaint, it is desirable to be pin-pointed to network
Problem generally requires a large amount of repetition measurement.
By opening periodic measurement report (measurement report, MR) function, existing network optimization personnel can be obtained
Take a large amount of user's measurement report.The abundant metrical information for including in measurement report can assist carrying out the analysis of network quality.
But since MR data itself only carry cell ID, using ME data can only distinguish main plot where user be macro station also
It is room substation.Therefore, for covering indoor region by macro station, can not be believed by the indoor external position of MR data separation user
Breath.
In view of the above-mentioned problems, covering room by macro station in order to make full use of MR data to carry out more accurate quality analysis
In interior region, needing to solve the problems, such as how to distinguish MR data is house data or outdoor data.It provides in the prior art
It is some to distinguish the method that MR data are house data or outdoor data.But in the implementation of the present invention, inventor
It was found that the existing accuracy for distinguishing the method that MR data are house data or outdoor data is lower.
Summary of the invention
In view of this, the present invention provides a kind of data processing method, device, equipment and computer readable storage medium, with
Raising is being covered in indoor region by macro station, distinguishes the accuracy that MR is house data or outdoor data.
In order to solve the above technical problems, the present invention provides a kind of data processing method, comprising:
Obtain measurement report MR to be sorted；
The MR to be sorted is pre-processed；
Using pretreated MR as input data, being input to SAE, (Stacked Auto Encoder, stack are compiled automatically
Code device) in indoor and outdoor data classification model and the model is run, obtain the corresponding indoor and outdoor data classification of the MR to be sorted
As a result.
It is wherein, described that the MR to be sorted is pre-processed, comprising:
It to the MR association work ginseng information to be sorted and screens, obtaining main plot is macro station and main serving cell
RSRP (Reference Signal Receiving Power, Reference Signal Received Power) is not empty target MR；
It is identified according to the timestamp information of the target MR, main serving cell, the same main service of a plurality of synchronization is small
The metrical information in area merges into the measurement record comprising all neighbor measurement informations；
The topological structure for all cells for including in the measurement record is described；
Using the topological structure, the RSRP of main serving cell, adjacent cell RSRP be normalized and uniform data tie up
Number processing.
Wherein, before the acquisition MR to be sorted, the method also includes:
Obtain sample MR；
The sample MR is pre-processed；
Utilize pretreated sample MR training SAE indoor and outdoor data classification model.
Wherein, it is described to the sample MR carry out pretreatment include:
The sample MR is screened, obtains received signal power RSRP that main plot is macro station and main serving cell not
For empty target sample MR；
It is identified according to the timestamp information of the target sample MR, main serving cell, by the same main clothes of a plurality of synchronization
The metrical information for cell of being engaged in merges into the measurement record comprising all neighbor measurement informations；
The topological structure for all cells for including in the measurement record is described；
Using the topological structure, the RSRP of main serving cell, adjacent cell RSRP be normalized and uniform data tie up
Number processing.
Second aspect, the embodiment of the present invention provide a kind of data processing equipment, comprising:
Module is obtained, for obtaining measurement report MR to be sorted；
Preprocessing module, for being pre-processed to the MR to be sorted；
Categorization module, for being input to stack autocoder SAE indoor and outdoor using pretreated MR as input data
In data classification model and the model is run, obtains the corresponding indoor and outdoor data classification result of the MR to be sorted.
The third aspect, the embodiment of the present invention provide a kind of electronic equipment, including memory, processor and are stored in described deposit
On reservoir and the computer program that can run on the processor；The processor realizes such as first party when executing described program
Step in the method for face.
Fourth aspect, the embodiment of the present invention provide a kind of computer readable storage medium, for storing computer program, institute
The step realized in method as described in relation to the first aspect can be executed by processor by stating computer program.
The advantageous effects of the above technical solutions of the present invention are as follows:
In embodiments of the present invention, MR to be sorted is pre-processed, and using pretreated MR as input data,
It is input in stack autocoder SAE indoor and outdoor data classification model and is run the model, obtains described MR pairs to be sorted
The indoor and outdoor data classification result answered.Therefore, feature is extracted without artificial using the scheme of the embodiment of the present invention, can excavated more
Potential feature, improve and covered in indoor region by macro station, distinguishing MR is the accurate of house data or outdoor data
Property.
