CN109429264B - Data processing method, device, equipment and computer readable storage medium - Google Patents
Data processing method, device, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN109429264B CN109429264B CN201710751113.9A CN201710751113A CN109429264B CN 109429264 B CN109429264 B CN 109429264B CN 201710751113 A CN201710751113 A CN 201710751113A CN 109429264 B CN109429264 B CN 109429264B
- Authority
- CN
- China
- Prior art keywords
- indoor
- sample
- cell
- main service
- rsrp
- 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.)
- Active
Links
Images
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 invention provides a data processing method, a data processing device, data processing equipment and a computer readable storage medium, relates to the technical field of communication, and aims to improve the accuracy of distinguishing whether MR is indoor data or outdoor data in an area covered by a macro station. The data processing method of the invention comprises the following steps: acquiring a measurement report MR to be classified; preprocessing the MR to be classified; and inputting the preprocessed MR as input data into an SAE indoor and outdoor data classification model and operating the model to obtain an indoor and outdoor data classification result corresponding to the MR to be classified. The invention can improve the accuracy of distinguishing whether the MR is indoor data or outdoor data.
Description
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a data processing method, an apparatus, a device, and a computer-readable storage medium.
Background
Currently, network optimization personnel mainly obtain Test data of specific routes and areas through a DT (Drive Test) \ CQT (Call Quality Test) Test for evaluating network Quality, but the above method mainly focuses on outdoor tests. The discovery of the indoor network quality problem is often completed by depending on the complaint of the user and the retest of the complaint. Meanwhile, due to the accuracy of description of time and place of occurrence of quality difference in the complaint process of the user, a large amount of retesting is often required for accurately positioning to a network problem.
By starting a periodic Measurement Report (MR) function, a current network optimizer can acquire a large number of user measurement reports. The rich measurement information contained in the measurement report may assist in the analysis of the network quality. However, since the MR data itself only carries the cell identifier, it is only possible to distinguish whether the main cell in which the user is located is a macro station or a cell substation using the ME data. Therefore, for an area indoors covered by the macro station, indoor and outdoor position information of the user cannot be distinguished by the MR data.
In view of the above problems, in order to make full use of MR data for more accurate quality analysis, in an area covered indoors by a macro station, a problem of how to distinguish whether MR data is indoor data or outdoor data needs to be solved. Methods are provided in the prior art to distinguish whether MR data is indoor data or outdoor data. However, in implementing the present invention, the inventors found that the existing method of distinguishing whether MR data is indoor data or outdoor data is less accurate.
Disclosure of Invention
In view of the above, the present invention provides a data processing method, apparatus, device and computer-readable storage medium to improve the accuracy of distinguishing whether an MR is indoor data or outdoor data in an area covered by a macro station.
To solve the above technical problem, the present invention provides a data processing method, including:
acquiring a measurement report MR to be classified;
preprocessing the MR to be classified;
and inputting the preprocessed MR as input data into an SAE (Stacked Auto Encoder) indoor and outdoor data classification model and operating the model to obtain an indoor and outdoor data classification result corresponding to the MR to be classified.
Wherein the preprocessing the MR to be classified comprises:
screening the work parameter information related to the MR to be classified to obtain a target MR of which a main cell is a macro station and the Reference Signal Receiving Power (Reference Signal Receiving Power) of the main service cell is not empty;
combining a plurality of pieces of measurement information of the same main service cell at the same time into a measurement record containing all the measurement information of the adjacent cells according to the timestamp information of the target MR and the identification of the main service cell;
describing the topology of all cells contained in the measurement record;
and carrying out normalization and unified data dimension processing by utilizing the topological structure, the RSRP of the main service cell and the RSRP of the adjacent cell.
Wherein, prior to the acquiring the MR to be classified, the method further comprises:
acquiring a sample MR;
preprocessing the sample MR;
and training an SAE indoor and outdoor data classification model by using the preprocessed sample MR.
