CN103596214A - Method and device for analyzing data - Google Patents
Method and device for analyzing data Download PDFInfo
- Publication number
- CN103596214A CN103596214A CN201310618200.9A CN201310618200A CN103596214A CN 103596214 A CN103596214 A CN 103596214A CN 201310618200 A CN201310618200 A CN 201310618200A CN 103596214 A CN103596214 A CN 103596214A
- Authority
- CN
- China
- Prior art keywords
- index
- data
- type
- fitting
- fit equation
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a method and device for analyzing data so as to better evaluate and optimize the quality of a network, and relates to the technical field of data processing. The method includes the steps of obtaining multiple data sets from a network management platform, determining the type of a fitting curve, and conducting curve fitting on the multiple data sets according to the type of the fitting curve to obtain a target fitted equation, wherein each data set is composed of first index data and second index data, and the type of the fitting curve is used for representing for the corresponding relations between the first index data and the second index data. The method and the device are used for obtaining a scene of the fitted equation representing for the corresponding relations between indexes.
Description
Technical field
The present invention relates to technical field of data processing, relate in particular to a kind of method and apparatus of analyzing data.
Background technology
Along with commercial network constantly expands, adopt merely the optimal way of drive test can not meet work requirements.This is because the place that drive test can only arrive at vehicle is tested, and can only obtain the performance situation of test terminal on main roads etc.In the network maturity period, how to fully understand network performance, will start with and study from the network management data of magnanimity.
At present, network management data is mainly used in network operation maintenance, main by monitoring single index realization to the estimation of network quality or optimization.This have certain limitation by the realization of monitoring single index to the method for the estimation of network quality or optimization, causes the poor effect to the estimation of network quality or optimization.
Summary of the invention
The embodiment of the present invention provides a kind of method and apparatus of analyzing data, can to network quality, assess better and optimize.
First aspect, provides a kind of method of analyzing data, comprising:
From network management platform, obtain a plurality of data groups, described data group consists of the first achievement data and the second achievement data;
Determine the type of matched curve; The type of described matched curve is for representing the corresponding relation between described the first index and described the second index;
According to the type of described matched curve, described a plurality of data groups are carried out curve fitting, obtain target fit equation.
In conjunction with first aspect, in the possible implementation of the first, describedly from network management platform, obtain a plurality of data groups, comprising:
From network management platform, obtain a plurality of data groups in m community, m >=2, described m is integer;
Described according to the type of described matched curve, described a plurality of data groups are carried out curve fitting, obtain target fit equation, comprising:
According to the type ，Yi community of described matched curve, be unit, respectively a plurality of data groups in m community carried out curve fitting, obtain m middle fit equation;
Coefficient of the same type in described m middle fit equation is carried out to average computing, according to operation result, obtain target fit equation.
In conjunction with first aspect, in the possible implementation of the second, before the type of described definite matched curve, described method also comprises:
Obtain the scatter diagram being formed by described a plurality of data groups;
Show described scatter diagram, to point out user to determine the type of matched curve according to described scatter diagram.
In conjunction with first aspect, in the third possible implementation, described, according to the type of described matched curve, described a plurality of data groups are carried out curve fitting, after obtaining target fit equation, described method also comprises:
Obtain fitting index; Described fitting index is for weighing the fitting degree between described target fit equation and real data.
In conjunction with the possible implementation of the first of first aspect, first aspect to the third possible implementation any, described the first index is operational indicator, described the second index is Radio Resource index.
Second aspect, provides a kind of device of analyzing data, comprising:
Data capture unit, for obtain a plurality of data groups from network management platform, described data group consists of the first achievement data and the second achievement data;
Determining unit, for determining the type of matched curve; The type of described matched curve is for representing the corresponding relation between described the first index and described the second index;
Matching unit, for according to the type of described matched curve, carries out curve fitting to described a plurality of data groups, obtains target fit equation.
In conjunction with second aspect, in the possible implementation of the first,
Described data capture unit specifically for, from network management platform, obtain a plurality of data groups in m community, m >=2, described m is integer;
Described matching unit specifically for, according to the type ，Yi community of described matched curve, be unit, respectively a plurality of data groups in m community are carried out curve fitting, obtain fit equation in the middle of m; Coefficient of the same type in described m middle fit equation is carried out to average computing, according to operation result, obtain target fit equation.
In conjunction with second aspect, in the possible implementation of the second, described device also comprises:
Scatter diagram acquiring unit, for obtaining the scatter diagram consisting of described a plurality of data groups;
Display unit, for showing described scatter diagram, to point out user to determine the type of matched curve according to described scatter diagram.