Detailed description of the invention
Fig. 1 is the flow chart of the data processing method of the embodiment of the present invention；
Fig. 2 is the flow chart of the data processing method of the embodiment of the present invention；
Fig. 3 is the schematic diagram of the data processing equipment of the embodiment of the present invention；
Fig. 4 is the structure chart of the data processing equipment of the embodiment of the present invention；
Fig. 5 is the schematic diagram of the electronic equipment of the embodiment of the present invention.
Specific embodiment
Below in conjunction with drawings and examples, specific embodiments of the present invention will be described in further detail.Following reality
Example is applied for illustrating the present invention, but is not intended to limit the scope of the invention.
As shown in Figure 1, the data processing method of the embodiment of the present invention, comprising:
Step 101 obtains MR to be sorted.
Wherein, the MR to be sorted can be the MR obtained when executing the embodiment of the present invention, be also possible to obtain in advance
MR data.
Step 102 pre-processes the MR to be sorted.
In embodiments of the present invention, information is joined to the MR association work to be sorted first and screened, obtain main plot
Received signal power RSRP for macro station and main serving cell is not empty target MR.Wherein, the work ginseng information includes base station
Title, cell name, the information such as longitude and latitude.Then, it is identified according to the timestamp information of the target MR, main serving cell, it will
The metrical information of a plurality of same main serving cell of synchronization merges into the measurement record comprising all neighbor measurement informations.So
Afterwards, the topological structure for all cells for including in the measurement record is described.Finally, small using the topological structure, main service
The RSRP in area, the RSRP of adjacent cell are normalized and the processing of uniform data dimension.
Due to receiving the difference of signal, the cell topology that indoor MR and outdoor MR are embodied is different.?
In the embodiment of the present invention, a kind of feasible topological structure describes method and is, the warp of the main plot and all adjacent areas that are recorded with every
Point centered on the average value position of latitude, the latitude and longitude of base station for calculating main serving cell and each adjacent area are inclined with respect to central point
It moves.
When being normalized and uniform data dimension handles, main serving cell and adjacent area RSRP, above-mentioned offset are carried out
Normalization, such as using min-max standardization, Z-score standardized method.Then, frequency point information is subjected to binary discretization.
For example, the frequency point information after binary discretization will extend if the frequency point of main serving cell and adjacent area includes F1, F2, D1, D2
For 4 column, whether whether whether respectively " F1 ", " F2 ", " D1 ", " D2 ", 0 indicates no, 1 indicate be.Meanwhile being arranged maximum
Adjacent area number carries out the insufficient record of adjacent area number to mend 0 operation.
Step 103, using pretreated MR as input data, be input in SAE indoor and outdoor data classification model and transport
The row model obtains the corresponding indoor and outdoor data classification result of the MR to be sorted.
In embodiments of the present invention, MR to be sorted is pre-processed, and using pretreated MR as input data,
It is input in stack autocoder SAE indoor and outdoor data classification model and is run the model, obtains described MR pairs to be sorted
The indoor and outdoor data classification result answered.Therefore, feature is extracted without artificial using the scheme of the embodiment of the present invention, can excavated more
Potential feature, improve and covered in indoor region by macro station, distinguishing MR is the accurate of house data or outdoor data
Property.
As shown in Fig. 2, the data processing method of the embodiment of the present invention, comprising:
Step 201 obtains sample MR.
Wherein, the sample MR may include drive test data, (Minimization of Drive Test minimizes road to MDT
Survey) measurement data comprising latitude and longitude information, main plot and neighbor received signal etc. such as data.It need to remember simultaneously in data acquisition
Record the indoor and outdoor mark of sample MR data.
Step 202 pre-processes the sample MR.
Here, screening to the sample MR, the received signal power that main plot is macro station and main serving cell is obtained
RSRP is not empty target sample MR, is then identified according to the timestamp information of the target sample MR, main serving cell, will be more
The metrical information of the same main serving cell of synchronization merges into the measurement record comprising all neighbor measurement informations, then
The topological structure for all cells for including in the measurement record is described, and utilizes the topological structure, main serving cell
RSRP, adjacent cell RSRP be normalized and uniform data dimension processing.