Wherein the preprocessing the sample MR comprises:
screening the sample MR to obtain a target sample MR of which the main cell is a macro station and the received signal power RSRP of the main service cell is not empty;
combining a plurality of pieces of measurement information of the same main service cell at the same time into a measurement record containing all the measurement information of the adjacent cells according to the timestamp information and the main service cell identification of the target sample MR;
describing the topology of all cells contained in the measurement record;
and carrying out normalization and unified data dimension processing by utilizing the topological structure, the RSRP of the main service cell and the RSRP of the adjacent cell.
In a second aspect, an embodiment of the present invention provides a data processing apparatus, including:
the acquisition module is used for acquiring a measurement report MR to be classified;
the preprocessing module is used for preprocessing the MR to be classified;
and the classification module is used for inputting the preprocessed MR as input data into an SAE (sample analysis and analysis) indoor and outdoor data classification model of the stacked automatic encoder and operating the model to obtain an indoor and outdoor data classification result corresponding to the MR to be classified.
In a third aspect, an embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor; the processor, when executing the program, performs the steps of the method according to the first aspect.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium for storing a computer program, where the computer program is executable by a processor to implement the steps in the method according to the first aspect.
The technical scheme of the invention has the following beneficial effects:
in the embodiment of the invention, the MR to be classified is preprocessed, the preprocessed MR is used as input data, the input data is input into an SAE (sample analysis and analysis) indoor and outdoor data classification model of the stacked automatic encoder, and the model is operated to obtain an indoor and outdoor data classification result corresponding to the MR to be classified. Therefore, by using the scheme of the embodiment of the invention, the characteristics do not need to be manually extracted, more potential characteristics can be mined, and the accuracy of distinguishing whether the MR is indoor data or outdoor data in the area covered by the macro station is improved.
Drawings
FIG. 1 is a flow chart of a data processing method according to an embodiment of the present invention;
FIG. 2 is a flow chart of a data processing method according to an embodiment of the present invention;
FIG. 3 is a diagram of a data processing apparatus according to an embodiment of the present invention;
FIG. 4 is a block diagram of a data processing apparatus according to an embodiment of the present invention;
fig. 5 is a schematic diagram of an electronic device according to an embodiment of the invention.
Detailed Description
The following detailed description of embodiments of the present invention will be made with reference to the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
As shown in fig. 1, the data processing method according to the embodiment of the present invention includes:
The MR to be classified may be an MR obtained when the embodiment of the present invention is performed, or may be MR data obtained in advance.
And step 102, preprocessing the MR to be classified.
In the embodiment of the invention, the work parameter information related to the MR to be classified is firstly screened to obtain the target MR of which the main cell is the macro station and the received signal power RSRP of the main service cell is not empty. The working parameter information comprises information such as a base station name, a cell name, longitude and latitude and the like. And then, combining a plurality of pieces of measurement information of the same main service cell at the same time into a measurement record containing all the measurement information of the adjacent cells according to the timestamp information of the target MR and the identification of the main service cell. Then, the topology of all cells contained in the measurement record is described. And finally, carrying out normalization and unified data dimension processing by utilizing the topological structure, the RSRP of the main service cell and the RSRP of the adjacent cell.
Due to the difference in the received signals, the indoor MR and the outdoor MR exhibit different cell topologies. In the embodiment of the invention, a feasible topological structure description method is that the average value position of the longitude and latitude of each recorded main cell and all adjacent cells is used as a central point, and the offset of the longitude and latitude of the base station of the main service cell and each adjacent cell relative to the central point is calculated.
During normalization and unified data dimension processing, the RSRP of the main serving cell and the neighboring cell, and the offset are normalized, for example, by adopting a min-max normalization method, a Z-score normalization method, and the like. Then, the frequency point information is subjected to binary discretization. For example, if the frequency points of the main serving cell and the neighboring cell include F1, F2, D1, and D2, the binary discretized frequency point information is expanded into 4 columns, which are respectively "whether F1", "whether F2", "whether D1", "whether D2", 0 indicates no, and 1 indicates yes. Meanwhile, the maximum number of the adjacent cells is set, and the record with insufficient number of the adjacent cells is subjected to 0 complementing operation.
