CN114745289A - Method, device, storage medium and equipment for predicting network performance data - Google Patents
Method, device, storage medium and equipment for predicting network performance data Download PDFInfo
- Publication number
- CN114745289A CN114745289A CN202210408256.0A CN202210408256A CN114745289A CN 114745289 A CN114745289 A CN 114745289A CN 202210408256 A CN202210408256 A CN 202210408256A CN 114745289 A CN114745289 A CN 114745289A
- Authority
- CN
- China
- Prior art keywords
- data
- network performance
- performance data
- measurement report
- decision tree
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/142—Network analysis or design using statistical or mathematical methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/08—Testing, supervising or monitoring using real traffic
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Abstract
According to the method, the device, the storage medium and the equipment for predicting the network performance data, at least one group of measurement report data of a cell to be detected, which is sent by terminal equipment, is obtained; and then, inputting at least one group of measurement report data into the trained decision tree model, and obtaining a prediction result output by the trained decision tree model, wherein the trained decision tree model is generated by training historical network performance data and historical measurement report data, the decision tree model is used for outputting a regression prediction result through cyclic iteration, and the prediction result comprises a prediction value of the network performance data corresponding to at least one group of measurement report data respectively. By the mode, the predicted value of the downlink signal to interference and noise ratio data corresponding to the terminal equipment can be obtained according to the measurement report data sent by the terminal equipment and the trained decision tree model, so that the efficiency of obtaining the downlink signal to interference and noise ratio data is effectively improved.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method, an apparatus, a storage medium, and a device for predicting network performance data.
Background
The Signal to Interference plus Noise Ratio (SINR) is a very important network performance indicator. In a Long Term Evolution (LTE) network, the signal-to-interference-and-noise ratio refers to a ratio of the strength of a useful signal received by a terminal device to the strength of a received interference signal, i.e., a power ratio of a signal to noise interference.
The sir may be divided into an uplink sir and a downlink sir, where the downlink sir directly determines a modulation coding order of wireless transmission and a size of a transmission block, thereby determining a data transmission rate and a quality of a Long Term Evolution Voice over service (VoLTE). Therefore, the acquisition of the downlink signal-to-interference-and-noise ratio data has great significance for the optimization and evaluation of the network quality.
In the prior art, downlink signal to interference and noise ratio data is mainly acquired by a drive test method. For example, a professional tester drives a vehicle through a target route, and tests the vehicle in the field with a drive test device to collect drive test data including downlink signal to interference and noise ratios. However, the field drive test process requires high skill of the tester, and the collection of drive test data requires equipping with special drive test equipment and vehicles. Therefore, it is difficult for the existing drive test method to efficiently acquire downlink signal-to-interference-and-noise ratio data.
Disclosure of Invention
The application provides a method, a device, a storage medium and equipment for predicting network performance data, which are used for solving the technical problem that downlink signal-to-interference-and-noise ratio data are difficult to obtain efficiently in the prior art.
In a first aspect, the present application provides a method for predicting network performance data, the method comprising:
acquiring at least one group of measurement report data of a cell to be detected, which is sent by terminal equipment;
inputting the at least one group of measurement report data into a trained decision tree model, and obtaining a prediction result output by the trained decision tree model, wherein the trained decision tree model is generated by training historical network performance data and historical measurement report data, the decision tree model is used for outputting a regression prediction result through loop iteration, and the prediction result comprises a prediction value of the network performance data corresponding to the at least one group of measurement report data.
In an alternative embodiment, the network performance data comprises a signal to interference plus noise ratio.
In an optional embodiment, before the inputting the measurement report data into the trained decision tree model, the method further comprises:
acquiring historical network performance data and historical measurement report data;
and training the decision tree model according to the historical network performance data and the historical measurement report data.
In an alternative embodiment, the training the decision tree model includes:
determining characteristic data from the historical measurement report data;
determining label data corresponding to the characteristic data from the historical network performance data;
and forming sample set data by the characteristic data and the label data corresponding to the characteristic data, and training the decision tree model.
In an optional implementation, the determining, from the historical network performance data, tag data corresponding to the feature data includes:
determining at least one target historical network performance data from the historical network performance data according to the time stamp of the characteristic data, wherein the time interval between the time stamp of the at least one target historical network performance data and the time stamp of the characteristic data is smaller than a preset time interval;
and determining label data corresponding to the characteristic data according to the at least one target historical network performance data.
In an optional embodiment, the determining the tag data corresponding to the feature data includes:
determining an associated historical network performance data related to the characteristic data from the at least one target historical network performance data;
and determining the associated historical network performance data as the label data corresponding to the characteristic data.
In an alternative embodiment, the time interval between the time stamp of the associated historical network performance data and the time stamp of the characteristic data is minimal.
In an optional embodiment, the determining tag data corresponding to the feature data includes:
and determining the average value of the at least one target historical network performance data as the label data corresponding to the characteristic data.
In an optional embodiment, after determining an associated historical network performance data related to the feature data from the at least one target historical network performance data, the method further comprises:
and determining label data corresponding to the characteristic data according to the average value of the at least one target historical network performance data and the associated historical network performance data.
In a second aspect, the present application provides an apparatus for predicting network performance data, the apparatus comprising:
the acquisition module is used for acquiring at least one group of measurement report data of the cell to be detected, which is sent by the terminal equipment;
the prediction module is used for inputting the at least one group of measurement report data into a trained decision tree model and obtaining a prediction result output by the trained decision tree model, the trained decision tree model is generated by training historical network performance data and historical measurement report data, the decision tree model is used for outputting a regression prediction result through cyclic iteration, and the prediction result comprises a prediction value of the network performance data corresponding to the at least one group of measurement report data.