Due to receiving the difference of signal, the cell topology that indoor MR and outdoor MR are embodied is different.?
In the embodiment of the present invention, a kind of feasible topological structure describes method and is, the warp of the main plot and all adjacent areas that are recorded with every
Point centered on the average value position of latitude, the latitude and longitude of base station for calculating main serving cell and each adjacent area are inclined with respect to central point
It moves.
When being normalized and uniform data dimension handles, main serving cell and adjacent area RSRP, above-mentioned offset are carried out
Normalization, such as using min-max standardization, Z-score standardized method.Then, frequency point information is subjected to binary discretization.
For example, the frequency point information after binary discretization will extend if the frequency point of main serving cell and adjacent area includes F1, F2, D1, D2
For 4 column, whether whether whether respectively " F1 ", " F2 ", " D1 ", " D2 ", 0 indicates no, 1 indicate be.Meanwhile being arranged maximum
Adjacent area number carries out the insufficient record of adjacent area number to mend 0 operation.
Step 203 utilizes pretreated sample MR training SAE indoor and outdoor data classification model.
By treated, pretreated sample MR is sent into mentioning automatically for stack autocoder (SAE model) progress feature
It takes and trains, and adjust the model number of plies of SAE, each layer of neuron number, loss function, every layer of pre-training number, whole mould
The parameters such as type frequency of training obtain indoor and outdoor disaggregated model.
Step 204 obtains MR to be sorted.
Wherein, the MR to be sorted can be the MR obtained when executing the embodiment of the present invention.
Step 205 pre-processes the MR to be sorted.
In embodiments of the present invention, information is joined to the MR association work to be sorted first and screened, obtain main plot
Received signal power RSRP for macro station and main serving cell is not empty target MR.Wherein, the work ginseng information includes base station
Title, cell name, the information such as longitude and latitude.Then, it is identified according to the timestamp information of the target MR, main serving cell, it will
The metrical information of a plurality of same main serving cell of synchronization merges into the measurement record comprising all neighbor measurement informations.So
Afterwards, the topological structure for all cells for including in the measurement record is described.Finally, small using the topological structure, main service
The RSRP in area, the RSRP of adjacent cell are normalized and the processing of uniform data dimension.
Difference of the indoor and outdoor measurement report due to receiving signal, the cell that indoor MR and outdoor MR are embodied is opened up
It is different to flutter structure.In embodiments of the present invention, it is that the master recorded with every is small that a kind of feasible topological structure, which describes method,
Point centered on the average value position of the longitude and latitude in area and all adjacent areas calculates the base station longitude and latitude of main serving cell and each adjacent area
Spend the offset relative to central point.
When being normalized and uniform data dimension handles, main serving cell and adjacent area RSRP, above-mentioned offset are carried out
Normalization, such as using min-max standardization, Z-score standardized method.Then, frequency point information is subjected to binary discretization.
For example, the frequency point information after binary discretization will extend if the frequency point of main serving cell and adjacent area includes F1, F2, D1, D2
For 4 column, whether whether whether respectively " F1 ", " F2 ", " D1 ", " D2 ", 0 indicates no, 1 indicate be.Meanwhile being arranged maximum
Adjacent area number carries out the insufficient record of adjacent area number to mend 0 operation.
Step 206, using pretreated MR as input data, be input in SAE indoor and outdoor data classification model and transport
The row model obtains the corresponding indoor and outdoor data classification result of the MR to be sorted.
In embodiments of the present invention, MR to be sorted is pre-processed, and using pretreated MR as input data,
It is input in stack autocoder SAE indoor and outdoor data classification model and is run the model, obtains described MR pairs to be sorted
The indoor and outdoor data classification result answered.Therefore, it using the scheme of the embodiment of the present invention, avoids artificial lay down a regulation and carries out interior
The inaccurate problem of outer differentiation, without the location information of MR data；It can use SAE model simultaneously and carry out mentioning automatically for feature
It takes, is not necessarily to artificial design features extracting method, the accuracy of MR indoor and outdoor classification can be improved, help to carry out using MR data
More accurate Network Quality Analysis.For the indoor and outdoor test zone of the same area, application is based on SVM (Support respectively
Vector Machine, support vector machines) machine learning algorithm and the machine learning algorithm based on SAE of this programme carry out room
Inside and outside identification prediction, through testing, precision of prediction improves 10-20 percentage points.
