CN112001563B - Method and device for managing ticket quantity, electronic equipment and storage medium - Google Patents
Method and device for managing ticket quantity, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112001563B CN112001563B CN202010920001.3A CN202010920001A CN112001563B CN 112001563 B CN112001563 B CN 112001563B CN 202010920001 A CN202010920001 A CN 202010920001A CN 112001563 B CN112001563 B CN 112001563B
- Authority
- CN
- China
- Prior art keywords
- target
- flow
- target user
- ticket
- historical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000007726 management method Methods 0.000 claims abstract description 44
- 230000003993 interaction Effects 0.000 claims description 38
- 230000006870 function Effects 0.000 claims description 34
- 238000004590 computer program Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000004891 communication Methods 0.000 claims description 11
- 238000011156 evaluation Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 4
- 230000000875 corresponding effect Effects 0.000 description 43
- 238000012417 linear regression Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 6
- 238000013459 approach Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 230000002596 correlated effect Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005251 gamma ray Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000000528 statistical test Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G06Q50/60—
Abstract
The invention discloses a ticket quantity management method, a ticket quantity management device, electronic equipment and a storage medium, belonging to the technical field of operator data service, comprising the following steps: after the historical flow data of the target user are obtained, the flow prediction parameters corresponding to the future target time of the target user are estimated by utilizing the historical flow data; determining a target step length of flow data of a target user based on a preset total cost function by utilizing the flow prediction parameters and the target time; and adjusting the ticket generation frequency of the target user according to the target step length so as to manage the ticket quantity of the target user. By implementing the method, the historical flow data of the target user is utilized to evaluate the flow use condition of the target user at the target time, and the target step length is determined according to the flow prediction parameters of the target user and the target time, so that the ticket generation frequency of the target user is adjusted, the ticket quantity of the target user is further effectively managed, the pressure caused by a large quantity of network ticket data quantity to the network element and the charging side is avoided, and the method has reliability.
Description
Technical Field
The present application relates to the technical field of operator data services, and in particular, to a method and apparatus for managing a ticket amount, an electronic device, and a storage medium.
Background
With the development of data services of operators, networks are developed from 3G and 4G to the current 5G, and the number of charging bills and messages is exponentially increased, and taking a charging bill of a certain province as an example, the number of charging bills is increased from 48 hundred million of month bill in the 3G age to 470 hundred million at present.
The related art is to implement management of step sizes based on fixed rules and empirical values to calculate ticket data for operator data traffic. After the 5G network is mature and commercial, the amount of call ticket data of the 5G network is obviously increased according to the current calculation processing mode based on fixed step length along with the influence of various charging factors such as network slice, content RG, 5G network quality of each dimension, and the like, which brings pressure on multiple aspects such as interaction frequency, call ticket data amount, machine performance, and the like to network elements and charging sides.
Therefore, it is necessary to provide a new call ticket data amount management technique to reduce the call ticket data amount of the network.
Disclosure of Invention
The application provides a ticket amount management method, a ticket amount management device, electronic equipment and a storage medium, which can solve the technical problem that the ticket amount of a network is obviously increased due to a fixed step processing mode.
The first aspect of the present invention provides a method for managing a ticket amount, the method comprising:
after the historical flow data of a target user are obtained, the flow prediction parameters corresponding to the future target time of the target user are estimated by utilizing the historical flow data;
determining a target step length of the flow data of the target user based on a preset total cost function by utilizing the flow prediction parameters and the target time;
and adjusting the ticket generation frequency of the target user according to the target step length so as to manage the ticket quantity of the target user.
A second aspect of the present invention provides a ticket amount management apparatus, the apparatus comprising:
the evaluation module is used for evaluating flow prediction parameters corresponding to future target time of the target user by utilizing the historical flow data after the historical flow data of the target user are acquired;
the determining module is used for determining a target step length of the flow data of the target user based on a preset total cost function by utilizing the flow prediction parameters and the target time;
and the adjusting module is used for adjusting the ticket generation frequency of the target user according to the target step length so as to manage the ticket quantity of the target user.
Optionally, the method further comprises:
the first acquisition module is used for acquiring the priority coefficient of the target user;
the optimization module is used for generating an optimized target step length according to the priority coefficient and the target step length;
the adjusting module is further used for adjusting the ticket generation frequency of the target user according to the optimized target step length;
and the management module is used for managing the ticket quantity of the target user according to the ticket generation frequency.
A third aspect of the present invention provides an electronic apparatus, comprising: the system comprises a memory, a processor and a communication bus, wherein the communication bus is respectively in communication connection with the memory and the processor, the memory is coupled with the processor, a computer program is stored on the memory, and when the processor executes the computer program, each step in the ticket quantity management method of the first aspect is realized.
A fourth aspect of the present invention provides a storage medium, which is a computer-readable storage medium having a computer program stored thereon, which when executed by a processor, implements the steps of the ticket amount management method of the first aspect.
The invention provides a ticket quantity management method, which comprises the following steps: after the historical flow data of the target user are obtained, the flow prediction parameters corresponding to the future target time of the target user are estimated by utilizing the historical flow data; determining a target step length of flow data of a target user based on a preset total cost function by utilizing the flow prediction parameters and the target time; and adjusting the ticket generation frequency of the target user according to the target step length so as to manage the ticket quantity of the target user. Compared with the related art, the method and the system can generate different target step sizes among different target users to control the call ticket generation amount, realize the management of the call ticket amount, evaluate the flow prediction parameters corresponding to the target users at the future target time by utilizing the historical flow data of the target users, pre-judge the flow use condition of the target users at the target time, determine the target step sizes of the flow data at the target time by utilizing the historical flow data and the target time, calculate the individual target step sizes according to the historical flow data of the target users, adjust the call ticket generation frequency of the target users, further effectively manage the call ticket amount of the target users, avoid the pressure brought to network elements and charging sides due to the increase of the call ticket amount of a network, and have reliability.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are necessary for the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention and that other drawings may be obtained from them without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of steps of a method for managing ticket amounts according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating another step of a method for managing ticket amounts according to an embodiment of the present invention;
FIG. 3 is a block diagram of a ticket quantity management device according to an embodiment of the present invention;
fig. 4 is a schematic diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, features and advantages of the present invention more comprehensible, the technical solutions in the embodiments of the present invention will be clearly described in conjunction with the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The fixed step processing mode in the prior art can cause the technical problem that the call ticket data volume of the network is obviously increased.