In an alternative embodiment, the network performance data comprises a signal to interference plus noise ratio.
In an optional embodiment, the prediction module is further configured to obtain historical network performance data and historical measurement report data; and training the decision tree model according to the historical network performance data and the historical measurement report data.
In an optional embodiment, the prediction module is specifically configured to determine feature data from the historical measurement report data; determining label data corresponding to the characteristic data from the historical network performance data; and forming sample set data by the characteristic data and the label data corresponding to the characteristic data, and training the decision tree model.
In an optional implementation manner, the prediction module is specifically configured to determine at least one target historical network performance data from the historical network performance data according to the time stamp of the feature data, where time intervals between the time stamp of the at least one target historical network performance data and the time stamp of the feature data are both smaller than a preset time interval; and determining label data corresponding to the characteristic data according to the at least one target historical network performance data.
In an optional implementation, the prediction module is specifically configured to determine, from the at least one target historical network performance data, an associated historical network performance data related to the feature data; and determining the associated historical network performance data as the label data corresponding to the characteristic data.
In an alternative embodiment, the time interval between the time stamp of the associated historical network performance data and the time stamp of the characteristic data is minimal.
In an optional implementation manner, the prediction module is specifically configured to determine an average value of the at least one target historical network performance data as the tag data corresponding to the feature data.
In an optional implementation manner, after determining one associated historical network performance data related to the feature data from the at least one target historical network performance data, the prediction module is further configured to determine tag data corresponding to the feature data according to an average value of the at least one target historical network performance data and the associated historical network performance data.
In a third aspect, the present application also provides a computer program product comprising a computer program that, when executed by a processor, performs the method of any of the first aspects.
In a fourth aspect, the present invention also provides a computer storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform the method according to any of the first aspect.
In a fifth aspect, the present application further provides an electronic device, including: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to perform the method according to any of the first aspects.
According to the method, the device, the storage medium and the equipment for predicting the network performance data, at least one group of measurement report data of a cell to be detected, which is sent by terminal equipment, is obtained; and then, inputting at least one group of measurement report data into the trained decision tree model, and obtaining a prediction result output by the trained decision tree model, wherein the trained decision tree model is generated by training historical network performance data and historical measurement report data, the decision tree model is used for outputting a regression prediction result through cyclic iteration, and the prediction result comprises a prediction value of the network performance data corresponding to at least one group of measurement report data respectively. By the mode, the predicted value of the downlink signal to interference and noise ratio data corresponding to the terminal equipment can be obtained according to the measurement report data sent by the terminal equipment and the trained decision tree model, so that the efficiency of obtaining the downlink signal to interference and noise ratio data is effectively improved.
Drawings
In order to more clearly illustrate the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can obtain other drawings without inventive labor.
Fig. 1 is a schematic view of an application scenario of a method for predicting network performance data according to an embodiment of the present application;
fig. 2 is a schematic flowchart of a method for predicting network performance data according to an embodiment of the present disclosure;
fig. 3 is a schematic distribution diagram of problem areas with network quality problems in a designated area a according to an embodiment of the present application;
FIG. 4 is a flowchart illustrating a training method of a decision tree model according to an embodiment of the present disclosure;
FIG. 5 is a schematic flow chart illustrating another method for training a decision tree model according to an embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of an apparatus for predicting network performance data according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
With the development of Mobile network Communication Technology, quality optimization for voice traffic and data traffic becomes more and more important at a key stage of the transition of the fifth Generation Mobile Communication Technology (5th Generation Mobile Communication Technology, 5G) from large-scale construction to network specialized operation. At present, since Voice Over New Radio (VoNR) is still in the pilot stage, Voice traffic of 5G network is mainly carried by Voice Over Long Term Evolution (VoLTE) of the fourth Generation Mobile Communication network (4th Generation Mobile Communication Technology, 4G). In addition, due to the lack of coverage depth of the 5G network, the 4G network is still an important network currently carrying voice traffic and data traffic.
In the quality optimization and evaluation process of the 4G network, a Signal to Interference plus Noise Ratio (SINR) is a very important network performance indicator. As a key parameter for adaptive coding and modulation mapping of the LTE network downlink, the signal to interference plus noise ratio can be used to judge the network quality. In a Long Term Evolution (LTE) network, the signal-to-interference-and-noise ratio refers to a ratio of the strength of a useful signal received by a terminal device to the strength of a received interference signal, i.e., a power ratio of a signal to noise interference. The sir can be divided into an uplink sir and a downlink sir. The downlink signal-to-interference-and-noise ratio directly determines the size and modulation coding order of a transmission block for wireless transmission, thereby determining the VoLTE voice service quality and the data transmission rate.
In the prior art, downlink signal to interference and noise ratio data is mainly acquired by a drive test method. For example, a specialized tester drives a vehicle through a target route, and tests in the field with a drive test device to collect drive test data including downlink signal-to-interference-and-noise ratios. However, since the field drive test process requires a high skill of the tester, and the collection of drive test data requires the equipping of special drive test equipment and vehicles. Therefore, it is difficult for the existing drive test method to efficiently acquire downlink signal-to-interference-and-noise ratio data.
In order to solve the foregoing technical problems, embodiments of the present application provide a method, an apparatus, a storage medium, and a device for predicting network performance data, where a predicted value of downlink signal to interference and noise ratio data corresponding to a terminal device is obtained according to measurement report data sent by the terminal device and a trained decision tree model, so as to effectively improve efficiency of obtaining the downlink signal to interference and noise ratio data.