And 103, inputting the preprocessed MR as input data into an SAE indoor and outdoor data classification model and operating the model to obtain an indoor and outdoor data classification result corresponding to the MR to be classified.
In the embodiment of the invention, the MR to be classified is preprocessed, the preprocessed MR is used as input data, the input data is input into an SAE (sample analysis and analysis) indoor and outdoor data classification model of the stacked automatic encoder, and the model is operated to obtain an indoor and outdoor data classification result corresponding to the MR to be classified. Therefore, by using the scheme of the embodiment of the invention, the characteristics do not need to be manually extracted, more potential characteristics can be mined, and the accuracy of distinguishing whether the MR is indoor data or outdoor data in the area covered by the macro station is improved.
As shown in fig. 2, the data processing method according to the embodiment of the present invention includes:
The sample MR may include measurement data such as Drive Test data, MDT (Minimization of Drive Test) data, and the like, including longitude and latitude information, primary cell and neighbor cell received signals, and the like. The indoor and outdoor identification of the sample MR data is recorded at the same time when the data is acquired.
The sample MR is screened to obtain a target sample MR of which a main cell is a macro station and the received signal power RSRP of the main serving cell is not empty, then, according to timestamp information and a main serving cell identifier of the target sample MR, a plurality of pieces of measurement information of the same main serving cell at the same time are combined into a measurement record containing all neighbor measurement information, then, the topological structures of all cells contained in the measurement record are described, and normalization and unified data dimension processing are performed by utilizing the topological structures, the RSRP of the main serving cell and the RSRP of the neighbor cells.
Due to the difference in the received signals, the indoor MR and the outdoor MR exhibit different cell topologies. In the embodiment of the invention, a feasible topological structure description method is that the average value position of the longitude and latitude of each recorded main cell and all adjacent cells is used as a central point, and the offset of the longitude and latitude of the base station of the main service cell and each adjacent cell relative to the central point is calculated.
During normalization and unified data dimension processing, the RSRP of the main serving cell and the neighboring cell, and the offset are normalized, for example, by adopting a min-max normalization method, a Z-score normalization method, and the like. Then, the frequency point information is subjected to binary discretization. For example, if the frequency points of the main serving cell and the neighboring cell include F1, F2, D1, and D2, the binary discretized frequency point information is expanded into 4 columns, which are respectively "whether F1", "whether F2", "whether D1", "whether D2", 0 indicates no, and 1 indicates yes. Meanwhile, the maximum number of the adjacent cells is set, and the record with insufficient number of the adjacent cells is subjected to 0 complementing operation.
And step 203, training an SAE indoor and outdoor data classification model by using the preprocessed sample MR.
And sending the processed and preprocessed sample MR into a stacked automatic encoder (SAE model) for automatic feature extraction and training, and adjusting parameters such as the number of model layers, the number of neurons in each layer, a loss function, the number of pre-training times of each layer, the number of training times of an integral model and the like of the SAE to obtain an indoor and outdoor classification model.
And step 204, acquiring the MR to be classified.
Wherein the MR to be classified may be an MR obtained when the embodiment of the present invention is performed.
And step 205, preprocessing the MR to be classified.
In the embodiment of the invention, the work parameter information related to the MR to be classified is firstly screened to obtain the target MR of which the main cell is the macro station and the received signal power RSRP of the main service cell is not empty. The working parameter information comprises information such as a base station name, a cell name, longitude and latitude and the like. And then, combining a plurality of pieces of measurement information of the same main service cell at the same time into a measurement record containing all the measurement information of the adjacent cells according to the timestamp information of the target MR and the identification of the main service cell. Then, the topology of all cells contained in the measurement record is described. And finally, carrying out normalization and unified data dimension processing by utilizing the topological structure, the RSRP of the main service cell and the RSRP of the adjacent cell.