Meanwhile the obtained outer classification results of MR data room, it can further input in the positioning application of MR data, promote MR
The positioning accuracy of data.
As shown in figure 3, the data processing equipment of the embodiment of the present invention, comprising:
First obtains module 301, for obtaining measurement report MR to be sorted；
First preprocessing module 302, for being pre-processed to the MR to be sorted；
Categorization module 303, for being input to the room stack autocoder SAE using pretreated MR as input data
In inside and outside data classification model and the model is run, obtains the corresponding indoor and outdoor data classification result of the MR to be sorted.
Wherein, first preprocessing module 302 includes:
Submodule is screened, for joining information to the MR association work to be sorted and screening, acquisition main plot is macro station
And the received signal power RSRP of main serving cell is not empty target MR；Merge submodule, for according to the target MR's
Timestamp information, main serving cell mark, the metrical information of the same main serving cell of a plurality of synchronization is merged into comprising institute
There is the measurement of neighbor measurement information to record；Topological structure describes submodule, all for describe to include in the measurement record
The topological structure of cell；Data processing submodule, for utilizing the topological structure, the RSRP of main serving cell, adjacent cell
RSRP is normalized and the processing of uniform data dimension.
As shown in figure 4, the data processing equipment of the embodiment of the present invention, may also include that
Second obtains module 304, for obtaining sample MR；
Second preprocessing module 305, for being pre-processed to the sample MR；
Training module 306, for utilizing pretreated sample MR training SAE indoor and outdoor data classification model.
Wherein, second module 304 is obtained can include:
Submodule is screened, for screening to the sample MR, obtaining main plot is connecing for macro station and main serving cell
Receiving signal power RSRP is not empty target sample MR；Merge submodule, for believing according to the timestamp of the target sample MR
The metrical information of the same main serving cell of a plurality of synchronization is merged into and is surveyed comprising all adjacent areas by breath, main serving cell mark
Measure the measurement record of information；Turbo codes submodule, the topology knot of all cells for describing to include in the measurement record
Structure；Data processing submodule, the RSRP for RSRP, adjacent cell using the topological structure, main serving cell carry out normalizing
Change and uniform data dimension is handled.
The working principle of device of the present invention can refer to the description of preceding method embodiment.
In embodiments of the present invention, MR to be sorted is pre-processed, and using pretreated MR as input data,
It is input in stack autocoder SAE indoor and outdoor data classification model and is run the model, obtains described MR pairs to be sorted
The indoor and outdoor data classification result answered.Therefore, feature is extracted without artificial using the scheme of the embodiment of the present invention, can excavated more
Potential feature, improve and covered in indoor region by macro station, distinguishing MR is the accurate of house data or outdoor data
Property.
As shown in figure 5, the electronic equipment of the embodiment of the present invention, comprising: processor 500, for reading in memory 520
Program executes following process:
Obtain measurement report MR to be sorted；The MR to be sorted is pre-processed；Using pretreated MR as input
Data are input in stack autocoder SAE indoor and outdoor data classification model and run the model, obtain described to be sorted
The corresponding indoor and outdoor data classification result of MR；
Transceiver 510, for sending and receiving data under control of the processor 500.
Wherein, in Fig. 5, bus architecture may include the bus and bridge of any number of interconnection, specifically by processor 500
The various circuits for the memory that the one or more processors and memory 520 of representative represent link together.Bus architecture is also
Various other circuits of such as peripheral equipment, voltage-stablizer and management circuit or the like can be linked together, these are all
It is it is known in the art, therefore, it will not be further described herein.Bus interface provides interface.Transceiver 510 can
To be multiple element, that is, includes transmitter and transceiver, the list for communicating over a transmission medium with various other devices is provided
Member.Processor 500, which is responsible for management bus architecture and common processing, memory 520, can store processor 500 and is executing operation
When used data.
Processor 500, which is responsible for management bus architecture and common processing, memory 520, can store processor 500 and is holding
Used data when row operation.