First, Measurement Report (MR) data will be described below. The MR data includes periodic Report objective (MRO) data, and the like, and the terminal device will continuously and actively Report the acquired MRO data to the MRO server during the use of the mobile network. The types of data contained in the MRO data are: time point, timestamp, International Mobile Subscriber Identity (International Mobile Subscriber Identity Number, IMSI), longitude, latitude, sampling point Number, serving Cell Identifier (E-UTRAN Cell Identifier, ECI), Frequency point Number (E-UTRA Absolute Radio Frequency Channel Number, earfcn), Physical Identifier (Physical-layer Cell Identifier, PCI), level strength (Reference Signal Receiving Power, RSRP), Signal Quality (Reference Signal Receiving Quality, RSRQ), Power Headroom (Power head Report, PHR), Timing advance (Timing advance, Ta), uplink Signal to interference plus noise ratio (sinr), uplink shared Channel Physical Resource Block (RSRQ), downlink shared Channel Identifier (PRB), PRB) Number, PRB Number, average Channel Identifier (PRB) and average Power difference, and average transmitted Power of neighboring Cell, CQI and average transmitted Power of neighboring Cell The minimum difference value of the level intensity of the adjacent cells, the overlapping quantity of the MR of the cells, the quantity of the adjacent cells with the level intensity difference value within 6 decibels (dB), the modulo three quantity, the average level intensity of the adjacent cells, the quantity of the pilot frequency adjacent cells, the quantity of the adjacent cells, the number, the frequency point number, the physical identification, the level intensity, the level quality and the like of the adjacent cells from the 1 st adjacent cell to the nth adjacent cell of the service cell.
An application scenario of the prediction method of network performance data according to the present application is described below.
Fig. 1 is a schematic application scenario diagram of a method for predicting network performance data according to an embodiment of the present application. As shown in fig. 1, the terminal apparatus 101 and the server 102 are included. First, the terminal device 101 may actively report MRO data to the server 102; then, the server 102 outputs the predicted value of the network performance data corresponding to the terminal device 101 according to the obtained MRO data and the trained decision tree model. In some embodiments, the network performance data includes downlink signal to interference plus noise ratio data.
The terminal device may be a mobile phone (mobile phone), a tablet personal computer (pad), a computer with a wireless transceiving function, a Virtual Reality (VR) terminal device, an Augmented Reality (AR) terminal device, a wireless terminal in unmanned driving (self driving), a wireless terminal in remote medical surgery (remote medical supply), a wireless terminal in smart grid (smart grid), a wireless terminal in smart home (smart home), and the like. In the embodiment of the present application, the apparatus for implementing the function of the terminal may be the terminal, or may be an apparatus capable of supporting the terminal to implement the function, for example, a system on chip, and the apparatus may be installed in the terminal. In the embodiment of the present application, the chip system may be composed of a chip, and may also include a chip and other discrete devices.
The server may be, but is not limited to, a single web server, a server group consisting of a plurality of web servers, or a cloud based on cloud computing consisting of a large number of computers or web servers.
It should be understood that the application scenario of the technical solution of the present application may be a prediction scenario of the network performance data in fig. 1, but is not limited thereto, and may also be applied to other scenarios that require processing of the network performance data.
It can be understood that the above-mentioned method for predicting network performance data can be implemented by the device for predicting network performance data provided in the embodiments of the present application, and the device for predicting network performance data may be part or all of a certain device, for example, a server or a relevant data analysis model in the server.
The following describes the technical solution of the embodiments of the present application in detail with specific embodiments, taking a server integrated or installed with relevant executable codes as an example. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments.
Fig. 2 is a schematic flowchart of a method for predicting network performance data according to an embodiment of the present disclosure, where the embodiment relates to a process of predicting network performance data. As shown in fig. 2, the method includes:
s201, at least one group of measurement report data of the cell to be detected, which is sent by the terminal equipment, is obtained.
In this embodiment, the server may first obtain at least one set of measurement report data, and then obtain the predicted value of the network performance data according to the obtained measurement report data.
The cell may include any base station cell, the measurement report data may include MRO data, and the network performance data may include a downlink signal to interference plus noise ratio, which is not limited in this embodiment of the present application.
The embodiment of the application does not limit how to determine the cell to be detected. In some embodiments, the cell to be detected may obtain downlink signal to interference and noise ratio data as needed or determine an area range in which network quality optimization and evaluation are needed. Illustratively, if the network quality needs to be optimized and evaluated in the target area a, and further the downlink signal-to-interference-and-noise ratio data in the target area a needs to be acquired, at this time, any base station cell in the target area a may be the cell to be detected.
The embodiment of the present application does not limit the method for dividing at least one set of measurement report data. In some embodiments, all measurement report data that meets the time range requirement may be partitioned according to the time stamp of the measurement report data. The timestamp may be determined according to the acquisition time or reporting time of the measurement report data. It should be noted that the terminal device may report the measurement report data to the server at a certain time interval, and a reporting period may be controlled by a receiving timer of the measurement report data started by the base station. Illustratively, the terminal device may report the acquired MRO data to the server at a period of 10 seconds.
S202, inputting at least one group of measurement report data into a trained decision tree model, and obtaining a prediction result output by the trained decision tree model, wherein the trained decision tree model is generated by training historical network performance data and historical measurement report data, the decision tree model is used for outputting a regression prediction result through loop iteration, and the prediction result comprises a prediction value of the network performance data corresponding to at least one group of measurement report data.
In this step, after obtaining at least one set of measurement report data, the server may input the at least one set of measurement report data into the trained decision tree model, and obtain a prediction result output by the trained decision tree model.
The embodiment of the present application does not limit the type of the decision tree model. In some embodiments, the decision tree model may be built by an eXtreme Gradient Boosting (XGBoost) algorithm.
It can be understood that, in the prior art, mainly through a field drive test method, downlink signal to interference and noise ratio data on a target route in a designated area a is collected by using a special drive test device, and then according to the collected downlink signal to interference and noise ratio data, a problem area in the designated area a, which may have a network quality problem, is located. In the embodiment of the application, downlink signal to interference and noise ratio data of the designated area a can be predicted according to measurement report data reported by any terminal device in the designated area a through a trained decision tree model, and then a problem area which may have a network quality problem in the designated area a is positioned according to the predicted downlink signal to interference and noise ratio data.
Exemplarily, fig. 3 is a schematic distribution diagram of problem areas with network quality problems in a designated area a according to an embodiment of the present application. As shown in fig. 3, a plurality of roads exist in the designated area a. It should be understood that the drive test equipment may collect downlink signal to interference and noise ratio data along the roads by a field drive test method, and combine the collected downlink signal to interference and noise ratio data with the positions of the roads in the designated area a to determine the problem area with the network quality problem. Similarly, the server may also obtain the test report data sent by the terminal devices on the multiple roads, then predict the downlink signal-to-interference-and-noise ratio data on the roads, and determine the problem area with the network quality problem by combining the predicted downlink signal-to-interference-and-noise ratio data with the positions of the roads. As shown in fig. 3, the problem areas in the designated area a where there is a problem in network quality include 4 problem areas "1" and 4 problem areas "2". Wherein, 4 problem areas '1' are determined according to downlink SINR data acquired by a field drive test method; the 4 problem areas "1" and 4 problem areas "2" are determined according to the downlink SINR data predicted by the trained decision tree model.
Further, through a field drive test method and a prediction method of network performance data provided by the embodiment of the present application, a consistent network quality problem area, that is, 4 problem areas "1" in fig. 3, can be found in the designated area a. Since the prediction method of the network performance data provided by the application can use more data and the data covers wider roads, more network quality problem areas, namely 4 problem areas '2' in fig. 3, can be found. According to the analysis result, the network performance data prediction method provided by the application has more diagnosis dimensionality on the network quality problem than a field drive test method.
In addition, in addition to the field drive test method, a virtual drive test method also exists in the prior art. The virtual drive test method mainly comprises the following steps: and the server analyzes and positions the network quality problem in the designated area A through MRO data and the like reported by the mass terminal equipment. However, since MRO data does not include downlink sir data, the virtual drive test method cannot analyze and locate the network quality problem according to the downlink sir. By the method for predicting the network performance data, the virtual drive test method can be combined with the trained decision tree model to directly obtain the predicted value of the downlink signal-to-interference-and-noise ratio (MRO) according to the MRO data, so that the workload of an engineer for acquiring the drive test data through the field drive test process is greatly reduced, and the project cost is effectively saved.
Exemplarily, the ratio of the downlink SINR of the 10-meter road section in the specified area A, which is obtained by the field drive test method, to be more than-3 dB is 93.76%; by combining the virtual drive test method with the prediction method of the network performance data provided by the application, the ratio of the downlink SINR of the 10-meter road section in the specified area A to be more than-3 dB is 98.73%. The difference of the ratio of the index of SINR of the 10-meter road section greater than-3 dB obtained by the two methods is 4.97%, and the reliability of the downlink signal-to-interference-and-noise ratio data obtained by combining the prediction method of the network performance data provided by the application based on the virtual drive test prediction is close to that of the field drive test method.
The method for predicting the network performance data includes the steps that at least one group of measurement report data of a cell to be detected and sent by terminal equipment is obtained; and then, inputting at least one group of measurement report data into the trained decision tree model, and obtaining a prediction result output by the trained decision tree model, wherein the trained decision tree model is generated by training historical network performance data and historical measurement report data, the decision tree model is used for outputting a regression prediction result through cyclic iteration, and the prediction result comprises a prediction value of the network performance data corresponding to at least one group of measurement report data respectively. By the method, the predicted value of the downlink signal to interference and noise ratio data corresponding to the terminal equipment can be obtained according to the measurement report data sent by the terminal equipment and the trained decision tree model, so that the obtaining efficiency of the downlink signal to interference and noise ratio data is effectively improved.
On the basis of the above embodiment, how to obtain the trained decision tree model is described below. Fig. 4 is a schematic flowchart of a training method for a decision tree model according to an embodiment of the present application, and as shown in fig. 4, the method includes:
s401, obtaining historical network performance data and historical measurement report data.
In an embodiment of the present application, a server may first obtain historical network performance data and historical measurement report data.
The embodiment of the application does not limit how to obtain the historical network performance data. In some embodiments, historical network performance data may be obtained by field drive test methods. Illustratively, the drive test equipment acquires drive test data in the target area B through road test, wherein the drive test data comprises downlink signal-to-interference-and-noise ratio data. The server can acquire the downlink signal to interference and noise ratio data collected by the drive test equipment from the previous drive test software according to the number or the identification of the drive test equipment and use the downlink signal to interference and noise ratio data as historical downlink signal to interference and noise ratio data.
It should be noted that the drive test data may include a Mobile Subscriber International ISDN number (MSISDN) and an IMSI identifier of the drive test equipment, a time of reporting a sampling point, a longitude and a latitude of reporting the sampling point, an ECI, a downlink quality SINR, a frequency point number, a physical identifier, a level Strength, a total Received bandwidth power (RSSI), a Signal quality of a main control cell to which the sampling point belongs, and data such as a frequency point number, a physical identifier, a level Strength, a Signal quality of a 1 st neighboring cell to an nth neighboring cell of the main control cell.