Because of the difference of the received signals, the indoor MR and the outdoor MR have different cell topologies. In the embodiment of the invention, a feasible topological structure description method is that the average value position of the longitude and latitude of each recorded main cell and all adjacent cells is used as a central point, and the offset of the longitude and latitude of the base station of the main service cell and each adjacent cell relative to the central point is calculated.
During normalization and unified data dimension processing, the RSRP of the main serving cell and the neighboring cell, and the offset are normalized, for example, by adopting a min-max normalization method, a Z-score normalization method, and the like. Then, the frequency point information is subjected to binary discretization. For example, if the frequency points of the main serving cell and the neighboring cell include F1, F2, D1, and D2, the binary discretized frequency point information is expanded into 4 columns, which are respectively "whether F1", "whether F2", "whether D1", "whether D2", 0 indicates no, and 1 indicates yes. Meanwhile, the maximum number of the adjacent cells is set, and the record with insufficient number of the adjacent cells is subjected to 0 complementing operation.
And step 206, inputting the preprocessed MR as input data into an SAE indoor and outdoor data classification model and operating the model to obtain an indoor and outdoor data classification result corresponding to the MR to be classified.
In the embodiment of the invention, the MR to be classified is preprocessed, the preprocessed MR is used as input data, the input data is input into an SAE (sample analysis and analysis) indoor and outdoor data classification model of the stacked automatic encoder, and the model is operated to obtain an indoor and outdoor data classification result corresponding to the MR to be classified. Therefore, by using the scheme of the embodiment of the invention, the inaccuracy problem of indoor and outdoor discrimination by artificially making rules is avoided, and the positioning information of MR data is not needed; meanwhile, the SAE model can be used for automatically extracting the features, a feature extraction method does not need to be designed manually, the accuracy of MR indoor and outdoor classification can be improved, and the MR data can be used for more accurate network quality analysis. Aiming at indoor and outdoor test areas in the same area, a Machine learning algorithm based on SVM (Support Vector Machine) and a Machine learning algorithm based on SAE (adaptive sampling and analysis) are respectively applied to carry out indoor and outdoor identification prediction, and through tests, the prediction precision is improved by 10-20 percentage points.
Meanwhile, the obtained MR data indoor and outdoor classification result can be further input into MR data positioning application, and the positioning precision of the MR data is improved.
As shown in fig. 3, the data processing apparatus according to the embodiment of the present invention includes:
a first obtaining module 301, configured to obtain a measurement report MR to be classified;
a first preprocessing module 302, configured to preprocess the MR to be classified;
and the classification module 303 is configured to input the preprocessed MR as input data into an SAE indoor and outdoor data classification model of the stacked automatic encoder and operate the model to obtain an indoor and outdoor data classification result corresponding to the MR to be classified.
Wherein the first pre-processing module 302 comprises:
the screening submodule is used for screening the work parameter information related to the MR to be classified to obtain a target MR of which the main cell is a macro station and the receiving signal power RSRP of the main service cell is not empty; a merging submodule, configured to merge multiple pieces of measurement information of the same main serving cell at the same time into a measurement record including measurement information of all neighboring cells according to the timestamp information of the target MR and the main serving cell identifier; a topology description submodule, configured to describe topology of all cells included in the measurement record; and the data processing submodule is used for carrying out normalization and unified data dimension processing by utilizing the topological structure, the RSRP of the main service cell and the RSRP of the adjacent cell.
As shown in fig. 4, the data processing apparatus according to the embodiment of the present invention may further include:
a second acquisition module 404 for acquiring the sample MR;
a second preprocessing module 405, configured to preprocess the sample MR;
and a training module 406 for training the SAE indoor and outdoor data classification model by using the preprocessed sample MR.
The second obtaining module 404 may include:
the screening submodule is used for screening the sample MR to obtain a target sample MR of which the main cell is a macro station and the received signal power RSRP of the main service cell is not empty; a merging submodule, configured to merge multiple pieces of measurement information of the same main serving cell at the same time into a measurement record including measurement information of all neighboring cells according to the timestamp information of the target sample MR and the identifier of the main serving cell; a topology description submodule, configured to describe a topology structure of all cells included in the measurement record; and the data processing submodule is used for carrying out normalization and unified data dimension processing by utilizing the topological structure, the RSRP of the main service cell and the RSRP of the adjacent cell.