Processor 500 is also used to read the computer program, executes following steps:
It to the MR to be sorted association work ginseng information and screens, obtaining main plot is connecing for macro station and main serving cell
Receiving signal power RSRP is not empty target MR；
It is identified according to the timestamp information of the target MR, main serving cell, the same main service of a plurality of synchronization is small
The metrical information in area merges into the measurement record comprising all neighbor measurement informations；
The topological structure for all cells for including in the measurement record is described；
Using the topological structure, the RSRP of main serving cell, adjacent cell RSRP be normalized and uniform data tie up
Number processing.
Processor 500 is also used to read the computer program, executes following steps:
Obtain sample MR；
The sample MR is pre-processed；
Utilize pretreated sample MR training SAE indoor and outdoor data classification model.
Processor 500 is also used to read the computer program, executes following steps:
The sample MR is screened, obtains received signal power RSRP that main plot is macro station and main serving cell not
For empty target sample MR；
It is identified according to the timestamp information of the target sample MR, main serving cell, by the same main clothes of a plurality of synchronization
The metrical information for cell of being engaged in merges into the measurement record comprising all neighbor measurement informations；
The topological structure for all cells for including in the measurement record is described；
Using the topological structure, the RSRP of main serving cell, adjacent cell RSRP be normalized and uniform data tie up
Number processing.
In addition, the computer readable storage medium of the embodiment of the present invention, for storing computer program, the computer journey
Sequence can be executed by processor and perform the steps of
Obtain measurement report MR to be sorted；
The MR to be sorted is pre-processed；
Using pretreated MR as input data, it is input to stack autocoder SAE indoor and outdoor data classification model
In and run the model, obtain the corresponding indoor and outdoor data classification result of the MR to be sorted.
It is wherein, described that the MR to be sorted is pre-processed, comprising:
It to the MR to be sorted association work ginseng information and screens, obtaining main plot is connecing for macro station and main serving cell
Receiving signal power RSRP is not empty target MR；
It is identified according to the timestamp information of the target MR, main serving cell, the same main service of a plurality of synchronization is small
The metrical information in area merges into the measurement record comprising all neighbor measurement informations；
The topological structure for all cells for including in the measurement record is described；
Using the topological structure, the RSRP of main serving cell, adjacent cell RSRP be normalized and uniform data tie up
Number processing.
Wherein, before the acquisition MR to be sorted, further includes:
Obtain sample MR；
The sample MR is pre-processed；
Utilize pretreated sample MR training SAE indoor and outdoor data classification model.
Wherein, it is described to the sample MR carry out pretreatment include:
The sample MR is screened, obtains received signal power RSRP that main plot is macro station and main serving cell not
For empty target sample MR；
It is identified according to the timestamp information of the target sample MR, main serving cell, by the same main clothes of a plurality of synchronization
The metrical information for cell of being engaged in merges into the measurement record comprising all neighbor measurement informations；
The topological structure for all cells for including in the measurement record is described；
Using the topological structure, the RSRP of main serving cell, adjacent cell RSRP be normalized and uniform data tie up
Number processing.
In several embodiments provided herein, it should be understood that disclosed method and apparatus, it can be by other
Mode realize.For example, the apparatus embodiments described above are merely exemplary, for example, the division of the unit, only
For a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components can combine
Or it is desirably integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed phase
Coupling, direct-coupling or communication connection between mutually can be through some interfaces, the INDIRECT COUPLING or communication of device or unit
Connection can be electrical property, mechanical or other forms.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that the independent physics of each unit includes, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of hardware adds SFU software functional unit.
The above-mentioned integrated unit being realized in the form of SFU software functional unit can store and computer-readable deposit at one
In storage media.Above-mentioned SFU software functional unit is stored in a storage medium, including some instructions are used so that a computer
Equipment (can be personal computer, server or the network equipment etc.) executes receiving/transmission method described in each embodiment of the present invention
Part steps.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (Read-Only Memory, abbreviation
ROM), random access memory (Random Access Memory, abbreviation RAM), magnetic or disk etc. are various can store
The medium of program code.
The above is a preferred embodiment of the present invention, it is noted that for those skilled in the art
For, without departing from the principles of the present invention, it can also make several improvements and retouch, these improvements and modifications
It should be regarded as protection scope of the present invention.