In conjunction with second aspect, in the third possible implementation, described device also comprises:
Fitting index acquiring unit, for obtaining fitting index; Described fitting index is for weighing the fitting degree between described target fit equation and real data.
In conjunction with the possible implementation of the first of second aspect, second aspect to the third possible implementation any, described the first index is operational indicator, described the second index is Radio Resource index.
The method and apparatus of the analysis data that the embodiment of the present invention provides, by obtain a plurality of data groups that formed by the first achievement data and the second achievement data from network management platform, according to the type of determined matched curve, the plurality of data group is carried out curve fitting, obtain target fit equation, wherein, the type of matched curve is for representing the corresponding relation between the first index and the second index.This programme, by obtaining data from network management platform, obtains for representing the fit equation of corresponding relation between index, can to network quality, assess better and optimize.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, to the accompanying drawing of required use in embodiment or description of the Prior Art be briefly described below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skills, do not paying under the prerequisite of creative work, can also obtain according to these accompanying drawings other accompanying drawing.
A kind of schematic flow sheet of analyzing the method for data that Fig. 1 provides for the embodiment of the present invention;
The another kind that Fig. 2 provides for the embodiment of the present invention is analyzed the schematic flow sheet of the method for data
The schematic diagram of a kind of fitted figure that Fig. 3 provides for the embodiment of the present invention;
The schematic diagram of the another kind of fitted figure that Fig. 4 provides for the embodiment of the present invention;
A kind of structural representation of analyzing the device of data that Fig. 5 provides for the embodiment of the present invention;
The another kind that Fig. 6 provides for the embodiment of the present invention is analyzed the structural representation of the device of data;
The another kind that Fig. 7 provides for the embodiment of the present invention is analyzed the structural representation of the device of data.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is only the present invention's part embodiment, rather than whole embodiment.Embodiment based in the present invention, those of ordinary skills, not making the every other embodiment obtaining under creative work prerequisite, belong to the scope of protection of the invention.
Embodiment mono-
As shown in Figure 1, a kind of method of analyzing data for the embodiment of the present invention provides, comprising:
101: from network management platform, obtain a plurality of data groups, described data group consists of the first achievement data and the second achievement data.
Exemplary, network management platform can be: WCDMA(Wide band Code Division Multiple Access, Wideband-CDMA) network management platform, TD-SCDMA (Time Division-Synchronous Code Division Multiple Access, TD SDMA) network management platform, CDMA2000 (Code Division Multiple Access2000, CDMA 2000) network management platform etc.
The embodiment of the present invention does not limit the particular content of the first index and the second index.For example, the first index is operational indicator, and the second index is Radio Resource index.Operational indicator can be: service-user number, service rate, traffic carrying capacity, business throughput rate etc., wherein, service-user number is specifically as follows speech business number of users, HSDPA(High Speed Downlink Packet Access, high speed downlink packet access) service-user number etc.; Radio Resource (mainly referring to interface-free resources) index is specifically as follows: the lifting ROT situation of change of making an uproar of the end on up direction, carrier transmit power on down direction etc., wherein, the carrier transmit power on down direction comprises non-HSDPA(Non-HSPA, nonHS) power, HSDPA power.
And for example, the first index is RAB(Radio Access Bearer, RAB) request msg, the second index is business datum.Wherein, RAB request msg can be HSDPA RAB request number of times, non-HSDPA RAB request number of times, voice RAB request number of times etc.Business datum can be HSDPA throughput, non-HSDPA throughput, telephone traffic etc.
102: the type of determining matched curve; The type of described matched curve is for representing the corresponding relation between described the first index and described the second index.
Exemplary, the type of matched curve can comprise: logarithm type, linear-type, etc.
Optionally, user can rule of thumb determine the type of matched curve.Concrete, user determines the type of matched curve according to the pointer type of the pointer type of the first index and the second index.For example, at research HSDPA service-user number, with respect to the matching of HSDPA power, be related to scene, or research HSDPA business throughput rate is related in the example of scene with respect to the matching of HSDPA power, can selects logarithm type as the type of matched curve; And for example, in research HSDPA service-user number, speech business number of users, the example of RRC request number of times with respect to the scene of the matching relation of HSDPA power, can select linear-type as the type of matched curve.
In addition, user can also determine according to described scatter diagram the type of matched curve.In this scene, optional, before step 102, the method can also comprise: obtain the scatter diagram consisting of described a plurality of data groups; Show described scatter diagram, to point out user to determine the type of matched curve according to described scatter diagram.
103: according to the type of described matched curve, described a plurality of data groups are carried out curve fitting, obtain target fit equation.
Exemplary, described target fit equation is for representing the corresponding relation between described the first index and described the second index.
During specific implementation, can be soft by mathematical analysis, according to the type of described matched curve, described a plurality of data groups are carried out curve fitting, obtain target fit equation, wherein, mathematical analysis software can be: Matlab, Excel etc.These mathematical softwares provide matching tool box and matching order, can utilize method of the prior art, according to the type of described matched curve, described a plurality of data groups are carried out curve fitting, thereby draw (target) fit equation.
Usually, the dependent variable in (target) fit equation has one, and independent variable can have one or more; When need to be to (target) fit equation of the relatively same group independent variable of different dependent variables, can repeatedly perform step 101-103.
With concrete example, the relation between the first index, the second index, independent variable, dependent variable is described below:
1) 1 independent variable, the scene of 1 dependent variable
For example, in the scene of corresponding relation of studying HSDPA service-user number and HSDPA power, the first index can be HSDPA service-user number, and the second index can be HSDPA power; Independent variable can be HSDPA service-user number, and dependent variable can be HSDPA power.
And for example, in the scene of corresponding relation of studying HSDPA business throughput rate and HSDPA power, the first index can be HSDPA business throughput rate, and the second index can be HSDPA power; Independent variable can be HSDPA business throughput rate, and dependent variable can be HSDPA power.
2) a plurality of independents variable, the scene of 1 dependent variable
For example, in the scene of corresponding relation of studying speech business number of users and non-HSDPA power, the first index can be speech business number of users, the second index can be non-HSDPA power, independent variable can be speech business number of users, HSDPA service-user number, RRC(Radio Resource Control, radio resource control) request number of times, dependent variable can be non-HSDPA power.
In one embodiment of the invention, step 101 can comprise: from network management platform, obtain a plurality of data groups in m community, and m >=2, described m is integer.
In this situation, step 103 specifically can comprise:
According to the type ，Yi community of described matched curve, be unit, respectively a plurality of data groups in m community carried out curve fitting, obtain m middle fit equation;
Coefficient of the same type in described m middle fit equation is carried out to average computing, according to operation result, obtain target fit equation.
Optionally, after step 103, the method can also comprise: obtain fitting index; Described fitting index is for weighing the fitting degree between described target fit equation and real data.
The method of the analysis data that the embodiment of the present invention provides, by obtain a plurality of data groups that formed by the first achievement data and the second achievement data from network management platform, according to the type of determined matched curve, the plurality of data group is carried out curve fitting, obtain target fit equation, wherein, the type of matched curve is for representing the corresponding relation between the first index and the second index.This programme, by obtaining data from network management platform, obtains for representing the fit equation of corresponding relation between index, can to network quality, assess better and optimize.
Embodiment bis-
As shown in Figure 2, the another kind providing for the embodiment of the present invention is analyzed the method for data, comprising:
201: from network management platform, obtain a plurality of data groups in m community, m >=2, m is integer, data group consists of the first achievement data and the second achievement data.
Exemplary, this m community can be same panel region Zhong community.During specific implementation, step 201 can be: from network management platform, obtain in the time period a plurality of data groups in m community.
As shown in table 1, for obtain a plurality of data groups in Yi Ge community from network management platform:
Table 1
Further, step 201 can be called to sampling process.In order to guarantee good fitting effect, make the error between target fitting function and real data less, performing step at 201 o'clock, can follow following rule:
Rule 1: sampled data is many.Be embodied as: the quantity of the data group of obtaining is many.Usually, the quantity of data group is larger, and fitting effect is better.
Rule 2: the sampling time is long.In different time sections, the impact due to the factors such as variation of number of users, may cause network performance to change a lot, and therefore, usually, the sampling time is longer, and fitting effect is better, for example, can select the data group in 10 * 24 hours.
Rule 3: sample range is wide.Be embodied as: the quantity of the community of sampling is many.Because the network performance of different districts may be different, in a plurality of communities, sample, can reduce the impact of single subdistrict on overall fit effect.
202: determine the type of matched curve, the type of matched curve is for representing the corresponding relation between the first index and the second index.
203: according to the type ，Yi community of matched curve, be unit, respectively a plurality of data groups in m community carried out curve fitting, obtain m middle fit equation, and obtain the fitting index of each middle fit equation.
Exemplary, the type of the matched curve of using in the process carrying out curve fitting due to the data in m community is identical, and therefore, the difference of fit equation is embodied in the difference of coefficient and/or the constant of each independent variable in the middle of the m obtaining.
Fitting index, for weighing the fitting degree between target fit equation and real data, is specifically as follows: matching Coefficient of determination R
2deng.With R
2for example describes, R
2the analytic ability of expression to variable, this value is more close to 1, represents byer force to the analytic ability of variable, illustrates that (centre) fit equation gets over close to real data.
It should be noted that, during specific implementation, in the process of utilizing mathematical analysis software to carry out curve fitting, can directly obtain Coefficient of determination R
2.Corresponding (centre) fit equation in one community, therefore, can this be called fitting index corresponding to (centre) fit equation the fitting index in this enemy camp, community.
As shown in table 2, fit equation in the middle of obtain for step 203 m:
Table 2
| Community (cell) | Middle fit equation |
| Community 1 | y1=f 1(x1,x2,…,xi…) |
| Community 2 | y2=f 2(x1,x2,…,xi…) |
| …… | ? |
| Cell i | yi=f i(x1,x2,…,xi…) |
| …… | …… |
| Community m | ym=f m(x1,x2,…,xi…) |
204: the coefficient of the same type in m middle fit equation is carried out to average computing, according to operation result, obtain target fit equation.
Exemplary, coefficient of the same type specifically refers to coefficient or the constant of same independent variable.For example,, about two equation: y1=a of y=f (x1, x2)
1x1+b
1x2+c
1and y2=a
2x1+b
2x2+c
2in, the coefficient a of independent variable x1
1and a
2for coefficient of the same type, the coefficient b of x2
1and b
2for coefficient of the same type, constant c
1and c
2for coefficient of the same type.
In this example, step 205 is specially: to a
1and a
2carry out average computing, obtain
to b
1and b
2carry out average computing, obtain
to c
1and c
2carry out average computing, obtain
The target fit equation of obtaining is specially:
205: judge whether fitting index reaches re-set target.
If so, finish.If not, return to step 202.
Exemplary, take fitting index as matching Coefficient of determination R
2describe, step 205 is specifically as follows: judgement R
2whether be greater than predetermined threshold value.Wherein, predetermined threshold value can be for arranging based on experience value.If the determination result is NO, in description of step 202, the type of definite matched curve is unreasonable, can carry out revise goal fitting function by redefining matched curve.
It should be noted that, if the type of definite matched curve is unreasonable in step 202, major part in the m obtaining in above-mentioned steps 203 fitting index all can not reach re-set target, step 205 is specifically as follows: judge whether most of fitting index reaches re-set target, the concrete numerical value of " major part " here does not limit, can be according to actual needs or empirical value arrange.
Optionally, the method can also comprise: show the fitted figure that each community is corresponding, and specifically can be with reference to Fig. 3 of following embodiment 2 and Fig. 4 of embodiment 3.
The method of the analysis data that the embodiment of the present invention provides, by obtain a plurality of data groups that formed by the first achievement data and the second achievement data from network management platform, according to the type of determined matched curve, the plurality of data group is carried out curve fitting, obtain target fit equation, wherein, the type of matched curve is for representing the corresponding relation between the first index and the second index.This programme, by obtaining data from network management platform, obtains for representing the fit equation of corresponding relation between index, can to network quality, assess better and optimize.
With concrete example, show the analysis result that the method for data obtains according to the above analysis below.
Embodiment 1
In the present embodiment, study the corresponding relation of the descending power of speech business number of users and consumption.Choose 30Ge community as sample range, take half an hour as granularity, gathered the achievement datas such as AMR speech business number of users, HSDPA service-user number, RRC request number of times, descending non-HSDPA power and carried out curve fitting, corresponding middle fit equation and the Coefficient of determination R in part community obtaining
2as shown in table 3:
Table 3
| Community | Coefficient of determination R2 | Middle fit equation |
| Community 1 | 0.9384 | y=0.3439+0.3307a+0.2600b-0.0007c |
| Community 2 | 0.9334 | y=0.0821+0.3293a+0.1677b |
| Community 3 | 0.9109 | y=0.5420+0.3262a+0.2511b+0.0001c |
| Community 4 | 0.9051 | y=0.7446+0.3284a+0.1515b-0.0008 |
| Community | ||
| 5 | 0.9022 | y=0.5854+0.3695a+0.2758b-0.0005c |
| Community 6 | 0.8566 | y=-0.0283+0.3456a+0.0622b+0.0012c |
| Community 7 | 0.912 | y=0.8393+0.3923a+0.3019b-0.0007c |
| Community 8 | 0.9342 | y=-0.4261+0.2943a+0.2860b+0.0004c |
Wherein, dependent variable y is descending non-HSDPA power, and independent variable a is speech business number of users, and independent variable b is HSDPA service-user number, and independent variable c is RRC request number of times.
Definite coefficients R that the matching of ，Ge community obtains as shown in Table 3
2mostly, more than 0.9, illustrate that fitting effect is better.The power (being the coefficient before independent variable a) that each voice user consumes roughly, in 0.32 fluctuation up and down, can determine that the power of voice user and consumption exists linear relationship thus, and the general power consuming of each voice user is 0.32W.
Embodiment 2
In the present embodiment, study the corresponding relation of HSDPA service-user number and descending HSDPA power.The middle fit equation that part community is corresponding and Coefficient of determination R
2as shown in table 4:
Table 4
| Community | Coefficient of determination R 2 | Middle fit equation |
| Community 1 | 0.8066 | y=4.814*log(x)+20.52 |
| Community 2 | 0.7747 | y=5.125*log(x)+18.14 |
| Community 3 | 0.8281 | y=6.265*log(x)+19.39 |
| Community 4 | 0.7365 | y=5.140*log(x)+23.14 |
| |
0.7457 | y=5.507*log(x)+19.23 |
| Community 6 | 0.7682 | y=5.094*log(x)+22.15 |
| Community 7 | 0.781 | y=4.999*log(x)+19.95 |
| Community 8 | 0.7339 | y=5.279*log(x)+19.93 |
| Community 9 | 0.654 | y=5.565*log(x)+20.11 |
| |
0.7182 | y=5.796*log(x)+21.70 |
Wherein, dependent variable y is descending HSDPA power (dBm of unit), and independent variable x is HSDPA service-user number.As shown in Table 4, HSDPA service-user number and descending HSDPA power are roughly logarithmic relationship, and after averaging computing, the target fit equation obtaining is roughly: y=5.36*log (x)+20.43.
In addition, as shown in Figure 3, be the fitted figure of table 4 small area 1 correspondence, abscissa represents HSDPA service-user number, ordinate represents descending HSDPA power.As shown in Figure 3, along with the increase of HSDPA service-user number, the descending HSDPA power of consumption increases thereupon.
Embodiment 3
In the present embodiment, study the corresponding relation of HSDPA throughput and descending HSDPA power.The middle fit equation that part community is corresponding and Coefficient of determination R
2as shown in table 5:
Table 5
| Community | Coefficient of determination R 2 | Middle fit equation |
| Community 1 | 0.8668 | y=3.793*log(x)+39.74 |
| Community 2 | 0.9273 | y=3.830*log(x)+36.28 |
| Community 3 | 0.8843 | y=4.173*log(x)+40.61 |
| Community 4 | 0.899 | y=3.566*log(x)+39.64 |
| |
0.9386 | y=3.592*log(x)+37.67 |
| Community 6 | 0.8864 | y=3.581*log(x)+39.59 |
| Community 7 | 0.9415 | y=3.866*log(x)+37.87 |
| Community 8 | 0.9095 | y=3.547*log(x)+36.64 |
| Community 9 | 0.9507 | y=3.716*log(x)+37.90 |
| |
0.7477 | y=3.851*log(x)+38.71 |
Wherein, dependent variable y is descending HSDPA power (dBm of unit), and independent variable x is HSDPA throughput (Mbps of unit).As shown in Table 5, HSDPA throughput and descending HSDPA power are roughly logarithmic relationship, and after averaging computing, the target fit equation obtaining is roughly: y=3.55*log (x)+38.47.
In addition, as shown in Figure 4, be the fitted figure of table 3 small area 1 correspondence, abscissa represents HSDPA throughput, ordinate represents descending HSDPA power.As shown in Figure 4, along with the increase of HSDPA throughput, the descending HSDPA power of consumption increases thereupon.
Embodiment tri-
As shown in Figure 5, be a kind of device 50 of analyzing data that the embodiment of the present invention provides, in order to the method for the analysis data shown in execution graph 1, this device 50 comprises:
Determining unit 52, for determining the type of matched curve; The type of described matched curve is for representing the corresponding relation between described the first index and described the second index;
Matching unit 53, for according to the type of described matched curve, carries out curve fitting to described a plurality of data groups, obtains target fit equation.
Optionally, described data capture unit 51 specifically for, from network management platform, obtain a plurality of data groups in m community, m >=2, described m is integer;
Described matching unit 53 specifically for, according to the type ，Yi community of described matched curve, be unit, respectively a plurality of data groups in m community are carried out curve fitting, obtain fit equation in the middle of m; Coefficient of the same type in described m middle fit equation is carried out to average computing, according to operation result, obtain target fit equation.
Optionally, as shown in Figure 6, described device 51 also comprises:
Scatter diagram acquiring unit 54, for obtaining the scatter diagram consisting of described a plurality of data groups;
Display unit 55, for showing described scatter diagram, to point out user to determine the type of matched curve according to described scatter diagram.
Optionally, as shown in Figure 6, described device 51 also comprises:
Fitting index acquiring unit 56, for obtaining fitting index; Described fitting index is for weighing the fitting degree between described target fit equation and real data.
Optionally, described the first index is operational indicator, and described the second index is Radio Resource index.
The device of the analysis data that the embodiment of the present invention provides, by obtain a plurality of data groups that formed by the first achievement data and the second achievement data from network management platform, according to the type of determined matched curve, the plurality of data group is carried out curve fitting, obtain target fit equation, wherein, the type of matched curve is for representing the corresponding relation between the first index and the second index.This programme, by obtaining data from network management platform, obtains for representing the fit equation of corresponding relation between index, can to network quality, assess better and optimize.
Embodiment tetra-
As shown in Figure 7, be a kind of device 50 of analyzing data that the embodiment of the present invention provides, in order to the method for the analysis data shown in execution graph 1, this device 50 comprises: memory 71 and processor 72, wherein,
Memory 71 is for storing one group of code, and this code is carried out following action for control processor:
From network management platform, obtain a plurality of data groups, described data group consists of the first achievement data and the second achievement data;
Determine the type of matched curve; The type of described matched curve is for representing the corresponding relation between described the first index and described the second index;
According to the type of described matched curve, described a plurality of data groups are carried out curve fitting, obtain target fit equation.
Optionally, processor 72 specifically for, from network management platform, obtain a plurality of data groups in m community, m >=2, described m is integer;
Optionally, processor 72 also for, obtain the scatter diagram being formed by described a plurality of data groups; Show described scatter diagram, to point out user to determine the type of matched curve according to described scatter diagram.
Optionally, processor 72 also for, obtain fitting index; Described fitting index is for weighing the fitting degree between described target fit equation and real data.
Optionally, described the first index is operational indicator, and described the second index is Radio Resource index.
The device of the analysis data that the embodiment of the present invention provides, by obtain a plurality of data groups that formed by the first achievement data and the second achievement data from network management platform, according to the type of determined matched curve, the plurality of data group is carried out curve fitting, obtain target fit equation, wherein, the type of matched curve is for representing the corresponding relation between the first index and the second index.This programme, by obtaining data from network management platform, obtains for representing the fit equation of corresponding relation between index, can to network quality, assess better and optimize.
Those skilled in the art can be well understood to, for convenience and simplicity of description, the system of foregoing description, the specific works process of device and unit, can, with reference to the corresponding process in preceding method embodiment, not repeat them here.
In the several embodiment that provide in the application, should be understood that, disclosed system, apparatus and method, can realize by another way.For example, device embodiment described above is only schematic, for example, the division of described unit, be only that a kind of logic function is divided, during actual realization, can have other dividing mode, for example a plurality of unit or assembly can in conjunction with or can be integrated into another system, or some features can ignore, or do not carry out.Another point, shown or discussed coupling each other or direct-coupling or communication connection can be by some interfaces, indirect coupling or the communication connection of device or unit can be electrically, machinery or other form.
The described unit as separating component explanation can or can not be also physically to separate, and the parts that show as unit can be or can not be also physical locations, can be positioned at a place, or also can be distributed in a plurality of network element.Can select according to the actual needs some or all of unit wherein to realize the object of the present embodiment scheme.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, can be also that the independent physics of unit comprises, also can be integrated in a unit two or more unit.Above-mentioned integrated unit both can adopt the form of hardware to realize, and the form that also can adopt hardware to add SFU software functional unit realizes.
The integrated unit that the above-mentioned form with SFU software functional unit realizes, can be stored in a computer read/write memory medium.Above-mentioned SFU software functional unit is stored in a storage medium, comprise some instructions with so that computer equipment (can be personal computer, server, or the network equipment etc.) carry out the part steps of method described in each embodiment of the present invention.And aforesaid storage medium comprises: USB flash disk, portable hard drive, ROM(Read-Only Memory, read-only memory), RAM(Random Access Memory, random access memory), the various media that can be program code stored such as magnetic disc or CD.
Finally it should be noted that: above embodiment only, in order to technical scheme of the present invention to be described, is not intended to limit; Although the present invention is had been described in detail with reference to previous embodiment, those of ordinary skill in the art is to be understood that: its technical scheme that still can record aforementioned each embodiment is modified, or part technical characterictic is wherein equal to replacement; And these modifications or replacement do not make the essence of appropriate technical solution depart from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (10)
1. a method of analyzing data, is characterized in that, comprising:
From network management platform, obtain a plurality of data groups, described data group consists of the first achievement data and the second achievement data;
Determine the type of matched curve; The type of described matched curve is for representing the corresponding relation between described the first index and described the second index;
According to the type of described matched curve, described a plurality of data groups are carried out curve fitting, obtain target fit equation.
2. method according to claim 1, is characterized in that, describedly from network management platform, obtains a plurality of data groups, comprising:
From network management platform, obtain a plurality of data groups in m community, m >=2, described m is integer;
Described according to the type of described matched curve, described a plurality of data groups are carried out curve fitting, obtain target fit equation, comprising:
According to the type ，Yi community of described matched curve, be unit, respectively a plurality of data groups in m community carried out curve fitting, obtain m middle fit equation;
Coefficient of the same type in described m middle fit equation is carried out to average computing, according to operation result, obtain target fit equation.
3. method according to claim 1, is characterized in that, before the type of described definite matched curve, described method also comprises:
Obtain the scatter diagram being formed by described a plurality of data groups;
Show described scatter diagram, to point out user to determine the type of matched curve according to described scatter diagram.
4. method according to claim 1, is characterized in that, described, according to the type of described matched curve, described a plurality of data groups is carried out curve fitting, and after obtaining target fit equation, described method also comprises:
Obtain fitting index; Described fitting index is for weighing the fitting degree between described target fit equation and real data.
5. according to the method described in claim 1-4 any one, it is characterized in that, described the first index is operational indicator, and described the second index is Radio Resource index.
6. a device of analyzing data, is characterized in that, comprising:
Data capture unit, for obtain a plurality of data groups from network management platform, described data group consists of the first achievement data and the second achievement data;
Determining unit, for determining the type of matched curve; The type of described matched curve is for representing the corresponding relation between described the first index and described the second index;
Matching unit, for according to the type of described matched curve, carries out curve fitting to described a plurality of data groups, obtains target fit equation.
7. device according to claim 6, is characterized in that,
Described data capture unit specifically for, from network management platform, obtain a plurality of data groups in m community, m >=2, described m is integer;
Described matching unit specifically for, according to the type ，Yi community of described matched curve, be unit, respectively a plurality of data groups in m community are carried out curve fitting, obtain fit equation in the middle of m; Coefficient of the same type in described m middle fit equation is carried out to average computing, according to operation result, obtain target fit equation.
8. device according to claim 6, is characterized in that, described device also comprises:
Scatter diagram acquiring unit, for obtaining the scatter diagram consisting of described a plurality of data groups;
Display unit, for showing described scatter diagram, to point out user to determine the type of matched curve according to described scatter diagram.
9. device according to claim 6, is characterized in that, described device also comprises:
Fitting index acquiring unit, for obtaining fitting index; Described fitting index is for weighing the fitting degree between described target fit equation and real data.
10. according to the device described in claim 6-9 any one, it is characterized in that, described the first index is operational indicator, and described the second index is Radio Resource index.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310618200.9A CN103596214A (en) | 2013-11-28 | 2013-11-28 | Method and device for analyzing data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310618200.9A CN103596214A (en) | 2013-11-28 | 2013-11-28 | Method and device for analyzing data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103596214A true CN103596214A (en) | 2014-02-19 |
Family
ID=50086152
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310618200.9A Pending CN103596214A (en) | 2013-11-28 | 2013-11-28 | Method and device for analyzing data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103596214A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105656709A (en) * | 2014-11-21 | 2016-06-08 | 中国移动通信集团广东有限公司 | Method and apparatus for predicting capacity of packet domain network |
| CN106598914A (en) * | 2015-10-15 | 2017-04-26 | 北京国双科技有限公司 | Data processing method and device |
| CN106879003A (en) * | 2015-12-11 | 2017-06-20 | 中国移动通信集团山东有限公司 | A network optimization quality assessment method and device |
| CN112953538A (en) * | 2021-02-23 | 2021-06-11 | 青岛鼎信通讯股份有限公司 | ADC calibration method applied to direct current meter calibrating device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080298303A1 (en) * | 2007-01-22 | 2008-12-04 | Qualcomm Incorporated | Multi-link support for network based mobility management systems |
| CN102300240A (en) * | 2011-08-26 | 2011-12-28 | 北京邮电大学 | Output performance parameter-based method for evaluating similarity of two systems |
| CN102958088A (en) * | 2012-12-03 | 2013-03-06 | 大唐电信科技股份有限公司 | Monitoring and evaluating system of WLAN (Wireless Local Area Network) wireless network |
| CN103298021A (en) * | 2013-05-31 | 2013-09-11 | 中国联合网络通信集团有限公司 | Method and device for predicting power resource consumption |
-
2013
- 2013-11-28 CN CN201310618200.9A patent/CN103596214A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080298303A1 (en) * | 2007-01-22 | 2008-12-04 | Qualcomm Incorporated | Multi-link support for network based mobility management systems |
| CN102300240A (en) * | 2011-08-26 | 2011-12-28 | 北京邮电大学 | Output performance parameter-based method for evaluating similarity of two systems |
| CN102958088A (en) * | 2012-12-03 | 2013-03-06 | 大唐电信科技股份有限公司 | Monitoring and evaluating system of WLAN (Wireless Local Area Network) wireless network |
| CN103298021A (en) * | 2013-05-31 | 2013-09-11 | 中国联合网络通信集团有限公司 | Method and device for predicting power resource consumption |
Non-Patent Citations (1)
| Title |
|---|
| 钟玲: "基于网管数据的WCDMA无线资源利用率计算方法研", 《北京邮电大学专业学位硕士学位论文》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105656709A (en) * | 2014-11-21 | 2016-06-08 | 中国移动通信集团广东有限公司 | Method and apparatus for predicting capacity of packet domain network |
| CN105656709B (en) * | 2014-11-21 | 2020-02-18 | 中国移动通信集团广东有限公司 | Method and device for predicting network capacity in packet domain |
| CN106598914A (en) * | 2015-10-15 | 2017-04-26 | 北京国双科技有限公司 | Data processing method and device |
| CN106879003A (en) * | 2015-12-11 | 2017-06-20 | 中国移动通信集团山东有限公司 | A network optimization quality assessment method and device |
| CN106879003B (en) * | 2015-12-11 | 2019-12-10 | 中国移动通信集团山东有限公司 | network optimization quality evaluation method and device |
| CN112953538A (en) * | 2021-02-23 | 2021-06-11 | 青岛鼎信通讯股份有限公司 | ADC calibration method applied to direct current meter calibrating device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106897109B (en) | Virtual machine performance prediction method based on random forest regression | |
| KR100921618B1 (en) | Technology evaluation method for technology start-up companies | |
| CN104090912A (en) | Information pushing method and device | |
| CN105607952B (en) | Method and device for scheduling virtualized resources | |
| CN109462853B (en) | Network capacity prediction method based on neural network model | |
| CN103596214A (en) | Method and device for analyzing data | |
| CN109830246B (en) | Audio quality appraisal procedure, device, electronic equipment and storage medium | |
| CN105869022B (en) | Application popularity prediction method and device | |
| CN110381151A (en) | A kind of warping apparatus detection method and device | |
| CN110728306B (en) | Target parameter selection method in reverse proxy evaluation model and related device | |
| CN111488994A (en) | Positive sample learning model evaluation method and device | |
| CN105224558A (en) | The evaluation disposal route of speech business and device | |
| CN117435025B (en) | Intelligent wearable device data processing method and system based on multi-source data | |
| CN109995549A (en) | A method and device for evaluating traffic value | |
| CN111311393A (en) | Credit risk assessment method, device, server and storage medium | |
| CN110673788A (en) | Data reading method, device and equipment of solid state disk and readable storage medium | |
| CN109583685B (en) | Terminal evaluation method, device, computer equipment and storage medium | |
| CN109495900B (en) | Capacity expansion method and device and computer readable storage medium | |
| CN111625720A (en) | Method, device, equipment and medium for determining data decision item execution strategy | |
| CN113205231B (en) | Off-network prediction method and device | |
| CN113469576B (en) | High-load cell identification method, device, storage medium and electronic device | |
| CN114792138B (en) | Machine learning model interpretation method, device and storage medium | |
| CN110147443A (en) | Topic classification evaluation method and device | |
| CN118043769A (en) | Air conditioner and control system thereof | |
| CN113640673A (en) | Method and device for predicting service life of lead-acid storage battery |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20140219 |