The working principle of the device according to the invention can be referred to the description of the method embodiment described above.
In the embodiment of the invention, the MR to be classified is preprocessed, the preprocessed MR is used as input data, the input data is input into an SAE (sample analysis and analysis) indoor and outdoor data classification model of the stacked automatic encoder, and the model is operated to obtain an indoor and outdoor data classification result corresponding to the MR to be classified. Therefore, by using the scheme of the embodiment of the invention, the characteristics do not need to be manually extracted, more potential characteristics can be mined, and the accuracy of distinguishing whether the MR is indoor data or outdoor data in the area covered by the macro station is improved.
As shown in fig. 5, the electronic device according to the embodiment of the present invention includes: the processor 500, which is used to read the program in the memory 520, executes the following processes:
acquiring a measurement report MR to be classified; preprocessing the MR to be classified; inputting the preprocessed MR as input data into an SAE (sample analysis and analysis) indoor and outdoor data classification model of a stacked automatic encoder and operating the model to obtain an indoor and outdoor data classification result corresponding to the MR to be classified;
a transceiver 510 for receiving and transmitting data under the control of the processor 500.
Wherein in fig. 5, the bus architecture may include any number of interconnected buses and bridges, with one or more processors, represented by processor 500, and various circuits, represented by memory 520, being linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. The bus interface provides an interface. The transceiver 510 may be a number of elements, including a transmitter and a transceiver, providing a means for communicating with various other apparatus over a transmission medium. The processor 500 is responsible for managing the bus architecture and general processing, and the memory 520 may store data used by the processor 500 in performing operations.
The processor 500 is responsible for managing the bus architecture and general processing, and the memory 520 may store data used by the processor 500 in performing operations.
The processor 500 is further configured to read the computer program and perform the following steps:
screening the MR-related working parameter information to be classified to obtain a target MR of which a main cell is a macro station and the received signal power (RSRP) of the main service cell is not empty;
combining a plurality of pieces of measurement information of the same main service cell at the same time into a measurement record containing all the measurement information of the adjacent cells according to the timestamp information of the target MR and the identification of the main service cell;
describing the topology of all cells contained in the measurement record;
and carrying out normalization and unified data dimension processing by utilizing the topological structure, the RSRP of the main service cell and the RSRP of the adjacent cell.
The processor 500 is further configured to read the computer program and perform the following steps:
acquiring a sample MR;
preprocessing the sample MR;
and training an SAE indoor and outdoor data classification model by using the preprocessed sample MR.
The processor 500 is further configured to read the computer program and perform the following steps:
screening the sample MR to obtain a target sample MR of which the main cell is a macro station and the received signal power RSRP of the main service cell is not empty;
combining a plurality of pieces of measurement information of the same main service cell at the same time into a measurement record containing all the measurement information of the adjacent cells according to the timestamp information and the main service cell identification of the target sample MR;
describing the topology of all cells contained in the measurement record;
and carrying out normalization and unified data dimension processing by utilizing the topological structure, the RSRP of the main service cell and the RSRP of the adjacent cell.
Furthermore, a computer-readable storage medium of an embodiment of the present invention stores a computer program executable by a processor to implement:
acquiring a measurement report MR to be classified;
preprocessing the MR to be classified;
and inputting the preprocessed MR as input data into an SAE (sample analysis and analysis) indoor and outdoor data classification model of the stacked automatic encoder, and operating the model to obtain an indoor and outdoor data classification result corresponding to the MR to be classified.
Wherein the preprocessing the MR to be classified comprises:
screening the MR-related working parameter information to be classified to obtain a target MR of which a main cell is a macro station and the received signal power (RSRP) of the main service cell is not empty;
combining a plurality of pieces of measurement information of the same main service cell at the same time into a measurement record containing all the measurement information of the adjacent cells according to the timestamp information of the target MR and the identification of the main service cell;
describing the topology of all cells contained in the measurement record;
and carrying out normalization and unified data dimension processing by utilizing the topological structure, the RSRP of the main service cell and the RSRP of the adjacent cell.
Before the acquiring of the MR to be classified, the method further comprises the following steps:
acquiring a sample MR;
preprocessing the sample MR;
and training an SAE indoor and outdoor data classification model by using the preprocessed sample MR.
Wherein the preprocessing the sample MR comprises:
screening the sample MR to obtain a target sample MR of which the main cell is a macro station and the received signal power RSRP of the main service cell is not empty;
combining a plurality of pieces of measurement information of the same main service cell at the same time into a measurement record containing all the measurement information of the adjacent cells according to the timestamp information and the main service cell identification of the target sample MR;
describing the topology of all cells contained in the measurement record;
and carrying out normalization and unified data dimension processing by utilizing the topological structure, the RSRP of the main service cell and the RSRP of the adjacent cell.
In the several embodiments provided in the present application, it should be understood that the disclosed method and apparatus may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be physically included alone, or two or more units may be integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) to execute some steps of the transceiving method according to various embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (4)
1. A data processing method, comprising:
acquiring a sample MR;
preprocessing the sample MR, including: screening the sample MR to obtain a target sample MR of which the main cell is a macro station and the received signal power RSRP of the main service cell is not empty; combining a plurality of pieces of measurement information of the same main service cell at the same time into a measurement record containing all the measurement information of the adjacent cells according to the timestamp information and the main service cell identification of the target sample MR; describing the topology of all cells contained in the measurement record; carrying out normalization and unified data dimension processing by utilizing the topological structure, the RSRP of the main service cell and the RSRP of the adjacent cell;
training an SAE indoor and outdoor data classification model by using the preprocessed sample MR, wherein the SAE indoor and outdoor data classification model comprises the following steps: sending the preprocessed sample MR into an SAE indoor and outdoor data classification model for automatic feature extraction and training, and adjusting the number of model layers, the number of neurons in each layer, a loss function, the number of pre-training times of each layer and the number of training times of an integral model of SAE to obtain an indoor and outdoor classification model;
acquiring a measurement report MR to be classified;
preprocessing the MR to be classified, comprising: screening the MR-related working parameter information to be classified to obtain a target MR of which a main cell is a macro station and the received signal power (RSRP) of the main service cell is not empty; combining a plurality of pieces of measurement information of the same main service cell at the same time into a measurement record containing all the measurement information of the adjacent cells according to the timestamp information of the target MR and the identification of the main service cell; describing the topology of all cells contained in the measurement record; carrying out normalization and unified data dimension processing by utilizing the topological structure, the RSRP of the main service cell and the RSRP of the adjacent cell;
and inputting the preprocessed MR as input data into an SAE (sample analysis and analysis) indoor and outdoor data classification model of the stacked automatic encoder, and operating the model to obtain an indoor and outdoor data classification result corresponding to the MR to be classified.
2. A data processing apparatus, comprising:
a second acquisition module (404) for acquiring the sample MR;
a second pre-processing module (405) for pre-processing the sample MR, comprising: screening the sample MR to obtain a target sample MR of which the main cell is a macro station and the received signal power RSRP of the main service cell is not empty; combining a plurality of pieces of measurement information of the same main service cell at the same time into a measurement record containing all the measurement information of the adjacent cells according to the timestamp information and the main service cell identification of the target sample MR; describing the topology of all cells contained in the measurement record; carrying out normalization and unified data dimension processing by utilizing the topological structure, the RSRP of the main service cell and the RSRP of the adjacent cell;
a training module (406) for training an SAE indoor and outdoor data classification model using the preprocessed sample MR, comprising: sending the preprocessed sample MR into an SAE indoor and outdoor data classification model for automatic feature extraction and training, and adjusting the number of model layers, the number of neurons in each layer, a loss function, the number of pre-training times of each layer and the number of training times of an integral model of SAE to obtain an indoor and outdoor classification model;
the first acquisition module is used for acquiring a measurement report MR to be classified;
the first preprocessing module is used for preprocessing the MR to be classified and comprises: screening the MR-related working parameter information to be classified to obtain a target MR of which a main cell is a macro station and the received signal power (RSRP) of the main service cell is not empty; combining a plurality of pieces of measurement information of the same main service cell at the same time into a measurement record containing all the measurement information of the adjacent cells according to the timestamp information of the target MR and the identification of the main service cell; describing the topology of all cells contained in the measurement record; carrying out normalization and unified data dimension processing by utilizing the topological structure, the RSRP of the main service cell and the RSRP of the adjacent cell;
and the classification module is used for inputting the preprocessed MR as input data into an SAE (sample analysis and analysis) indoor and outdoor data classification model of the stacked automatic encoder and operating the model to obtain an indoor and outdoor data classification result corresponding to the MR to be classified.
3. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor; wherein the processor implements the steps of the method of claim 1 when executing the program.
4. A computer-readable storage medium for storing a computer program, the computer program being executable by a processor for performing the steps of the method as claimed in claim 1.
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 CN109429264A (en) | 2019-03-05 |
| CN109429264B true 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) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN110691369B (en) * | 2019-11-27 | 2021-06-04 | 北京天元创新科技有限公司 | Indoor signal leakage analysis method and system based on MDT |
| 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 |
| US20240080686A1 (en) * | 2021-02-01 | 2024-03-07 | 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 |
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 |
|---|
| 基于KNN算法的MRR数据分类研究;徐承亮等;《移动通信》;20170228;正文第69-73页，图2-4 * |
| 基于深度学习的网页分类算法研究;陈芊希等;《微型电脑应用》;20160228;正文第1章 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109429264A (en) | 2019-03-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109429264B (en) | Data processing method, device, equipment and computer readable storage medium | |
| DE60025978T2 (en) | Device and method for the geostatic analysis of the propagation of a radio signal | |
| CN109996168B (en) | Method and device for acquiring terminal position | |
| CN105372581A (en) | Flexible circuit board manufacturing process automatic monitoring and intelligent analysis system and method | |
| CN108616900B (en) | Method for distinguishing indoor and outdoor measurement reports and network equipment | |
| CN109982361B (en) | Signal interference analysis method, device, equipment and medium | |
| CN107809766B (en) | Method and device for generating machine learning sample for network optimization | |
| CN109874104B (en) | User position positioning method, device, equipment and medium | |
| CN111163482B (en) | Data processing method, device and storage medium | |
| CN115471625A (en) | Cloud robot platform big data intelligent decision method and system | |
| CN113140109B (en) | Drive test data processing method and device, computer equipment and storage medium | |
| CN111786476A (en) | Method for predicting position of receiving coil of wireless power transmission system | |
| CN112149770A (en) | Data radio frequency identification display system, method and device of intelligent cable | |
| CN109996270A (en) | Network coverage analysis method, device, equipment and medium | |
| CN107025293A (en) | A kind of second power equipment defective data method for digging and system | |
| CN111343664B (en) | User positioning method, device, equipment and medium | |
| CN107517474B (en) | Network analysis optimization method and device | |
| CN111741526B (en) | Positioning method, positioning device, electronic equipment and computer storage medium | |
| Kupp et al. | Confidence estimation in non-RF to RF correlation-based specification test compaction | |
| CN109788501A (en) | 2G+4G mobile network's voice quality joint assessment method and device | |
| CN114580482A (en) | Radio signal characteristic acquisition method based on edge computing node and data center | |
| CN112215256A (en) | Multi-source data processing method for low-voltage distribution network | |
| CN110890978B (en) | Cross-region communication quality prediction method with privacy protection based on model reuse | |
| Sardroud | Developing Rfid-based electronic specimen and test coding system in construction quality management | |
| CN114095947B (en) | Network coverage evaluation method and device, electronic equipment and 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 |