Claims (7)
1. a kind of data processing method characterized by comprising
Obtain measurement report MR to be sorted；
The MR to be sorted is pre-processed；
Using pretreated MR as input data, it is input in stack autocoder SAE indoor and outdoor data classification model simultaneously
The model is run, the corresponding indoor and outdoor data classification result of the MR to be sorted is obtained.
2. the method according to claim 1, wherein described pre-process the MR to be sorted, comprising:
It to the MR association work ginseng information to be sorted and screens, obtains the reception letter that main plot is macro station and main serving cell
Number power RSRP is not empty target MR；
It is identified according to the timestamp information of the target MR, main serving cell, by the same main serving cell of a plurality of synchronization
Metrical information merges into the measurement record comprising all neighbor measurement informations；
The topological structure for all cells for including in the measurement record is described；
Using the topological structure, the RSRP of main serving cell, adjacent cell RSRP be normalized and uniform data dimension at
Reason.
3. the method according to claim 1, wherein it is described obtain MR to be sorted before, the method also includes:
Obtain sample MR；
The sample MR is pre-processed；
Utilize pretreated sample MR training SAE indoor and outdoor data classification model.
4. according to the method described in claim 3, it is characterized in that, it is described to the sample MR carry out pretreatment include:
The sample MR is screened, it is not empty for obtaining the received signal power RSRP that main plot is macro station and main serving cell
Target sample MR；
It is identified according to the timestamp information of the target sample MR, main serving cell, the same main service of a plurality of synchronization is small
The metrical information in area merges into the measurement record comprising all neighbor measurement informations；
The topological structure for all cells for including in the measurement record is described；
Using the topological structure, the RSRP of main serving cell, adjacent cell RSRP be normalized and uniform data dimension at
Reason.
5. a kind of data processing equipment characterized by comprising
Module is obtained, for obtaining measurement report MR to be sorted；
Preprocessing module, for being pre-processed to the MR to be sorted；
Categorization module, for being input to stack autocoder SAE indoor and outdoor data using pretreated MR as input data
In disaggregated model and the model is run, obtains the corresponding indoor and outdoor data classification result of the MR to be sorted.
6. a kind of electronic equipment, including memory, processor and it is stored on the memory and can transports on the processor
Capable computer program；It is characterized in that, the processor is realized when executing described program such as any one of claim 1-5 institute
State the step in method.
7. a kind of computer readable storage medium, for storing computer program, which is characterized in that the computer program can quilt
Processor executes the step realized as in any one of claim 1-5 the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710751113.9A CN109429264B (en) | 2017-08-28 | 2017-08-28 | Data processing method, device, equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710751113.9A CN109429264B (en) | 2017-08-28 | 2017-08-28 | Data processing method, device, equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109429264A true CN109429264A (en) | 2019-03-05 |
| CN109429264B CN109429264B (en) | 2022-04-29 |
Family
ID=65502591
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710751113.9A Active CN109429264B (en) | 2017-08-28 | 2017-08-28 | Data processing method, device, equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109429264B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110881191A (en) * | 2019-11-20 | 2020-03-13 | 中国联合网络通信集团有限公司 | Method, device and system for acquiring longitude and latitude of cell and storage medium |
| WO2021103577A1 (en) * | 2019-11-27 | 2021-06-03 | 北京天元创新科技有限公司 | Mdt-based indoor signal leakage analysis method and system |
| CN112954708A (en) * | 2021-03-22 | 2021-06-11 | 中电积至(海南)信息技术有限公司 | Positioning method and device based on measurement report |
| CN113194426A (en) * | 2020-01-14 | 2021-07-30 | 中移动信息技术有限公司 | Fingerprint library updating method, device, equipment and computer storage medium |
