CN112633955A - Advertisement conversion abnormity detection method and system and computer readable storage medium - Google Patents
Advertisement conversion abnormity detection method and system and computer readable storage medium Download PDFInfo
- Publication number
- CN112633955A CN112633955A CN202110253175.3A CN202110253175A CN112633955A CN 112633955 A CN112633955 A CN 112633955A CN 202110253175 A CN202110253175 A CN 202110253175A CN 112633955 A CN112633955 A CN 112633955A
- Authority
- CN
- China
- Prior art keywords
- data
- detection
- conversion
- advertisement
- detection result
- 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.)
- Granted
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- 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
- G06Q30/0248—Avoiding fraud
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
- H04L63/1408—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic by monitoring network traffic
- H04L63/1425—Traffic logging, e.g. anomaly detection
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
- H04L63/1408—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic by monitoring network traffic
- H04L63/1416—Event detection, e.g. attack signature detection
Abstract
The embodiment of the application provides a method and a system for detecting advertisement conversion abnormity, electronic equipment and a computer readable storage medium, and relates to the field of advertisements. The method is realized based on a block chain and comprises the following steps: multiplexing the obtained original data to obtain target data; the original data comprises at least two types of subdata; performing advertisement conversion abnormity detection on the target data based on a detection strategy of at least one dimension to obtain a detection result; and outputting the detection result by adopting at least one target format. The method and the device have the advantages that the multiplexing of original data is realized, the problems of single detection mode and narrow application range in the prior art are solved, the intelligent detection of unknown advertisement conversion abnormity is realized, the diversified display of detection results is realized, and the individual requirements of different services are met.
Description
Technical Field
The present application relates to the field of advertisement technologies, and in particular, to a method, a system, an electronic device, and a computer-readable storage medium for detecting an advertisement conversion abnormality.
Background
The Optimized Cost per Action (opcpa) is the current mainstream advertising bidding model. In this mode, the advertiser needs to upload the conversion data brought by the advertisement to the advertisement platform, and the advertisement platform then splices the conversion data with the click data to complete the delivery life cycle of the advertisement. The process involves multi-party data, and the data quality is not controllable, such as uploading abnormality of conversion data, advertisement attribution abnormality, advertisement putting abnormality, and the like, which eventually cause advertisement conversion abnormality, and therefore, the advertisement conversion abnormality needs to be detected.
The existing main detection modes are as follows:
(1) rule-based advertisement anti-cheating identification
False conversion data in the advertisement platform is identified through various characteristics and manual rules so as to eliminate error data influencing the advertisement platform.
But the method has single identification task and narrow application range.
(2) Network traffic attack detection
And judging whether the flow is invalid or not based on means such as a request message, a request flow increase ratio and the like so as to protect the advertisement platform.
However, this method can only identify abnormal accesses of traffic, and has a narrow application range.
Disclosure of Invention
The application provides an advertisement conversion abnormity detection method, an advertisement conversion abnormity detection system, electronic equipment and a computer readable storage medium, which can solve the problems of single task and narrow application range of the conventional advertisement conversion abnormity detection and identification. The technical scheme is as follows:
according to an aspect of the present application, there is provided an advertisement conversion abnormality detection method, which is performed by an advertisement conversion abnormality detection system, the method including:
multiplexing the obtained original data to obtain target data; the original data comprises at least two types of subdata;
performing advertisement conversion abnormity detection on the target data based on a detection strategy of at least one dimension to obtain a detection result;
and outputting the detection result by adopting at least one target format.
In one or more embodiments, when the detection result is that the advertisement conversion is abnormal, the method further includes:
responding to a processing instruction of a detection result aiming at the advertisement conversion abnormity, and generating a processing result of the detection result;
updating the detection strategy of the at least one dimension based on the processing result.
In one or more embodiments, the multiplexing the acquired original data to obtain target data includes:
obtaining at least one piece of raw data from at least one storage device;
performing data splicing on the at least one piece of original data to obtain original total data;
and segmenting the original total data to obtain at least one data slice, and taking the at least one data slice as target data.
In one or more embodiments, the segmenting the raw total data to obtain at least one data slice includes:
and segmenting the original total data based on at least one of time dimension, advertiser dimension, flow dimension and conversion data dimension reported by an advertiser to obtain at least one data slice.
In one or more embodiments, the advertisement conversion anomaly detection is performed on the target data based on the detection strategy of at least one dimension, and a detection result is obtained, where the detection result includes at least one of:
performing advertisement conversion abnormity detection on the target data based on conversion data in the target data to obtain a detection result;
performing advertisement conversion abnormity detection on the target data based on the advertisement conversion attribution rate to obtain a detection result;
performing advertisement conversion abnormity detection on the target data based on advertisement putting abnormity to obtain a detection result;
and carrying out advertisement conversion abnormity detection on the target data based on an abnormity detection model to obtain a detection result.
In one or more embodiments, the performing advertisement conversion anomaly detection on the target data based on the conversion data in the target data to obtain a detection result includes:
acquiring conversion data in the target data;
and if at least one of concentrated data reporting, field filling errors and behavior type errors is detected in the conversion data, judging that the target data has advertisement conversion abnormity.
In one or more embodiments, the performing advertisement conversion anomaly detection on the target data based on the advertisement conversion attribution rate to obtain a detection result includes:
determining the advertiser attribution failure rate and the conversion data attribution failure rate of the target data;
and if the attribution failure rate of the advertiser exceeds the attribution failure rate threshold of the advertiser, and/or the attribution failure rate of the conversion data exceeds the attribution failure rate threshold of the conversion data, judging that the target data has advertisement conversion abnormity.
In one or more embodiments, the performing advertisement conversion anomaly detection on the target data based on advertisement delivery anomaly to obtain a detection result includes:
determining the advertisement conversion rate prediction deviation and the advertisement achievement rate of the target data;
and if the advertisement conversion rate prediction deviation exceeds a deviation threshold value and/or the advertisement achievement rate exceeds an advertisement achievement rate threshold value, judging that the target data has advertisement conversion abnormity.
In one or more embodiments, the outputting the detection result in at least one target format includes:
obtaining format templates corresponding to the at least one target format respectively;
and filling the detection result into each format template to obtain the detection result of the at least one target format, and outputting the detection result of the at least one target format.
According to another aspect of the present application, there is provided an advertisement conversion abnormality detection system, including:
the data management layer is used for multiplexing the obtained original data to obtain target data; the original data comprises at least two types of subdata;
the anomaly detection algorithm layer is used for carrying out advertisement conversion anomaly detection on the target data based on a detection strategy of at least one dimension to obtain a detection result;
and the alarm monitoring management layer is used for outputting the detection result by adopting at least one target format.
In one or more embodiments, when the detection result is an advertisement conversion abnormality, the system further includes:
the processing module is used for responding to a processing instruction of a detection result aiming at the advertisement conversion abnormity and generating a processing result of the detection result;
the anomaly detection algorithm layer is further used for updating the detection strategy of the at least one dimension based on the processing result.
In one or more embodiments, the data management layer comprises:
the device comprises an original data acquisition module, a data storage module and a data processing module, wherein the original data acquisition module is used for acquiring at least one piece of original data from at least one storage device;
the splicing module is used for carrying out data splicing on the at least one piece of original data to obtain original total data;
and the segmentation module is used for segmenting the original total data to obtain at least one data slice, and taking the at least one data slice as target data.
In one or more embodiments, the cutting module is specifically configured to:
and segmenting the original total data based on at least one of time dimension, advertiser dimension, flow dimension and conversion data dimension reported by an advertiser to obtain at least one data slice.
In one or more embodiments, the anomaly detection algorithm layer comprises:
the first detection module is used for carrying out advertisement conversion abnormity detection on the target data based on conversion data in the target data to obtain a detection result;
the second detection module is used for carrying out advertisement conversion abnormity detection on the target data based on the advertisement conversion attribution rate to obtain a detection result;
the third detection module is used for carrying out advertisement conversion abnormity detection on the target data based on advertisement putting abnormity to obtain a detection result;
and the fourth detection module is used for carrying out advertisement conversion abnormity detection on the target data based on the abnormity detection model to obtain a detection result.
In one or more embodiments, the first detection module comprises:
the conversion data acquisition submodule is used for acquiring conversion data in the target data;
and the first judgment submodule is used for judging that the target data has advertisement conversion abnormity if at least one of concentrated data reporting, field filling errors and behavior type errors is detected in the conversion data.
In one or more embodiments, the second detection module comprises:
the first determining submodule is used for determining the advertiser attribution failure rate and the conversion data attribution failure rate of the target data;
and the second judging submodule is used for judging that the target data has advertisement conversion abnormity if the attribution failure rate of the advertiser exceeds the attribution failure rate threshold of the advertiser and/or the attribution failure rate of the conversion data exceeds the attribution failure rate threshold of the conversion data.
In one or more embodiments, the third detection module comprises:
the second determining submodule is used for determining the advertisement conversion rate prediction deviation and the advertisement achievement rate of the target data;
and the third judgment submodule is used for judging that the target data has advertisement conversion abnormity if the advertisement conversion rate prediction deviation exceeds a deviation threshold value and/or the advertisement achievement rate exceeds an advertisement achievement rate threshold value.
In one or more embodiments, the alarm monitoring management layer comprises:
the format module acquisition module is used for acquiring a format template corresponding to each of the at least one target format;
and the generating module is used for filling the detection result into each format template to obtain the detection result of the at least one target format and outputting the detection result of the at least one target format.
According to another aspect of the present application, there is provided an electronic device including:
one or more processors;
a memory;
one or more computer programs, wherein the one or more computer programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to: and executing the operation corresponding to the advertisement conversion abnormity detection method shown in the first aspect of the application.
According to yet another aspect of the present application, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the advertisement conversion abnormality detection method shown in the first aspect of the present application.
According to an aspect of the application, a computer program product or computer program is provided, comprising computer instructions, the computer instructions being stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the method provided in the various alternative implementations of any of the aspects described above.
The beneficial effect that technical scheme that this application provided brought is:
the advertisement conversion abnormity detection system multiplexes the obtained original data to obtain target data; the original data comprises at least two types of subdata; and then carrying out advertisement conversion abnormity detection on the target data based on a detection strategy of at least one dimension to obtain a detection result, and outputting the detection result by adopting at least one target format. In this way, the obtained original data is managed through the data management layer, including data splicing and data segmentation, so that target data is obtained, and the original data is multiplexed; furthermore, the anomaly detection algorithm layer performs advertisement conversion anomaly detection on target data through a multi-dimensional detection strategy to obtain a detection result, so that the problems of single detection mode and narrow application range in the prior art are solved, and meanwhile, an anomaly detection model is introduced to realize intelligent detection on unknown advertisement conversion anomaly; furthermore, the report monitoring management layer outputs the detection result by adopting various target formats, thereby realizing diversified display of the detection result and meeting the individual requirements of different services.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings used in the description of the embodiments of the present application will be briefly described below.
FIG. 1 is a block diagram of an embodiment of an advertisement conversion anomaly detection system;
fig. 2 is a schematic flowchart of an advertisement conversion anomaly detection method according to an embodiment of the present application;
FIG. 3 is a schematic diagram of detection logic of an anomaly detection algorithm layer according to an embodiment of the present application;
fig. 4 is a schematic flowchart of an advertisement conversion anomaly detection method according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an advertisement conversion anomaly detection system according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of an electronic device for detecting an advertisement conversion abnormality according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary only for the purpose of explaining the present application and are not to be construed as limiting the present application.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. As used herein, the term "and/or" includes all or any element and all combinations of one or more of the associated listed items.
To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
The terms referred to in this application will first be introduced and explained:
CVR: conversion Rate, Conversion Rate. Is an index for measuring the effectiveness of CPA (Cost Per Action) advertisement placement, in short, the conversion rate from the user clicking the advertisement to becoming an effective activated or registered or even paying user.
For example, the advertisement a points to a download page of the application a, after the user sees and clicks the advertisement a, the user jumps to the download page and downloads the application a in the download page, and then the user installs the application a in the terminal, which belongs to an effective activation of the application a, and the CVR of this click is 1. If the user jumps to the download page after clicking the advertisement A, the user does not download the application program A at the moment, but quits the download page, the user does not belong to the effective activation of the application program A, and the CVR clicked at the moment is 0. The registered users, paid users and active activation principles are the same and will not be described herein.
Abnormal advertisement conversion: the method refers to that the conversion amount and conversion rate of the advertisement are not in accordance with expectations due to the uploading data of the advertiser, the logic attributed to the conversion of the advertisement and the like. For example, the conversion rate is 0, the conversion amount is higher than the click rate, and the like.
The advertisement conversion attribute is that: refers to a set of logic and rules that identify which advertisement or channel the activation or conversion of an advertisement is ultimately brought by. When the advertisement conversion is attributed, most of the information is attributed through matching, that is, when the user clicks the advertisement, the user information (such as IMEI (International Mobile Equipment Identity) or IDFA (identifier for advertisement) of the user and the advertisement information (such as advertisement tracking ID, advertisement Application package name or APP (Application) ID) of the clicked advertisement) and the advertisement information (such as Identity document) are uploaded and recorded, and after the advertisement is converted, the user information and the advertisement attribute information of the advertisement conversion are matched with the user information and the advertisement information of the clicked advertisement to accomplish the attribution. The logic attributed to the ad conversion can be done in the background of the ad platform or on a third party attribution platform, or in the background of the advertiser, and the logic is basically the same.
The oCPA is the advertisement bidding mode of the current mainstream. In this mode, the advertiser needs to upload the conversion data brought by the advertisement to the advertisement platform, and the advertisement platform then splices the conversion data with the click data to complete the delivery life cycle of the advertisement. The process involves multi-party data, and the data quality is not controllable, such as uploading abnormality of conversion data, advertisement attribution abnormality, advertisement putting abnormality, and the like, which eventually cause advertisement conversion abnormality, and therefore, the advertisement conversion abnormality needs to be detected.
The existing main detection modes are as follows:
(1) rule-based advertisement anti-cheating identification
False conversion data in the advertisement platform is identified through various characteristics and manual rules so as to eliminate error data influencing the advertisement platform.
But the method has single identification task and narrow application range.
(2) Network traffic attack detection
And judging whether the flow is invalid or not based on means such as a request message, a request flow increase ratio and the like so as to protect the advertisement platform.
However, this method can only identify abnormal accesses of traffic, and has a narrow application range.
The application provides an advertisement conversion abnormity detection method, system, electronic device and computer readable storage medium, which aim to solve the above technical problems in the prior art.
The following describes the technical solutions of the present application and how to solve the above technical problems with specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
An embodiment of the present invention provides a system architecture for performing ad conversion anomaly detection, and referring to fig. 1, the system architecture includes: the system comprises a data management layer, an anomaly detection algorithm layer and an alarm monitoring management layer. The data management layer is used for acquiring original data and managing the original data, wherein the original data comprises at least two types of sub-data, including but not limited to: conversion data, attribution logs, and click logs. When the conversion data is advertisement clicking, clicking the advertisement user related information and advertisement related information, such as user ID, equipment ID, advertisement ID and the like; the click log is a log which is directly generated after the advertisement is clicked and used for recording the exposure and the click of the advertisement; the attribution log is generated when the combination of the conversion data and the click log is successful.
That is, in the embodiment of the present invention, the original data includes, but is not limited to, the conversion data, the attribution log, and the click log, wherein the attribution log is generated when the combination of the conversion data and the click log is successful, and the conversion data and the click log which remain after the combination is failed exist independently.
The anomaly detection algorithm layer comprises at least one preset anomaly detection operator and at least one preset anomaly detection model, and is used for carrying out anomaly detection on target data output by the data management layer by adopting each operator and each detection model to obtain a detection result.
The report monitoring management layer is used for outputting the detection result by adopting at least one target format, wherein the target format comprises but is not limited to a report format and an email format, and storing the detection result so as to facilitate subsequent query, analysis and the like.
Further, when a processing instruction for the output detection result is received, a corresponding processing result is generated, then the processing result is stored, and the processing result is input into an anomaly detection algorithm layer, and the anomaly detection algorithm layer updates various anomaly detection operators and various detection models by adopting the processing result.
For example, the detection result of a certain target data is an advertisement conversion exception, the received processing instruction is to update the advertisement conversion exception to the advertisement conversion normality, so that the generated processing result is that the target data is the advertisement conversion normality, then the processing result is stored, and the processing result is adopted to update a corresponding operator or detection model in the exception detection algorithm layer.
For another example, the detection result of a certain target data is to determine whether advertisement conversion is abnormal, and the received processing instruction is to determine that advertisement conversion is abnormal, so that the generated processing result is that the target data is abnormal for advertisement conversion, and then the processing result is stored, and an operator or a detection model in the abnormal detection algorithm layer is updated by using the processing result.
Further, the advertisement in the embodiment of the present invention may be displayed in an application program, the application program may be installed in a terminal, and the terminal may have the following characteristics:
(1) on a hardware architecture, a device has a central processing unit, a memory, an input unit and an output unit, that is, the device is often a microcomputer device having a communication function. In addition, various input modes such as a keyboard, a mouse, a touch screen, a microphone, a camera and the like can be provided, and input can be adjusted as required. Meanwhile, the equipment often has a plurality of output modes, such as a telephone receiver, a display screen and the like, and can be adjusted according to needs;
(2) on a software system, the device must have an operating system, such as Windows Mobile, Symbian, Palm, Android, iOS, and the like. Meanwhile, the operating systems are more and more open, and personalized application programs developed based on the open operating system platforms are infinite, such as a communication book, a schedule, a notebook, a calculator, various games and the like, so that the requirements of personalized users are met to a great extent;
(3) in terms of communication capacity, the device has flexible access mode and high-bandwidth communication performance, and can automatically adjust the selected communication mode according to the selected service and the environment, thereby being convenient for users to use. The device may support 3GPP (3 rd Generation Partnership Project), 4GPP (4 rd Generation Partnership Project), 5GPP (5 rd Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), mobile communication based on TCP/IP (Transmission Control Protocol/Internet Protocol), UDP (User data Protocol, User Datagram Protocol) Protocol, computer network communication based on TCP/IP Protocol, and short-range wireless Transmission based on bluetooth and infrared Transmission standards, not only supporting voice services, but also supporting various wireless data services;
(4) in the aspect of function use, the equipment focuses more on humanization, individuation and multi-functionalization. With the development of computer technology, devices enter a human-centered mode from a device-centered mode, and the embedded computing, control technology, artificial intelligence technology, biometric authentication technology and the like are integrated, so that the human-oriented purpose is fully embodied. Due to the development of software technology, the equipment can be adjusted and set according to individual requirements, and is more personalized. Meanwhile, the device integrates a plurality of software and hardware, and the function is more and more powerful.
Further, according to the advertisement conversion abnormality detection method disclosed in the present application, the above-mentioned various types of data may be stored in a blockchain.
An advertisement conversion abnormality detection method may be performed in the system, as shown in fig. 2, and includes:
step S201, multiplexing the obtained original data to obtain target data; the original data comprises at least two types of subdata;
the original data includes, but is not limited to, conversion data, an attribution log and a click log, the attribution log is generated when the conversion data and the click log are successfully combined, and the conversion data and the click log which remain after the combination fails independently exist. The conversion data, the attribution log, and the click log are each a type of child data.
After the system acquires the original data, the original data is multiplexed to obtain target data to be detected.
In a preferred embodiment of the present invention, multiplexing the obtained original data to obtain target data includes:
obtaining at least one piece of raw data from at least one storage device;
performing data splicing on at least one piece of original data to obtain original total data;
and segmenting the original total data to obtain at least one data slice, and taking the at least one data slice as target data.
Specifically, after the system acquires the original data, the original data may be stored in at least one storage device in advance to be multiplexed. During multiplexing, at least one piece of original data is obtained from at least one storage device, then data splicing is carried out on the at least one piece of original data to obtain an original total data, then the original total data is segmented to obtain at least one data slice, and the at least one data slice is respectively used as target data to be input into an anomaly detection algorithm layer to carry out advertisement conversion anomaly detection.
The method includes the following steps of segmenting original total data to obtain at least one data slice, wherein the data slice comprises the following steps:
and segmenting the original total data based on at least one of time dimension, advertiser dimension, flow dimension and conversion data dimension reported by the advertiser to obtain at least one data slice.
Specifically, the time dimension may be time for clicking an advertisement, the advertiser dimension may be an advertiser ID, the traffic dimension may be a traffic corresponding to the same advertisement, and the conversion data reported by the advertiser may be a conversion data reported by the same advertiser. At least one of the above dimensions may be used in slicing the raw total data, resulting in one less slice of data.
Of course, the dimension used for the segmentation may also be other than the above dimensions, and may be adjusted according to actual requirements in actual applications, which is not limited in the embodiment of the present invention.
Step S202, advertisement conversion abnormity detection is carried out on target data based on a detection strategy of at least one dimension, and a detection result is obtained;
after the data management layer obtains the target data through the processing, the target data can be output to an anomaly detection algorithm layer, the anomaly detection algorithm layer comprises at least one preset anomaly detection operator and at least one preset anomaly detection model, each anomaly detection operator and each anomaly detection model are respectively used as a dimension, and each operator and each detection model are scheduled to carry out anomaly detection on the target data output by the data management layer, so that a detection result is obtained.
Further, before detecting the target data, the anomaly detection algorithm layer needs to initialize, including but not limited to loading various anomaly detection operators, initializing various detection models, and loading various basic components required for detection, such as an initialization function, a conversion data-advertiser mapping dictionary.
Wherein the conversion data-advertiser mapping dictionary is generated as follows:
the system in the embodiment of the invention adopts two sets of account systems of an advertiser and conversion data, wherein the advertiser account is used for putting advertisements, and the conversion data account is used for generating the conversion data and reporting the conversion data to the system. And no dependency relationship exists between the two account systems, and the system establishes a mapping relationship between the advertiser and the conversion data according to the successfully attributed data, so that a conversion data-advertiser mapping dictionary is obtained.
When the target data is detected, the advertisers can be matched based on the conversion data-advertiser mapping dictionary, so that conversion data corresponding to each advertiser is obtained.
In a preferred embodiment of the present invention, the detection strategy based on at least one dimension performs advertisement conversion anomaly detection on the target data to obtain a detection result, where the detection result includes at least one of the following:
performing advertisement conversion abnormity detection on the target data based on conversion data in the target data to obtain a detection result;
performing advertisement conversion abnormity detection on the target data based on the advertisement conversion attribution rate to obtain a detection result;
performing advertisement conversion abnormity detection on the target data based on advertisement putting abnormity to obtain a detection result;
and carrying out advertisement conversion abnormity detection on the target data based on an abnormity detection model to obtain a detection result.
Specifically, each anomaly detection operator is specifically used for including, but not limited to: performing advertisement conversion abnormity detection on the target data based on conversion data in the target data to obtain a detection result; performing advertisement conversion abnormity detection on the target data based on the advertisement conversion attribution rate to obtain a detection result; and carrying out advertisement conversion abnormity detection on the target data based on advertisement putting abnormity to obtain a detection result. And the anomaly detection model directly performs advertisement conversion anomaly detection on the target data to obtain a detection result. And then determining a final detection result in the obtained and each detection result.
Fig. 3 is a schematic diagram of detection logic of the anomaly detection algorithm layer. Specifically, after target data is input into the anomaly detection algorithm layer, each anomaly detection operator is called to detect the target data, and meanwhile, the target data is input into the anomaly detection model. And after each abnormal detection operator detects and obtains each operator detection result, determining a final operator detection result from each operator detection result. And the anomaly detection model performs advertisement conversion anomaly detection on the direct target data to obtain a model detection result, and then determines one of the operator detection result and the model detection result as a final detection result.
The method for detecting the advertisement conversion abnormity of the target data based on the conversion data in the target data to obtain a detection result comprises the following steps:
acquiring conversion data in target data;
and if at least one of concentrated data reporting, field filling errors and behavior type errors is detected in the conversion data, judging that the target data has advertisement conversion abnormity.
Specifically, conversion data corresponding to each advertiser is obtained from target data based on a conversion data-advertiser mapping dictionary and an advertiser ID, and then whether at least one of centralized data reporting, field filling errors and behavior type errors exists in the conversion data corresponding to each advertiser is detected, wherein centralized data reporting may be that the number of times of conversion data reporting of the same advertiser exceeds a number threshold within a preset time period, for example, within 10 seconds, the number of times of conversion data reporting of an advertiser is 20 times, and exceeds the number threshold 5 times; the field filling error can be a content filling error of any field in the conversion data, for example, a content filling error of an advertisement ID field in the conversion data; the behavior type error may be that the converted behavior type is incorrect, for example, the conversion attribution of a certain advertisement should be an application activation, and if the conversion attribution becomes a registered user, the behavior type error is.
The detection algorithm may include, but is not limited to:
1) centralized conversion feedback (for example, transmitting all day conversion data within 1 hour);
2) the next day is reserved and converted in the current day;
3) the deep target conversion is always equal to the shallow target conversion;
4) the deep layer target conversion amount is larger than the shallow layer target conversion amount; (ii) a
5) There are multiple conversions with the advertisement and the device.
If at least one of the above conditions is detected, then it can be determined that ad conversion anomalies exist with the target data. Of course, the detection may be performed in other manners besides the above detection manner, and may be set according to actual requirements in practical application, which is not limited in this embodiment of the present invention.
Further, performing advertisement conversion anomaly detection on the target data based on the advertisement conversion attribution rate to obtain a detection result, wherein the detection result comprises:
determining the advertiser attribution failure rate and the conversion data attribution failure rate of the target data;
and if the attribution failure rate of the advertiser exceeds the attribution failure rate threshold of the advertiser, and/or the attribution failure rate of the conversion data exceeds the attribution failure rate threshold of the conversion data, judging that the target data has advertisement conversion abnormity.
Specifically, the successful conversion amount attributed to the advertiser can be determined and recorded asCV_userThe conversion amount of the advertiser corresponding to the conversion data due to success is recorded asCVAnd, the amount of failed due conversion of the conversion data, recorded asfailed_count。
Then based on the amount of conversion attributed to success by the advertiserCV_userAmount of conversion due to failure of conversion datafailed_ countCalculated to obtain the time of dayiFailure rate of the advertiserNtrace_ratio i As shown in equation (1):
and, an amount of conversion attributed to success by the advertiser based on the conversion dataCVAmount of conversion due to failure of conversion datafailed_countCalculated to obtain the time of dayiThe conversion data is attributed to failure rate and is recorded asNraw_trace_ratio i As shown in equation (2):
if the calculated attribution failure rate of the advertiser exceeds the attribution failure rate threshold of the advertiser, and/or the calculated attribution failure rate of the conversion data exceeds the attribution failure rate threshold of the conversion data, it can be judged that the target data has advertisement conversion abnormity.
For example, ifNtrace_ratio i 、Nraw_trace_ratio i If any index in the target data exceeds 0.8, the target data is judged to have advertisement conversion abnormity.
Further, advertisement conversion abnormity detection is carried out on the target data based on advertisement putting abnormity, and a detection result is obtained, wherein the detection result comprises the following steps:
determining the advertisement conversion rate prediction deviation and the advertisement achievement rate of the target data;
and if the advertisement conversion rate prediction deviation exceeds the deviation threshold value and/or the advertisement achievement rate exceeds the advertisement achievement rate threshold value, judging that the target data has advertisement conversion abnormity.
Specifically, the time of day may be determined firstiCVR budget value of the lower advertisement, notedpcvr i At the moment of timeiConversion of ads incvr i At the moment of timeiEstimated conversion bid for the underlying advertisement, notedcpa i And, at the time of dayiSingle conversion bid of advertisementtarget_cpa i 。
Advertisement-based CVR pre-evaluationpcvr i And conversion rate of advertisementscvr i Calculated to obtain the time of dayiThe forecast deviation of the advertisement conversion rate is recorded asNpcvr_ratio i As shown in equation (3):
and, pre-estimated conversion bids based on advertisementscpa i And single conversion bidding for advertisementstarget_cpa i Calculated to obtain the time of dayiThe advertisement achievement rate is recordedNcpa_ratio i As shown in formula (4)：
and if the calculated advertisement conversion rate prediction deviation exceeds a deviation threshold value and/or the calculated advertisement achievement rate exceeds an advertisement achievement rate threshold value, judging that the target data has advertisement conversion abnormity.
For example, ifNpcvr_ratio i If the conversion rate is less than 0.8, judging that the hidden danger of conversion under-reporting exists; if it isNpcvr_ratio i If the conversion rate is more than 1.2, the hidden danger of conversion and multi-report exists.
It should be noted that, when the advertisement conversion anomaly detection is performed on the target data, the multiple dimension detection strategies may be executed in parallel or in series, and may be set according to actual requirements in actual applications, which is not limited in this embodiment of the present invention.
And step S203, outputting the detection result by adopting at least one target format.
After the anomaly detection algorithm layer obtains a detection result through detection, the detection result is input into the alarm monitoring management layer, and the alarm monitoring management layer can output the detection result by adopting at least one target format.
In a preferred embodiment of the present invention, outputting the detection result in at least one target format includes:
obtaining format templates corresponding to at least one target format respectively;
and filling the detection result into each format template to obtain the detection result of at least one target format, and outputting the detection result of at least one target format.
Specifically, the target formats include, but are not limited to, a report format and a mail format, after the alarm monitoring management layer obtains the detection results, the alarm monitoring management layer further obtains at least one format template corresponding to each target format, then fills the detection results into each format template, so that the detection results of at least one target format can be obtained, and outputs the detection results of at least one target format. For example, the detection result is filled into the report format, and the detection result in the report format can be obtained.
Further, the alarm monitoring management layer may store the detection result, for example, by using an HDFS (Hadoop Distributed File System) to facilitate subsequent query and analysis of the detection result.
It should be noted that the target format may be other formats besides the format described above, and may be set according to actual requirements in practical applications, which is not limited in this embodiment of the present invention.
In the embodiment of the invention, an advertisement conversion abnormity detection system multiplexes the obtained original data to obtain target data; the original data comprises at least two types of subdata; and then carrying out advertisement conversion abnormity detection on the target data based on a detection strategy of at least one dimension to obtain a detection result, and outputting the detection result by adopting at least one target format. In this way, the obtained original data is managed through the data management layer, including data splicing and data segmentation, so that target data is obtained, and the original data is multiplexed; furthermore, the anomaly detection algorithm layer performs advertisement conversion anomaly detection on target data through a multi-dimensional detection strategy to obtain a detection result, so that the problems of single detection mode and narrow application range in the prior art are solved, and meanwhile, an anomaly detection model is introduced to realize intelligent detection on unknown advertisement conversion anomaly; furthermore, the report monitoring management layer outputs the detection result by adopting various target formats, thereby realizing diversified display of the detection result and meeting the individual requirements of different services.
In another embodiment, a method for detecting an advertisement conversion abnormality is provided, as shown in fig. 4, the method includes.
Step S401, multiplexing the obtained original data to obtain target data; the original data comprises at least two types of subdata;
s402, carrying out advertisement conversion abnormity detection on target data based on a detection strategy of at least one dimension to obtain a detection result;
step S403, outputting the detection result by adopting at least one target format;
the principle of steps S401 to S403 is the same as that of steps S201 to S203, and reference may be made to steps S201 to S203, which is not repeated here.
Step S404, when the detection result is the advertisement conversion abnormity, responding to the processing instruction of the detection result aiming at the advertisement conversion abnormity, and generating a processing result of the detection result;
step S405, updating the detection strategy of at least one dimension based on the processing result.
Specifically, the detection result of the advertisement conversion abnormality may be any result other than the advertisement conversion being normal, for example, the advertisement conversion result is unknown, the failure rate of the advertiser due to the failure is too high, and the like. And after the detection result is output by adopting at least one target format, if a processing instruction aiming at the detection result with abnormal advertisement conversion is received, generating a processing result corresponding to the detection result.
For example, if a processing instruction for modifying the detection result into the normal advertisement conversion is received for the detection result with an unknown advertisement conversion result, a processing result with the normal advertisement conversion is generated; for another example, if a confirmed processing instruction is received for a detection result of an advertiser with an excessively high cause failure rate, a processing result of an advertisement conversion abnormality is generated.
After the processing result is generated, the processing result can be input into the anomaly detection algorithm management layer, so that the anomaly detection algorithm management layer can update the detection strategy of at least one dimension by adopting the processing result, namely, each anomaly detection operator and each detection model are updated by adopting the processing result; meanwhile, each processing result is stored, so that the processing results can be conveniently inquired and analyzed subsequently.
In the embodiment of the invention, an advertisement conversion abnormity detection system multiplexes the obtained original data to obtain target data; the original data comprises at least two types of subdata; and then carrying out advertisement conversion abnormity detection on the target data based on a detection strategy of at least one dimension to obtain a detection result, and outputting the detection result by adopting at least one target format. In this way, the obtained original data is managed through the data management layer, including data splicing and data segmentation, so that target data is obtained, and the original data is multiplexed; furthermore, the anomaly detection algorithm layer performs advertisement conversion anomaly detection on target data through a multi-dimensional detection strategy to obtain a detection result, so that the problems of single detection mode and narrow application range in the prior art are solved, and meanwhile, an anomaly detection model is introduced to realize intelligent detection on unknown advertisement conversion anomaly; furthermore, the report monitoring management layer outputs the detection result by adopting various target formats, thereby realizing diversified display of the detection result and meeting the individual requirements of different services.
Further, when the detection result is an advertisement conversion exception and a processing instruction for the detection result is received, the processing instruction can be responded to, a processing result corresponding to the detection result is generated, then the processing result is input into the exception detection algorithm management layer, and the exception detection algorithm management layer can update each exception detection operator and each detection model by adopting the processing result, so that the detection precision of the exception detection algorithm management layer is improved.
Fig. 5 is a schematic structural diagram of an advertisement conversion abnormality detection system provided in the embodiment of the present application, and as shown in fig. 5, the system of the embodiment may include:
the data management layer is used for multiplexing the obtained original data to obtain target data; the original data comprises at least two types of subdata;
the anomaly detection algorithm layer is used for carrying out advertisement conversion anomaly detection on the target data based on a detection strategy of at least one dimension to obtain a detection result;
and the alarm monitoring management layer is used for outputting the detection result by adopting at least one target format.
In a preferred embodiment of the present invention, when the detection result is an abnormal advertisement conversion, the system further includes:
the processing module is used for responding to a processing instruction of a detection result aiming at the advertisement conversion abnormity and generating a processing result of the detection result;
and the anomaly detection algorithm layer is also used for updating the detection strategy of at least one dimension based on the processing result.
In a preferred embodiment of the present invention, the data management layer comprises:
the device comprises an original data acquisition module, a data storage module and a data processing module, wherein the original data acquisition module is used for acquiring at least one piece of original data from at least one storage device;
the splicing module is used for carrying out data splicing on at least one piece of original data to obtain original total data;
and the segmentation module is used for segmenting the original total data to obtain at least one data slice, and taking the at least one data slice as target data.
In a preferred embodiment of the present invention, the cutting module is specifically configured to:
and segmenting the original total data based on at least one of time dimension, advertiser dimension, flow dimension and conversion data dimension reported by the advertiser to obtain at least one data slice.
In a preferred embodiment of the present invention, the anomaly detection algorithm layer comprises:
the first detection module is used for carrying out advertisement conversion abnormity detection on the target data based on the conversion data in the target data to obtain a detection result;
the second detection module is used for carrying out advertisement conversion abnormity detection on the target data based on the advertisement conversion attribution rate to obtain a detection result;
the third detection module is used for carrying out advertisement conversion abnormity detection on the target data based on advertisement putting abnormity to obtain a detection result;
and the fourth detection module is used for carrying out advertisement conversion abnormity detection on the target data based on the abnormity detection model to obtain a detection result.
In a preferred embodiment of the present invention, the first detection module includes:
the conversion data acquisition submodule is used for acquiring conversion data in the target data;
and the first judgment submodule is used for judging that the target data has advertisement conversion abnormity if at least one of concentrated data reporting, field filling errors and behavior type errors is detected in the conversion data.
In a preferred embodiment of the present invention, the second detection module includes:
the first determining submodule is used for determining the advertiser attribution failure rate and the conversion data attribution failure rate of the target data;
and the second judging submodule is used for judging that the target data has advertisement conversion abnormity if the attribution failure rate of the advertiser exceeds the attribution failure rate threshold of the advertiser and/or the attribution failure rate of the conversion data exceeds the attribution failure rate threshold of the conversion data.
In a preferred embodiment of the present invention, the third detecting module includes:
the second determining submodule is used for determining the advertisement conversion rate prediction deviation and the advertisement achievement rate of the target data;
and the third judgment submodule is used for judging that the target data has advertisement conversion abnormity if the advertisement conversion rate prediction deviation exceeds the deviation threshold value and/or the advertisement achievement rate exceeds the advertisement achievement rate threshold value.
In a preferred embodiment of the present invention, the alarm monitoring management layer comprises:
the format module acquisition module is used for acquiring a format template corresponding to at least one target format;
and the generating module is used for filling the detection result into each format template to obtain the detection result of at least one target format and outputting the detection result of at least one target format.
The advertisement conversion abnormality detection system of the present embodiment may execute the advertisement conversion abnormality detection method shown in the foregoing embodiments of the present application, and the implementation principles thereof are similar, and are not described herein again.
In the embodiment of the invention, an advertisement conversion abnormity detection system multiplexes the obtained original data to obtain target data; the original data comprises at least two types of subdata; and then carrying out advertisement conversion abnormity detection on the target data based on a detection strategy of at least one dimension to obtain a detection result, and outputting the detection result by adopting at least one target format. In this way, the obtained original data is managed through the data management layer, including data splicing and data segmentation, so that target data is obtained, and the original data is multiplexed; furthermore, the anomaly detection algorithm layer performs advertisement conversion anomaly detection on target data through a multi-dimensional detection strategy to obtain a detection result, so that the problems of single detection mode and narrow application range in the prior art are solved, and meanwhile, an anomaly detection model is introduced to realize intelligent detection on unknown advertisement conversion anomaly; furthermore, the report monitoring management layer outputs the detection result by adopting various target formats, thereby realizing diversified display of the detection result and meeting the individual requirements of different services.
Further, when the detection result is an advertisement conversion exception and a processing instruction for the detection result is received, the processing instruction can be responded to, a processing result corresponding to the detection result is generated, then the processing result is input into the exception detection algorithm management layer, and the exception detection algorithm management layer can update each exception detection operator and each detection model by adopting the processing result, so that the detection precision of the exception detection algorithm management layer is improved.
An embodiment of the present application provides an electronic device, including: a memory and a processor; at least one program stored in the memory for execution by the processor, which when executed by the processor, implements: in the embodiment of the invention, an advertisement conversion abnormity detection system multiplexes the obtained original data to obtain target data; the original data comprises at least two types of subdata; and then carrying out advertisement conversion abnormity detection on the target data based on a detection strategy of at least one dimension to obtain a detection result, and outputting the detection result by adopting at least one target format. In this way, the obtained original data is managed through the data management layer, including data splicing and data segmentation, so that target data is obtained, and the original data is multiplexed; furthermore, the anomaly detection algorithm layer performs advertisement conversion anomaly detection on target data through a multi-dimensional detection strategy to obtain a detection result, so that the problems of single detection mode and narrow application range in the prior art are solved, and meanwhile, an anomaly detection model is introduced to realize intelligent detection on unknown advertisement conversion anomaly; furthermore, the report monitoring management layer outputs the detection result by adopting various target formats, thereby realizing diversified display of the detection result and meeting the individual requirements of different services.
In an alternative embodiment, an electronic device is provided, as shown in fig. 6, an electronic device 6000 shown in fig. 6 comprising: a processor 6001 and a memory 6003. Processor 6001 and memory 6003 are coupled, such as via bus 6002. Optionally, the electronic device 6000 may further include a transceiver 6004, and the transceiver 6004 may be used for data interaction between the electronic device and other electronic devices, such as transmission of data and/or reception of data. It should be noted that the transceiver 6004 is not limited to one in practical applications, and the structure of the electronic device 6000 is not limited to the embodiment of the present application.
The Processor 6001 may be a CPU (Central Processing Unit), a general-purpose Processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (field programmable Gate Array), or other programmable logic device, transistor logic device, hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the disclosure. The processor 6001 might also be a combination that performs a computing function, such as a combination comprising one or more microprocessors, a combination of a DSP and a microprocessor, or the like.
The bus 6002 may include a path that conveys information between the aforementioned components. The bus 6002 may be a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus 6002 can be divided into an address bus, a data bus, a control bus, and so forth. For ease of illustration, only one thick line is shown in FIG. 6, but this is not intended to represent only one bus or type of bus.
The Memory 6003 can be, but is not limited to, a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical Disc storage, optical Disc storage (including Compact Disc, laser Disc, optical Disc, digital versatile Disc, blu-ray Disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
The memory 6003 is used to store application program code (computer programs) that implement aspects of the subject application, and is controlled for execution by the processor 6001. The processor 6001 is configured to execute application program code stored in the memory 6003 to implement the aspects of the foregoing method embodiments.
Among them, electronic devices include but are not limited to: mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like.
The present application provides a computer-readable storage medium, on which a computer program is stored, which, when running on a computer, enables the computer to execute the corresponding content in the foregoing method embodiments.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
The foregoing is only a partial embodiment of the present invention, 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 invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (12)
1. An advertisement conversion anomaly detection method, wherein the method is executed by an advertisement conversion anomaly detection system, and the method comprises:
multiplexing the obtained original data to obtain target data; the original data comprises at least two types of subdata;
performing advertisement conversion abnormity detection on the target data based on a detection strategy of at least one dimension to obtain a detection result;
and outputting the detection result by adopting at least one target format.
2. The advertisement conversion abnormality detection method according to claim 1, when the detection result is an advertisement conversion abnormality, the method further comprising:
responding to a processing instruction of a detection result aiming at the advertisement conversion abnormity, and generating a processing result of the detection result;
updating the detection strategy of the at least one dimension based on the processing result.
3. The method for detecting advertisement conversion abnormality according to claim 1, wherein the multiplexing the acquired original data to obtain target data includes:
obtaining at least one piece of raw data from at least one storage device;
performing data splicing on the at least one piece of original data to obtain original total data;
and segmenting the original total data to obtain at least one data slice, and taking the at least one data slice as target data.
4. The method of claim 3, wherein the segmenting the raw total data to obtain at least one data slice comprises:
and segmenting the original total data based on at least one of time dimension, advertiser dimension, flow dimension and conversion data dimension reported by an advertiser to obtain at least one data slice.
5. The method for detecting advertisement conversion abnormality according to claim 1, wherein the detection strategy based on at least one dimension performs advertisement conversion abnormality detection on the target data to obtain a detection result, and the detection result includes at least one of:
performing advertisement conversion abnormity detection on the target data based on conversion data in the target data to obtain a detection result;
performing advertisement conversion abnormity detection on the target data based on the advertisement conversion attribution rate to obtain a detection result;
performing advertisement conversion abnormity detection on the target data based on advertisement putting abnormity to obtain a detection result;
and carrying out advertisement conversion abnormity detection on the target data based on an abnormity detection model to obtain a detection result.
6. The method for detecting advertisement conversion abnormality according to claim 5, wherein the detecting advertisement conversion abnormality for the target data based on the conversion data in the target data to obtain a detection result includes:
acquiring conversion data in the target data;
and if at least one of concentrated data reporting, field filling errors and behavior type errors is detected in the conversion data, judging that the target data has advertisement conversion abnormity.
7. The method for detecting advertisement conversion abnormality according to claim 5, wherein the detecting advertisement conversion abnormality of the target data based on the advertisement conversion attribution rate to obtain a detection result comprises:
determining the advertiser attribution failure rate and the conversion data attribution failure rate of the target data;
and if the attribution failure rate of the advertiser exceeds the attribution failure rate threshold of the advertiser, and/or the attribution failure rate of the conversion data exceeds the attribution failure rate threshold of the conversion data, judging that the target data has advertisement conversion abnormity.
8. The method for detecting advertisement conversion abnormality according to claim 5, wherein the detecting advertisement conversion abnormality for the target data based on advertisement delivery abnormality to obtain a detection result includes:
determining the advertisement conversion rate prediction deviation and the advertisement achievement rate of the target data;
and if the advertisement conversion rate prediction deviation exceeds a deviation threshold value and/or the advertisement achievement rate exceeds an advertisement achievement rate threshold value, judging that the target data has advertisement conversion abnormity.
9. The advertisement conversion abnormality detection method according to any one of claims 1 to 8, wherein said outputting the detection result by using at least one target format includes:
obtaining format templates corresponding to the at least one target format respectively;
and filling the detection result into each format template to obtain the detection result of the at least one target format, and outputting the detection result of the at least one target format.
10. An advertisement conversion anomaly detection system, comprising:
the data management layer is used for multiplexing the obtained original data to obtain target data; the original data comprises at least two types of subdata;
the anomaly detection algorithm layer is used for carrying out advertisement conversion anomaly detection on the target data based on a detection strategy of at least one dimension to obtain a detection result;
and the alarm monitoring management layer is used for outputting the detection result by adopting at least one target format.
11. An electronic device, characterized in that the electronic device comprises:
one or more processors;
a memory;
one or more computer programs, wherein the one or more computer programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to: executing the advertisement conversion abnormality detection method according to any one of claims 1 to 9.
12. A computer-readable storage medium storing at least one instruction, at least one program, a set of codes, or a set of instructions, which is loaded and executed by a processor to implement the advertisement conversion anomaly detection method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110253175.3A CN112633955B (en) | 2021-03-09 | 2021-03-09 | Advertisement conversion abnormity detection method and system and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110253175.3A CN112633955B (en) | 2021-03-09 | 2021-03-09 | Advertisement conversion abnormity detection method and system and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112633955A true CN112633955A (en) | 2021-04-09 |
| CN112633955B CN112633955B (en) | 2022-12-27 |
Family
ID=75297597
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110253175.3A Active CN112633955B (en) | 2021-03-09 | 2021-03-09 | Advertisement conversion abnormity detection method and system and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112633955B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008066339A1 (en) * | 2006-11-30 | 2008-06-05 | Seung Hoon Lee | Advertising method and system utilizing error page information attained at isp server |
| US7827128B1 (en) * | 2007-05-11 | 2010-11-02 | Aol Advertising Inc. | System identification, estimation, and prediction of advertising-related data |
| CN108021497A (en) * | 2016-11-04 | 2018-05-11 | 北京飞如许信息科技有限责任公司 | Ad click converts test device and method |
| CN109034906A (en) * | 2018-08-03 | 2018-12-18 | 北京木瓜移动科技股份有限公司 | Anti- cheat method, device, electronic equipment and the storage medium of advertising conversion |
| CN110177135A (en) * | 2019-05-21 | 2019-08-27 | 深圳壹账通智能科技有限公司 | Channel information processing method, device and the computer equipment of application program |
| CN110348715A (en) * | 2019-06-28 | 2019-10-18 | 北京淇瑀信息科技有限公司 | Channel method for detecting abnormality, device and electronic equipment based on flow indicator monitoring |
| CN111080362A (en) * | 2019-12-17 | 2020-04-28 | 上海新数网络科技股份有限公司 | Advertisement monitoring system and method |
| CN111401950A (en) * | 2020-03-12 | 2020-07-10 | 上海数川数据科技有限公司 | Advertisement flow anti-cheating method and device based on wavelet feature clustering |
| CN111738770A (en) * | 2020-06-28 | 2020-10-02 | 北京达佳互联信息技术有限公司 | Advertisement abnormal flow detection method and device |
| CN112182508A (en) * | 2020-09-16 | 2021-01-05 | 支付宝(杭州)信息技术有限公司 | Abnormity monitoring method and device for compliance business indexes |
-
2021
- 2021-03-09 CN CN202110253175.3A patent/CN112633955B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008066339A1 (en) * | 2006-11-30 | 2008-06-05 | Seung Hoon Lee | Advertising method and system utilizing error page information attained at isp server |
| US7827128B1 (en) * | 2007-05-11 | 2010-11-02 | Aol Advertising Inc. | System identification, estimation, and prediction of advertising-related data |
| CN108021497A (en) * | 2016-11-04 | 2018-05-11 | 北京飞如许信息科技有限责任公司 | Ad click converts test device and method |
| CN109034906A (en) * | 2018-08-03 | 2018-12-18 | 北京木瓜移动科技股份有限公司 | Anti- cheat method, device, electronic equipment and the storage medium of advertising conversion |
| CN110177135A (en) * | 2019-05-21 | 2019-08-27 | 深圳壹账通智能科技有限公司 | Channel information processing method, device and the computer equipment of application program |
| CN110348715A (en) * | 2019-06-28 | 2019-10-18 | 北京淇瑀信息科技有限公司 | Channel method for detecting abnormality, device and electronic equipment based on flow indicator monitoring |
| CN111080362A (en) * | 2019-12-17 | 2020-04-28 | 上海新数网络科技股份有限公司 | Advertisement monitoring system and method |
| CN111401950A (en) * | 2020-03-12 | 2020-07-10 | 上海数川数据科技有限公司 | Advertisement flow anti-cheating method and device based on wavelet feature clustering |
| CN111738770A (en) * | 2020-06-28 | 2020-10-02 | 北京达佳互联信息技术有限公司 | Advertisement abnormal flow detection method and device |
| CN112182508A (en) * | 2020-09-16 | 2021-01-05 | 支付宝(杭州)信息技术有限公司 | Abnormity monitoring method and device for compliance business indexes |
Non-Patent Citations (1)
| Title |
|---|
| 薛富波: "《SAS 8.2 统计应用教程》", 31 August 2004, 北京希望电子出版社 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112633955B (en) | 2022-12-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11711432B1 (en) | Remote management of application settings | |
| US9183072B1 (en) | Error troubleshooting using a correlated knowledge base | |
| CN109918205B (en) | Edge equipment scheduling method, system, device and computer storage medium | |
| US20180183651A1 (en) | Content push method and server, and terminal | |
| US20140181262A1 (en) | Use of internet information services logging to collect user information in an asynchronous manner | |
| CN110771126B (en) | System for matching and attributing user equipment events | |
| CN107786601B (en) | Information processing method, terminal and server | |
| US10810106B1 (en) | Automated application security maturity modeling | |
| CN106874273B (en) | Channel information statistical method, device and system | |
| CN107609122B (en) | Advertisement shielding rule updating method, device, server and storage medium | |
| US20180025064A1 (en) | System and method for synchronizing identifiers associated with users | |
| CN109376534B (en) | Method and apparatus for detecting applications | |
| US20140289719A1 (en) | Automatic version management | |
| US9755844B2 (en) | Techniques to transform network resource requests to zero rated network requests | |
| US10742642B2 (en) | User authentication based on predictive applications | |
| CN108989383B (en) | Data processing method and client | |
| CN110930253B (en) | Method and device for generating main key inside intelligent contract, computer equipment and storage medium | |
| US10958522B1 (en) | Configuration tracking perimeter | |
| CN112633955B (en) | Advertisement conversion abnormity detection method and system and computer readable storage medium | |
| CN109598531B (en) | Monitoring code generation method and verification method | |
| WO2015073057A1 (en) | Techniques to rate-adjust data usage with a virtual private network | |
| US20140040456A1 (en) | Managing website registrations | |
| US9730038B2 (en) | Techniques to manage platform migrations | |
| CN110557351A (en) | Method and apparatus for generating information | |
| CN112083945A (en) | NPM installation package update prompting method and device, electronic equipment and storage medium |
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 | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40041932 Country of ref document: HK |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |