CN117217830B - Advertisement bill monitoring and identifying method, system and readable storage medium - Google Patents
Advertisement bill monitoring and identifying method, system and readable storage medium Download PDFInfo
- Publication number
- CN117217830B CN117217830B CN202311465909.XA CN202311465909A CN117217830B CN 117217830 B CN117217830 B CN 117217830B CN 202311465909 A CN202311465909 A CN 202311465909A CN 117217830 B CN117217830 B CN 117217830B
- Authority
- CN
- China
- Prior art keywords
- data
- advertisement
- curve
- time period
- click
- 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 38
- 238000012544 monitoring process Methods 0.000 title claims abstract description 30
- 230000002159 abnormal effect Effects 0.000 claims abstract description 108
- 238000001514 detection method Methods 0.000 claims abstract description 46
- 230000001680 brushing effect Effects 0.000 claims abstract description 27
- 238000001914 filtration Methods 0.000 claims abstract description 19
- 230000006399 behavior Effects 0.000 claims description 22
- 230000008859 change Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 9
- 230000008901 benefit Effects 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000007789 sealing Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000000903 blocking effect Effects 0.000 claims description 5
- 238000007405 data analysis Methods 0.000 claims description 3
- 238000004088 simulation Methods 0.000 claims 4
- 230000011218 segmentation Effects 0.000 abstract description 3
- 238000004458 analytical method Methods 0.000 description 6
- 230000005856 abnormality Effects 0.000 description 4
- 238000013475 authorization Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 206010000117 Abnormal behaviour Diseases 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 235000014510 cooky Nutrition 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000005242 forging Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an advertisement bill monitoring and identifying method, a system and a readable storage medium, wherein the method comprises the following steps: acquiring advertisement click data; analyzing according to the advertisement click data, and filtering the invalid click data to obtain effective click data; drawing a daily related data curve according to the effective click data; setting a reference interval curve for the daily relevant data curve according to the historical data, and marking abnormal data in the daily relevant data curve based on the reference interval curve; analyzing according to the abnormal data to obtain advertisement brushing lines of each time period as detection data; and integrating the bill detection data of each time period to obtain the bill detection data of the advertisement bill. According to the invention, the daily related data curve is set with the reference interval curve through the living rule of the advertisement facing the user, and the advertisement click data is analyzed in a time period segmentation mode, so that the efficiency and the accuracy of advertisement brushing row behavior detection are improved.
Description
Technical Field
The present application relates to the field of data processing and data transmission, and more particularly, to a method, a system, and a readable storage medium for monitoring and identifying advertisement listings.
Background
At present, the internet advertisement platform adopts some basic anti-cheating technologies, such as IP filtering, cookie identification and equipment identification, and the methods judge whether malicious traffic exists by detecting the IP address, cookie and equipment characteristics of a user, but the methods have the following defects:
1. the method is easy to bypass, and an attacker can hide own real request information by using a proxy server and an application splitting and code forging mode;
2. lack of accuracy, multiple users may share one IP address, possibly causing erroneous judgment; in addition, there are advanced anti-cheating technologies, for example, machine learning, which are used for identifying malicious traffic through analysis modeling and filtering of advertisement click data, but these methods require a large amount of training data, and require a large amount of time and resources to perform model training optimization.
Therefore, the prior art has defects, and improvement is needed.
Disclosure of Invention
In view of the above problems, an object of the present invention is to provide a method, a system and a readable storage medium for monitoring and identifying advertisement brush bill, which records information such as ID, device identifier, IP address, operation record, etc. of a user in detail through a big data database, and records and statistics the click operation performance of advertisement completely. Modeling analysis is carried out by a big data statistical analysis method, and according to the overall data of the statistical history, the larger the data quantity is, the more accurate the identification is, the cheating abnormal behavior is accurately identified, and the cheating abnormal behavior cannot be bypassed by an attacker.
The first aspect of the invention provides an advertisement brush bill monitoring and identifying method, which comprises the following steps:
acquiring advertisement click data;
analyzing according to the advertisement click data, and filtering invalid click data to obtain effective click data;
drawing a daily related data curve according to the effective click data;
setting a reference interval curve for the daily relevant data curve according to historical data, and marking abnormal data in the daily relevant data curve based on the reference interval curve;
analyzing according to the abnormal data to obtain advertisement brushing list as detection data in each time period;
and integrating the bill detection data of each time period to obtain advertisement bill detection data.
In this scheme, the analyzing according to the advertisement click data filters invalid click data, including:
acquiring a user ID, a device identifier and a device ip address;
judging whether the user ID and the equipment identifier are consistent with user data stored in a database;
if the access intervals are inconsistent, the access interval between the current access time and the last access time of the user ID is calculated, if the access interval is larger than a first preset threshold value, the user ID is judged to be an invalid user, otherwise, the user data in the database is updated;
If the device ip addresses are consistent, analyzing according to the device ip addresses, and judging whether the device ip addresses are in the advertising area or not;
if not, judging the advertisement click data to be invalid click data, and filtering the invalid click data;
if so, the advertisement click data is effective click data.
In this scheme, still include:
the daily related data curve is at least one of a unit time advertisement display frequency curve, a unit time total click frequency curve, a unit time average click frequency curve and a unit time advertisement conversion data curve.
In this aspect, the setting a reference interval curve for the daily relevant data curve according to historical data, and marking abnormal data in the daily relevant data curve based on the reference interval curve includes:
according to the data change condition of advertisement click data in each time period in the historical data, respectively setting a corresponding threshold interval for each item of related data in the daily advertisement click data in each time period;
drawing a reference interval curve for each item of related data according to the corresponding threshold interval;
Comparing the daily related data curves with corresponding reference interval curves respectively, and marking data which are not in the reference interval curves to obtain abnormal data;
the reference interval curve includes a first reference interval curve and a second reference interval curve.
In this scheme, according to the analysis is carried out to the abnormal data, obtain the advertisement brush row of every time quantum and be the detection data, include:
multiplying each item of abnormal data in each time period by corresponding weight respectively, and accumulating calculation results to obtain data abnormal values of each time period;
comparing the abnormal value of the data in each time period with a second preset threshold value respectively, and if the abnormal value of the data in the current time period is larger than the second preset threshold value, judging that advertisement bill behavior exists in the current time period; otherwise, it is not present.
In this scheme, still include:
analyzing advertisement click data with advertisement brushing row as a time period to obtain an abnormal user ID;
performing blocking processing on the abnormal user ID;
and sealing and banning the benefits generated by the abnormal user ID, and banning the presentation.
The second aspect of the present invention provides an advertisement bill monitoring and identifying system, comprising a memory and a processor, wherein the memory comprises an advertisement bill monitoring and identifying method program, and the advertisement bill monitoring and identifying method program when executed by the processor realizes the following steps:
The data acquisition module is used for acquiring advertisement click data;
the data analysis module is used for analyzing the advertisement click data and filtering the invalid click data to obtain effective click data; drawing a daily related data curve according to the effective click data; setting a reference interval curve for the daily relevant data curve according to historical data, and marking abnormal data in the daily relevant data curve based on the reference interval curve; analyzing according to the abnormal data to obtain advertisement brushing list as detection data in each time period; and integrating the bill detection data of each time period to obtain advertisement bill detection data.
In this scheme, the analyzing according to the advertisement click data filters invalid click data, including:
acquiring a user ID, a device identifier and a device ip address;
judging whether the user ID and the equipment identifier are consistent with user data stored in a database;
if the access intervals are inconsistent, the access interval between the current access time and the last access time of the user ID is calculated, if the access interval is larger than a first preset threshold value, the user ID is judged to be an invalid user, otherwise, the user data in the database is updated;
If the device ip addresses are consistent, analyzing according to the device ip addresses, and judging whether the device ip addresses are in the advertising area or not;
if not, judging the advertisement click data to be invalid click data, and filtering the invalid click data;
if so, the advertisement click data is effective click data.
In this scheme, still include:
the daily related data curve is at least one of a unit time advertisement display frequency curve, a unit time total click frequency curve, a unit time average click frequency curve and a unit time advertisement conversion data curve.
In this aspect, the setting a reference interval curve for the daily relevant data curve according to historical data, and marking abnormal data in the daily relevant data curve based on the reference interval curve includes:
according to the data change condition of advertisement click data in each time period in the historical data, respectively setting a corresponding threshold interval for each item of related data in the daily advertisement click data in each time period;
drawing a reference interval curve for each item of related data according to the corresponding threshold interval;
Comparing the daily related data curves with corresponding reference interval curves respectively, and marking data which are not in the reference interval curves to obtain abnormal data;
the reference interval curve includes a first reference interval curve and a second reference interval curve.
In this scheme, according to the analysis is carried out to the abnormal data, obtain the advertisement brush row of every time quantum and be the detection data, include:
multiplying each item of abnormal data in each time period by corresponding weight respectively, and accumulating calculation results to obtain data abnormal values of each time period;
comparing the abnormal value of the data in each time period with a second preset threshold value respectively, and if the abnormal value of the data in the current time period is larger than the second preset threshold value, judging that advertisement bill behavior exists in the current time period; otherwise, it is not present.
In this scheme, still include:
analyzing advertisement click data with advertisement brushing row as a time period to obtain an abnormal user ID;
performing blocking processing on the abnormal user ID;
and sealing and banning the benefits generated by the abnormal user ID, and banning the presentation.
A third aspect of the present invention provides a computer-readable storage medium having embodied therein an advertisement brush bill monitoring and identifying method program which, when executed by a processor, implements the steps of an advertisement brush bill monitoring and identifying method as described in any one of the above.
The invention discloses an advertisement bill monitoring and identifying method, a system and a readable storage medium, wherein the method comprises the following steps: acquiring advertisement click data; analyzing according to the advertisement click data, and filtering the invalid click data to obtain effective click data; drawing a daily related data curve according to the effective click data; setting a reference interval curve for the daily relevant data curve according to the historical data, and marking abnormal data in the daily relevant data curve based on the reference interval curve; analyzing according to the abnormal data to obtain advertisement brushing lines of each time period as detection data; and integrating the bill detection data of each time period to obtain the bill detection data of the advertisement bill. According to the invention, the daily related data curve is set with the reference interval curve through the living rule of the advertisement facing the user, and the advertisement click data is analyzed in a time period segmentation mode, so that the efficiency and the accuracy of advertisement brushing row behavior detection are improved.
Drawings
FIG. 1 is a flow chart of an advertisement brush bill monitoring and identifying method of the present invention;
FIG. 2 is a flow chart of a method of marking abnormal data in a daily relevant data curve in accordance with the present invention;
FIG. 3 is a flow chart showing a method of detecting advertisement brush behavior for each time slot according to the present invention;
FIG. 4 illustrates a block diagram of an advertisement brush bill monitoring and identification system of the present invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
FIG. 1 shows a flow chart of an advertisement brush bill monitoring and identifying method of the present invention.
As shown in fig. 1, the invention discloses an advertisement brush bill monitoring and identifying method, which comprises the following steps:
s102, acquiring advertisement click data;
s104, analyzing according to the advertisement click data, and filtering invalid click data to obtain valid click data;
s106, drawing a daily relevant data curve according to the effective click data;
S108, setting a reference interval curve for the daily relevant data curve according to historical data, and marking abnormal data in the daily relevant data curve based on the reference interval curve;
s110, analyzing according to the abnormal data to obtain advertisement brushing row of each time period as detection data;
and S112, integrating the bill detection data of each time period to obtain advertisement bill detection data.
According to the embodiment of the invention, after the advertisement click data is obtained, the user ID and the equipment identifier are compared with the user data stored in the database through the system, the click data generated by the user with incomplete user information is filtered, the invalid click data outside the advertisement putting area is filtered based on the ip address of the user using the equipment, the quantity of the filtered data is recorded, the invalid click rate of the whole click data is calculated according to the quantity of the filtered data, when the invalid click rate is larger than the preset threshold value of the system, the current advertisement is judged to be attacked by the user, and the preset threshold value of the system is dynamically adjusted according to the historical advertisement click data through the system. When the invalid click rate of the advertisement click data is smaller than a system preset threshold value, a daily relevant data curve is drawn according to the limited click data in the advertisement click data, a corresponding reference interval curve is set for the daily relevant data curve through historical data and advertisement facing life rules of a user, abnormal data in the daily relevant data curve are marked through comparing the daily relevant data curve with the corresponding reference interval curve, advertisement click data with abnormal data time periods are analyzed according to the marked abnormal data, the sum of products of all abnormal data and corresponding influence weights in the current time periods is calculated, and the sum is compared with a second preset threshold value, so that whether the abnormal data in the current time periods are caused by a single brushing line or not is judged. In addition, the invention analyzes the advertisement click data in the time period of the brushing line, seals the user ID of the abnormal user, reduces the network pressure of the advertisement putting page and reduces the economic loss of the client.
According to an embodiment of the present invention, the analyzing the advertisement click data and filtering the invalid click data includes:
acquiring a user ID, a device identifier and a device ip address;
judging whether the user ID and the equipment identifier are consistent with user data stored in a database;
if the access intervals are inconsistent, the access interval between the current access time and the last access time of the user ID is calculated, if the access interval is larger than a first preset threshold value, the user ID is judged to be an invalid user, otherwise, the user data in the database is updated;
if the device ip addresses are consistent, analyzing according to the device ip addresses, and judging whether the device ip addresses are in the advertising area or not;
if not, judging the advertisement click data to be invalid click data, and filtering the invalid click data;
if so, the advertisement click data is effective click data.
It should be noted that, when the user clicks the advertisement, the authorization information of the user is obtained, and after the user is authorized, the user ID of the user using the software and the device identifier of the user using the device are obtained, where each user is used for a unique user ID, the device identifier of the device may be IMEI, MEID, IDFA, UDID, and each device has a unique device identifier, and through the user ID and the device identifier, it can be determined whether the user repeatedly clicks the advertisement by switching the user account or replacing the login device, thereby determining whether the user has a behavior of refreshing.
After the user clicks the advertisement page, the system obtains the user ID and the equipment identifier of the access user according to the user authorization information to obtain access user data, compares the access user data with the user data stored in the database, and if the access user data and the user data are inconsistent, the system indicates that the current user possibly has the function of refreshing or replacing the equipment. Calculating the access interval of clicking advertisements by the user under the condition, and judging that the user replaces the using equipment if the access interval is larger than a first preset threshold value; otherwise, judging that the user switches the user account or changes the login equipment to conduct the action of the game bill. In addition, if the corresponding user data does not exist in the database, the current user is a new user who clicks the advertisement for the first time to enter the advertisement interface, and the user ID and the equipment identifier of the new user are bound to generate the user data and stored in the database. Wherein the first preset threshold is 30 minutes.
Advertisers typically place advertisements regionally based on customer needs, such as placing restaurant advertisements on the user's devices in a range of areas around the restaurant's physical store, thereby achieving the current attractions to the customer's store. The system judges whether the access user is in a preset advertisement putting area or not through the equipment ip address, so that invalid clicks outside the advertisement putting area are filtered.
According to an embodiment of the present invention, further comprising:
the daily related data curve is at least one of a unit time advertisement display frequency curve, a unit time total click frequency curve, a unit time average click frequency curve and a unit time advertisement conversion data curve.
The daily relevant data is counted by taking 24 hours a day as unit time, including daily advertisement display times, daily click total number, daily average click times, daily advertisement conversion data and the like, and the system draws a daily relevant data curve according to the counted relevant data and displays advertisement click data in a visual mode.
FIG. 2 is a flow chart of a method of marking abnormal data in a daily relevant data curve in accordance with the present invention.
As shown in fig. 2, according to an embodiment of the present invention, the setting a reference interval curve for the daily relevant data curve according to historical data, and marking the abnormal data in the daily relevant data curve based on the reference interval curve includes:
s202, according to the data change condition of advertisement click data in historical data in each time period, respectively setting a corresponding threshold interval for each item of related data in the advertisement click data in each time period;
S204, drawing a reference interval curve for each item of related data according to the corresponding threshold interval;
s206, comparing the daily related data curves with corresponding reference interval curves respectively, and marking data which are not in the reference interval curves to obtain abnormal data;
the reference interval curve includes a first reference interval curve and a second reference interval curve.
It should be noted that, the historical data is analyzed integrally, and the abnormal threshold value of the daily relevant data curve is adjusted by combining the daily life rule of the advertisement facing the group. The advertisement click data of each day is different, and in a normal case, the click quantity of the advertisement click data of the late midnight of each day is lower, the change range of the advertisement click data of the working day is larger, the click quantity of the working time of the day is lower, the click quantity of the midday and the rest time of the evening is higher, and the advertisement click data of the weekend and holidays is more stable and the change range is lower. In addition, click data for the advertisement may rise sharply during a holiday associated with the advertisement content. Thus, the system divides the daily relevant data curve into a plurality of sections, for example, a low click section and a high click section, according to the variation amplitude of the advertisement click data. The daily correlation data curve for each interval is then divided into correlation data curves for a plurality of time periods with each full-point time as a standard.
The advertisement clicking data of the current day are simulated through the advertisement clicking data in the same time period in the historical data, the maximum value and the minimum value of the simulated data are used as reference interval curves of the current time period of the current day, all the reference interval curves are connected after the clicking data in all the time periods are simulated, the connection is smoothed to obtain a final reference interval curve, the final reference interval curve comprises a first reference interval curve and a second reference interval curve, the first reference interval curve is formed by the range between the curve drawn by the maximum value and the curve drawn by the minimum value of the simulated data, and the interval range of the second reference interval curve is 120% of the interval range of the first reference interval curve. And comparing each daily related data curve with a corresponding reference interval curve, marking data outside the first reference interval curve as abnormal data, indicating that the current daily related data curve has abnormality, and determining the time corresponding to the abnormal data, the corresponding related data type and the like.
FIG. 3 is a flow chart showing a method of detecting advertisement brush behavior per time period according to the present invention.
As shown in fig. 3, according to an embodiment of the present invention, the analyzing according to the anomaly data to obtain advertisement brush behavior detection data of each time period includes:
s302, multiplying each item of abnormal data in each time period by corresponding weight respectively, and accumulating calculation results to obtain data abnormal values of each time period;
s304, comparing the abnormal value of the data in each time period with a second preset threshold value respectively, and if the abnormal value of the data in the current time period is larger than the second preset threshold value, judging that advertisement bill refreshing behavior exists in the current time period; otherwise, it is not present.
In order to improve the detection efficiency of the advertisement brush list detection, the advertisement brush list detection of each time period is respectively detected, advertisement click data of the time period without abnormal data is automatically filtered in each analysis process of the system, whether the advertisement brush list detection exists in the current time period is judged, and the detection result is normal. And then respectively analyzing the advertisement click data of the time period with the abnormal data, so as to accurately locate the time period with the advertisement bill behavior.
Different weights are respectively arranged between the first reference interval curve and the second reference interval curve and outside the second reference interval curve, the weights between the first reference interval curve and the second reference interval curve are set according to influence factors of different related data on advertisement bill behavior, and the value range is between 0 and 1; the weight outside the second reference interval curve is 1, which indicates that there is advertisement billing behavior in the current time period. The second preset threshold value is obtained by calculating the system according to the advertisement historical delivery data or the historical delivery data of the advertisements of the same type, and the value range is 0-1.
According to an embodiment of the present invention, further comprising:
analyzing advertisement click data with advertisement brushing row as a time period to obtain an abnormal user ID;
performing blocking processing on the abnormal user ID;
and sealing and banning the benefits generated by the abnormal user ID, and banning the presentation.
It should be noted that, the abnormal users include an invalid user, an ip abnormal user and a non-human click user, wherein the invalid user can be judged by the matching relationship between the user ID and the device identifier; the user with the ip abnormality can judge the clicking times and the clicking frequencies of the same ip users with the advertisement brushing row as a time period; the unclassified click users can judge the click areas and the advertisement browsing time of all users in the time period when the advertisement brushing row exists. And then extracting abnormal user IDs through the user data stored in the database, and performing sealing and forbidden processing on the abnormal user IDs to reduce the network pressure of the advertisement putting page. And meanwhile, the benefit generated by the abnormal user ID is blocked, so that the economic loss of the client is reduced.
FIG. 4 illustrates a block diagram of an advertisement brush bill monitoring and identification system of the present invention.
As shown in fig. 4, a second aspect of the present invention provides an advertisement brush bill monitoring and identifying system, comprising:
The data acquisition module is used for acquiring advertisement click data;
the data analysis module is used for analyzing the advertisement click data and filtering the invalid click data to obtain effective click data; drawing a daily related data curve according to the effective click data; setting a reference interval curve for the daily relevant data curve according to historical data, and marking abnormal data in the daily relevant data curve based on the reference interval curve; analyzing according to the abnormal data to obtain advertisement brushing list as detection data in each time period; and integrating the bill detection data of each time period to obtain advertisement bill detection data.
According to the embodiment of the invention, after the advertisement click data is obtained, the user ID and the equipment identifier are compared with the user data stored in the database through the system, the click data generated by the user with incomplete user information is filtered, the invalid click data outside the advertisement putting area is filtered based on the ip address of the user using the equipment, the quantity of the filtered data is recorded, the invalid click rate of the whole click data is calculated according to the quantity of the filtered data, when the invalid click rate is larger than the preset threshold value of the system, the current advertisement is judged to be attacked by the user, and the preset threshold value of the system is dynamically adjusted according to the historical advertisement click data through the system. When the invalid click rate of the advertisement click data is smaller than a system preset threshold value, a daily relevant data curve is drawn according to the limited click data in the advertisement click data, a corresponding reference interval curve is set for the daily relevant data curve through historical data and advertisement facing life rules of a user, abnormal data in the daily relevant data curve are marked through comparing the daily relevant data curve with the corresponding reference interval curve, advertisement click data with abnormal data time periods are analyzed according to the marked abnormal data, the sum of products of all abnormal data and corresponding influence weights in the current time periods is calculated, and the sum is compared with a second preset threshold value, so that whether the abnormal data in the current time periods are caused by a single brushing line or not is judged. In addition, the invention analyzes the advertisement click data in the time period of the brushing line, seals the user ID of the abnormal user, reduces the network pressure of the advertisement putting page and reduces the economic loss of the client.
According to an embodiment of the present invention, the analyzing the advertisement click data and filtering the invalid click data includes:
acquiring a user ID, a device identifier and a device ip address;
judging whether the user ID and the equipment identifier are consistent with user data stored in a database;
if the access intervals are inconsistent, the access interval between the current access time and the last access time of the user ID is calculated, if the access interval is larger than a first preset threshold value, the user ID is judged to be an invalid user, otherwise, the user data in the database is updated;
if the device ip addresses are consistent, analyzing according to the device ip addresses, and judging whether the device ip addresses are in the advertising area or not;
if not, judging the advertisement click data to be invalid click data, and filtering the invalid click data;
if so, the advertisement click data is effective click data.
It should be noted that, when the user clicks the advertisement, the authorization information of the user is obtained, and after the user is authorized, the user ID of the user using the software and the device identifier of the user using the device are obtained, where each user is used for a unique user ID, the device identifier of the device may be IMEI, MEID, IDFA, UDID, and each device has a unique device identifier, and through the user ID and the device identifier, it can be determined whether the user repeatedly clicks the advertisement by switching the user account or replacing the login device, thereby determining whether the user has a behavior of refreshing.
After the user clicks the advertisement page, the system obtains the user ID and the equipment identifier of the access user according to the user authorization information to obtain access user data, compares the access user data with the user data stored in the database, and if the access user data and the user data are inconsistent, the system indicates that the current user possibly has the function of refreshing or replacing the equipment. Calculating the access interval of clicking advertisements by the user under the condition, and judging that the user replaces the using equipment if the access interval is larger than a first preset threshold value; otherwise, judging that the user switches the user account or changes the login equipment to conduct the action of the game bill. In addition, if the corresponding user data does not exist in the database, the current user is a new user who clicks the advertisement for the first time to enter the advertisement interface, and the user ID and the equipment identifier of the new user are bound to generate the user data and stored in the database. Wherein the first preset threshold is 30 minutes.
Advertisers typically place advertisements regionally based on customer needs, such as placing restaurant advertisements on the user's devices in a range of areas around the restaurant's physical store, thereby achieving the current attractions to the customer's store. The system judges whether the access user is in a preset advertisement putting area or not through the equipment ip address, so that invalid clicks outside the advertisement putting area are filtered.
According to an embodiment of the present invention, further comprising:
the daily related data curve is at least one of a unit time advertisement display frequency curve, a unit time total click frequency curve, a unit time average click frequency curve and a unit time advertisement conversion data curve.
The daily relevant data is counted by taking 24 hours a day as unit time, including daily advertisement display times, daily click total number, daily average click times, daily advertisement conversion data and the like, and the system draws a daily relevant data curve according to the counted relevant data and displays advertisement click data in a visual mode.
According to an embodiment of the present invention, the setting a reference interval curve for the daily relevant data curve according to historical data, and marking abnormal data in the daily relevant data curve based on the reference interval curve includes:
according to the data change condition of advertisement click data in each time period in the historical data, respectively setting a corresponding threshold interval for each item of related data in the daily advertisement click data in each time period;
drawing a reference interval curve for each item of related data according to the corresponding threshold interval;
Comparing the daily related data curves with corresponding reference interval curves respectively, and marking data which are not in the reference interval curves to obtain abnormal data;
the reference interval curve includes a first reference interval curve and a second reference interval curve.
It should be noted that, the historical data is analyzed integrally, and the abnormal threshold value of the daily relevant data curve is adjusted by combining the daily life rule of the advertisement facing the group. The advertisement click data of each day is different, and in a normal case, the click quantity of the advertisement click data of the late midnight of each day is lower, the change range of the advertisement click data of the working day is larger, the click quantity of the working time of the day is lower, the click quantity of the midday and the rest time of the evening is higher, and the advertisement click data of the weekend and holidays is more stable and the change range is lower. In addition, click data for the advertisement may rise sharply during a holiday associated with the advertisement content. Thus, the system divides the daily relevant data curve into a plurality of sections, for example, a low click section and a high click section, according to the variation amplitude of the advertisement click data. The daily correlation data curve for each interval is then divided into correlation data curves for a plurality of time periods with each full-point time as a standard.
The advertisement clicking data of the current day are simulated through the advertisement clicking data in the same time period in the historical data, the maximum value and the minimum value of the simulated data are used as reference interval curves of the current time period of the current day, all the reference interval curves are connected after the clicking data in all the time periods are simulated, the connection is smoothed to obtain a final reference interval curve, the final reference interval curve comprises a first reference interval curve and a second reference interval curve, the first reference interval curve is formed by the range between the curve drawn by the maximum value and the curve drawn by the minimum value of the simulated data, and the interval range of the second reference interval curve is 120% of the interval range of the first reference interval curve. And comparing each daily related data curve with a corresponding reference interval curve, marking data outside the first reference interval curve as abnormal data, indicating that the current daily related data curve has abnormality, and determining the time corresponding to the abnormal data, the corresponding related data type and the like.
According to an embodiment of the present invention, the analyzing according to the abnormal data to obtain advertisement brush behavior detection data of each time period includes:
Multiplying each item of abnormal data in each time period by corresponding weight respectively, and accumulating calculation results to obtain data abnormal values of each time period;
comparing the abnormal value of the data in each time period with a second preset threshold value respectively, and if the abnormal value of the data in the current time period is larger than the second preset threshold value, judging that advertisement bill behavior exists in the current time period; otherwise, it is not present.
In order to improve the detection efficiency of the advertisement brush list detection, the advertisement brush list detection of each time period is respectively detected, advertisement click data of the time period without abnormal data is automatically filtered in each analysis process of the system, whether the advertisement brush list detection exists in the current time period is judged, and the detection result is normal. And then respectively analyzing the advertisement click data of the time period with the abnormal data, so as to accurately locate the time period with the advertisement bill behavior.
Different weights are respectively arranged between the first reference interval curve and the second reference interval curve and outside the second reference interval curve, the weights between the first reference interval curve and the second reference interval curve are set according to influence factors of different related data on advertisement bill behavior, and the value range is between 0 and 1; the weight outside the second reference interval curve is 1, which indicates that there is advertisement billing behavior in the current time period. The second preset threshold value is obtained by calculating the system according to the advertisement historical delivery data or the historical delivery data of the advertisements of the same type, and the value range is 0-1.
According to an embodiment of the present invention, further comprising:
analyzing advertisement click data with advertisement brushing row as a time period to obtain an abnormal user ID;
performing blocking processing on the abnormal user ID;
and sealing and banning the benefits generated by the abnormal user ID, and banning the presentation.
It should be noted that, the abnormal users include an invalid user, an ip abnormal user and a non-human click user, wherein the invalid user can be judged by the matching relationship between the user ID and the device identifier; the user with the ip abnormality can judge the clicking times and the clicking frequencies of the same ip users with the advertisement brushing row as a time period; the unclassified click users can judge the click areas and the advertisement browsing time of all users in the time period when the advertisement brushing row exists. And then extracting abnormal user IDs through the user data stored in the database, and performing sealing and forbidden processing on the abnormal user IDs to reduce the network pressure of the advertisement putting page. And meanwhile, the benefit generated by the abnormal user ID is blocked, so that the economic loss of the client is reduced.
A third aspect of the present invention provides a computer-readable storage medium having embodied therein an advertisement brush bill monitoring and identifying method program which, when executed by a processor, implements the steps of an advertisement brush bill monitoring and identifying method as described in any one of the above.
The invention discloses an advertisement bill monitoring and identifying method, a system and a readable storage medium, wherein the method comprises the following steps: acquiring advertisement click data; analyzing according to the advertisement click data, and filtering the invalid click data to obtain effective click data; drawing a daily related data curve according to the effective click data; setting a reference interval curve for the daily relevant data curve according to the historical data, and marking abnormal data in the daily relevant data curve based on the reference interval curve; analyzing according to the abnormal data to obtain advertisement brushing lines of each time period as detection data; and integrating the bill detection data of each time period to obtain the bill detection data of the advertisement bill. According to the invention, the daily related data curve is set with the reference interval curve through the living rule of the advertisement facing the user, and the advertisement click data is analyzed in a time period segmentation mode, so that the efficiency and the accuracy of advertisement brushing row behavior detection are improved.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
Claims (6)
1. The advertisement bill monitoring and identifying method is characterized by comprising the following steps:
acquiring advertisement click data;
analyzing according to the advertisement click data, and filtering invalid click data to obtain effective click data;
drawing a daily related data curve according to the effective click data;
setting a reference interval curve for the daily relevant data curve according to historical data, and marking abnormal data in the daily relevant data curve based on the reference interval curve;
Analyzing according to the abnormal data to obtain advertisement brushing list as detection data in each time period;
integrating the bill detection data of each time period to obtain advertisement bill detection data;
the step of setting a reference interval curve for the daily relevant data curve according to historical data and marking abnormal data in the daily relevant data curve based on the reference interval curve comprises the following steps:
according to the data change condition of advertisement click data in each time period in the historical data, respectively setting a corresponding threshold interval for each item of related data in the daily advertisement click data in each time period;
drawing a reference interval curve for each item of related data according to the corresponding threshold interval;
comparing the daily related data curves with corresponding reference interval curves respectively, and marking data which are not in the reference interval curves to obtain abnormal data;
the reference interval curve comprises a first reference interval curve and a second reference interval curve;
simulating advertisement click data of the current day through advertisement click data in the same time period in the historical data to obtain simulation data; the first reference interval curve consists of a range between a curve drawn by the maximum value and a curve drawn by the minimum value of the simulation data, and the interval range of the second reference interval curve is 120% of the interval range of the first reference interval curve;
Analyzing according to the abnormal data to obtain advertisement brushing row behavior detection data of each time period, wherein the method comprises the following steps:
multiplying each item of abnormal data in each time period by corresponding weight respectively, and accumulating calculation results to obtain data abnormal values of each time period;
comparing the abnormal value of the data in each time period with a second preset threshold value respectively, and if the abnormal value of the data in the current time period is larger than the second preset threshold value, judging that advertisement bill behavior exists in the current time period; otherwise, it is not present.
2. The advertisement brush bill monitoring and recognizing method according to claim 1, wherein the analyzing the invalid click data according to the advertisement click data, filtering the invalid click data, comprises:
acquiring a user ID, a device identifier and a device ip address;
judging whether the user ID and the equipment identifier are consistent with user data stored in a database;
if the access intervals are inconsistent, the access interval between the current access time and the last access time of the user ID is calculated, if the access interval is larger than a first preset threshold value, the user ID is judged to be an invalid user, otherwise, the user data in the database is updated;
If the device ip addresses are consistent, analyzing according to the device ip addresses, and judging whether the device ip addresses are in the advertising area or not;
if not, judging the advertisement click data to be invalid click data, and filtering the invalid click data;
if so, the advertisement click data is effective click data.
3. The advertisement brush bill monitoring and identifying method according to claim 1, further comprising:
the daily related data curve is at least one of a unit time advertisement display frequency curve, a unit time total click frequency curve, a unit time average click frequency curve and a unit time advertisement conversion data curve.
4. The advertisement brush bill monitoring and identifying method according to claim 1, further comprising:
analyzing advertisement click data with advertisement brushing row as a time period to obtain an abnormal user ID;
performing blocking processing on the abnormal user ID;
and sealing and banning the benefits generated by the abnormal user ID, and banning the presentation.
5. The advertisement bill monitoring and identifying system is characterized by comprising a memory and a processor, wherein the memory comprises an advertisement bill monitoring and identifying method program, and the advertisement bill monitoring and identifying method program realizes the following steps when being executed by the processor:
The data acquisition module is used for acquiring advertisement click data;
the data analysis module is used for analyzing the advertisement click data and filtering the invalid click data to obtain effective click data; drawing a daily related data curve according to the effective click data; setting a reference interval curve for the daily relevant data curve according to historical data, and marking abnormal data in the daily relevant data curve based on the reference interval curve; analyzing according to the abnormal data to obtain advertisement brushing list as detection data in each time period; integrating the bill detection data of each time period to obtain advertisement bill detection data;
the step of setting a reference interval curve for the daily relevant data curve according to historical data and marking abnormal data in the daily relevant data curve based on the reference interval curve comprises the following steps:
according to the data change condition of advertisement click data in each time period in the historical data, respectively setting a corresponding threshold interval for each item of related data in the daily advertisement click data in each time period;
drawing a reference interval curve for each item of related data according to the corresponding threshold interval;
Comparing the daily related data curves with corresponding reference interval curves respectively, and marking data which are not in the reference interval curves to obtain abnormal data;
the reference interval curve comprises a first reference interval curve and a second reference interval curve;
simulating advertisement click data of the current day through advertisement click data in the same time period in the historical data to obtain simulation data; the first reference interval curve consists of a range between a curve drawn by the maximum value and a curve drawn by the minimum value of the simulation data, and the interval range of the second reference interval curve is 120% of the interval range of the first reference interval curve;
analyzing according to the abnormal data to obtain advertisement brushing row behavior detection data of each time period, wherein the method comprises the following steps:
multiplying each item of abnormal data in each time period by corresponding weight respectively, and accumulating calculation results to obtain data abnormal values of each time period;
comparing the abnormal value of the data in each time period with a second preset threshold value respectively, and if the abnormal value of the data in the current time period is larger than the second preset threshold value, judging that advertisement bill behavior exists in the current time period; otherwise, it is not present.
6. A computer readable storage medium, characterized in that it comprises an advertisement ticket monitoring and identifying method program, which, when executed by a processor, implements the steps of an advertisement ticket monitoring and identifying method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311465909.XA CN117217830B (en) | 2023-11-07 | 2023-11-07 | Advertisement bill monitoring and identifying method, system and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311465909.XA CN117217830B (en) | 2023-11-07 | 2023-11-07 | Advertisement bill monitoring and identifying method, system and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117217830A CN117217830A (en) | 2023-12-12 |
| CN117217830B true CN117217830B (en) | 2024-02-27 |
Family
ID=89041080
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311465909.XA Active CN117217830B (en) | 2023-11-07 | 2023-11-07 | Advertisement bill monitoring and identifying method, system and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117217830B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102289756A (en) * | 2010-06-18 | 2011-12-21 | 百度在线网络技术（北京）有限公司 | Method and system for judging click validation |
| CN103593415A (en) * | 2013-10-29 | 2014-02-19 | 北京国双科技有限公司 | Method and device for detecting cheating on visitor volumes of web pages |
| CN103605697A (en) * | 2013-11-06 | 2014-02-26 | 北京掌阔移动传媒科技有限公司 | Method for judging cheat clicking of mobile phone advertising |
| CN105760455A (en) * | 2016-02-04 | 2016-07-13 | 腾讯科技（深圳）有限公司 | Anti-cheating method and device for advertisement clicking |
| CN111028011A (en) * | 2019-12-10 | 2020-04-17 | 北京华峰创业科技有限公司 | Advertisement clicking anti-cheating method, intelligent terminal and server |
| KR102194273B1 (en) * | 2020-04-27 | 2020-12-23 | 주식회사 알오아이플러스 | Method, apparatus and computer-readable medium of automatic bid for keyword advertisement based on analysis of advertising execution pattern |
| KR20210009128A (en) * | 2019-07-16 | 2021-01-26 | 주식회사 티앤케이팩토리 | Method and system for advertisement exposure based on advertising effectiveness learning |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8701136B2 (en) * | 2008-01-07 | 2014-04-15 | Nielsen Company (Us), Llc | Methods and apparatus to monitor, verify, and rate the performance of airings of commercials |
-
2023
- 2023-11-07 CN CN202311465909.XA patent/CN117217830B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102289756A (en) * | 2010-06-18 | 2011-12-21 | 百度在线网络技术（北京）有限公司 | Method and system for judging click validation |
| CN103593415A (en) * | 2013-10-29 | 2014-02-19 | 北京国双科技有限公司 | Method and device for detecting cheating on visitor volumes of web pages |
| CN103605697A (en) * | 2013-11-06 | 2014-02-26 | 北京掌阔移动传媒科技有限公司 | Method for judging cheat clicking of mobile phone advertising |
| CN105760455A (en) * | 2016-02-04 | 2016-07-13 | 腾讯科技（深圳）有限公司 | Anti-cheating method and device for advertisement clicking |
| KR20210009128A (en) * | 2019-07-16 | 2021-01-26 | 주식회사 티앤케이팩토리 | Method and system for advertisement exposure based on advertising effectiveness learning |
| CN111028011A (en) * | 2019-12-10 | 2020-04-17 | 北京华峰创业科技有限公司 | Advertisement clicking anti-cheating method, intelligent terminal and server |
| KR102194273B1 (en) * | 2020-04-27 | 2020-12-23 | 주식회사 알오아이플러스 | Method, apparatus and computer-readable medium of automatic bid for keyword advertisement based on analysis of advertising execution pattern |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117217830A (en) | 2023-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6878450B2 (en) | Methods and devices to prevent advertising fraud and storage media | |
| CN111614690A (en) | Abnormal behavior detection method and device | |
| CN106355431B (en) | Cheating flow detection method and device and terminal | |
| KR101300517B1 (en) | Optimum Tender Price prediction method and system | |
| CN105357195A (en) | Unauthorized web access vulnerability detecting method and device | |
| CN106612216A (en) | Method and apparatus of detecting website access exception | |
| CN111310120A (en) | Abnormal electricity utilization user identification method, device, terminal and medium based on big data | |
| CN111611519A (en) | Method and device for detecting personal abnormal behaviors | |
| CN110532485B (en) | User behavior detection method and device based on multi-source data fusion | |
| CN109634820A (en) | A kind of fault early warning method, relevant device and the system of the collaboration of cloud mobile terminal | |
| CN112819476A (en) | Risk identification method and device, nonvolatile storage medium and processor | |
| CN111782735A (en) | Wool party flow identification method and device | |
| CN106301979A (en) | The method and system of the abnormal channel of detection | |
| CN112437034A (en) | False terminal detection method and device, storage medium and electronic device | |
| CN107135199A (en) | The detection method and device at webpage back door | |
| CN107093092A (en) | Data analysing method and device | |
| CN117217830B (en) | Advertisement bill monitoring and identifying method, system and readable storage medium | |
| CN108650145A (en) | Phone number characteristic automatic extraction method under a kind of home broadband WiFi | |
| CN116610821A (en) | Knowledge graph-based enterprise risk analysis method, system and storage medium | |
| CN114422168A (en) | Malicious machine traffic identification method and system | |
| CN111127059B (en) | User quality analysis method and device | |
| CN110399399B (en) | User analysis method, device, electronic equipment and storage medium | |
| CN101753724A (en) | System and method for automatically judging cluster subscriber number | |
| CN113506125B (en) | User value prediction method, device and storage medium | |
| CN112580089A (en) | Information leakage early warning method, device and system, storage medium and electronic device |
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 |