In order to solve the technical problems, the invention provides a ticket quantity management method, a ticket quantity management device, electronic equipment and a storage medium.
The invention mainly discovers characteristics from data, predicts step length by utilizing a big data technology and an AI intelligent algorithm, avoids realizing step length management in a mode of fixing rules and experience values, and brings pressure on multiple aspects of interaction frequency, call ticket data quantity, machine performance and the like to network elements and charging sides.
The target step length obtained based on the big data and the AI algorithm is calculated according to the use condition of the historical flow data of each target user, namely, the target step length of the future target time of different target users is different, and the step length management of different target times of the same target user among different target users in a dynamic step length mode is realized, so that the ticket quantity of the related target users is managed. The method comprises the steps of extracting characteristics of big data, analyzing user use behaviors, generating user flow prediction parameters by adopting algorithms such as random forest regression, gradient lifting tree, LSTM and the like, combining a plurality of correlation factors of step sizes and the flow prediction parameters, configuring according to a flow reminding threshold strategy, and generating user dynamic step sizes based on a preset dynamic step size calculation formula model.
Referring to fig. 1, a step flow chart of a ticket amount management method according to an embodiment of the present invention is provided, and the method includes the following steps:
step S101: after the historical flow data of the target user is obtained, the flow prediction parameters corresponding to the future target time of the target user are estimated by utilizing the historical flow data.
After each user registers with a certain operator, the service data corresponding to the service used by the user is calculated by the corresponding operator to generate a related ticket, and the ticket can be a consumption ticket or a prompt ticket, which is not limited in this embodiment. With the development of the data service of the operator, the data service is developed from 3G and 4G to 5G, so that the telephone bill corresponding to the data service is correspondingly increased while the data service experience is diversified for each user, and the network element and the charging side of the operator system are burdened. In this regard, the present embodiment uses historical traffic data of the target user or related users as a basis for evaluating traffic prediction parameters corresponding to a future target time, thereby evaluating a target step size of the target user at the target time.
Specifically, the historical traffic data is traffic data generated by the target user using the traffic service at the past time or at a certain moment, for example, the traffic service needs to be consumed when the user views the video or audio program at the historical moment (the past moment or the past time period); further, the historical traffic data includes: the total flow (total amount of flow) subscribed to or owned by the target user, the flow consumption used by the target user during the historical time period or the historical time, and the historical flow data may further include: the user basic information, the user consumption habit, the flow consumption condition, the flow usage habit, the flow consumption detail of each time slice of history, the holiday attribute and the like can be specifically set according to the actual condition, and the embodiment will not be further described.
According to the historical flow data of the target user, all historical time periods of the flow used by the user or all time periods of the habit of using the flow can be learned, the habit of using the flow by the user at the future moment is analyzed through the time periods, the flow using habit of the corresponding future target time period or target moment is evaluated, and the description and understanding are convenient in the future, and in the embodiment, the future target moment, the target time period and other time are collectively called as target time.
And using the historical flow data to evaluate flow prediction parameters corresponding to the target user at the future target time, namely, evaluating the flow consumption used by the user at the target time, the target time when the user will use the flow, and the like. It should be noted that, the flow prediction parameters corresponding to the target user in the future target time are estimated by using the historical flow data, and may be obtained by performing calculation and estimation through algorithm models such as random forest regression, gradient lifting tree, LSTM, and the like. Taking a regression model as an example, a regression model (regression model) is a mathematical model for quantitatively describing statistical relationships, for example, a mathematical model of multiple linear regression can be expressed as y=β 0 +β 1 ·x+ε i, wherein ,β0 ，β 1 …, βp is p+1 parameters to be estimated, ε i Are independent of each other and obey the same normal distribution N (0, sigma) 2 ) Y is a random variable, x can be a random variable or a non-random variable, βi is called a regression coefficient, and represents the influence degree of an independent variable on a dependent variable; in this embodiment, after the historical flow data of the target user is obtained, a regression model may be constructed by using the historical flow data, where the regression model may be a unitary linear regression model or a multiple linear regression model, specifically according to the historical flow data, and taking the multiple linear regression model as an example, for example, the historical flow data includes: flow consumption, flow usage habit (each time period of flow usage history), flow usage detail of each time period of history, and the like, a multiple linear regression model can be constructed according to the historical flow data, and the construction process of the multiple linear regression model is not further described in this embodiment.
After the regression model is constructed, the historical flow data of the target user is used as sample data, various statistical tests are carried out on the credibility of the relation by determining mathematical relation among the variables, the influence of which variables is obvious and the influence of which is not obvious is found out from a plurality of variables influencing a certain specific variable, the value of another specific variable is predicted or controlled according to the value of one or a plurality of variables by utilizing the obtained relation, so that more accurate flow prediction data of the future target time of the target user is obtained, the accuracy of evaluating the flow use condition of the target user is improved, and the reliability is realized.
In one embodiment, step S101 includes: establishing a flow regression model corresponding to the target user based on the acquired historical flow data; and utilizing the historical flow data to estimate the flow prediction parameters corresponding to the target time based on the flow regression model. Specifically, after the historical flow data of the target user is obtained, a regression model is built based on the obtained historical flow data of the target user, for example, a multiple linear regression model is built, the historical flow data and the future target time can be used as variables, the historical flow data can also be used as variables, specifically, according to the built regression model and the actual situation, the flow prediction data of the target user at the future target time is estimated based on the built multiple linear regression model, for example, the flow consumption, the flow residual quantity and the like of the target user at the target time are obtained. This step can improve the accuracy of evaluating the flow prediction data.
Step S102: and determining a target step length of the flow data of the target user based on a preset total cost function by utilizing the flow prediction parameters and the target time.
The embodiment comprises a constructed total cost function, wherein the total cost function is a cost function taking a step length as an independent variable, and comprises a plurality of costs, such as interaction cost, excessive flow limiting risk and comprehensive risk, wherein the costs are set to be related to the step length of the flow, such as the interaction cost is in direct proportion to the interaction times and in inverse proportion to the time step length; the overflow limiting cost and the overflow limiting risk are linearly and positively correlated with the time step; the comprehensive risk is linearly and positively correlated with the time step; when the minimum value of the total cost function is obtained by using the total cost function containing the relation, a target step length can be obtained, the target step length can be understood as an optimal step length, and the ticket generation frequency can be adjusted through the target step length.
The variables or operation parameters related to the total cost function include: the flow rate v of the target time, the flow step allocation m of the target time, the time step allocation tau of the target time and the flow residual h of the target time. Since the flow step allocation m=v·τ of the target time, when the flow rate v of the target time is determined, the flow step allocation m of the target time may also be determined, and for convenience of representation, the embodiment focuses on obtaining the time step allocation τ of the target time, and for convenience of description and understanding, the time step allocation τ of the target time is collectively referred to as a target step. The construction of the total cost function is as follows:
in order to obtain the flow step allocation m of the target time and the time step allocation τ of the target time corresponding to the minimum value of the total cost function, that is, the target step corresponding to the minimum value of the total cost function in this embodiment, the estimated flow prediction parameters are used to calculate, in an embodiment, the flow prediction parameters include: and when the target step size tau is a certain time step size, calculating a target total cost value L (tau, v, h) of the target user by combining the flow rate with the flow residual size, wherein the target step size is an optimal step size, and the optimal step size corresponds to the minimum total cost value L (tau, v, h).
Specifically, T is 0 The time period is taken as the target time, and the total cost function is as follows:
wherein ,T0 Representing the maximum target time of the step size of the limitation, a representing the cost of a single interaction, and beta representing the flow limitation coefficient;
further, the derivative of the total cost function is obtained, and the derivative of the total cost function is calculated as follows:
when the derivative is equal to 0, the smallest total cost value L (τ, v, h) At this time, an optimal step length and a target step length can be obtained>
Further, in order to consider the flow remaining amount h, a safety factor beta of the flow service of the target user when the flow is not exceeded is set 1 Setting an overflow loss coefficient or an overflow cost coefficient beta of the flow business of the target user when the flow is exceeded 2 ；
In one embodiment of step S102, step S102 specifically includes: calculating based on a preset total cost function by using the flow residual quantity, the flow rate and the target time to obtain a target total cost value; and determining the target step length of the flow data of the target user according to the target total cost value.
The target total cost value is calculated as follows:
wherein L (τ, v, h) represents the target total cost value, T 0 Representing target time, a representing preset single interaction cost, beta 1 Indicating the safety coefficient of the flow, beta 2 The loss coefficient exceeding the flow rate is represented by h, the flow residual amount is represented by v, the flow rate is represented by τ, and the target step size is represented by τ.
Further, if the determined time step of the target user is too small, when the target user views the consumption flow of video and the like through the terminal, the interaction frequency between the terminal and the network element and the charging side of the operator system is too low, which can lead to failure of the system not being solved in time and degradation of user experience perception, such as untimely updating of the ticket queried by the user, inaccurate statistics and the like. To avoid the above problem, the overall risk term τ·w is increased when calculating the total cost value, where w represents the overall risk factor, and the cost of this overall risk term is positively correlated with the step size. Thus, the total cost function for calculating the target total cost value is as follows:
in order to simplify the total cost function, a safety cost coefficient B which does not exceed the flow is set in the interaction cost in the target time 1 ＝β 1 /(T 0 A) risk cost coefficient B for excess flow 2 ＝β 2 /(T 0 A), the composite term cost w=w/(T) 0 A), let the simplified total cost function be:
then L (τ, v, h) = (T) 0 ·a)·F(τ,v,h)。
Further, determining an optimal step length of the flow data of the target user according to the target total cost value, namely determining a target step length of the flow data of the target user according to the target total cost value, when the target total cost value has a minimum value, an optimal solution of the step length exists, namely an extremum point of the target step length exists, and the extremum point of the target step length can be understood as a target step length value, wherein the method specifically comprises the following steps:
Obtaining a target step extreme value corresponding to an optimal solution of the target total cost value, and obtaining a corresponding target step value when the target step extreme value is obtained, wherein the target step value comprises a first target step value tau 1 A second target step value τ 2 Wherein the first target step value is greater than the second target step value;
generating a corresponding step threshold according to the flow residual quantity and the flow rate, wherein the step threshold is h/v;
comparing the target step value with a step threshold value;
if the first target step value is less than or equal to the step threshold, the target step is the first target step value τ 1 The method is characterized by comprising the following steps:
when (when)When (I)>
If the second target step value is greater than the step threshold, the target step is a second target step value τ 2 The method is characterized by comprising the following steps:
when (when)When (I)>
If the first target step value is greater than the step threshold and the second target step value is less than the step threshold, the target step is the step threshold, and at this time, for convenience of description and understanding, the target step is set to be the third target step τ 3 The method is characterized by comprising the following steps:
when (when)When (I)>
Further, in still another implementation manner of the present embodiment, if the flow rate v in the estimated flow prediction parameter is zero, that is, v=0, at the target time, a safe step size, for example, 150 minutes, may be allocated to the target user at the target time according to the service experience of the service end of the operator system, which is not limited in this embodiment, and the size of the safe step size may be specifically set according to the actual requirement. When the flow rate v=0 in the flow prediction parameter, the safety step length T of the target time is set 1 The safety step of the target time is expressed as follows:
then->
Further, in still another implementation manner of this embodiment, the target step size is determined according to the flow remaining amount in the flow prediction parameter and the preset flow reminding threshold, that is, when the flow remaining amount approaches the flow reminding threshold, the allocation target step size is reduced, so as to increase the ticket generation amount of the target user when the flow remaining amount approaches the flow reminding threshold, where the ticket is exemplified by a short message, and when the flow remaining amount approaches the short message reminding point, the flow reminding threshold can be understood as a short message reminding point, and when the flow remaining amount approaches the short message reminding point, the network element and the charging side of the operator system reduce the target step size allocated to the target user, so as to increase the ticket generation amount and remind the target user.
Specifically, the traffic reminding threshold may be set to 20% and 30%, that is, the short message reminding point is the remaining traffic 20% and 30%, and the maximum remaining traffic (total traffic amount or total traffic) is H 0 ，H 0 40G, the residual flow of the short message reminding point is H respectively 1 ＝0.3·H 0 H is as follows 2 ＝0.2·H 0 . Then, in order to increase the interaction frequency before the short message reminding point, the safety cost coefficient B of the flow is not exceeded 1 And risk cost coefficient B of the excess flow 2 The values of (2) are set as follows:
B 1 ′＝B 1 ·(1+γ 1 +γ 2 )，
B 2 ′＝B 2 ·(1+γ 1 +γ 2 )，
wherein ,γ1 An alarm coefficient indicating that the flow remaining amount is 20%, or referred to as a first alarm coefficient; gamma ray 2 An alarm coefficient indicating 30% of the remaining flow is referred to as a second alarm coefficient. The first alarm coefficient and the second alarm coefficient are set as follows:
wherein whenWhen (I)>When H is less than H 2 Or->When gamma is 1 ＝0；
Wherein whenWhen (I)>When H is less than H 1 Or->γ 2 ＝0。
Acquiring a target step value corresponding to the target total cost value, wherein the target step value comprises a first target step value tau 1 A second target step value τ 2 Wherein the first target step value is greater than the second target step value;
generating a corresponding step threshold according to the flow residual quantity and the flow rate, wherein the step threshold is h/v;
comparing the target step value with a step threshold value;
if the first target step value is less than or equal to the step threshold, the target step is the first target step value τ 1 The method is characterized by comprising the following steps:
when (when)When (I)>
If the second target step value is greater than the step threshold, the target step is the second targetTarget step size value τ 2 The method is characterized by comprising the following steps:
when (when)When (I)>
If the second target step value is greater than the step threshold, the target step is a second target step value τ 2 The method is characterized by comprising the following steps:
when (when)When (I)>
It will be appreciated that due to B 2 ′＞B 1 'τ' is then 1 ＞τ 2 That is, when any one of the conditions is satisfied, different target extreme points do not appear at the same time,
such as when meetingWhen only the extreme point of the optimal step length is tau 1 The optimal target step size is->The same is true for the step extreme points that satisfy other conditions, which will not be further described in this embodiment.
The above-mentioned step S102 is a process of determining the target step size of the flow data of the target user based on the preset total cost function by using the flow prediction parameter and the target time, and regarding the determined target step size, the step size is used for determining the interaction frequency of the target user in the future target time by the network element and the charging side of the operator system. Furthermore, after the target step length is determined, the method can be directly used for managing the interaction frequency of the target user terminal, the network element of the operator system and the charging side, or can be used as the final target step length of each target user after optimizing or calculating the weight of the determined target step length, for example, the target user used as a super member, and the final target step length can be prolonged on the basis of the originally determined target step length so as to reduce the interaction frequency when the residual flow is lower and manage the ticket quantity.
Step S103: and adjusting the ticket generation frequency of the target user according to the target step length so as to manage the ticket quantity of the target user.
After the operator 5G network is mature and commercial, along with the influence of various charging factors such as network slicing, content RG, 5G network quality of each dimension and the like, the target step length of different target time of each target user can be calculated, so that the different target time of different target users has different target step length, namely the operator system does not manage each user in a fixed step length mode; specifically, the ticket generation frequency of the target users is adjusted according to the determined target step length, so that the interaction frequency between the terminal of each target user and the network element and the charging side of the operator system is effectively managed, and the ticket generation quantity of each user or the target user is effectively managed. After the operator 5G network optimizes the system capacity, the system resource is increased, the ticket generation amount is effectively managed, and the system pressure is reduced.
The invention provides a ticket quantity management method, which comprises the following steps: after the historical flow data of the target user are obtained, the flow prediction parameters corresponding to the future target time of the target user are estimated by utilizing the historical flow data; determining a target step length of flow data of a target user based on a preset total cost function by utilizing the flow prediction parameters and the target time; and adjusting the ticket generation frequency of the target user according to the target step length so as to manage the ticket quantity of the target user. Compared with the related art, the method and the system can generate different target step sizes among different target users to control the call ticket generation amount, realize the management of the call ticket amount, evaluate the flow prediction parameters corresponding to the target users at the future target time by utilizing the historical flow data of the target users, pre-judge the flow use condition of the target users at the target time, determine the target step sizes of the flow data at the target time by utilizing the historical flow data and the target time, calculate the individual target step sizes according to the historical flow data of the target users, adjust the call ticket generation frequency of the target users, further effectively manage the call ticket amount of the target users, avoid the pressure brought to network elements and charging sides due to the increase of the call ticket amount of a network, and have reliability.
Referring to fig. 2, a flowchart of another step of the ticket amount management method according to the embodiment of the present invention is shown. Specifically, the process flow is as follows:
step S201: and receiving interaction information sent by a terminal corresponding to the target user, wherein the interaction information comprises historical flow data.
