CN108009862A - A kind of method and device of advertising expenditure remaining sum early warning - Google Patents

Abstract

The invention discloses a method and device for early warning of advertising fee balance. The method includes: predicting and obtaining the advertising fee consumption amount of the advertising delivery platform at the target time according to the historical consumption data of the advertising fee; The advertising expense consumption amount of the platform determines the advertising expense consumption distribution coefficient of the advertiser to be analyzed on the advertising delivery platform; calculates the predicted value of advertising expense consumption of the advertiser to be analyzed at the target moment; according to the advertiser to be analyzed at the target Calculate the predicted value of advertising cost consumption at the moment, and calculate the remaining consuming time of the advertising cost of the advertiser to be analyzed at the target time; judge whether the remaining consuming time meets the preset warning time range, and if so, give an early warning . The present invention realizes the purpose of early warning that the advertising fee is about to be consumed.

Description

Method and device for early warning of advertising fee balance

technical field

The invention relates to the technical field of advertisement delivery, in particular to a method and device for early warning of advertisement fee balance.

Background technique

With the continuous development of Internet technology, applications have been more and more widely used by users in Internet activities. Therefore, displaying advertisements through application programs has become one of the main ways to promote services or information. When an application displays an advertisement, the advertiser needs to pay the corresponding advertisement fee.

Because in the advertising delivery system, the consumption of advertising fees paid by advertisers occurs in real time. This will lead to the fact that the advertising fee paid by an advertiser has been exhausted, but the advertiser cannot know this situation in time, and thus cannot continue to pay the advertising fee in time, thereby affecting the effect of advertising.

Contents of the invention

In view of the above problems, the present invention provides a method and device for early warning of advertising fee balance, which realizes the purpose of early warning that the advertising fee is about to be consumed.

In order to achieve the above object, the present invention provides the following technical solutions:

A method for early warning of an advertising fee balance, the method comprising:

Obtaining the historical consumption data of advertising costs of the advertising delivery platform, and predicting the consumption amount of advertising costs of the advertising delivery platform at the target moment according to the historical consumption data of advertising costs;

According to the amount of advertising expense consumption of each advertiser on the advertising delivery platform at the target historical moment, determine the advertising expense consumption distribution coefficient of the advertiser to be analyzed on the advertising delivery platform;

According to the advertising expense consumption amount of the advertising delivery platform at the target moment and the advertising expense consumption distribution coefficient of the advertiser to be analyzed on the advertising delivery platform, calculate and obtain the predicted advertising expense consumption value of the advertiser to be analyzed at the target moment ;

According to the predicted value of the advertising expense consumption of the advertiser to be analyzed at the target moment, calculate and obtain the remaining consuming duration of the advertising expense of the advertiser to be analyzed at the target moment;

It is judged whether the remaining consumable duration satisfies the preset warning duration range, and if so, an early warning is performed.

Preferably, the method also includes:

When an early warning is issued, early warning information will be generated according to the remaining consuming time, and the early warning information will be sent to the advertiser to be analyzed.

Preferably, according to the amount of advertising expense consumption of each advertiser on the advertising delivery platform at the target historical moment, determining the advertising expense consumption distribution coefficient of the advertiser to be analyzed on the advertising delivery platform includes:

Summing up the amount of advertising expense consumption of each advertiser on the advertising delivery platform at the target historical moment to obtain the total value of the advertising expense consumption of each advertiser at the target historical moment;

Calculate the ratio between the advertising fee consumption value of the advertiser to be analyzed at the target historical moment and the total advertising fee consumption value of each advertiser, and record the ratio as the advertiser to be analyzed at the The advertising cost consumption distribution coefficient of the above-mentioned advertising delivery platform.

Preferably, before calculating and obtaining the remaining consuming duration of the advertisement fee of the advertiser to be analyzed at the target moment according to the predicted value of the advertiser to be analyzed's advertising expense consumption at the target moment, the method further includes:

Acquiring the advertising fee balance of the advertiser to be analyzed on the advertising delivery platform at the target moment.