| WO2022164363A1 (en) * | 2021-02-01 | 2022-08-04 | Telefonaktiebolaget Lm Ericsson (Publ) | Classification of indoor-to-outdoor traffic and user equipment distribution |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102595480A (en) * | 2012-01-19 | 2012-07-18 | 大唐移动通信设备有限公司 | Position information determining method and device |
| CN106211194A (en) * | 2016-07-28 | 2016-12-07 | 武汉虹信技术服务有限责任公司 | The outer separation method of a kind of MR data room based on statistical model |
-
2017
- 2017-08-28 CN CN201710751113.9A patent/CN109429264B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102595480A (en) * | 2012-01-19 | 2012-07-18 | 大唐移动通信设备有限公司 | Position information determining method and device |
| CN106211194A (en) * | 2016-07-28 | 2016-12-07 | 武汉虹信技术服务有限责任公司 | The outer separation method of a kind of MR data room based on statistical model |
Non-Patent Citations (2)
| Title |
|---|
| 徐承亮等: "基于KNN算法的MRR数据分类研究", 《移动通信》 * |
| 陈芊希等: "基于深度学习的网页分类算法研究", 《微型电脑应用》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110881191A (en) * | 2019-11-20 | 2020-03-13 | 中国联合网络通信集团有限公司 | Method, device and system for acquiring longitude and latitude of cell and storage medium |
| CN110881191B (en) * | 2019-11-20 | 2022-08-05 | 中国联合网络通信集团有限公司 | Method, device and system for acquiring longitude and latitude of cell and storage medium |
| WO2021103577A1 (en) * | 2019-11-27 | 2021-06-03 | 北京天元创新科技有限公司 | Mdt-based indoor signal leakage analysis method and system |
| CN113194426A (en) * | 2020-01-14 | 2021-07-30 | 中移动信息技术有限公司 | Fingerprint library updating method, device, equipment and computer storage medium |
| CN113194426B (en) * | 2020-01-14 | 2022-09-06 | 中移动信息技术有限公司 | Fingerprint database updating method, device, equipment and computer storage medium |
| WO2022164363A1 (en) * | 2021-02-01 | 2022-08-04 | Telefonaktiebolaget Lm Ericsson (Publ) | Classification of indoor-to-outdoor traffic and user equipment distribution |
| CN112954708A (en) * | 2021-03-22 | 2021-06-11 | 中电积至(海南)信息技术有限公司 | Positioning method and device based on measurement report |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109429264B (en) | 2022-04-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109429264A (en) | A kind of data processing method, device, equipment and computer readable storage medium | |
| CN109253888A (en) | Detection method and system for vehicle vehicle condition | |
| CN109996168A (en) | A kind of method and device obtaining terminal location | |
| CN108320278A (en) | Product defects detect localization method, device, equipment and computer-readable medium | |
| JP2016519288A (en) | Scalable real-time position detection based on overlapping neural networks | |
| CN105372581A (en) | Flexible circuit board manufacturing process automatic monitoring and intelligent analysis system and method | |
| CN105101408A (en) | Indoor positioning method based on distributed AP selection strategy | |
| US11762396B2 (en) | Positioning system and positioning method based on WI-FI fingerprints | |
| CN103068035A (en) | Wireless network location method, device and system | |
| CN112543470B (en) | Terminal positioning method and system based on machine learning | |
| CN104461751A (en) | AUTOMATED EVALUATION OF TEST LOGS IN telecom field | |
| CN105787364A (en) | Automated testing method, device and system for task | |
| CN109145828A (en) | Method and apparatus for generating video classification detection model | |
| US20210282033A1 (en) | Positioning system for integrating machine learning positioning models and positioning method for the same | |
| CN112860676B (en) | Data cleaning method applied to big data mining and business analysis and cloud server | |
| CN110392122A (en) | The determination method and apparatus of address style, storage medium, electronic device | |
| CN109991591A (en) | Localization method, device, computer equipment and storage medium based on deep learning | |
| CN112687022A (en) | Intelligent building inspection method and system based on video | |
| CN108956173A (en) | A kind of method and device of motor-car bolt and component detection based on mechanical arm | |
| CN110139315B (en) | Wireless network fault detection method based on self-learning | |
| CN109446327A (en) | A kind of diagnostic method and system of client mobile communication complaint | |
| CN107316133A (en) | Based on Internet of Things partial discharge electrification detection data platform and GPS emerging systems | |
| CN111786476A (en) | Method for predicting position of receiving coil of wireless power transmission system | |
| Fritz et al. | Read-Error-Rate evaluation for RFID system on-line testing | |
| CN111741526B (en) | Positioning method, positioning device, electronic equipment and computer storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |