CN116761185A - Method, system and medium for predicting daily active users based on signaling - Google Patents
Method, system and medium for predicting daily active users based on signaling Download PDFInfo
- Publication number
- CN116761185A CN116761185A CN202311047789.1A CN202311047789A CN116761185A CN 116761185 A CN116761185 A CN 116761185A CN 202311047789 A CN202311047789 A CN 202311047789A CN 116761185 A CN116761185 A CN 116761185A
- Authority
- CN
- China
- Prior art keywords
- active user
- data
- active
- signaling
- model
- 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
- 230000011664 signaling Effects 0.000 title claims abstract description 70
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000012360 testing method Methods 0.000 claims abstract description 26
- 238000013112 stability test Methods 0.000 claims abstract description 23
- 230000009471 action Effects 0.000 claims description 20
- 238000013439 planning Methods 0.000 abstract description 10
- 238000001514 detection method Methods 0.000 description 18
- 238000005311 autocorrelation function Methods 0.000 description 10
- 230000000694 effects Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 241001123248 Arma Species 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
- H04W16/18—Network planning tools
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/06—Testing, supervising or monitoring using simulated traffic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/029—Location-based management or tracking services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2123/00—Data types
- G06F2123/02—Data types in the time domain, e.g. time-series data
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Telephonic Communication Services (AREA)
Abstract
The application provides a method, a system and a medium for predicting daily active users based on signaling, wherein the method comprises the following steps: acquiring a first active user value corresponding to a target area, wherein the first active user value is the number of active users in a first time period, and the active users are mobile equipment generating signaling in the target area; performing stability test on the first active user value; when the test result is stable, performing white noise test on first data, wherein the first data is stable after the first active user value is subjected to the stability test; when the first data is a non-white noise sequence, determining a time sequence model corresponding to the first data; acquiring a second active user value based on the time sequence model, wherein the second active user value is the predicted number of the active users in a second time period; thus predicting the daily active user value of a specific area and providing important reference value for planning cities and regions.
Description
Technical Field
The application relates to the technical field of communication, in particular to a method, a system and a medium for predicting daily active users based on signaling.
Background
Population distribution is one of important contents of urban theoretical research, population is continuously gathered in cities, space patterns of urban population are remodeled, urban expansion and urban transformation are promoted, new requirements are brought to urban public resource allocation, and new challenges are brought to urban planning and management. Therefore, predicting daily active users in a particular area can provide important reference value for planning cities and regions.
A solution is needed to address the above-mentioned problems.
Disclosure of Invention
The application aims to provide a method, a system and a medium for predicting daily active users based on signaling, wherein the first active user value is the number of active users in a first time period and is a mobile device generating signaling in a target area according to the acquired first active user value corresponding to the target area, the first active user value is subjected to stability test, white noise test is carried out on first data when a test result is stable, the first data is the data which is stable after the first active user value is subjected to the stability test, then a time sequence model corresponding to the first data is determined when the first data is a non-white noise sequence, a second active user value is acquired based on the time sequence model, and the second active user value is the predicted number of active users in a second time period and is the same as the time interval of the first time period. The application aims to predict the daily active user value of a specific area, namely a target area, and provides important reference value for planning cities and regions.
The first aspect of the present application provides a method for predicting daily active users based on signaling, comprising the following steps:
acquiring a first active user value corresponding to a target area, wherein the first active user value is the number of active users in a first time period, and the active users are mobile equipment generating signaling in the target area;
performing stability test on the first active user value;
when the test result is stable, performing white noise test on first data, wherein the first data is stable after the first active user value is subjected to the stability test;
when the first data is a non-white noise sequence, determining a time sequence model corresponding to the first data;
and acquiring a second active user value based on the time sequence model, wherein the second active user value is the predicted number of the active users in a second time period.
Optionally, in the method for predicting daily active users based on signaling according to the present application, the obtaining a first active user value corresponding to the target area includes:
acquiring an action track of the active user in the first time period based on an international mobile user identification (IMSI) of the active user;
and performing deduplication statistics on the active users in the target area based on the action track to acquire the first active user value.
Optionally, in the method for predicting a daily active user based on signaling according to the present application, the determining a time sequence model corresponding to the first data includes:
determining model parameters corresponding to the first data;
a time series model is determined based on the model parameters.
Optionally, in the method for predicting a daily active user based on signaling according to the present application, the determining a model parameter corresponding to the first data includes:
when the first data is a non-white noise sequence, determining an autoregressive order and a moving average based on a red-pool information amount criterion and a Bayesian information amount criterion.
Optionally, in the method for predicting daily active users based on signaling according to the present application, the obtaining the second active user value based on the time sequence model includes:
obtaining a model residual sequence based on the time sequence model;
when it is verified that the model residual sequence is not a white noise sequence, the second active user value is predicted.
Optionally, in the method for predicting a daily active user based on signaling according to the present application, the determining a time sequence model corresponding to the first data includes:
the time series model is generated based on the first data and an expert modeler.
Optionally, in the method for predicting daily active users based on signaling according to the present application, after the performing the stability test on the first active user value, the method further includes:
and when the detection result is unstable, carrying out d times of difference on the detected unstable data, and then continuing to carry out stability detection.
In a second aspect, the present application provides a signaling-based prediction day-active user system, which is characterized in that the system includes: the memory comprises a program for predicting the daily active user based on the signaling, and the program for predicting the daily active user based on the signaling realizes the following steps when being executed by the processor:
acquiring a first active user value corresponding to a target area, wherein the first active user value is the number of active users in a first time period, and the active users are mobile equipment generating signaling in the target area;
performing stability test on the first active user value;
when the test result is stable, performing white noise test on first data, wherein the first data is stable after the first active user value is subjected to the stability test;
when the first data is a non-white noise sequence, determining a time sequence model corresponding to the first data;
and acquiring a second active user value based on the time sequence model, wherein the second active user value is the predicted number of the active users in a second time period.
Optionally, in the signaling-based active user system according to the present application, the obtaining the first active user value corresponding to the target area includes:
acquiring an action track of the active user in the first time period based on an international mobile user identification (IMSI) of the active user;
and performing deduplication statistics on the active users in the target area based on the action track to acquire the first active user value.
Optionally, in the signaling-based active daily user system according to the present application, the determining the time sequence model corresponding to the first data includes:
determining model parameters corresponding to the first data;
a time series model is determined based on the model parameters.
In a third aspect, the present application also provides a computer readable storage medium, where a method program for predicting a daily active user based on signaling is included, where the method program for predicting a daily active user based on signaling is executed by a processor, and the steps of a method for predicting a daily active user based on signaling according to any one of the above are implemented.
As can be seen from the above, the method, system and medium for predicting daily active users based on signaling provided by the present application firstly obtain a first active user value corresponding to a target area, where the first active user value is the number of active users in a first period of time, and the active users are mobile devices generating signaling in the target area. And then carrying out stability test on the obtained first active user value, carrying out white noise test on the data which are tested stably, namely the first data, when the test result is stable, and determining a time sequence model corresponding to the first data when the first data are tested to be a non-white noise sequence, and acquiring a second active user value based on the time sequence model. The application aims to predict the daily active user value of a specific area, namely a target area, and provides important reference value for planning cities and regions.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application. The objectives and other advantages of the application will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and should not be considered as limiting the scope, and other related drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for predicting a daily active user based on signaling according to an embodiment of the present application;
fig. 2 is a flowchart of a method for predicting a daily active user based on signaling to obtain a first active user value according to an embodiment of the present application;
FIG. 3 is a flowchart of a method for predicting a daily active user based on signaling according to an embodiment of the present application;
fig. 4 is an effect diagram of model fitting degree of a method for predicting a daily active user based on signaling according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a system for predicting daily active users based on signaling according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by a person skilled in the art without making any inventive effort, are intended to be within the scope of the present application.
It should be noted that like reference numerals and letters refer to like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
Referring to fig. 1, fig. 1 is a flowchart of a method for predicting daily active users based on signaling according to an embodiment of the present application. The method for predicting the daily active users based on the signaling is used in intelligent equipment, a computer or a terminal. The method for predicting the daily active users based on the signaling comprises the following steps:
s101, acquiring a first active user value corresponding to a target area.
And acquiring a first active user value corresponding to a target area, wherein the first active user value is the number of active users in a first time period, and the active users are mobile equipment generating signaling in the target area.
S102, performing stability test on the first active user value.
Specifically, stationarity means that the statistical properties of a sequence are not affected by the observation time, i.e., the mean, variance, autocorrelation coefficients, etc. do not change due to time variations. According to the embodiment of the application, the first active user value is subjected to stability test by a run length test method, and is found to be a stable time sequence.
S103, when the test result is stable, performing white noise test on the first data.
And when the test result is stable, performing white noise test on first data, wherein the first data is stable after the first active user value is subjected to the stability test.
The method includes the steps that after data are stable, white noise detection is carried out on the data, the white noise sequence is a completely random sequence, whether the data are the white noise sequence or not is verified by adopting an Ljung_Box detection method, the significance (P value) of Ljung_Box Q (18) statistics is smaller than 0.05 in the method, an original assumption is rejected, the sequence is a stable non-white noise sequence, and model identification is carried out to determine a corresponding time sequence model.
And S104, when the first data is a non-white noise sequence, determining a time sequence model corresponding to the first data.
S105, acquiring a second active user value based on the time sequence model.
And acquiring a second active user value based on the time sequence model, wherein the second active user value is the predicted number of the active users in a second time period.
It should be noted that, in order to predict daily active users in a specific area, an important reference value is provided for planning cities and regions, first, a first active user value corresponding to a target area is obtained, where the first active user value is the number of active users in a first period of time, and the active users are mobile devices generating signaling in the target area. And then carrying out stability test on the obtained first active user value, carrying out white noise test on the data which are tested stably, namely the first data, when the test result is stable, and determining a time sequence model corresponding to the first data when the first data are tested to be a non-white noise sequence, and acquiring a second active user value based on the time sequence model.
Optionally, in the method for predicting daily active users based on signaling according to the present application, after the performing the stability test on the first active user value, the method further includes:
and when the detection result is unstable, carrying out d times of difference on the detected unstable data, and then continuing to carry out stability detection.
When the numerical value of the first active user is not stable, carrying out d times of difference on the data after the detection, continuing to carry out stability detection, if the detection result is still not stable, continuing to carry out d times of difference, and carrying out stability detection until the detection result is stable, thereby obtaining the first data.
Referring to fig. 2, fig. 2 is a flowchart of a method for predicting a daily active user based on signaling to obtain a first active user value according to an embodiment of the present application. According to an embodiment of the present application, the obtaining a first active user value corresponding to a target area includes:
s201, acquiring an action track of the active user in the first time period based on an international mobile subscriber identity (international mobile subscriber identity, IMSI) of the active user.
Illustratively, the user, i.e. the mobile device, who has a signaling generation, i.e. captured, of at least one piece of location information in the statistical area, i.e. the target area, is an active user on the day. The historical value of the active user in the area can be used for early daily, and the value of the active user in the area, namely the second active user value, can be predicted quantitatively in the future daily. For example, dividing each area, such as a large area, a street town, a business district, a scenic spot, a park, etc., to form a daily action track of the mobile phone user on the basis of the original signaling, so long as the area captures at least one piece of signaling information of the mobile phone user on the same day, the mobile phone user is an active user of the ground. In addition, the mobile phone user information which does not meet the caliber of the active user can be deleted.
Specifically, signaling data of three operators can be utilized, in each normalized area, all base station sector information of each user IMSI, which includes sector position and in-out sector time information, is collected, and aiming at obtaining information of a mobile phone user or a smart watch real-time track, real-time signaling data is subscribed by using a Spark Streaming access Kafka message system, so that a mobile phone user or a smart watch daily action track is obtained.
S202, performing deduplication statistics on the active users in the target area based on the action track to obtain the first active user value.
After determining the action track of the mobile phone user or the smart watch in each day in the continuous time period, the first active user value in the first time period in the target area can be obtained after determining which areas the action track passes and performing deduplication statistics.
It should be noted that, directly obtain the action track of the active user in the first time period through the IMSI of the active user, and perform deduplication statistics on the active user in the target area based on the action track to obtain the first active user value, so that a relatively accurate historical active user value can be obtained, and the accuracy of the data is improved.
Referring to fig. 3, fig. 3 is a flowchart of a determining time sequence model of a method for predicting a daily active user based on signaling according to an embodiment of the present application. According to an embodiment of the present application, the determining a time sequence model corresponding to the first data includes:
s301, determining model parameters corresponding to the first data.
According to an embodiment of the present application, the determining the model parameter corresponding to the first data includes:
an autoregressive order and a moving average are determined based on the red pool information amount criterion and the bayesian information amount criterion.
Illustratively, when the first data is a non-white noise sequence, the autoregressive order p and the moving average term number q are determined by a red pool information amount criterion (akaike information criterion, AIC), a bayesian information amount criterion (bayesian information criterions, BIC) information criterion. It should be noted that, in order to avoid the occurrence of the over-fitting, the embodiment of the present application applies the AIC criterion and the BIC criterion to determine the optimal order.
In general, AIC can be expressed as:
wherein: k is the number of parameters and L is the likelihood function.
BIC can be expressed as:
wherein: k is the number of model parameters, n is the number of samples, and L is the likelihood function.
The order (p, q) that maximizes AIC and BIC is found as the best order.
Other parameters in the estimation model can be determined by using maximum likelihood estimation, a conditional least squares method, and the like.
It should be noted that, determining the autoregressive order and the moving average based on the red-pool information amount criterion and the bayesian information amount criterion can facilitate the subsequent determination of the time series model.
S302, determining a time sequence model based on the model parameters.
Illustratively, the model is identified as belonging to one of an autoregressive model (autoregressive model, AR), a moving average model (moving average model, MA), and an autoregressive moving average model (auto-regressive moving average model, ARMA) based on the autoregressive order p and the moving average term q.
Typically, if the autocorrelation function (autocorrelation function, ACF) is tailing, the partial autocorrelation function (partial autocorrelation function, PACF) models the AR (p) when the p-order is truncated;
if the autocorrelation function ACF is truncated at the q-order, and the partial autocorrelation function PACF is trailing, establishing an MA (q) model;
if the ACF and PACF are both trailing, the most significant order in the ACF graph is taken as q value, and the most significant order in the PACF graph is taken as p value, an ARMA (p, q) model is established.
After the parameters are determined, the following models are obtained respectively:
wherein, the p-order autoregressive model AR (p) is:
wherein:is a time sequence->White noise at point t, p is the autoregressive order.
The q-order moving average model MA (q) is:
wherein:is the number of moving average terms.
Autoregressive moving average model ARMA (p, q):
differential autoregressive moving average model ARIMA (p, d, q):
wherein the method comprises the steps ofTo perform the time series after d-order differential processing:
it should be noted that, determining the model parameters corresponding to the first data and determining the time-series model based on the model data, so as to determine a more suitable time-series model according to the first active user value.
According to an embodiment of the present application, the obtaining a second active user value based on the time-series model includes:
obtaining a model residual sequence based on the time sequence model;
when it is verified that the model residual sequence is not a white noise sequence, the second active user value is predicted.
Illustratively, it is checked whether the model residual sequence belongs to a white noise sequence. If the residual sequence is verified to be a white noise sequence, the useful information in the sequence is extracted, and the rest random disturbance cannot be predicted and analyzed. In the embodiment of the application, the significance (P value) of the ljung_boxq (18) statistic is=0.071, which is greater than 0.05, the original assumption is accepted, and the residual sequence is a white noise sequence. The R square is 0.727, the stable R square is 0.394, and the data fitting degree is high.
It should be noted that, when the model residual sequence is not the white noise sequence, the second active user value can be predicted, that is, the daily active user value can be predicted, so as to provide important reference value for planning cities and regions.
According to an embodiment of the present application, the determining a time sequence model corresponding to the first data includes:
the time series model is generated based on the first data and an expert modeler.
For example, in order to ensure that the constructed model effect is optimal, in the embodiment of the present application, an spis tool expert modeler is used to select an ARIMA model, and select a seasonal model to be considered, and a time-series model is automatically generated, and compared with the model in the step S302, in the ARIMA model generated by the expert modeler, the significance (P value) of the ljung_box q (18) statistic (P value) =0.307 is greater than 0.05, and both the R-side and the stationary R-side are 0.727, and compared with the model constructed in the step S302, the model data fitting degree is higher, the effect is better, part of model parameters are corrected again, so that the model fitting degree of the final construction is ensured to be optimal, and the fitting effect is as shown in fig. 4, and fig. 4 is an effect diagram of the model fitting degree of the method for predicting the day-active user based on signaling provided by the embodiment of the present application.
It should be noted that, the time series model generated by the expert modeler has higher fitting degree of the obtained second active user data, better effect and improved accuracy of predicting the daily active user value.
As shown in fig. 5, the present application further discloses a system 5 for predicting daily active users based on signaling, and fig. 5 is a schematic structural diagram of a system for predicting daily active users based on signaling provided by an embodiment of the present application, including a memory 51 and a processor 52, where the memory includes a method program for predicting daily active users based on signaling, where the method program for predicting daily active users based on signaling is executed by the processor to implement the following steps:
acquiring a first active user value corresponding to a target area, wherein the first active user value is the number of active users in a first time period, and the active users are mobile equipment generating signaling in the target area;
performing stability test on the first active user value;
when the test result is stable, performing white noise test on first data, wherein the first data is stable after the first active user value is subjected to the stability test;
when the first data is a non-white noise sequence, determining a time sequence model corresponding to the first data;
and acquiring a second active user value based on the time sequence model, wherein the second active user value is the predicted number of the active users in a second time period.
It should be noted that, in order to predict daily active users in a specific area, an important reference value is provided for planning cities and regions, first, a first active user value corresponding to a target area is obtained, where the first active user value is the number of active users in a first period of time, and the active users are mobile devices generating signaling in the target area. And then carrying out stability test on the obtained first active user value, carrying out white noise test on the data which are tested stably, namely the first data, when the test result is stable, and determining a time sequence model corresponding to the first data when the first data are tested to be a non-white noise sequence, and acquiring a second active user value based on the time sequence model.
According to an embodiment of the present application, the obtaining a first active user value corresponding to a target area includes:
acquiring an action track of the active user in the first time period based on an international mobile user identification (IMSI) of the active user;
and performing deduplication statistics on the active users in the target area based on the action track to acquire the first active user value.
It should be noted that, directly obtain the action track of the active user in the first time period through the IMSI of the active user, and perform deduplication statistics on the active user in the target area based on the action track to obtain the first active user value, so that a relatively accurate historical active user value can be obtained, and the accuracy of the data is improved.
According to an embodiment of the present application, the determining a time sequence model corresponding to the first data includes:
determining model parameters corresponding to the first data;
a time series model is determined based on the model parameters.
It should be noted that, determining the model parameters corresponding to the first data and determining the time-series model based on the model data, so as to determine a more suitable time-series model according to the first active user value.
According to an embodiment of the present application, the determining the model parameter corresponding to the first data includes:
an autoregressive order and a moving average are determined based on the red pool information amount criterion and the bayesian information amount criterion.
It should be noted that, determining the autoregressive order and the moving average based on the red pool information amount criterion and the bayesian information amount criterion may facilitate the subsequent determination of the time series model.
According to an embodiment of the present application, the obtaining a second active user value based on the time-series model includes:
obtaining a model residual sequence based on the time sequence model;
when it is verified that the model residual sequence is not a white noise sequence, the second active user value is predicted.
It should be noted that, when the model residual sequence is not the white noise sequence, the second active user value can be predicted, that is, the daily active user value can be predicted, so as to provide important reference value for planning cities and regions.
According to an embodiment of the present application, the determining a time sequence model corresponding to the first data includes:
the time series model is generated based on the first data and an expert modeler.
It should be noted that, the time series model generated by the expert modeler has higher fitting degree of the obtained second active user data, better effect and improved accuracy of predicting the daily active user value.
According to an embodiment of the present application, after the performing a stationarity check on the first active user value, the method further includes:
and when the detection result is unstable, carrying out d times of difference on the detected unstable data, and then continuing to carry out stability detection.
When the numerical value of the first active user is not stable, carrying out d times of difference on the data after the detection, continuing to carry out stability detection, if the detection result is still not stable, continuing to carry out d times of difference, and carrying out stability detection until the detection result is stable, thereby obtaining the first data.
A third aspect of the present application provides a readable storage medium having embodied therein a method program for predicting a daily active user based on signaling, which when executed by a processor, implements the steps of the method for predicting a daily active user based on signaling as described in any of the above.
The application provides a method, a system and a medium for predicting daily active users based on signaling, which are characterized in that first active user values corresponding to a target area are obtained, wherein the first active user values are the number of active users in a first time period, and the active users are mobile devices generating signaling in the target area. And then carrying out stability test on the obtained first active user value, carrying out white noise test on the data which are tested stably, namely the first data, when the test result is stable, and determining a time sequence model corresponding to the first data when the first data are tested to be a non-white noise sequence, and acquiring a second active user value based on the time sequence model. The application aims to predict the daily active user value of a specific area, namely a target area, and provides important reference value for planning cities and regions.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present application may be stored in a readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solution of the embodiments of the present application may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
Claims (10)
1. A method for predicting daily active users based on signaling, comprising the steps of:
acquiring a first active user value corresponding to a target area, wherein the first active user value is the number of active users in a first time period, and the active users are mobile equipment generating signaling in the target area;
performing stability test on the first active user value;
when the test result is stable, performing white noise test on first data, wherein the first data is stable after the first active user value is subjected to the stability test;
when the first data is a non-white noise sequence, determining a time sequence model corresponding to the first data;
and acquiring a second active user value based on the time sequence model, wherein the second active user value is the predicted number of the active users in a second time period.
2. The method for predicting daily active users based on signaling according to claim 1, wherein the obtaining the first active user value corresponding to the target area comprises:
acquiring an action track of the active user in the first time period based on an international mobile user identification (IMSI) of the active user;
and performing deduplication statistics on the active users in the target area based on the action track to acquire the first active user value.
3. The method for predicting a daily active user based on signaling according to claim 1 or 2, wherein the determining a time series model corresponding to the first data comprises:
determining model parameters corresponding to the first data;
a time series model is determined based on the model parameters.
4. The method for signaling-based prediction of a daily active user according to claim 3, wherein said determining model parameters corresponding to the first data comprises:
an autoregressive order and a moving average are determined based on the red pool information amount criterion and the bayesian information amount criterion.
5. The method for signaling-based prediction of a daily active user as recited in claim 4, wherein the obtaining a second active user value based on the time series model comprises:
obtaining a model residual sequence based on the time sequence model;
when it is verified that the model residual sequence is not a white noise sequence, the second active user value is predicted.
6. The method for predicting a daily active user based on signaling according to claim 1 or 2, wherein the determining a time series model corresponding to the first data comprises:
the time series model is generated based on the first data and an expert modeler.
7. A signaling-based prediction day-active user system, the system comprising: the memory comprises a program for predicting the daily active user based on the signaling, and the program for predicting the daily active user based on the signaling realizes the following steps when being executed by the processor:
acquiring a first active user value corresponding to a target area, wherein the first active user value is the number of active users in a first time period, and the active users are mobile equipment generating signaling in the target area;
performing stability test on the first active user value;
when the test result is stable, performing white noise test on first data, wherein the first data is stable after the stability test;
when the first data is a non-white noise sequence, determining a time sequence model corresponding to the first data;
and acquiring a second active user value based on the time sequence model, wherein the second active user value is the predicted number of the active users in a second time period.
8. The signaling-based active user system of claim 7, wherein the obtaining the first active user value corresponding to the target area comprises:
acquiring an action track of the active user in the first time period based on an international mobile user identification (IMSI) of the active user;
and performing deduplication statistics on the active users in the target area based on the action track to acquire the first active user value.
9. A signalling based prediction day active user system as claimed in claim 7 or 8, wherein said determining a time series model to which said first data corresponds comprises:
determining model parameters corresponding to the first data;
a time series model is determined based on the model parameters.
10. Computer readable storage medium, characterized in that it comprises a method program for predicting active users based on signaling, which, when being executed by a processor, implements the steps of the method for predicting active users based on signaling according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311047789.1A CN116761185A (en) | 2023-08-21 | 2023-08-21 | Method, system and medium for predicting daily active users based on signaling |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311047789.1A CN116761185A (en) | 2023-08-21 | 2023-08-21 | Method, system and medium for predicting daily active users based on signaling |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116761185A true CN116761185A (en) | 2023-09-15 |
Family
ID=87948306
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311047789.1A Pending CN116761185A (en) | 2023-08-21 | 2023-08-21 | Method, system and medium for predicting daily active users based on signaling |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116761185A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117177184A (en) * | 2023-10-30 | 2023-12-05 | 北京融信数联科技有限公司 | Airport day-active user prediction method, system and medium based on mobile phone signaling |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109583946A (en) * | 2018-11-16 | 2019-04-05 | 北京奇虎科技有限公司 | A kind of forecasting system and method for active users |
| WO2019085704A1 (en) * | 2017-11-06 | 2019-05-09 | 北京京东尚科信息技术有限公司 | Method and apparatus for increasing the number of active users |
| CN111148118A (en) * | 2019-12-18 | 2020-05-12 | 福建省南鸿通讯科技有限公司 | Flow prediction and carrier turn-off method and system based on time sequence |
| CN113181660A (en) * | 2021-04-20 | 2021-07-30 | 杭州电魂网络科技股份有限公司 | Method and system for predicting number of active people in real time in game, electronic equipment and storage medium |
-
2023
- 2023-08-21 CN CN202311047789.1A patent/CN116761185A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019085704A1 (en) * | 2017-11-06 | 2019-05-09 | 北京京东尚科信息技术有限公司 | Method and apparatus for increasing the number of active users |
| CN109583946A (en) * | 2018-11-16 | 2019-04-05 | 北京奇虎科技有限公司 | A kind of forecasting system and method for active users |
| CN111148118A (en) * | 2019-12-18 | 2020-05-12 | 福建省南鸿通讯科技有限公司 | Flow prediction and carrier turn-off method and system based on time sequence |
| CN113181660A (en) * | 2021-04-20 | 2021-07-30 | 杭州电魂网络科技股份有限公司 | Method and system for predicting number of active people in real time in game, electronic equipment and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117177184A (en) * | 2023-10-30 | 2023-12-05 | 北京融信数联科技有限公司 | Airport day-active user prediction method, system and medium based on mobile phone signaling |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110505196B (en) | Internet of things network card abnormality detection method and device | |
| CN107547633B (en) | User constant standing point processing method and device and storage medium | |
| CN109635857B (en) | Human-vehicle track monitoring and analyzing method, device, equipment and storage medium | |
| CN105205155A (en) | Big data criminal accomplice screening system and method | |
| CN116761185A (en) | Method, system and medium for predicting daily active users based on signaling | |
| CN111479321B (en) | Grid construction method and device, electronic equipment and storage medium | |
| CN115866547B (en) | Fixed-area tourist statistics method, system and storage medium based on signaling data | |
| CN112446549A (en) | Urban garbage intelligent supervision platform based on big data | |
| CN110891071A (en) | Network traffic information acquisition method, device and related equipment | |
| CN116010228B (en) | Time estimation method and device for network security scanning | |
| CN112073495A (en) | Smart city management Internet of things application system convenient for information integration | |
| CN114331206B (en) | Point location addressing method and device, electronic equipment and readable storage medium | |
| CN107580329B (en) | Network analysis optimization method and device | |
| CN115119253B (en) | Method, device and equipment for monitoring regional pedestrian flow and determining monitoring parameters | |
| CN116861197B (en) | Big data-based floating population monitoring method, system and storage medium | |
| CN115965137B (en) | Specific object relevance prediction method, system, terminal and storage medium | |
| CN117010703A (en) | Planning site value attribute prediction method and device based on machine learning | |
| CN116720644B (en) | Pedestrian dynamic evacuation method and system based on social force model and path finding algorithm | |
| CN116912069B (en) | Data processing method applied to smart city and electronic equipment | |
| CN116992267B (en) | Regional population gender identification method and system based on signaling data | |
| CN117202106B (en) | Regional space place attribute labeling method, system and medium based on signaling data | |
| CN117172516B (en) | Charging pile dynamic scheduling decision-making method, device, equipment and storage medium | |
| CN114386529B (en) | Community service analysis method and system based on big data and readable storage medium | |
| CN117475367B (en) | Sewage image processing method and system based on multi-rule coordination | |
| CN112689131B (en) | Gridding-based moving target monitoring method and device and related equipment |
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 |