Preferably, the remaining consuming duration of the advertising fee of the advertiser to be analyzed at the target moment is calculated according to the predicted value of the advertiser's advertising fee consumption at the target moment, including:

Obtaining the initial advertising fee amount of the advertiser to be analyzed on the advertisement delivery platform, and calculating the advertising fee consumption amount of the advertiser to be analyzed according to the advertising fee balance of the advertiser to be analyzed;

Obtaining the duration of advertisement delivery corresponding to the consumption amount of the advertisement fee, calculating the ratio between the consumption amount of the advertisement fee of the advertiser to be analyzed and the duration of the advertisement delivery, and recording the ratio as the unit price of the advertisement fee;

Calculating the ratio between the predicted advertising expense consumption of the advertiser to be analyzed at the target moment and the unit price of the advertising expense to obtain the remaining consuming duration of the advertising expense of the advertiser to be analyzed at the target moment.

A device for early warning of advertising fee balance, comprising:

The prediction module is used to obtain the historical consumption data of advertising expenses of the advertising delivery platform, and predict the consumption amount of advertising expenses of the advertising delivery platform at the target moment according to the historical consumption data of advertising expenses;

A determining module, configured to determine the distribution coefficient of the advertiser to be analyzed on the advertising cost consumption on the advertising platform according to the advertising cost consumption amount of each advertiser on the advertising platform at the target historical moment;

The first calculation module is used to calculate and obtain the advertiser to be analyzed according to the advertising expense consumption amount of the advertisement delivery platform at the target moment and the advertisement expense consumption distribution coefficient of the advertiser to be analyzed on the advertisement delivery platform. The predicted value of advertising cost consumption at each moment;

The second calculation module is used to calculate the remaining consuming duration of the advertisement fee of the advertiser to be analyzed at the target moment according to the predicted value of the advertisement fee consumption of the advertiser to be analyzed at the target moment;

A judging module, configured to judge whether the remaining consumable time meets the preset warning time range, and if yes, perform a warning.

Preferably, it also includes:

The sending module is configured to generate early warning information according to the remaining consumable duration when an early warning is issued, and send the early warning information to the advertiser to be analyzed.

Preferably, the determination module includes:

The processing unit is used to add and process the amount of advertising expense consumption of each advertiser on the advertisement delivery platform at the target historical moment, so as to obtain the total value of the advertising expense consumption of each advertiser at the target historical moment;

The first calculation unit is used to calculate the ratio between the advertising fee consumption value of the advertiser to be analyzed and the total advertising fee consumption value of each advertiser at the target historical moment, and record the ratio as the The advertising cost consumption distribution coefficient of the advertiser on the advertising delivery platform is to be analyzed.

Preferably, it also includes:

The balance obtaining module is used to obtain the advertising fee balance of the advertiser to be analyzed on the advertising delivery platform at the target moment.

Preferably, the second calculation module includes:

The second calculation unit is used to obtain the initial advertising fee amount of the advertiser to be analyzed on the advertisement delivery platform, and calculate the advertising fee of the advertiser to be analyzed according to the balance of the advertisement fee of the advertiser to be analyzed consumption amount;

The third calculation unit is used to obtain the advertisement delivery duration corresponding to the advertising fee consumption amount, calculate the ratio between the advertising fee consumption amount of the advertiser to be analyzed and the advertisement delivery duration, and calculate the ratio Recorded as the unit price of advertising expenses;

The fourth calculation unit is used to calculate the ratio between the predicted value of advertising expense consumption of the advertiser to be analyzed at the target moment and the unit price of the advertising expense, and obtain the remaining possible advertising expense of the advertiser to be analyzed at the target moment. Duration of consumption.

Compared with the prior art, the present invention first predicts the advertising expense consumption amount of the advertisement placement platform at the target time according to the advertisement expense history consumption data of the advertisement placement platform; then determines the advertisement expense consumption of the advertiser to be analyzed on the advertisement placement platform Distribution coefficient, and based on this coefficient, the predicted value of the advertising cost consumption of the advertiser to be analyzed at the target time is calculated. Finally, the consumption time of the advertising cost is calculated according to the predicted consumption value, and the early warning function can be realized by judging with the threshold value . Since the calculation of the predicted consumption of the advertiser to be analyzed is obtained by calculating the forecast of the overall consumption of advertising expenses and the distribution coefficient, the predicted consumption of the advertiser to be analyzed is more accurate, and then according to the consumption forecast of the advertiser to be analyzed The value can be used for early warning of consumption time. Since the early warning can be carried out at any target time through the predicted value, the purpose of early warning of the imminent consumption of advertising costs can be realized in advance.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only It is an embodiment of the present invention, and those skilled in the art can also obtain other drawings according to the provided drawings without creative work.

FIG. 1 is a schematic flowchart of a method for early warning of an advertising fee balance provided by an embodiment of the present invention;

FIG. 2 is a schematic flow chart of a method for determining an advertising cost allocation coefficient provided by an embodiment of the present invention;

FIG. 3 is a schematic flow chart of a method for calculating the remaining consumable duration provided by an embodiment of the present invention;

Fig. 4 is a schematic structural diagram of an advertising fee balance early warning device provided by an embodiment of the present invention.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

Referring to FIG. 1, it is a schematic flow chart of a method for early warning of advertising fee balance provided by an embodiment of the present invention. The method may include the following steps:

S11. Obtain the historical consumption data of advertising costs of the advertising delivery platform, and predict the consumption amount of advertising costs of the advertising delivery platform at the target time according to the historical consumption data of advertising costs;

S12. According to the amount of advertising expense consumption of each advertiser on the advertising delivery platform at the target historical moment, determine the advertising expense consumption distribution coefficient of the advertiser to be analyzed on the advertising delivery platform;

S13. Calculate and obtain the advertising cost consumption of the advertiser to be analyzed at the target time according to the advertising cost consumption amount of the advertising delivery platform at the target time and the advertising cost consumption distribution coefficient of the advertiser to be analyzed on the advertising delivery platform Predictive value;

S14. According to the predicted value of the advertising expense consumption of the advertiser to be analyzed at the target moment, calculate and obtain the remaining consuming duration of the advertising expense of the advertiser to be analyzed at the target moment;

S15. Judging whether the remaining consumable duration satisfies the preset warning duration range, if yes, execute step S16;

S16. Pre-warning.

It can be understood that, in step S11, the historical consumption data of the advertising platform is the historical consumption data of the overall advertising amount received by the advertising platform from each advertiser. For example, the platform is a video platform, and the collected Historical advertising data, the advertising costs of each advertiser in the historical advertising data, that is, the overall advertising of the advertiser on the video platform, that is, including the advertising cost data of each advertiser on the video platform, and the advertising cost of the advertiser The advertising cost is the overall data of the advertising cost of the video platform, that is, some advertisers will place the cost of multiple advertisements on the video platform, and can obtain the consumption of each advertiser's advertising cost in real time.

In this embodiment, it is preferable to use the ARIMA model to predict the consumption amount of the advertising fee according to the historical consumption data of the advertising fee. The full name of the ARIMA model is the Autoregressive Integrated Moving Average Model (ARIMA for short), which is a time series forecasting method, which refers to converting a non-stationary time series into a stationary time series, and then the dependent variable is only applied to its lag value And the model established by regression of the present value and lag value of the random error term. Therefore, through the ARIMA model, the current moment can be used as the segmentation point, and the historical data before the current moment can be used to predict the overall consumption of advertising costs after the current moment. The predicted value is accurate. Of course, the ARIMA model is not the only prediction model or algorithm, and other algorithms or models can also be used for prediction, but this model is the most accurate prediction model, and it is also the preferred model of this embodiment.

In step S12, the advertising cost allocation coefficient of the advertiser to be analyzed on the advertising delivery platform is determined, as shown in FIG. 2 for details. This process may include the following steps:

S121. Summing the amount of advertising expense consumption of each advertiser on the advertisement delivery platform at the target historical moment to obtain the total amount of advertising expense consumption of each advertiser at the target historical moment;

S122. Calculate the ratio between the advertising fee consumption value of the advertiser to be analyzed at the target historical moment and the total advertising fee consumption value of each advertiser, and record the ratio as the advertiser to be analyzed The advertising cost consumption distribution coefficient on the advertising delivery platform.

The target historical moment is a real data time point before the predicted moment. For example, if the target moment to be analyzed is set to January 2, the target historical moment can be any moment on or before January 1, but when the target historical moment is selected In terms of time, it is necessary to consider the entry time of the advertiser to be analyzed on the advertising delivery platform. Taking the above example as an example, for example, the time when the advertiser to be analyzed entered the advertising delivery platform is December 20, then the target historical moment The selection of should be a certain time between December 20 and January 1 of the next year, because there is no statistical significance for the advertiser to be analyzed during this period, and there is no predictive value after that.

During the process of advertising, the advertiser will choose the playing period of the advertisement, wherein the playing period includes the expected playing cycle and a fixed playing time period every day. The software platform or application program will play the advertisement according to the playing period selected by the advertiser. After the advertisement is played during this period, the amount corresponding to the period will be deducted from the advertiser's advertising fee. Therefore, the consumption of the advertiser at each moment accounts for The ratio is basically stable. Therefore, in the analysis process, the broadcast time period selected by the advertiser to be analyzed is selected for analysis, and the total amount of advertising fee consumption of each advertiser at the current moment within the broadcast time period is obtained. The total consumption amount at this time is advertising The sum of consumption amounts of all advertisers undertaken by the delivery platform. Furthermore, the consumption amount of each advertiser can be obtained, and the consumption distribution coefficient of each advertiser in the total consumption amount can be obtained by taking the ratio between the consumption amount of each advertiser and the total consumption amount. For example, the number of advertisers in a certain broadcasting period on a certain video broadcasting platform is stable. Assume that the total amount of advertising expenses consumed by each advertiser in this broadcasting period is 10,000 yuan, and there are three advertisers at this time. The consumption amount of the first advertiser is 3,000 yuan, the consumption amount of the second advertiser is 2,000 yuan, and the consumption amount of the third advertiser is 5,000 yuan. If the advertiser to be analyzed is the third advertiser, Then the distribution coefficient of the third advertiser at this moment is 0.5.

After the distribution coefficient is obtained, the predicted value of the overall consumption of advertising expenses can be obtained according to the forecast, and the predicted consumption value of the advertiser to be analyzed can be calculated. That is, the product of the consumption distribution coefficient of the advertiser to be analyzed and the consumption amount of the advertisement fee is calculated to obtain the predicted consumption value of the advertiser to be analyzed. Therefore, through the calculation of the overall forecast and distribution coefficient, the accuracy of the future consumption forecast of the advertiser to be analyzed is improved.

After calculating the predicted value of advertising cost consumption of the advertiser to be analyzed at the target moment, the remaining consumable duration will be calculated according to step S15. Please refer to Figure 3. In the embodiment of the present invention, a method for calculating the remaining consumable duration is also provided. methods can include:

S151. Obtain the initial advertising fee amount of the advertiser to be analyzed on the advertisement delivery platform, and calculate the advertising fee consumption amount of the advertiser to be analyzed according to the advertising fee balance of the advertiser to be analyzed at the target time;

S152. Obtain the duration of advertisement delivery corresponding to the consumption amount of the advertisement fee, calculate the ratio between the consumption amount of the advertisement fee of the advertiser to be analyzed and the duration of the advertisement delivery, and record the ratio as the unit price of the advertisement fee ;

S153. Calculate the ratio between the predicted advertising cost consumption of the advertiser to be analyzed at the target time and the unit price of the advertising cost, and obtain the remaining consuming duration of the advertising cost of the advertiser to be analyzed at the target time.

It should be noted that, before step S15 is executed, it is also necessary to obtain the advertising fee balance of the advertiser to be analyzed on the advertising delivery platform at the target moment. Then in step S151, the advertising expense consumption amount of the advertiser to be analyzed at the target time is calculated, which can be obtained by subtracting the initial advertising expense amount and the real-time expense balance. For example, the initial advertising amount is 50,000 yuan, If the balance of the advertising fee is 20,000 yuan, the consumption amount of the advertising fee is 30,000 yuan, which is the accurate consumption amount of the advertiser to be analyzed at the target time.

The consumed amount of the advertiser to be analyzed at the current moment is known, and the consumption time is also known, so it can be calculated that the consumption amount within the unit time period before the current moment is also known, and is obtained according to the consumed amount , the accuracy of this value is higher.

Because the advertising period of the advertiser is fixed, the amount of consumption per unit time is also accurate. According to the ratio, the predicted consumption value of the advertiser to be analyzed is calculated to obtain the remaining consumable amount of the advertiser to be analyzed. duration. Compared with calculating the remaining time directly based on the remaining amount, the calculation based on the advertiser's consumption prediction value to be analyzed can better reflect the accuracy of the advertiser's remaining consuming time. Because the predicted consumption of advertisers to be analyzed is obtained through the proportionate distribution of the predicted overall consumption, it can better reflect the distribution of future consumption of advertisers to be analyzed, while the calculation of the remaining time based on the remaining amount only reflects that the average level of consumption is not representative .

After obtaining the remaining consumable duration of the advertiser to be analyzed, it is judged through the duration range of the warning, and the warning is given according to the judgment result.

On the basis of the technical solution provided in this embodiment, the embodiment of the present invention also provides a method for triggering an early warning, including:

When an early warning is issued, early warning information will be generated according to the remaining consuming time, and the early warning information will be sent to the advertiser to be analyzed.

First, an early warning message is generated based on the remaining consumable time. The early warning information can include warning priority information. For example, if the remaining consumable time is extremely short, the priority of the early warning information will be the highest. It can also include the remaining time length prompt information, that is, the early warning information The remaining time is displayed in , which can be flexibly configured according to actual usage scenarios.

When sending the early warning information to the advertiser to be analyzed, it is necessary to obtain the contact information of the advertiser to be analyzed in advance, and determine the sending method, such as whether to give priority to email or SMS, which mainly depends on the receiving habits of the advertiser, that is, Make corresponding settings according to the receiving habits of the advertiser.

It should be noted that the target time in this embodiment of the present invention refers to the time when the advertiser to be analyzed conducts cost warning analysis. Of course, this time can also be a certain time in the future, that is, a time that has not occurred, and the time in this embodiment The method can carry out real-time analysis on the early warning of the advertising cost balance, that is, select a time granularity, and perform an analysis every time this time granularity, which can be set in minutes or days, according to the actual demand and purpose, and the present invention does not limit it .

According to the technical scheme of a method for early warning of advertising fee balance disclosed by the embodiment of the present invention, firstly, the advertising fee consumption amount of the advertising delivery platform at the target time is obtained by predicting the advertising fee historical consumption data of the advertising delivery platform; and then the advertisement to be analyzed is determined. The advertising cost consumption allocation coefficient of the advertiser on the advertising delivery platform, and based on this coefficient, the predicted advertising cost consumption of the advertiser to be analyzed at the target time is calculated, and finally, the consumption time of the advertising cost is calculated based on the predicted consumption value , judging with the threshold can finally realize the early warning function. Since the calculation of the predicted consumption of the advertiser to be analyzed is obtained by calculating the forecast of the overall consumption of advertising expenses and the distribution coefficient, the predicted consumption of the advertiser to be analyzed is more accurate, and then according to the consumption forecast of the advertiser to be analyzed The value can be used for early warning of consumption time. Since the early warning can be carried out at any target time through the predicted value, the purpose of early warning of the imminent consumption of advertising costs can be realized in advance.

Corresponding to the method for early warning of advertising fee balance provided by the embodiment of the present invention, the embodiment of the present invention also provides a device for early warning of the balance of advertising fee, see Figure 4, the device includes:

The prediction module 1 is used to obtain the historical consumption data of advertising expenses of the advertising delivery platform, and predict the consumption amount of the advertising expenses of the advertising delivery platform at the target moment according to the historical consumption data of the advertising expenses;

Determining module 2, for determining the advertising cost consumption distribution coefficient of the advertiser to be analyzed on the advertising delivery platform according to the advertising fee consumption amount of each advertiser on the advertising delivery platform at the target historical moment;

The first calculation module 3 is used to calculate and obtain the advertiser to be analyzed according to the advertising expense consumption amount of the advertisement delivery platform at the target moment and the advertisement expense consumption distribution coefficient of the advertiser to be analyzed on the advertisement delivery platform. The predicted value of advertising cost consumption at the target moment;

The second calculation module 4 is used to calculate the remaining consuming duration of the advertisement fee of the advertiser to be analyzed at the target moment according to the predicted value of the advertisement fee consumption of the advertiser to be analyzed at the target moment;

The judging module 5 is used to judge whether the remaining consumable duration satisfies the preset warning duration range, and if so, perform a warning.

Correspondingly, it also includes:

The sending module is configured to generate early warning information according to the remaining consumable duration when an early warning is issued, and send the early warning information to the advertiser to be analyzed.

Specifically, the determination module includes:

The processing unit is used to add and process the amount of advertising expense consumption of each advertiser on the advertisement delivery platform at the target historical moment, so as to obtain the total value of the advertising expense consumption of each advertiser at the target historical moment;

The first calculation unit is used to calculate the ratio between the advertising fee consumption value of the advertiser to be analyzed and the total advertising fee consumption value of each advertiser at the target historical moment, and record the ratio as the The advertising cost consumption distribution coefficient of the advertiser on the advertising delivery platform is to be analyzed.

Correspondingly, it also includes:

The balance obtaining module is used to obtain the advertising fee balance of the advertiser to be analyzed on the advertising delivery platform at the target moment.

Specifically, the second calculation module includes:

The second calculation unit is used to obtain the initial advertising fee amount of the advertiser to be analyzed on the advertisement delivery platform, and calculate the advertising fee of the advertiser to be analyzed according to the balance of the advertisement fee of the advertiser to be analyzed consumption amount;

The third calculation unit is used to obtain the advertisement delivery duration corresponding to the advertising fee consumption amount, calculate the ratio between the advertising fee consumption amount of the advertiser to be analyzed and the advertisement delivery duration, and calculate the ratio recorded as the unit price of advertising expenses;

The fourth calculation unit is used to calculate the ratio between the predicted value of advertising expense consumption of the advertiser to be analyzed at the target moment and the unit price of the advertising expense, and obtain the remaining possible advertising expense of the advertiser to be analyzed at the target moment. Duration of consumption.

In the advertising fee balance early warning device provided by the embodiment of the present invention, the advertising fee consumption amount of the advertising delivery platform at the target time is obtained through the prediction module, and then the consumption distribution coefficient of the advertiser to be analyzed is determined through the determination module, and then through The first calculation module and the second calculation module calculate the remaining consuming time of the advertiser to be analyzed at the target time, and finally judge with the warning time range in the judgment module to realize the early warning. Since the calculation of the predicted consumption of the advertiser to be analyzed is obtained by calculating the forecast of the overall consumption of advertising expenses and the distribution coefficient, the predicted consumption of the advertiser to be analyzed is more accurate, and then according to the consumption forecast of the advertiser to be analyzed The value can be used for early warning of consumption time. Since the early warning can be carried out at any target time through the predicted value, the purpose of early warning of the imminent consumption of advertising costs can be realized in advance.

The terms "first" and "second" in the description and claims of the present invention and the above drawings are used to distinguish different objects, rather than to describe a specific order. Furthermore, the terms "comprising" and "having", and any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, product or apparatus comprising a series of steps or units is not defined by listed steps or units, but may include unlisted steps or units.

Each embodiment in this specification is described in a progressive manner, each embodiment focuses on the difference from other embodiments, and the same and similar parts of each embodiment can be referred to each other. As for the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and for the related information, please refer to the description of the method part.

The above description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention will not be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (10)

1. A kind of 1. method of advertising expenditure remaining sum early warning, it is characterised in that this method includes：

   The advertising expenditure history consumption data of advertisement launching platform is obtained, and is predicted according to the advertising expenditure history consumption data Obtain the advertising expenditure consumption amount of advertisement launching platform described in object time；

   According to target histories moment each advertiser in the advertising expenditure consumption amount of the advertisement launching platform, determine to be analyzed Advertiser consumes distribution coefficient in the advertising expenditure of the advertisement launching platform；

   According to the advertising expenditure consumption amount of advertisement launching platform described in object time and the advertiser to be analyzed described wide The advertising expenditure consumption distribution coefficient of release platform is accused, advertising expenditure of the advertiser to be analyzed in object time is calculated Consumption forecast value；

   According to the advertiser to be analyzed in the advertising expenditure consumption forecast value of object time, the advertisement to be analyzed is calculated The main residue in the advertising expenditure of object time can consume duration；

   Judging the residue can consume whether duration meets default early warning duration scope, if it is, carrying out early warning.
2. 2. according to the method described in claim 1, it is characterized in that, this method further includes：

   When carrying out early warning, will can be consumed according to the residue duration generation warning information, and by the warning information send to The advertiser to be analyzed.
3. 3. according to the method described in claim 1, it is characterized in that, it is described according to target histories moment each advertiser described The advertising expenditure consumption amount of advertisement launching platform, determines advertising expense of the advertiser to be analyzed in the advertisement launching platform With consumption distribution coefficient, including：

   Target histories moment each advertiser is summed up in the advertising expenditure consumption amount of the advertisement launching platform, Obtain consuming total value in the advertising expenditure of each advertiser at the target histories moment；

   Calculate the advertising expenditure consumption numerical value in the advertiser to be analyzed at the target histories moment and each advertisement Ratio between main advertising expenditure consumption total value, is denoted as the advertiser to be analyzed by the ratio and is put down in the advertisement putting The advertising expenditure consumption distribution coefficient of platform.
4. 4. according to the method described in claim 1, it is characterized in that, it is described according to the advertiser to be analyzed in object time Advertising expenditure consumption forecast value, when the residue of advertising expenditure of the advertiser to be analyzed in object time, which is calculated, to consume Before length, further include：

   Obtain the object time the advertiser to be analyzed the advertisement launching platform advertising expenditure remaining sum.
5. 5. according to the method described in claim 4, it is characterized in that, it is described according to the advertiser to be analyzed in object time Advertising expenditure consumption forecast value, when the residue of advertising expenditure of the advertiser to be analyzed in object time, which is calculated, to consume It is long, including：

   Initial ad Fee Amount of the advertiser to be analyzed in the advertisement launching platform is obtained, and according to object time institute The advertising expenditure remaining sum of advertiser to be analyzed is stated, the advertising expenditure consumption amount of the advertiser to be analyzed is calculated；

   Advertisement putting duration corresponding with the advertising expenditure consumption amount is obtained, calculates the described wide of the advertiser to be analyzed The ratio between the cost consumption amount of money and the advertisement putting duration is accused, the ratio is denoted as advertising expenditure unit price；

   The advertiser to be analyzed is calculated between the advertising expenditure consumption forecast value of object time and the advertising expenditure unit price Ratio, duration can be consumed by obtaining the residue of advertising expenditure of the advertiser to be analyzed in object time.
6. A kind of 6. device of advertising expenditure remaining sum early warning, it is characterised in that including：

   Prediction module, for obtaining the advertising expenditure history consumption data of advertisement launching platform, and goes through according to the advertising expenditure History consumption data predicts to obtain the advertising expenditure consumption amount of advertisement launching platform described in object time；

   Determining module, for consuming gold in the advertising expenditure of the advertisement launching platform according to target histories moment each advertiser Volume, determines that advertiser to be analyzed consumes distribution coefficient in the advertising expenditure of the advertisement launching platform；

   First computing module, for the advertising expenditure consumption amount according to advertisement launching platform described in object time and described is treated point The advertising expenditure that advertiser is analysed in the advertisement launching platform consumes distribution coefficient, and the advertiser to be analyzed is calculated in mesh The advertising expenditure consumption forecast value that timestamp is carved；

   Second computing module, for according to the advertiser to be analyzed object time advertising expenditure consumption forecast value, calculate Duration can be consumed by obtaining the residue of advertising expenditure of the advertiser to be analyzed in object time；

   Judgment module, for judging that the residue can consume whether duration meets default early warning duration scope, if it is, into Row early warning.
7. 7. the device stated according to claim 6, it is characterised in that further include：

   Sending module, for duration generation warning information when carrying out early warning, will can be consumed according to the residue, and will be described pre- Alert information is sent to the advertiser to be analyzed.
8. 8. device according to claim 6, it is characterised in that the determining module includes：

   Processing unit, for by target histories moment each advertiser the advertisement launching platform advertising expenditure consumption amount Sum up, obtain consuming total value in the advertising expenditure of each advertiser at the target histories moment；

   First computing unit, the advertising expenditure for calculating in the advertiser to be analyzed at the target histories moment consume number Ratio between value and the advertising expenditure of each advertiser consumption total value, the advertiser to be analyzed is denoted as by the ratio Distribution coefficient is consumed in the advertising expenditure of the advertisement launching platform.
9. 9. device according to claim 6, it is characterised in that further include：

   Remaining sum acquisition module, for obtaining the advertiser to be analyzed in the object time in the advertisement launching platform Advertising expenditure remaining sum.
10. 10. device according to claim 9, it is characterised in that second computing module includes：

    Second computing unit, for obtaining initial ad expense gold of the advertiser to be analyzed in the advertisement launching platform Volume, and according to the advertising expenditure remaining sum of the advertiser to be analyzed, the advertising expenditure that the advertiser to be analyzed is calculated disappears Consume the amount of money；

    3rd computing unit, for obtaining advertisement putting duration corresponding with the advertising expenditure consumption amount, is treated described in calculating The ratio between the advertising expenditure consumption amount of advertiser and the advertisement putting duration is analyzed, the ratio is denoted as extensively Accuse expense unit price；

    4th computing unit, for calculate the advertiser to be analyzed object time advertising expenditure consumption forecast value with it is described Ratio between advertising expenditure unit price, when obtaining the residue of advertising expenditure of the advertiser to be analyzed in object time can consume It is long.