The embodiment of the application does not limit how to obtain the historical measurement report data. In some embodiments, the historical measurement report data reported by the drive test equipment may be obtained at the same time as the historical network performance data is obtained. For example, the drive test device may also actively report the MRO data to the server during the road test, so that the MRO data reported by the drive test device may be obtained as the historical measurement report data according to the number or the identifier of the drive test device.
S402, training the decision tree model according to the historical network performance data and the historical measurement report data.
In this step, after obtaining the historical network performance data and the historical measurement report data, the server may train the decision tree model according to the obtained data.
The embodiment of the application does not limit how the decision tree model is trained. In some embodiments, the server may first determine feature data from historical measurement report data; then, determining label data corresponding to the characteristic data from the historical network performance data; and then, forming sample set data by the feature data and the label data corresponding to the feature data, and training the decision tree model.
It will be appreciated that the historical measurement report data comprises a plurality of types of data, and the characteristic data may be at least one type of data that is more highly correlated with the historical network performance data. The embodiment of the application does not limit how to determine the feature data. In some embodiments, the obtained historical network performance data and the historical measurement report data may be associated according to the number or the identifier of the drive test equipment, the data generation or reporting time, and the like; then, respectively evaluating the correlation between the historical network performance data and multiple types of data in the historical measurement report data; then, characteristic data is determined from the historical measurement report data according to the level of the correlation. Illustratively, when the historical network performance data is downlink signal-to-interference-and-noise ratio data, the characteristic data may include level strength of the master serving cell, signal quality, physical identifier, power headroom, timing advance, number of neighboring cells, average difference of level strength with neighboring cells, number of MR overlaps of cells, and modulo three number.
In other embodiments, the screened feature data may be processed by data cleaning or the like. By way of example, the specific processing manner may include missing value filling, outlier processing, normalization, one-hot encoding, feature fusion and disassembly, and the like, which is not limited in this embodiment of the application.
The embodiment of the application does not limit how to determine the tag data corresponding to the feature data. In some embodiments, the server may determine at least one target historical network performance data from the historical network performance data based on the timestamp of the feature data; and then, determining label data corresponding to the characteristic data according to at least one target historical network performance data. The timestamp can be acquisition time or reporting time, and the time interval between the timestamp of the at least one target historical network performance data and the timestamp of the characteristic data is smaller than a preset time interval. The preset time interval may be 1 second or 0.1 second, etc., which is not limited in this application.
The following describes in detail how to determine tag data corresponding to feature data from at least one target historical network performance data.
Exemplarily, table 1 is a drive test data list acquired by a drive test device a according to an embodiment of the present application. Table 1 includes the time and place of the drive test data collected by the drive test device a, and the data such as the frequency point numbers of the sampling point main control cell and the 1 st and 2 nd neighboring cells. It is to be understood that the data contained in table 1 is only a part of the drive test data collected by the drive test device a. It should be noted that the drive test device a acquires data many times within 1 second, and basically acquires drive test data 1 time within about 100 milliseconds, and the acquisition frequency is related to the chip performance of the drive test device a. As shown in table 1, 8 downlink signal to interference and noise ratio data were collected within 1s of time "10: 50: 30".
TABLE 1
Exemplarily, table 2 is a list of historical measurement report data collected by the drive test device a according to an embodiment of the present application. Table 2 includes time when the drive test device a collects the historical measurement report data, the international mobile subscriber identity of the drive test device a, and data such as the frequency point number, the physical cell identifier, and the level strength of the master cell "nc 1" and the 1 st neighboring cell "nc 2" and the 2 nd neighboring cell "nc 3". It is understood that the data contained in table 2 is only a portion of the historical measurement report data, where the data that was not collected appears to be null. The data in tables 1 and 2 were collected on the same day. As shown in table 2, the drive test equipment a collects the reported historical measurement report data in a cycle of 10 seconds, and there are only 1 group of historical measurement report data in 1s of time "10: 50: 30".
TABLE 2
Based on table 1 and table 2, the embodiment of the present application provides 3 methods for determining tag data corresponding to feature data. The first method comprises the following steps: and determining associated historical network performance data related to the characteristic data from at least one target historical network performance data, and determining the associated historical network performance data as the label data corresponding to the characteristic data. In some embodiments, the time interval between the time stamp of the association historical network performance data and the time stamp of the characterization data is minimal. Illustratively, first, the closest timestamp is matched according to the "UE Time" field in table 1 and the "obj _ timestamp" field in table 2. For example, by the time fields in tables 1 and 2, 1 adjacent timestamp of "10: 50: 30" can be matched. In table 1, a total of 8 drive test data were collected in 1 second of "10: 50: 30"; in Table 2, only 1 historical MRO data was collected within 1 second of "10: 50: 30". And then, determining 1 associated downlink signal-to-interference ratio data from 8 downlink signal-to-interference ratio data corresponding to 8 times of drive test data by a main control and adjacent region approximate matching method, wherein the associated downlink signal-to-interference ratio data is used as label data corresponding to the characteristic data of the second 10:50: 30. The main control and adjacent cell approximate matching method can be as follows: for the drive test data acquired each time, a field intensity vector (a, b, …, n) of the drive test data can be formed according to the level intensity a of the main service cell and the level intensity b … n of the 1 st adjacent cell; for the historical measurement report data collected each time, a field intensity vector (a ', b', …, n ') of the historical measurement report data can be formed according to the level intensity a' of the main serving cell, the level intensity b '… of the 1 st neighboring cell and the level intensity n' of the nth neighboring cell. And after the nearest timestamp is matched, calculating a Euclidean distance D between the field intensity vector of the drive test data corresponding to the timestamp and the field intensity vector of the historical measurement report data, wherein if the value of the Euclidean distance D is minimum, the two groups of data are in the most relevant matching. By the method, 1 piece of associated downlink signal to interference and noise ratio data S1 can be determined from the total 8 times of drive test data collected in the table 1 of 10:50:30, and S1 is used as the label data corresponding to the feature data with the time stamp of 10:50: 30. The level strength used for constructing the vector may also be replaced by other types of data, which is not limited in this embodiment of the present application.
The second method is as follows: and determining the average value of at least one target historical network performance data as the label data corresponding to the characteristic data. Illustratively, the closest timestamp is first matched according to the "UE Time" field in table 1 and the "obj _ timestamp" field in table 2. For example, 1 adjacent timestamp of "10: 50: 30" may be matched. Then, the average value S2 of 8 downlink signal to interference and noise ratio data in the total 8 times of drive test data collected in table 1 "10: 50: 30" is used as the tag data corresponding to the feature data with the time stamp "10: 50: 30". It can be understood that there is a jump fluctuation in the data value of the downlink signal to interference and noise ratio in table 1, for example, the data value of the downlink signal to interference and noise ratio appears 0.3, and deviates greatly from the data values of the adjacent downlink signal to interference and noise ratios. In order to avoid the error caused by determining the data value with large jump fluctuation as the label data in the first method, the error can be reduced by averaging a plurality of downlink signal to interference and noise ratio data.
The third method is as follows: and determining label data corresponding to the characteristic data according to the average value of the at least one target historical network performance data and the associated historical network performance data. Illustratively, the closest timestamp is first matched according to the "UE Time" field in table 1 and the "obj _ timestamp" field in table 2; then, according to the time stamp, 1 piece of associated downlink signal to interference and noise ratio data S1 is determined from the table 1 by a main control and adjacent region approximate matching method; then, determining an average value S2 of downlink signal to interference and noise ratio data in at least one set of drive test data corresponding to the timestamp from table 1; finally, the average value of S1 and S2 is used as the tag data of the feature data corresponding to the time stamp.
Further, after determining the label data corresponding to each group of feature data, the feature data and the label data corresponding to the feature data may be combined into sample set data; then, dividing the sample set data into training set data and test set data according to a preset division ratio; and then, respectively training the decision tree model according to the training set data and the test set data. The preset division ratio may be 7:3, which is not limited in the embodiment of the present application.
Illustratively, table 3 is a list of training and verification results of a decision tree model provided in an embodiment of the present application.
TABLE 3
Wherein, the 'R2' can be used for reflecting the proportion that all the variation of the dependent variable can be explained by the independent variable through the regression relationship, and the larger the proportion is, the more accurate the model is, and the more remarkable the regression effect is. As shown in table 3, the decision tree model is trained by using 3 different label data determination methods, wherein the accuracy of the decision tree model trained by the third method is the highest.
The technical terms, technical effects, technical features, and alternative embodiments of S401 to S402 can be understood with reference to S201 to S202 shown in fig. 2, and repeated descriptions thereof will not be repeated here.
On the basis of the above-described embodiment, how to determine the tag data corresponding to the feature data is described below. Fig. 5 is a schematic flow chart of another method for training a decision tree model according to an embodiment of the present application, and as shown in fig. 5, the method includes:
s501, obtaining historical network performance data and historical measurement report data.
And S502, determining characteristic data from the historical measurement report data.
S503, determining at least one target historical network performance data from the historical network performance data according to the time stamp of the characteristic data.
S504, determining label data corresponding to the characteristic data according to at least one target historical network performance data.
And S505, forming sample set data by the characteristic data and the label data corresponding to the characteristic data, and training the decision tree model.
The technical terms, technical effects, technical features, and alternative embodiments of S501-S505 can be understood with reference to S201-S202 shown in fig. 2, and repeated descriptions will not be repeated here.
The method for predicting the network performance data includes the steps that at least one group of measurement report data of a cell to be detected and sent by terminal equipment is obtained; and then, inputting at least one group of measurement report data into the trained decision tree model, and obtaining a prediction result output by the trained decision tree model, wherein the trained decision tree model is generated by training historical network performance data and historical measurement report data, the decision tree model is used for outputting a regression prediction result through cyclic iteration, and the prediction result comprises a prediction value of the network performance data corresponding to at least one group of measurement report data respectively. By the mode, the predicted value of the downlink signal to interference and noise ratio data corresponding to the terminal equipment can be obtained according to the measurement report data sent by the terminal equipment and the trained decision tree model, so that the efficiency of obtaining the downlink signal to interference and noise ratio data is effectively improved.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer readable storage medium, and when executed, performs steps comprising the method embodiments; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Fig. 6 is a schematic structural diagram of a device for predicting network performance data according to an embodiment of the present disclosure. The network performance data prediction device may be implemented by software, hardware or a combination of the two, and may be, for example, a server in the above embodiment, to execute the network performance data prediction method in the above embodiment. As shown in fig. 6, the network performance data prediction apparatus 600 includes:
an obtaining module 601, configured to obtain at least one set of measurement report data of a cell to be detected, where the measurement report data is sent by a terminal device;
the prediction module 602 is configured to input at least one set of measurement report data into a trained decision tree model, and obtain a prediction result output by the trained decision tree model, where the trained decision tree model is generated by training historical network performance data and historical measurement report data, the decision tree model is configured to output a regression prediction result through loop iteration, and the prediction result includes a prediction value of network performance data corresponding to each of the at least one set of measurement report data.
In an alternative embodiment, the network performance data comprises a signal to interference plus noise ratio.
In an optional embodiment, the prediction module 602 is further configured to obtain historical network performance data and historical measurement report data; and training the decision tree model according to the historical network performance data and the historical measurement report data.
In an optional embodiment, the prediction module 602 is specifically configured to determine feature data from historical measurement report data; determining label data corresponding to the characteristic data from the historical network performance data; and forming sample set data by the characteristic data and the label data corresponding to the characteristic data, and training the decision tree model.
In an optional implementation, the prediction module 602 is specifically configured to determine at least one target historical network performance data from the historical network performance data according to a timestamp of the feature data, where time intervals between the timestamp of the at least one target historical network performance data and the timestamp of the feature data are both smaller than a preset time interval; and determining label data corresponding to the characteristic data according to at least one target historical network performance data.
In an optional embodiment, the prediction module 602 is specifically configured to determine, from at least one target historical network performance data, an associated historical network performance data related to the feature data; and determining the associated historical network performance data as the label data corresponding to the characteristic data.
In an alternative embodiment, the time interval between the time stamp of the association historical network performance data and the time stamp of the characterization data is minimal.
In an optional implementation, the prediction module 602 is specifically configured to determine an average value of at least one target historical network performance data as the tag data corresponding to the feature data.
In an alternative embodiment, after determining an associated historical network performance data related to the feature data from the at least one target historical network performance data, the prediction module 602 is further configured to determine the tag data corresponding to the feature data according to an average value of the at least one target historical network performance data and the associated historical network performance data.
It should be noted that the prediction apparatus for network performance data provided in the embodiment shown in fig. 6 may be configured to execute the prediction method for network performance data provided in any of the above embodiments, and specific implementation and technical effects are similar, and are not described herein again.
Fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 7, the electronic device 700 may include: at least one processor 701 and a memory 702. Fig. 7 shows an electronic device as an example of a processor.
And a memory 702 for storing programs. In particular, the program may include program code including computer operating instructions.
The memory 702 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The processor 701 is configured to execute computer-executable instructions stored in the memory 702 to implement the method for predicting network performance data described above; the processor 701 may be a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement embodiments of the present Application.
Optionally, in a specific implementation, if the communication interface, the memory 702 and the processor 701 are implemented independently, the communication interface, the memory 702 and the processor 701 may be connected to each other through a bus and perform communication with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. Buses may be classified as address buses, data buses, control buses, etc., but do not represent only one bus or type of bus.
Alternatively, in a specific implementation, if the communication interface, the memory 702 and the processor 701 are integrated into a chip, the communication interface, the memory 702 and the processor 701 may complete communication through an internal interface.
The embodiment of the application also provides a chip which comprises a processor and an interface. Wherein the interface is used for inputting and outputting data or instructions processed by the processor. The processor is adapted to perform the method provided in the above method embodiments. The chip can be applied to a prediction device of network performance data.
Embodiments of the present application also provide a program, which when executed by a processor, is configured to perform the method for predicting network performance data provided by the above method embodiments.
Embodiments of the present application further provide a program product, such as a computer-readable storage medium, having stored therein instructions, which, when run on a computer, cause the computer to perform the method for predicting network performance data provided by the above method embodiments.
The present application also provides a computer-readable storage medium, which may include: 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. Specifically, the computer-readable storage medium has stored therein program information for the above-described method of predicting network performance data.
In the above embodiments, all or part of the implementation may be realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The procedures or functions according to the embodiments of the invention are all or partially generated when the computer program instructions are loaded and executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. Computer-readable storage media can be any available media that can be accessed by a computer or a data storage device, such as a server, data center, etc., that includes one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (12)
1. A method for predicting network performance data, the method comprising:
acquiring at least one group of measurement report data of a cell to be detected, which is sent by terminal equipment;
inputting the at least one group of measurement report data into a trained decision tree model, and obtaining a prediction result output by the trained decision tree model, wherein the trained decision tree model is generated by training historical network performance data and historical measurement report data, the decision tree model is used for outputting a regression prediction result through loop iteration, and the prediction result comprises a prediction value of the network performance data corresponding to the at least one group of measurement report data.
2. The method of claim 1, wherein the network performance data comprises a signal to interference plus noise ratio.
3. The method of claim 1 or 2, wherein prior to said inputting the measurement report data into a trained decision tree model, the method further comprises:
acquiring historical network performance data and historical measurement report data;
and training the decision tree model according to the historical network performance data and the historical measurement report data.
4. The method of claim 3, wherein training the decision tree model comprises:
determining characteristic data from the historical measurement report data;
determining label data corresponding to the characteristic data from the historical network performance data;
and forming sample set data by the characteristic data and the label data corresponding to the characteristic data, and training the decision tree model.
5. The method of claim 4, wherein the determining the tag data corresponding to the feature data from the historical network performance data comprises:
determining at least one target historical network performance data from the historical network performance data according to the time stamp of the characteristic data, wherein the time interval between the time stamp of the at least one target historical network performance data and the time stamp of the characteristic data is smaller than a preset time interval;
and determining label data corresponding to the characteristic data according to the at least one target historical network performance data.
6. The method of claim 5, wherein the determining the tag data corresponding to the feature data comprises:
determining an associated historical network performance data related to the characteristic data from the at least one target historical network performance data;
and determining the associated historical network performance data as the label data corresponding to the characteristic data.
7. The method of claim 6, wherein a time interval between the time stamp of the association historical network performance data and the time stamp of the characterization data is minimized.
8. The method of claim 5, wherein the determining the tag data corresponding to the feature data comprises:
and determining the average value of the at least one target historical network performance data as the label data corresponding to the characteristic data.
9. The method of claim 6, wherein after said determining an associated historical network performance data associated with said characteristic data from said at least one target historical network performance data, said method further comprises:
and determining label data corresponding to the characteristic data according to the average value of the at least one target historical network performance data and the associated historical network performance data.
10. An apparatus for predicting network performance data, the apparatus comprising:
the system comprises an acquisition module, a sending module and a receiving module, wherein the acquisition module is used for acquiring at least one group of measurement report data of a cell to be detected, which is sent by terminal equipment;
the prediction module is used for inputting the at least one group of measurement report data into a trained decision tree model and obtaining a prediction result output by the trained decision tree model, the trained decision tree model is generated by training historical network performance data and historical measurement report data, the decision tree model is used for outputting a regression prediction result through cyclic iteration, and the prediction result comprises a prediction value of the network performance data corresponding to the at least one group of measurement report data.
11. A computer storage medium having stored thereon computer executable instructions for performing the method of any one of claims 1 to 9 when executed by a processor.
12. An electronic device, comprising: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to perform the method according to any of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210408256.0A CN114745289A (en) | 2022-04-19 | 2022-04-19 | Method, device, storage medium and equipment for predicting network performance data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210408256.0A CN114745289A (en) | 2022-04-19 | 2022-04-19 | Method, device, storage medium and equipment for predicting network performance data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114745289A true CN114745289A (en) | 2022-07-12 |
Family
ID=82282279
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210408256.0A Pending CN114745289A (en) | 2022-04-19 | 2022-04-19 | Method, device, storage medium and equipment for predicting network performance data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114745289A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115941991A (en) * | 2023-01-10 | 2023-04-07 | 北京微吼时代科技有限公司 | Method and system for verifying stability of message receiving under large concurrency |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017016472A1 (en) * | 2015-07-28 | 2017-02-02 | Huawei Technologies Co., Ltd. | Predicting network performance |
| 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 |
| CN110266412A (en) * | 2019-07-01 | 2019-09-20 | 中国电信股份有限公司 | The predictably method and apparatus of Tie Tong communication network SINR |
| CN111145905A (en) * | 2019-12-31 | 2020-05-12 | 北京懿医云科技有限公司 | Target decision model construction method and device, electronic equipment and storage medium |
| WO2021012697A1 (en) * | 2019-07-23 | 2021-01-28 | 华为技术有限公司 | Training method, device, and system using mos model |
| CN112907254A (en) * | 2021-03-25 | 2021-06-04 | 中国建设银行股份有限公司 | Fraud transaction identification and model training method, device, equipment and storage medium |
| CN113382477A (en) * | 2021-05-14 | 2021-09-10 | 北京邮电大学 | Method for modeling uplink interference between wireless network users |
-
2022
- 2022-04-19 CN CN202210408256.0A patent/CN114745289A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017016472A1 (en) * | 2015-07-28 | 2017-02-02 | Huawei Technologies Co., Ltd. | Predicting network performance |
| 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 |
| CN110266412A (en) * | 2019-07-01 | 2019-09-20 | 中国电信股份有限公司 | The predictably method and apparatus of Tie Tong communication network SINR |
| WO2021012697A1 (en) * | 2019-07-23 | 2021-01-28 | 华为技术有限公司 | Training method, device, and system using mos model |
| CN111145905A (en) * | 2019-12-31 | 2020-05-12 | 北京懿医云科技有限公司 | Target decision model construction method and device, electronic equipment and storage medium |
| CN112907254A (en) * | 2021-03-25 | 2021-06-04 | 中国建设银行股份有限公司 | Fraud transaction identification and model training method, device, equipment and storage medium |
| CN113382477A (en) * | 2021-05-14 | 2021-09-10 | 北京邮电大学 | Method for modeling uplink interference between wireless network users |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115941991A (en) * | 2023-01-10 | 2023-04-07 | 北京微吼时代科技有限公司 | Method and system for verifying stability of message receiving under large concurrency |
| CN115941991B (en) * | 2023-01-10 | 2023-10-27 | 北京微吼时代科技有限公司 | Method and system for verifying stability of message collection under large concurrency |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104853379B (en) | A kind of quality of wireless network appraisal procedure and device | |
| CN111867049B (en) | Positioning method, positioning device and storage medium | |
| CN111817868B (en) | Method and device for positioning network quality abnormity | |
| CN108307427B (en) | LTE network coverage analysis and prediction method and system | |
| SE521227C2 (en) | Mobile radio system and a method for channel allocation in a mobile radio system | |
| CN108738064B (en) | Uplink interference positioning method and device | |
| CN113382477B (en) | Method for modeling uplink interference between wireless network users | |
| Raida et al. | Crowdsensed performance benchmarking of mobile networks | |
| CN109495413B (en) | Method for transmitting synchronization signal block, method for measuring cell quality, base station and terminal | |
| CN114745289A (en) | Method, device, storage medium and equipment for predicting network performance data | |
| CN109040744B (en) | Method, device and storage medium for predicting key quality index of video service | |
| CN112867147B (en) | Positioning method and positioning device | |
| CN112383936B (en) | Method and device for evaluating number of accessible users | |
| CN109981196B (en) | Network structure evaluation method and device | |
| CN109246610B (en) | Fingerprint base method for building up, localization method, device, server and storage medium | |
| CN112153679B (en) | Network switching method and device | |
| TW202123743A (en) | System and method for predicting customer complaint hot zone of mobile communication network | |
| EP4150861B1 (en) | Determining cell upgrade | |
| CN106879003B (en) | network optimization quality evaluation method and device | |
| US11758351B2 (en) | Determining geolocation of devices in a communication network | |
| US11743856B2 (en) | Determining geolocation of devices in a communication network | |
| CN106796277B (en) | Location adjustment in a mobile communication network | |
| CN115442814B (en) | Continuous weak coverage identification method and device, electronic equipment and storage medium | |
| CN113055924B (en) | Voice quality evaluation method and device and computer readable storage medium | |
| CN112312448B (en) | Method and device for evaluating RRC connection number |
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 |