CN112734469B - Advertisement monitoring method and device and electronic equipment - Google Patents
Advertisement monitoring method and device and electronic equipment Download PDFInfo
- Publication number
- CN112734469B CN112734469B CN202011643173.7A CN202011643173A CN112734469B CN 112734469 B CN112734469 B CN 112734469B CN 202011643173 A CN202011643173 A CN 202011643173A CN 112734469 B CN112734469 B CN 112734469B
- Authority
- CN
- China
- Prior art keywords
- user data
- current user
- data
- advertisement
- data set
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
- G06Q30/0245—Surveys
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The application discloses an advertisement monitoring method, an advertisement monitoring device and electronic equipment, wherein the method comprises the following steps: acquiring a current user data set associated with a target advertisement in a current data period, wherein the data types of the current user data in the current user data set are different from each other; according to the data type of the current user data, after a historical user data set with the same data type as the current user data is obtained, the position of the current user data in the historical user data set is determined, wherein the historical user data set comprises a plurality of historical user data, and the data periods of the historical user data and the current user data are the same; determining an abnormal score of the current user data according to the position of the current user data in the historical user data set; and determining the abnormal condition of the target advertisement according to the abnormal score of each current user data in the current user data set.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to an advertisement monitoring method and apparatus, and an electronic device.
Background
With the development of the internet, more and more game manufacturers select a media platform on the line to launch advertisements, and images or videos of some new products are displayed in the form of banner advertisements and the like in the media platform on the line, so as to attract users to click corresponding advertisement pages to enter introduction or purchase pages of game products.
To facilitate adjusting the advertisement delivery plan, user data of the user on the advertisement, such as the retention time and click operation on the advertisement, are usually obtained from the media side, and detected. Currently, a method for detecting user data sets a fixed threshold of certain user data, alarms when the user data exceeds the corresponding fixed threshold, and performs corresponding operations on delivery information. However, this method needs to be configured separately for monitoring different types of user data, the configuration process is complicated, and as the user data increases continuously, the overall trend of the user data changes, and if the detection is abnormal depending on the set fixed threshold, there are often more false alarms, which is not favorable for making an accurate adjustment on the delivery plan.
Disclosure of Invention
The application aims to at least solve one of the technical problems in the prior art, and provides an advertisement monitoring method, an advertisement monitoring device and electronic equipment, so that false alarms are reduced, the accuracy of data monitoring is improved, and the subsequent delivery plan can be conveniently and accurately adjusted.
The embodiment of the application provides an advertisement monitoring method, which comprises the following steps:
acquiring a current user data set associated with a target advertisement in a current data period, wherein the data types of the current user data in the current user data set are different from each other;
according to the data type of the current user data, after a historical user data set with the same data type as the current user data is obtained, the position of the current user data in the historical user data set is determined, wherein the historical user data set comprises a plurality of historical user data, and the data cycle of the historical user data is the same as that of the current user data;
determining the abnormal score of the current user data according to the position of the current user data in the historical user data set;
and determining the abnormal condition of the target advertisement according to the abnormal score of each current user data in the current user data set.
Further, the obtaining a current user data set associated with the targeted advertisement includes:
acquiring a plurality of first current user data associated with the target advertisement from a media end, and simultaneously acquiring a plurality of second current user data associated with the target advertisement from a local database, wherein the plurality of first current user data comprise advertisement browsing data and advertisement clicking data, and the plurality of second current user data comprise registration data and cost data;
and forming the current user data set according to the plurality of first current user data and the plurality of second current user data.
Further, the obtaining a current user data set associated with the targeted advertisement includes:
and responding to a data selection operation initiated by a source user, and acquiring the current user data set in the data dimension according to the data dimension and the data type selected by the data selection operation.
Further, the determining the location of the current user data in the historical user data set includes:
according to the current user data, traversing a binary tree formed by the historical user data set, and determining the position of the current user data in the binary tree;
and determining the position of the current user data in the historical user data set according to the position of the current user data in the binary tree.
Further, after determining the location of the current user data in the historical user data set, the method further includes:
and updating the binary tree according to the current user data.
Further, determining an abnormal condition of the target advertisement according to an abnormal score of each current user data in the current user data set, including:
weighting a first preset weight and an abnormal score of each first current user data and a second preset weight and an abnormal score of each second current user data to obtain monitoring data of a user data set, wherein the second preset weight is greater than the first preset weight;
and detecting the monitoring data, and sending alarm information aiming at the target advertisement when the grade of the monitoring data does not meet the preset condition.
Further, in the embodiment of the present application, the method further includes:
and periodically sending a shutdown instruction to an advertisement putting unit for putting the target advertisement until shutdown information fed back by the advertisement putting unit is received, wherein the shutdown information is used for indicating that the target advertisement is stopped to be put.
Further, in an embodiment of the present application, an advertisement monitoring apparatus is further provided, including:
the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring a current user data set associated with a target advertisement in a current data period, and the data types of each current user data in the current user data set are different from each other;
the data analysis module is used for determining the position of the current user data in a historical user data set after acquiring the historical user data set which has the same data type as the current user data according to the data type of the current user data, wherein the historical user data set comprises a plurality of historical user data, and the data cycle of the historical user data is the same as that of the current user data;
the data processing module is used for determining the abnormal score of the current user data according to the position of the current user data in the historical user data set;
and the anomaly detection module is used for determining the anomaly condition of the target advertisement according to the anomaly score of each current user data in the current user data set.
Further, the data obtaining module is specifically configured to:
acquiring a plurality of first current user data associated with the target advertisement from a media end, and simultaneously acquiring a plurality of second current user data associated with the target advertisement from a local database, wherein the plurality of first current user data comprise advertisement browsing data and advertisement clicking data, and the plurality of second current user data comprise registration data and cost data;
and forming the current user data set according to a plurality of first current user data and a plurality of second current user data.
Further, an embodiment of the present application provides an electronic device, including: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the advertisement monitoring method as described in the above embodiments when executing the program.
Further, the present application provides a computer-readable storage medium, which stores computer-executable instructions for causing a computer to execute the advertisement monitoring method according to the above embodiment.
Compared with the prior art, in the embodiment, the current user data set in the current data cycle is obtained, the data types of the current user data in the current user data set are different, the historical user data set which is the same as the current user data cycle is obtained according to the data types of the current user data, the abnormal score of the current user data is determined according to the position of the current user data in the historical user data set, and the abnormal condition of the target advertisement is determined according to the abnormal score of the current user data in the current user data set, so that the abnormal detection caused by the overall trend change of the user data under the condition of fixing the threshold value can be avoided, the false alarm condition is reduced, the accurate adjustment of the delivery plan is facilitated, and the separate configuration is not needed when the different types of user data are monitored, and the configuration process is simplified.
In the embodiment, the first current user data is acquired from the media end, and the second current user data is acquired from the local database to form the current user data set, so that the current user data can avoid the deviation of a monitoring result caused by that the second current user data of the media end aims at the advertisement putting effect more, low-cost malicious operation occurring in the media end can be better identified, the difference of the user data of the media end and the user data of the server can be controlled within a reasonable range, the first current user data and the second current user data are acquired and operated in a parallel mode, and time consumption can be reduced under the condition of not influencing the data accuracy.
In the above embodiment, the data dimension and the data type are selected according to the data selection operation initiated by the source user, and the current user data set in the selected data dimension is acquired, so that the acquired current data set can be associated with the target advertisement as much as possible in the data dimension and the data type, and can be more suitable for the target advertisement.
In the above embodiment, the historical user data set forms a binary tree, and the position of the current user data in the binary tree is determined by traversing the binary tree, so that the position of the current user data in the historical user data set is determined, and the position of the current user data in the historical user data set can be determined more clearly and quickly.
In the embodiment, after the position of the current user data in the historical user data set is determined, the current user data is added into the binary tree for updating, so that the historical user data set can be continuously updated, and the accuracy in use is kept.
In the above embodiment, the abnormal score of the first current user data and the abnormal score of the second current user data are weighted with the corresponding preset weights respectively to obtain the monitoring data of the user data set, and the relation between the monitoring data grade and the preset condition is used as a sending condition of the warning information, so that the advertisement monitoring effect can be better improved according to the association degree between different current user data and the target advertisement, and the second preset weight corresponding to the second current user data is greater than the first preset weight corresponding to the first current user data, so that the monitoring result can be better prevented from deviating due to the fact that the second current user data of the media end is more directed at the advertisement putting effect.
According to the embodiment, the shutdown instruction is periodically sent to the advertisement putting unit until the advertisement putting unit shuts down and feeds back the target advertisement, so that the effect of shutting down the target advertisement can be ensured.
Drawings
The present application is further described below with reference to the accompanying drawings and examples;
FIG. 1 is a diagram of an application environment of a method for advertisement monitoring in one embodiment;
FIG. 2 is a flow diagram that illustrates a method for advertisement monitoring, according to one embodiment;
FIG. 3 is a diagram of a binary tree constructed from a historical user data set in one embodiment;
FIG. 4 is a diagram of an updated binary tree in one embodiment;
FIG. 5 is a block diagram of an advertisement monitoring device in one embodiment;
FIG. 6 is a block diagram of a computer device in one embodiment.
Detailed Description
Reference will now be made in detail to the present embodiments of the present application, preferred embodiments of which are illustrated in the accompanying drawings, which are for the purpose of visually supplementing the description with figures and detailed description, so as to enable a person skilled in the art to visually and visually understand each and every feature and technical solution of the present application, but not to limit the scope of the present application.
With the development of the internet, more and more game manufacturers choose to launch advertisements on the media platform on the line, and images or videos of some new products are displayed in the form of banner advertisements and the like in the media platform on the line, so as to attract users to click corresponding advertisement pages to enter introduction or purchase pages of game products.
To facilitate the adjustment of the advertisement delivery plan, user data of the user on the advertisement, such as the retention time and click operation on the advertisement, are generally obtained from the media side, and detected. Currently, a method for detecting user data sets a fixed threshold of certain user data, alarms when the user data exceeds the corresponding fixed threshold, and performs corresponding operations on delivery information. However, this method needs to be configured separately for monitoring different types of user data, the configuration process is complicated, and as the user data continuously increases, the overall trend of the user data changes, and if the abnormality is detected by means of the set fixed threshold, there are often more false alarms, which is not favorable for making accurate adjustment of the delivery plan. The media end is a server adopted by network media or television media.
To solve the above technical problem, fig. 1 is an application environment diagram of an advertisement monitoring method in an embodiment. Referring to fig. 1, the advertisement monitoring system includes a user terminal 110 and a server 120. The user terminal 110 and the server 120 are connected through a network. The user terminal 110 may specifically be a desktop user terminal. The user terminal 110 may be implemented as a stand-alone user terminal or as a user terminal cluster consisting of a plurality of user terminals. The server 120 may be implemented as a stand-alone server or a server cluster comprising a plurality of servers. The server 120 obtains a current user data set in a current data cycle, obtains a historical user data set with the same type as the current user data cycle according to the data type of the current user data, determines an abnormal score of the current user data according to the position of the current user data in the historical user data set, and determines the abnormal condition of the target advertisement according to the abnormal score of each current user data in the current user data set.
Hereinafter, the advertisement monitoring method provided by the embodiment of the present application will be described and explained in detail through several specific embodiments.
As shown in FIG. 2, in one embodiment, an advertisement monitoring method is provided. The embodiment is mainly illustrated by applying the method to computer equipment. The computer device may specifically be the server 120 in fig. 1 described above.
Referring to fig. 2, the advertisement monitoring method specifically includes the following steps:
s11, a current user data set associated with the target advertisement in a current data period is obtained, wherein the data types of the current user data in the current user data set are different.
In this embodiment, the server obtains a current user data set in a current data cycle, where the current user data set is associated with the target advertisement, and specifically, the current user data set may be determined according to the content of the target advertisement, for example, the content of the target advertisement is issued for a new game, and then the current user data set may include the number of users registered for the new game, the number of users trying to play the new game, or the average online duration of users of the new game. The content of the target advertisement is recommended by the game gift bag, and the current user data set can comprise the number of gift bag purchasing users, data of gift bag purchasing situations, average recharging amount of users and the like.
In this embodiment, in order to ensure the monitoring effect of the current user data on the advertisement, it is necessary to classify each current user data in the current user data set into different data types, and it is ensured that each current user data can perform position sorting with historical user data of the same type in the following steps, and therefore, the data types of each current user data in the current user data set of the current user data are different from each other, where the data types may include a consumption type, a budget type, a registration type, a cost type, a production type, and the like.
In one embodiment, obtaining a current user data set associated with a targeted advertisement includes:
the method comprises the steps of obtaining a plurality of first current user data associated with a target advertisement from a media end, and simultaneously obtaining a plurality of second current user data associated with the target advertisement from a local database, wherein the plurality of first current user data comprise advertisement browsing data and advertisement clicking data, and the plurality of second current user data comprise registration data and cost data.
And forming a current user data set according to the plurality of first current user data and the plurality of second current user data.
In this embodiment, the server obtains first current user data from the media end, where the first current user data includes advertisement browsing data and advertisement clicking data. And the server acquires second current user data from the local database, wherein the second current user data comprises registration data and cost data. The local server may be a database in the monitoring server or another server located in the same local area network as the monitoring server. The server acquires the first current user data from the media end and the server acquires the second current user data from the local database in a parallel operation mode. The server forms a current user data set according to the first current user data and the second current user data, wherein the current user data set is formed by directly combining the first current user data and the second current user data into a set, or by using different types of current user data as a subset, and all subsets form the current user data set.
In this embodiment, the first current user data is acquired from the media end, and the second current user data is acquired from the local database to form the current user data set, so that the current user data can avoid deviation of a monitoring result caused by that the second current user data of the media end is more effective to advertisement delivery, low-cost malicious operation occurring in the media end can be better identified, the difference of the user data of the media end and the user data of the server can be controlled within a reasonable range, the first current user data and the second current user data are acquired and run in a parallel mode, and time consumption can be reduced without affecting data accuracy.
In one embodiment, obtaining a current user data set associated with a targeted advertisement includes:
and responding to a data selection operation initiated by a source user, and acquiring a current user data set under the data dimension according to the data dimension and the data type selected by the data selection operation.
In this embodiment, the server responds to a data selection operation initiated by a source user, wherein the data selection operation may be input into the server by the source user by clicking or dragging or inputting a code; or automatically generated by the user terminal or other servers according to the instructions of the source user and sent to the servers. The data selecting operation is an operation for selecting a required data dimension and a required data type. The specific data selection operation mode may be an operation of selecting one of the data dimensions and the data types by clicking or dragging on an interface with different data dimensions and data types. For example, the user sends a data selection operation to the server through the user terminal 1, where the data selection operation is specific to a current user data set associated with a campaign advertisement of "song of city on the cloud", and the data selection operation is specific to that the user selects a corresponding configuration form in an interface of the server with three configuration forms by clicking. The three configuration forms are a configuration form 1, a configuration form 2 and a configuration form 3.
In this embodiment, the server selects the data dimension and the data type according to the data selection operation, and the specific manner is to determine the data dimension and the data type according to a configuration form selected by clicking or dragging in the data selection operation, where the data dimension may include a game dimension, a channel dimension, an account dimension, an advertisement dimension, and the like. For example, the user selects the configuration form 2 by clicking, and the information corresponding to the configuration form is the selected data dimension and data type. After the data dimension and the data type are selected, the server obtains a current user data set under the data dimension, for example, the server selects the data dimension and the data type corresponding to the configuration form 2, the data dimension is a game dimension, and the data type is a registration type, so that the server can obtain data under the game dimension, and the game dimension has multiple types of data including a registration type, a cost type, a consumption type and the like.
In this embodiment, a data dimension and a data type are selected according to a data selection operation initiated by a source user, and a current user data set in the selected data dimension is acquired, so that the acquired current data set can be associated with a target advertisement as much as possible in the data dimension and the data type, and the target advertisement can be better fitted.
S12, according to the data type of the current user data, after a historical user data set with the same data type as the current user data is obtained, the position of the current user data in the historical user data set is determined, wherein the historical user data set comprises a plurality of historical user data, and the data period of the historical user data is the same as that of the current user data.
In the embodiment, the server acquires the historical user data set with the same data type as the current user data according to the data type of the current user data. For example, the server obtains data of all data types in the game dimension as the current user data set, wherein the data types comprise a registration class, a cost class, a consumption class and the like. And when the data type of the current user data is the registration class, the server acquires a historical user data set which is the registration class under the game dimensionality. When the data type of the current user data is the cost class, the server acquires a historical user data set which is the cost class under the game dimension.
The server determines the position of the current user data in the historical user data set according to the historical user data set, wherein the historical user data set comprises a plurality of historical user data, and the position of the current user data in the historical user data set can be ranked from high to low or from low to high. For example, the current user data and the historical user data set are both data of the registry class in the game dimension. The current user data of the registration class is 5000, the historical user data set comprises five historical user data, the historical user data of the registration class are respectively 500, 1000, 10000, 8000 and 3000, and at this time, the position of the current user data in the historical user data set from high to low is the third.
In this embodiment, in order to ensure the standard of the position of the current user data in the historical user data set, it is necessary to make the data cycle of the current user data be the same as that of the historical user data in the historical user data set, that is, the time period length is the same, for example, if the data cycle of the current user data is 24 hours, then the data cycle of each historical user data in the historical user data set is also 24 hours.
In one embodiment, determining the location of the current user data in the historical user data set comprises:
according to the current user data, traversing a binary tree formed by the historical user data set, and determining the position of the current user data in the binary tree;
and determining the position of the current user data in the historical user data set according to the position of the current user data in the binary tree.
In this embodiment, the server constructs a binary tree from the historical user data of the same data type in the historical user data set, sorts the historical user data from high to low or from low to high, and stores the historical user data in the binary tree from top to bottom and from left to right according to the sort to construct the binary tree of the data type. For example, the historical user data set of the registration class includes seven pieces of historical user data, the historical user data of the registration class are respectively 500, 1000, 10000, 8000, 3000, 2000, 4000, and are ranked from top to bottom as 10000, 8000, 4000, 3000, 2000, 1000, 500, at this time, the server constructs a binary tree according to the ranking from top to bottom and from left to right, the root node of the first layer of the constructed binary tree is 10000, the two nodes of the second layer are from left to right as 8000 and 4000, and the four nodes of the third layer are from left to right as 3000, 2000, 1000, 500.
The server determines the position of the current user data in the historical user set according to the position of the current user data in the binary tree, specifically, the server traverses the historical user data in the binary tree, compares the current user data with each historical user data one by one, and when the current user data set is larger than the previous historical user data and smaller than the next historical user data, or the current user data set is smaller than the previous historical user data and larger than the next historical user data, the position of the next historical user data is the position of the current historical user data. For example, the current user data is 5000, as shown in fig. 3, the binary tree constructed by the historical user data is 10000, 8000, 4000, 3000, 2000, 1000, 500 from top to bottom from left to right, then 5000 is smaller than 8000 and larger than 4000, at this time, the position (third) of the historical user data 4000 is the position (third) of the current user data 5000, and then the position of the current user data in the historical user data set is third.
In this embodiment, the historical user data set forms a binary tree, and the position of the current user data in the binary tree is determined by traversing the binary tree, so as to determine the position of the current user data in the historical user data set, and the position of the current user data in the historical user data set can be determined more clearly and quickly.
In one embodiment, after determining the location of the current user data in the historical user data set, further comprising:
updating the binary tree according to the current user data.
In this embodiment, after determining the position of the current user data in the historical user data set, the server stores the current user data in the corresponding position of the binary tree, and updates the binary tree. For example, the position of the current user data 5000 in the historical user data set is the third, the binary tree constructed by the historical user data is 10000, 8000, 4000, 3000, 2000, 1000 and 500 from high to low and from left to right, as shown in fig. 4, at this time, the server stores the current user data 5000 to the right node of the second layer of the binary tree, the historical user data 4000, 3000, 2000, 1000 and 500 after sorting are updated according to the principle of from top to bottom and from left to right, that is, the four nodes of the third layer are originally 3000, 2000, 1000 and 500 from left to right and are updated to be 4000, 3000, 2000 and 1000.
In this embodiment, after the position of the current user data in the historical user data set is determined, the current user data is added into the binary tree for updating, so that the historical user data set can be continuously updated, and the accuracy in use is maintained.
And S13, determining the abnormal score of the current user data according to the position of the current user data in the historical user data set.
In this embodiment, the server determines the abnormal score of the current user data according to the position of the current user data in the historical user data set, where the abnormal score corresponding to each position may be set by a user or a server administrator, or may be automatically generated by the server. For example, the first anomaly score is set to 100, the second anomaly score is set to 90, and the third anomaly score is set to 80 for the position of the current user data in the historical user data set.
And S14, determining the abnormal condition of the target advertisement according to the abnormal score of each current user data in the current user data set.
In this embodiment, the server determines an abnormal condition of the target advertisement according to an abnormal score of each current user data in the current user data set, specifically, by setting an abnormal threshold, when the abnormal score exceeds the abnormal threshold, the target advertisement is abnormal; when the anomaly score does not exceed the anomaly threshold, the targeted advertisement is normal.
In one embodiment, determining an abnormal condition of a target advertisement according to an abnormal score of each current user data in a current user data set includes:
weighting a first preset weight and an abnormal score of each first current user data and a second preset weight and an abnormal score of each second current user data to obtain monitoring data of a user data set, wherein the second preset weight is larger than the first preset weight;
and detecting the monitoring data, and sending alarm information aiming at the target advertisement when the grade of the monitoring data does not meet the preset condition.
In this embodiment, after the server sets a first preset weight for each first current user data and sets a second preset weight for a second current user data, the server determines the position of the first current user data in the first historical user data set according to the steps in the above embodiment, and further determines the abnormal score of the first current user data according to the position of the first current user data in the first historical user data set. And determining the position of the second current user data in the second historical user data set according to the steps in the embodiment, and further determining the abnormal score of the second current user data according to the position of the second current user data in the second historical user data set. The first current user data and the first user historical data are data of the same data type in the same data dimension in the same data period, and the second current user data and the second user historical data are data of the same data type in the same data dimension in the same data period. The difference is that the first current user data and the first user historical data are both obtained from a local database, and the second current user data and the second user historical data are both obtained from a media end.
The server performs weighting according to a first preset weight and an abnormal score of each first current user data and according to a second preset weight and an abnormal score of each second current user data to obtain monitoring data of the user data set, and specifically adds an abnormal value weighted by the abnormal score of the first current user data and an abnormal value weighted by the abnormal score of the second current user data to obtain the monitoring data of the user data set. For example, the anomaly score of the first current user data 5000 is 90, the first preset weight is 2, the anomaly score of the second current user data 3000 is 80, the first preset weight is 1, and the monitoring data is 260.
In this embodiment, more user data acquired by the media side is the delivery effect for the advertisement delivery channel, and the pertinence to the product corresponding to each advertisement is not high, so that a deviation may occur in monitoring the advertisement according to the user data, an original monitoring effect cannot be achieved, and a plurality of operation records exist in the media side, that is, the advertisement on the media side or the page on the media side can be used as the user data by clicking and browsing the advertisement by the user, and the server is difficult to identify. Therefore, the set second preset weight is significantly larger than the first preset weight.
And after the server acquires the monitoring data, determining the grade of the monitoring data according to the monitoring data, and sending alarm information aiming at the target advertisement when the grade of the monitoring data does not meet the preset condition. The monitoring data interval is set to correspond to the levels of different monitoring data, for example, when the monitoring data is in the range of [0, 100), the monitoring data level is 1, when the monitoring data is in the range of [100, 200), the monitoring data level is 2, when the monitoring data is in the range of [200, 300), the monitoring data level is 3, and when the monitoring data is greater than or equal to 300, the monitoring data level is 4. At this time, it is understood that the monitoring data 260 has a monitoring data level of 3. And comparing the grade of the monitoring data with a preset condition, and generating alarm information when the preset condition is not met, for example, the preset condition is that the grade of the monitoring data is required to be less than or equal to 2, so that the preset condition is not met when the grade of the monitoring data is 3, and the server generates the alarm information aiming at the target advertisement.
In this embodiment, both the interval setting of the level of the monitoring data and the setting of the preset condition may be set by a user or a server administrator, or may be automatically generated by the server, and the specific manner of the interval setting and the setting of the preset condition is not specifically limited.
In this embodiment, the abnormal score of the first current user data and the abnormal score of the second current user data are weighted with the corresponding preset weights respectively to obtain the monitoring data of the user data set, and the relation between the monitoring data grade and the preset condition is used as a sending condition of the warning information, so that the advertisement monitoring effect can be better improved according to the association degree between different current user data and the target advertisement, and the second preset weight corresponding to the second current user data is greater than the first preset weight corresponding to the first current user data, so that the monitoring result can be better prevented from deviating due to the fact that the second current user data of the media end is more directed at the advertisement putting effect.
In one embodiment, the advertisement monitoring method further comprises:
and periodically sending a shutdown instruction to an advertisement putting unit for putting the target advertisement until shutdown information fed back by the advertisement putting unit is received, wherein the shutdown information is used for indicating that the target advertisement is stopped to be put.
In this embodiment, the server periodically sends a shutdown instruction to an advertisement delivery unit for delivering a targeted advertisement, wherein the advertisement delivery unit may be a user terminal or an electronic device for delivering the targeted advertisement. The shutdown instruction may be in the form of a file or code. After the user terminal or the electronic device receives the shutdown instruction, the user terminal or the electronic device can automatically stop the target advertisement or manually stop the target advertisement from being delivered through the user terminal or the electronic device. The shutdown command can be sent to the advertisement delivery unit to prompt in the form of flashing lights or pop windows or alarming sounds. The user terminal or the electronic equipment feeds back shutdown information to the server after stopping the target advertisement, and the server stops sending the shutdown instruction after receiving the shutdown information. The shutdown information may be in the form of a file or a code.
In this embodiment, the shutdown instruction is periodically sent to the advertisement delivery unit until the advertisement delivery unit shuts down and feeds back the target advertisement, so that the effect of shutting down the target advertisement can be ensured.
In the embodiment, by acquiring the current user data set in the current data cycle, the data types of the current user data in the current user data set are different from each other, acquiring the historical user data set with the same type as the current user data cycle according to the data types of the current user data, determining the abnormal score of the current user data according to the position of the current user data in the historical user data set, and determining the abnormal condition of the target advertisement according to the abnormal score of the current user data in the current user data set, the detection abnormality caused by the overall trend change of the user data under the condition of a fixed threshold value can be avoided, the false alarm condition is reduced, the accurate adjustment of the delivery plan is facilitated, and the separate configuration is not needed when the different types of user data are monitored, so that the configuration process is simplified.
In one embodiment, as shown in fig. 5, there is provided an advertisement monitoring apparatus including:
the data obtaining module 101 is configured to obtain a current user data set associated with a target advertisement in a current data period, where data types of current user data in the current user data set are different from each other.
The data analysis module 102 is configured to, after obtaining a historical user data set having the same data type as the current user data according to the data type of the current user data, determine a position of the current user data in the historical user data set, where the historical user data set includes a plurality of historical user data, and a data period of the historical user data is the same as a data period of the current user data.
And the data processing module 103 is configured to determine an abnormal score of the current user data according to a position of the current user data in the historical user data set.
And the anomaly detection module 104 is configured to determine an anomaly condition of the target advertisement according to an anomaly score of each current user data in the current user data set.
In one embodiment, the data obtaining module 101 is further configured to:
the method comprises the steps of obtaining a plurality of first current user data associated with a target advertisement from a media end, and simultaneously obtaining a plurality of second current user data associated with the target advertisement from a local database, wherein the plurality of first current user data comprise advertisement browsing data and advertisement clicking data, and the plurality of second current user data comprise registration data and cost data;
and forming a current user data set according to the plurality of first current user data and the plurality of second current user data.
In one embodiment, the data obtaining module 101 is further configured to:
and responding to a data selection operation initiated by a source user, and acquiring a current user data set under the data dimension according to the data dimension and the data type selected by the data selection operation.
In one embodiment, the data processing module 103 is further configured to:
traversing a binary tree formed by a historical user data set according to the current user data, and determining the position of the current user data in the binary tree;
and determining the position of the current user data in the historical user data set according to the position of the current user data in the binary tree.
In one embodiment, the data processing module 103 is further configured to:
after determining the location of the current user data in the historical user data set, the binary tree is updated based on the current user data.
In one embodiment, the anomaly detection module 104 is further configured to:
weighting a first preset weight and an abnormal score of each first current user data and a second preset weight and an abnormal score of each second current user data to obtain monitoring data of a user data set, wherein the second preset weight is greater than the first preset weight;
and detecting the monitoring data, and sending alarm information aiming at the target advertisement when the grade of the monitoring data does not meet the preset condition.
In one embodiment, the anomaly detection module 104 is further configured to:
and periodically sending a shutdown instruction to an advertisement putting unit for putting the target advertisement until shutdown information fed back by the advertisement putting unit is received, wherein the shutdown information is used for indicating that the target advertisement is stopped to be put.
In one embodiment, a computer apparatus is provided, as shown in fig. 6, which includes a processor, a memory, a network interface, an input device, and a display screen connected by a system bus. The memory comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program that, when executed by the processor, causes the processor to implement the advertisement monitoring method. The internal memory may also have stored therein a computer program that, when executed by the processor, causes the processor to perform an advertisement monitoring method. It will be appreciated by those skilled in the art that the configuration shown in fig. 6 is a block diagram of only a portion of the configuration associated with the present application, and is not intended to limit the computing device to which the present application may be applied, and that a particular computing device may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, the advertisement monitoring apparatus provided in the present application may be implemented in the form of a computer program, and the computer program may be run on a computer device as shown in fig. 6. The memory of the computer device may store various program modules that make up the advertising monitoring apparatus. The computer program of each program module causes the processor to execute the steps of the advertisement monitoring method of each embodiment of the present application described in the present specification.
In one embodiment, there is provided an electronic device including: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to perform the steps of the advertisement monitoring method described above. Here, the steps of the advertisement monitoring method may be the steps in the advertisement monitoring method of the above-described embodiments.
In one embodiment, a computer-readable storage medium is provided, having stored thereon computer-executable instructions for causing a computer to perform the steps of the above-described advertisement monitoring method. Here, the steps of the advertisement monitoring method may be the steps in the advertisement monitoring method of the above-described embodiments.
The foregoing is a preferred embodiment of the present application, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present application, and these modifications and decorations are also regarded as the protection scope of the present application.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by a computer program, which may be stored in a computer readable storage medium and executed by a computer to implement the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
Claims (10)
1. An advertisement monitoring method, comprising:
acquiring a current user data set associated with a target advertisement in a current data period, wherein the data types of the current user data in the current user data set are different from each other;
after a historical user data set with the same data type as the current user data is obtained according to the data type of the current user data, determining the position of the current user data in the historical user data set according to the sequence of the current user data in the historical user data set, wherein the historical user data set comprises a plurality of historical user data, and the data periods of the historical user data and the current user data are the same;
determining the abnormal score of the current user data according to the position of the current user data in the historical user data set;
and determining the abnormal condition of the target advertisement according to the abnormal score of each current user data in the current user data set.
2. The advertisement monitoring method of claim 1, wherein the obtaining a current user data set associated with a targeted advertisement comprises:
acquiring a plurality of first current user data associated with the target advertisement from a media end, and simultaneously acquiring a plurality of second current user data associated with the target advertisement from a local database, wherein the plurality of first current user data comprise advertisement browsing data and advertisement clicking data, and the plurality of second current user data comprise registration data and cost data;
and forming the current user data set according to the plurality of first current user data and the plurality of second current user data.
3. The advertisement monitoring method according to claim 1 or 2, wherein the obtaining of the current user data set associated with the targeted advertisement comprises:
and responding to a data selection operation initiated by a source user, and acquiring the current user data set in the data dimension according to the data dimension and the data type selected by the data selection operation.
4. The method of claim 1, wherein the determining the location of the current user data in the historical user data set comprises:
according to the current user data, traversing a binary tree formed by the historical user data set, and determining the position of the current user data in the binary tree;
and determining the position of the current user data in the historical user data set according to the position of the current user data in the binary tree.
5. The advertisement monitoring method of claim 4, further comprising, after determining the location of the current user data in the historical user data set:
and updating the binary tree according to the current user data.
6. The method of claim 2, wherein determining the abnormal status of the target advertisement according to the abnormal score of each current user data in the current user data set comprises:
weighting a first preset weight and an abnormal score of each first current user data and a second preset weight and an abnormal score of each second current user data to obtain monitoring data of a user data set, wherein the second preset weight is greater than the first preset weight;
and detecting the monitoring data, and sending alarm information aiming at the target advertisement when the grade of the monitoring data does not meet the preset condition.
7. The advertisement monitoring method of claim 6, further comprising:
and periodically sending a shutdown instruction to an advertisement putting unit for putting the target advertisement until shutdown information fed back by the advertisement putting unit is received, wherein the shutdown information is used for indicating that the target advertisement is stopped to be put.
8. An advertisement monitoring device, comprising:
the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring a current user data set associated with a target advertisement in a current data period, and the data types of each current user data in the current user data set are different from each other;
the data analysis module is used for obtaining a historical user data set which has the same data type as the current user data according to the data type of the current user data, and then determining the position of the current user data in the historical user data set according to the sequence of the current user data in the historical user data set, wherein the historical user data set comprises a plurality of historical user data, and the data periods of the historical user data and the current user data are the same;
the data processing module is used for determining the abnormal score of the current user data according to the position of the current user data in the historical user data set;
and the anomaly detection module is used for determining the anomaly condition of the target advertisement according to the anomaly score of each current user data in the current user data set.
9. The advertisement monitoring device of claim 8, wherein the data acquisition module is specifically configured to:
acquiring a plurality of first current user data associated with the target advertisement from a media end, and simultaneously acquiring a plurality of second current user data associated with the target advertisement from a local database, wherein the plurality of first current user data comprise advertisement browsing data and advertisement clicking data, and the plurality of second current user data comprise registration data and cost data;
and forming the current user data set according to the plurality of first current user data and the plurality of second current user data.
10. An electronic device, comprising: memory, processor and computer program stored on the memory and executable on the processor, characterized in that the processor implements the advertisement monitoring method according to any of claims 1 to 7 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011643173.7A CN112734469B (en) | 2020-12-31 | 2020-12-31 | Advertisement monitoring method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011643173.7A CN112734469B (en) | 2020-12-31 | 2020-12-31 | Advertisement monitoring method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112734469A CN112734469A (en) | 2021-04-30 |
| CN112734469B true CN112734469B (en) | 2023-01-24 |
Family
ID=75609263
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011643173.7A Active CN112734469B (en) | 2020-12-31 | 2020-12-31 | Advertisement monitoring method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112734469B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107578263A (en) * | 2017-07-21 | 2018-01-12 | 北京奇艺世纪科技有限公司 | A kind of detection method, device and the electronic equipment of advertisement abnormal access |
| CN109088775A (en) * | 2018-08-29 | 2018-12-25 | 阿里巴巴集团控股有限公司 | abnormality monitoring method, device and server |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7346471B2 (en) * | 2005-09-02 | 2008-03-18 | Microsoft Corporation | Web data outlier detection and mitigation |
| JP5235251B1 (en) * | 2012-09-28 | 2013-07-10 | 楽天株式会社 | Information processing apparatus, information processing method, and information processing program |
-
2020
- 2020-12-31 CN CN202011643173.7A patent/CN112734469B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107578263A (en) * | 2017-07-21 | 2018-01-12 | 北京奇艺世纪科技有限公司 | A kind of detection method, device and the electronic equipment of advertisement abnormal access |
| CN109088775A (en) * | 2018-08-29 | 2018-12-25 | 阿里巴巴集团控股有限公司 | abnormality monitoring method, device and server |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112734469A (en) | 2021-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107918905B (en) | Abnormal transaction identification method and device and server | |
| US10592308B2 (en) | Aggregation based event identification | |
| CN111082966B (en) | Positioning method and device based on batch alarm events, electronic equipment and medium | |
| EP3407285B1 (en) | Target user orientation method and device, and computer storage medium | |
| US20160285672A1 (en) | Method and system for processing network media information | |
| KR102111223B1 (en) | Push information roughly select sorting method, device and computer storage media | |
| US9836554B2 (en) | Method and system for providing query suggestions including entities | |
| CN116805254B (en) | Product marketing state evaluation system based on big data | |
| CN116797282A (en) | Real-time monitoring system and monitoring method for advertisement delivery | |
| CN110401567B (en) | Alarm data processing method and device, computing equipment and medium | |
| US20150324581A1 (en) | Displaying real-time security events | |
| CN110619530A (en) | Agricultural product tracing method, electronic equipment and computer readable storage medium | |
| KR102288408B1 (en) | Advertising generation method, computer readable storage medium and system | |
| CN112734469B (en) | Advertisement monitoring method and device and electronic equipment | |
| CN104978670A (en) | Method and apparatus for presenting data information of a plurality of indicators | |
| CN111340540B (en) | Advertisement recommendation model monitoring method, advertisement recommendation method and advertisement recommendation model monitoring device | |
| CN111177564B (en) | Product recommendation method and device | |
| JP7363910B2 (en) | Display method, display program and information processing device | |
| JP6705123B2 (en) | Purchase motivation estimation program and information processing device | |
| CN111563765A (en) | Cheating user screening method, device and equipment and readable storage medium | |
| CN106547802A (en) | For the bid method of adjustment and device of keyword | |
| US20220222580A1 (en) | Deterioration detection method, non-transitory computer-readable storage medium, and information processing device | |
| CN113158029B (en) | Content display method, device and computer readable storage medium | |
| CN113987034A (en) | Information display method and device, electronic equipment and readable storage medium | |
| US11017415B2 (en) | Fast calculations of total unduplicated reach and frequency statistics |
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 |