Specifically, after the terminal of the target user sends the interaction information to the operator system, the operator system processor or the server or the network element and the charging side receive the interaction information from the terminal of the target user, where the interaction information is used to learn the traffic usage situation of the target user, for example, the interaction information may be used to learn the usage situation of each data service of the target user registered account number or member with the runtime system, or may be the usage situation of the target user after subscribing to the traffic data service, and in this embodiment, by taking the traffic data service as an example, the interaction information sent by the terminal corresponding to the target user is received, where the interaction information includes historical traffic data.
Step S202: extracting flow consumption and total flow corresponding to target historical time in historical flow data, wherein the target historical time corresponds to target time; the historical flow data comprises flow consumption and total flow.
Specifically, the flow consumption corresponding to the target historical time in the historical flow data is extracted, and the total flow or the total flow business amount in the target user subscription flow data business is extracted so as to learn the flow amount or the flow use condition used by the user in the historical time or the past. It can be understood that the target historical time is a time corresponding to the target time, for example, in order to predict that the target time is the traffic usage situation of 20:30 a night, the extractable historical target time is the traffic usage situation of 20:30 a night, or may be the traffic usage situation of all the past night 20:30, and average calculation is performed to obtain the predicted traffic usage situation of 20:30 a night, or weight calculation is performed to obtain the predicted traffic usage situation of 20:30 a night. Further, the target time may be a certain time period, for example, 12:00-14:00 in the midday of tomorrow, and the target history time is a corresponding time period in the past, and the obtaining or calculating manner of the traffic usage condition of the time period is the same as or similar to the foregoing, which is not further described in this embodiment.
Step S203: and estimating the flow residual quantity in the flow prediction parameters corresponding to the target time by using the total flow and the flow consumption, and estimating the flow rate in the flow prediction parameters corresponding to the target time by using the flow consumption and the historical time parameters.
Step S204: and determining a target step length of the flow data of the target user based on a preset total cost function by using the flow residual quantity, the flow rate and the target time.
Specifically, the method steps described in steps S203-S204 are similar or similar to the method steps of steps S101 and S102, and the content description of the partial flow is identical to the content descriptions of steps S101-S102, which are not further described in this embodiment.
Step S205: acquiring a priority coefficient of a target user;
specifically, in order to perform different management on the interaction frequency between each user terminal and the network element of the operator system and the charging side, the network operator avoids that when the traffic surplus is too low, the interaction frequency is too high, so that too many call ticket amounts are generated to disturb the user, and the use experience of the user is reduced. After the target step size of the flow data of the target user is obtained through step S102 or step S204, for example, the target step size of the target user can be managed through the member level, the interaction frequency of the target user is adjusted, specifically, the ranking of the target user in all users is obtained, and the ranking priority coefficient of the target user in a mode is calculated according to the preset ranking rate, specifically as follows:
R＝(N-K)/(N-1)
Wherein R represents a ranking priority weight coefficient, N represents the number of all users, and K represents the ranking of the target user.
Furthermore, the ranking priority coefficient may be used in combination with the credit priority coefficient to determine the priority coefficient of the target user, which will not be further described in this embodiment.
Step S206: and generating an optimized target step length according to the priority weight coefficient and the target step length.
Specifically, the calculation mode of the optimized target step length is as follows:
wherein ,τop Represents an optimized target step size, τ represents a target step size, which may include a first target step size τ 1 And a second target step size tau 2 ，a 1 Representing the minimum step-up rate, a, of the target user 2 Representing the maximum step-up rate of the target user.
Step S207: adjusting the ticket generation frequency of the target user according to the optimized target step length;
specifically, the interaction frequency between the terminal of the target user and the network element of the operator system and the charging side is adjusted according to the optimized target step length, so that the ticket generation frequency of the target user is managed, and the ticket generation amount of the target user is effectively managed.
Step S208: and managing the quantity of the call ticket of the target user according to the call ticket generation frequency.
Specifically, the ticket generation frequency of the target user is adjusted according to the determined target step length, and the ticket generation amount of each user or the target user is effectively managed, so that after the operator 5G network optimizes the system capacity, the system resource is increased, the network ticket amount is prevented from being obviously increased due to the fixed step length, the ticket generation amount is effectively managed, and the system pressure is reduced.
Referring to fig. 3, fig. 3 is a block diagram of a ticket amount management device according to an embodiment of the present invention, where the ticket amount management device corresponds to an execution body processor of a ticket amount management method, and the device 300 includes:
the evaluation module 301 is configured to evaluate, after obtaining historical traffic data of the target user, a traffic prediction parameter corresponding to a future target time of the target user using the historical traffic data;
a determining module 302, configured to determine a target step size of flow data of a target user based on a preset total cost function by using a flow prediction parameter and a target time;
and the adjusting module 303 is configured to adjust the ticket generating frequency of the target user according to the target step size, so as to manage the ticket amount of the target user.
Further, the apparatus 300 further includes:
the receiving module 304 is configured to receive interaction information sent by a terminal corresponding to a target user, where the interaction information includes historical flow data.
Specifically, after the terminal of the target user sends the interaction information to the operator system, the receiving module 304 of the operator system server or the network element and the processor of the charging side receives the interaction information from the terminal of the target user, where the interaction information is used to learn the traffic usage situation of the target user, for example, the interaction information may be used to learn the usage situation of each data service of the target user registered account number or member to the runtime system, or may be the usage situation of the target user after subscribing to the traffic data service, and in this embodiment, by taking the traffic data service as an example, the interaction information sent by the terminal corresponding to the target user is received, where the interaction information includes the historical traffic data.
The extracting module 305 is configured to extract a flow consumption amount and a total flow corresponding to a target historical time in the historical flow data, where the target historical time corresponds to the target time; the historical flow data comprises flow consumption and total flow.
Specifically, the extraction module 305 extracts the flow consumption corresponding to the target historical time in the historical flow data, and the extraction module 305 extracts the total flow or the total flow business amount in the target user subscription flow data business so as to learn the flow amount or the flow use condition used by the user in the historical time or the past. It can be understood that the target historical time is a time corresponding to the target time, for example, in order to predict that the target time is the traffic usage situation of 20:30 a night, the extractable historical target time is the traffic usage situation of 20:30 a night, or may be the traffic usage situation of all the past night 20:30, and average calculation is performed to obtain the predicted traffic usage situation of 20:30 a night, or weight calculation is performed to obtain the predicted traffic usage situation of 20:30 a night. Further, the target time may be a certain time period, for example, 12:00-14:00 in the midday of tomorrow, and the target history time is a corresponding time period in the past, and the obtaining or calculating manner of the traffic usage condition of the time period is the same as or similar to the foregoing, which is not further described in this embodiment.
Further, the apparatus 300 further includes:
an optimizing module 306, configured to generate an optimized target step according to the priority weight coefficient and the target step;
the adjusting module 303 is further configured to adjust a ticket generating frequency of the target user according to the optimized target step size;
and a management module 307 for managing the ticket amount of the target user according to the ticket generation frequency.
Specifically, the optimizing module 306 and the managing module 307 in the ticket amount managing apparatus provided in this embodiment are device modules corresponding to step S206 and step S208 in the ticket amount managing method steps provided in the foregoing embodiment of the present invention, and the content description of the relevant module is consistent with the corresponding content description in the embodiment of the ticket amount managing method provided in the present invention, which is not further described in this embodiment.
The invention provides a ticket quantity management device, comprising: an evaluation module 301, a determination module 302, an adjustment module 303, a receiving module 304, an extraction module 305, an optimization module 306 and a management module 307; specifically, the method comprises the following steps: after the historical flow data of the target user is acquired through the evaluation module 301, the flow prediction parameters corresponding to the future target time of the target user are evaluated by utilizing the historical flow data; determining, by the determining module 302, a target step size of flow data of the target user based on a preset total cost function by using the flow prediction parameter and the target time; the ticket generation frequency of the target user is adjusted by the adjustment module 303 according to the target step size to manage the ticket amount of the target user. Compared with the related art, the invention can generate different target step sizes among different target users through the modules so as to control the call ticket generation quantity, realize the management of the call ticket quantity, evaluate the flow prediction parameters corresponding to the target users at the future target time by utilizing the historical flow data of the target users, so as to predict the flow use condition of the target users at the target time, determine the target step sizes of the flow data at the target time by utilizing the historical flow data and the target time, realize the calculation of individual target step sizes according to the historical flow data of the target users, so as to adjust the call ticket generation frequency of the target users, further effectively manage the call ticket quantity of the target users, avoid the pressure brought to network elements and charging sides due to the increase of the call ticket quantity of the network, and have reliability.
The invention provides an electronic device, please refer to fig. 4, which is a structural diagram of the electronic device according to an embodiment of the invention, the electronic device includes: the system comprises a memory 401, a processor 402 and a communication bus 403, wherein the communication bus 403 is respectively connected with the memory 401 and the processor 402 in a communication way, the memory 401 is coupled with the processor 402, a computer program is stored in the memory 401, and when the processor 402 executes the computer program, each step in the ticket quantity management method of any one of the above steps is realized.
The computer program of the ticket quantity management method mainly includes: after the historical flow data of the target user are obtained, the flow prediction parameters corresponding to the future target time of the target user are estimated by utilizing the historical flow data; determining a target step length of flow data of a target user based on a preset total cost function by utilizing the flow prediction parameters and the target time; and adjusting the ticket generation frequency of the target user according to the target step length so as to manage the ticket quantity of the target user. In addition, a computer program may also be divided into one or more modules, one or more modules being stored in a memory and executed by a processor to accomplish the present invention. One or more modules may be a series of computer program instruction segments capable of performing particular functions to describe execution of a computer program in a computing device. For example, the computer program may be divided into an evaluation module 301, a determination module 302, an adjustment module 303, a reception module 304, an extraction module 305, an optimization module 306 and a management module 307 as shown in fig. 3.
The processor 402 may be a central processing module (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The application also provides a storage medium, which is a computer readable storage medium, and the computer readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the ticket quantity management method of any one of the above steps are realized.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of modules is merely a logical function division, and there may be additional divisions of actual implementation, e.g., multiple modules or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or modules, which may be in electrical, mechanical, or other forms.
The modules illustrated as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, i.e., may be located in one place, or may be distributed over a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist alone physically, or two or more modules may be integrated into one module. The integrated modules may be implemented in hardware or in software functional modules.
The integrated modules, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in essence or a part contributing to the prior art or all or part of the technical solution 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 perform all or part of the steps of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
It should be noted that, for the sake of simplicity of description, the foregoing method embodiments are all expressed as a series of combinations of actions, but it should be understood by those skilled in the art that the present invention is not limited by the order of actions described, as some steps may be performed in other order or simultaneously in accordance with the present invention. Further, those skilled in the art will appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily all required for the present invention.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to the related descriptions of other embodiments.
The foregoing describes a ticket amount management method, apparatus, electronic device, and storage medium provided by the present invention, and those skilled in the art may change the specific implementation and application scope according to the idea of the embodiment of the present invention, so that the disclosure should not be construed as limiting the present invention.
Claims (9)
1. A method of managing a ticket quantity, the method comprising:
After the historical flow data of a target user are obtained, the flow prediction parameters corresponding to the future target time of the target user are estimated by utilizing the historical flow data;
determining a target step length of the flow data of the target user based on a preset total cost function by utilizing the flow prediction parameters and the target time;
adjusting the ticket generation frequency of the target user according to the target step length so as to manage the ticket quantity of the target user;
the step of determining the target step size of the flow data of the target user based on a preset total cost function by using the flow prediction parameter and the target time includes:
calculating based on a preset total cost function by using the flow residual quantity, the flow rate and the target time to obtain a target total cost value;
the calculation mode of the target total cost value is as follows:
wherein ,representing the target total cost value, +.>Representing the target time,/->Representing a preset single interaction cost, +.>Safety factor indicating that the flow is not exceeded, +.>Loss coefficient indicating excess flow, +.>Indicating the flow remaining- >Representing the flow rate, +_>Representing the target step size;
and determining a target step length of the flow data of the target user according to the target total cost value.
2. The ticket amount management method according to claim 1, wherein the historical flow data includes a flow consumption amount and a total flow amount, and the step of evaluating the flow prediction parameter corresponding to the target time in the future of the target user using the historical flow data includes, before:
receiving interaction information sent by a terminal corresponding to the target user, wherein the interaction information comprises historical flow data;
extracting flow consumption and total flow corresponding to target historical time in the historical flow data, wherein the target historical time corresponds to the target time;
the estimating, by using the historical traffic data, a traffic prediction parameter corresponding to the target time of the target user includes:
estimating the flow remaining amount in the flow prediction parameter corresponding to the target time by using the total flow and the flow consumption;
and evaluating the flow rate in the flow prediction parameters corresponding to the target time by using the flow consumption and the historical time parameters.
3. The ticket amount management method according to claim 1, wherein the step of evaluating the flow prediction parameter corresponding to the target time of the target user using the historical flow data includes:
establishing a flow regression model corresponding to the target user based on the acquired historical flow data;
and evaluating the flow prediction parameters corresponding to the target time based on the flow regression model by utilizing the historical flow data.
4. The ticket amount management method according to claim 1, wherein the step of determining a target step size of the traffic data of the target user according to the target total cost value includes:
obtaining a target step value corresponding to the target total cost value, wherein the target step value comprises a first target step value and a second target step value, and the first target step value is larger than the second target step value;
generating a corresponding step threshold according to the flow residual quantity and the flow rate;
comparing the target step value with the step threshold;
if the first target step value is smaller than or equal to the step threshold, the target step is the first target step value;
If the second target step value is greater than the step threshold, the target step is the second target step value;
and if the first target step length value is larger than the step length threshold value and the second target step length value is smaller than the step length threshold value, the target step length is the step length threshold value.
5. The ticket amount management method according to any one of claims 1 to 4, wherein the step of determining a target step size of the traffic data of the target user based on a preset total cost function using the traffic prediction parameter and the target time further comprises:
acquiring a priority coefficient of the target user;
generating an optimized target step length according to the priority coefficient and the target step length;
the step of managing the generation frequency of the ticket quantity of the target user according to the target step length to manage the ticket quantity of the target user includes:
adjusting the ticket generation frequency of the target user according to the optimized target step length;
and managing the ticket quantity of the target user according to the ticket generation frequency.
6. A ticket amount management apparatus for implementing the ticket amount management method according to any one of claims 1 to 5, comprising:
The evaluation module is used for evaluating flow prediction parameters corresponding to future target time of the target user by utilizing the historical flow data after the historical flow data of the target user are acquired;
the determining module is used for determining a target step length of the flow data of the target user based on a preset total cost function by utilizing the flow prediction parameters and the target time; comprising the following steps:
calculating based on a preset total cost function by using the flow residual quantity, the flow rate and the target time to obtain a target total cost value;
the calculation mode of the target total cost value is as follows:
wherein ,representing the target total cost value, +.>Representing the target time,/->Representing a preset single interaction cost, +.>Safety factor indicating that the flow is not exceeded, +.>Loss coefficient indicating excess flow, +.>Indicating the flow remaining->Representing the flow rate, +_>Representing the target step size;
determining a target step length of the flow data of the target user according to the target total cost value;
and the adjusting module is used for adjusting the ticket generation frequency of the target user according to the target step length so as to manage the ticket quantity of the target user.
7. The ticket quantity management apparatus according to claim 6, further comprising:
the first acquisition module is used for acquiring the priority coefficient of the target user;
the optimization module is used for generating an optimized target step length according to the priority coefficient and the target step length;
the adjusting module is further used for adjusting the ticket generation frequency of the target user according to the optimized target step length;
and the management module is used for managing the ticket quantity of the target user according to the ticket generation frequency.
8. An electronic device, comprising: the system comprises a memory, a processor and a communication bus, wherein the communication bus is respectively in communication connection with the memory and the processor, and the memory is coupled with the processor, and is characterized in that the memory stores a computer program, and the processor realizes the steps in the ticket quantity management method according to any one of claims 1 to 5 when executing the computer program.
9. A storage medium, which is a computer-readable storage medium, wherein the computer-readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the ticket amount management method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010920001.3A CN112001563B (en) | 2020-09-04 | 2020-09-04 | Method and device for managing ticket quantity, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010920001.3A CN112001563B (en) | 2020-09-04 | 2020-09-04 | Method and device for managing ticket quantity, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112001563A CN112001563A (en) | 2020-11-27 |
| CN112001563B true CN112001563B (en) | 2023-10-31 |
Family
ID=73468313
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010920001.3A Active CN112001563B (en) | 2020-09-04 | 2020-09-04 | Method and device for managing ticket quantity, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112001563B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112672296B (en) * | 2020-12-25 | 2022-05-03 | 中国联合网络通信集团有限公司 | Call bill collection method and device |
| CN114449466B (en) * | 2021-12-16 | 2023-05-16 | 广东联想懂的通信有限公司 | User charging intelligent monitoring method and device, electronic equipment and storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102056182A (en) * | 2010-12-13 | 2011-05-11 | 哈尔滨工业大学 | Method for predicting mobile traffic based on LS-SVM |
| CN102083077A (en) * | 2010-12-24 | 2011-06-01 | 大唐移动通信设备有限公司 | Baseband pool shared resource distribution method and device |
| CN103796247A (en) * | 2012-11-02 | 2014-05-14 | 中国移动通信集团浙江有限公司 | User traffic speed control method and system |
| CN103987056A (en) * | 2014-05-30 | 2014-08-13 | 南京华苏科技有限公司 | Wireless network telephone traffic prediction method based on big-data statistical model |
| CN104041091A (en) * | 2012-01-06 | 2014-09-10 | 华为技术有限公司 | Systems And Methods For Predictive Downloading In Congested Networks |
| CN104581779A (en) * | 2014-12-11 | 2015-04-29 | 华为技术有限公司 | Business processing method and device |
| WO2018019769A1 (en) * | 2016-07-26 | 2018-02-01 | Electricite De France | Method for predicting consumption demand using an advanced prediction model |
| CN107786351A (en) * | 2016-08-24 | 2018-03-09 | 中国电信股份有限公司 | Service bandwidth self-adapting regulation method, system and SDN controllers |
| CN108574933A (en) * | 2017-03-07 | 2018-09-25 | 华为技术有限公司 | User trajectory restoration methods and device |
| CN110443657A (en) * | 2019-08-19 | 2019-11-12 | 泰康保险集团股份有限公司 | Customer traffic data processing method, device, electronic equipment and readable medium |
| CN110618922A (en) * | 2019-08-15 | 2019-12-27 | 平安普惠企业管理有限公司 | Performance test method and related equipment |
| CN111325310A (en) * | 2018-12-13 | 2020-06-23 | 中国移动通信集团有限公司 | Data prediction method, device and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8731983B2 (en) * | 2005-02-24 | 2014-05-20 | Sap Ag | System and method for designing effective business policies via business rules analysis |
-
2020
- 2020-09-04 CN CN202010920001.3A patent/CN112001563B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102056182A (en) * | 2010-12-13 | 2011-05-11 | 哈尔滨工业大学 | Method for predicting mobile traffic based on LS-SVM |
| CN102083077A (en) * | 2010-12-24 | 2011-06-01 | 大唐移动通信设备有限公司 | Baseband pool shared resource distribution method and device |
| CN104041091A (en) * | 2012-01-06 | 2014-09-10 | 华为技术有限公司 | Systems And Methods For Predictive Downloading In Congested Networks |
| CN103796247A (en) * | 2012-11-02 | 2014-05-14 | 中国移动通信集团浙江有限公司 | User traffic speed control method and system |
| CN103987056A (en) * | 2014-05-30 | 2014-08-13 | 南京华苏科技有限公司 | Wireless network telephone traffic prediction method based on big-data statistical model |
| CN104581779A (en) * | 2014-12-11 | 2015-04-29 | 华为技术有限公司 | Business processing method and device |
| WO2018019769A1 (en) * | 2016-07-26 | 2018-02-01 | Electricite De France | Method for predicting consumption demand using an advanced prediction model |
| CN107786351A (en) * | 2016-08-24 | 2018-03-09 | 中国电信股份有限公司 | Service bandwidth self-adapting regulation method, system and SDN controllers |
| CN108574933A (en) * | 2017-03-07 | 2018-09-25 | 华为技术有限公司 | User trajectory restoration methods and device |
| CN111325310A (en) * | 2018-12-13 | 2020-06-23 | 中国移动通信集团有限公司 | Data prediction method, device and storage medium |
| CN110618922A (en) * | 2019-08-15 | 2019-12-27 | 平安普惠企业管理有限公司 | Performance test method and related equipment |
| CN110443657A (en) * | 2019-08-19 | 2019-11-12 | 泰康保险集团股份有限公司 | Customer traffic data processing method, device, electronic equipment and readable medium |
Non-Patent Citations (2)
| Title |
|---|
| 一种面向互联网运营的流量管理模式;谭晖;李婧琦;杨林;廖振松;;信息通信(01);全文 * |
| 基于机器学习的细分业务用户感知评估方法;马敏;李威;陈洁;;电信工程技术与标准化(05);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112001563A (en) | 2020-11-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112001563B (en) | Method and device for managing ticket quantity, electronic equipment and storage medium | |
| CN107632697B (en) | Processing method, device, storage medium and the electronic equipment of application program | |
| CN110289994B (en) | Cluster capacity adjusting method and device | |
| CN110896357B (en) | Flow prediction method, device and computer readable storage medium | |
| CN111324533A (en) | A/B test method and device and electronic equipment | |
| CN108171570A (en) | A kind of data screening method, apparatus and terminal | |
| CN113032142B (en) | Resource adjusting method and device, electronic equipment and computer readable storage medium | |
| CN112416590A (en) | Server system resource adjusting method and device, computer equipment and storage medium | |
| CN111800807A (en) | Method and device for alarming number of base station users | |
| CN107728772B (en) | Application processing method and device, storage medium and electronic equipment | |
| CN108463813B (en) | Method and device for processing data | |
| CN107844496B (en) | Statistical information output method and device | |
| CN112187870A (en) | Bandwidth smoothing method and device | |
| CN116819352A (en) | Self-adaptive setting method, device and equipment for battery threshold value and storage medium | |
| CN110134575B (en) | Method and device for calculating service capacity of server cluster | |
| CN110246026B (en) | Data transfer output combination setting method and device and terminal equipment | |
| CN112669091A (en) | Data processing method, device and storage medium | |
| CN110083517B (en) | User image confidence optimization method and device | |
| CN111164633B (en) | Method and device for adjusting scoring card model, server and storage medium | |
| CN110570136B (en) | Distribution range determining method, distribution range determining device, electronic equipment and storage medium | |
| CN115130026A (en) | Target object determination method, device, medium and electronic equipment | |
| CN114254841A (en) | Resource limit processing method, computing device, user device and server | |
| CN113656275B (en) | User activity prediction method, device, electronic equipment and storage medium | |
| CN114090854B (en) | Intelligent label weight updating method and system based on information entropy and computer equipment | |
| CN113673080B (en) | Method, device, equipment and medium for predicting duration of application and training model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |