Method and apparatus for monitoring advertising

Abstract

The application provides an advertisement monitoring method and device. Each advertisement in an advertisement set to be displayed is preprocessed by a backend service plug-in, feature information of the advertisement is generated, and the feature information of all the advertisements is added to feedback information. The feedback information is fed back to an advertisement SDK by the backend service, the monitoring SDK acquires the feedback information received by the advertisement SDK, when the monitoring SDK receives advertisement click information reported by the advertisement SDK, a target advertisement ID is used to determine a combination ID of the target advertisement and a device, report information is generated from the target advertisement ID, the combination ID of the target advertisement and the device, and a click time, and is reported to the backend service plug-in. Operation information of a user for a forced confirmation pop-up window is fed back to the backend service plug-in. The backend service plug-in generates a monitoring result of the advertisement according to the report information and the operation information of the user for the forced confirmation pop-up window. Thus, whether the advertisement after the forced confirmation pop-up window is successfully jumped is accurately and timely monitored.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of advertisement monitoring, in particular to an advertisement monitoring method and device. BACKGROUND

[0002] At present, major mobile phone manufacturers strictly control the advertisement jump behavior in the operating system. When the advertisement jumps, the operating system will forcibly pop up a confirmation pop-up window to require the user to confirm the jump before jumping to the target application, which greatly reduces the wake-up rate of the advertisement application (APP). In view of this situation, it is necessary to obtain the current advertisement wake-up success state in time to supplement the advertisement effect.

[0003] In the prior art, the wake-up success or failure can be obtained by means of burying points and reporting monitoring in the target APP. However, most advertisement budget applications do not support the opening of reporting or return interfaces to the third party due to network and data security reasons, which leads to the fact that there is no effective way to judge the wake-up state at present. SUMMARY

[0004] Therefore, the present application provides an advertisement monitoring method and device, which effectively improves the wake-up success rate of the advertisement APP and accurately and timely monitors whether the advertisement jump is successful after the forced confirmation pop-up window.

[0005] The first aspect of the present application provides an advertisement monitoring method applied to a backend service plug-in, wherein the backend service plug-in runs in the form of a plug-in in an advertisement backend service. The advertisement monitoring method comprises the following steps:

[0006] Preprocessing each advertisement in a set of advertisements to be displayed to generate feature information of the advertisement; wherein the feature information of the advertisement comprises a combination ID of the advertisement and a device; the set of advertisements to be displayed is determined by the advertisement backend service according to an advertisement request sent by an advertisement SDK;

[0007] Adding the feature information of all advertisements to feedback information; wherein the advertisement backend service feeds back the feedback information to the advertisement SDK; a monitoring SDK acquires the feedback information received by the advertisement SDK, and when the monitoring SDK receives advertisement click information reported by the advertisement SDK, determines a combination ID of a target advertisement and a device according to a target advertisement ID; the advertisement click information comprises the target advertisement ID; the target advertisement ID is the ID of the advertisement clicked by the user; the monitoring SDK generates report information comprising the target advertisement ID, the combination ID of the target advertisement and the device, and a click time, and reports the report information to the backend service plug-in; the monitoring SDK feeds back operation information of the user to the backend service plug-in in response to a forced confirmation pop-up window; the monitoring SDK runs in the form of a plug-in in the advertisement SDK;

[0008] receive the report information returned by the monitoring SDK and the operation information of the user for the forced confirmation pop-up window;

[0009] generate a monitoring result of the advertisement according to the report information and the operation information of the user for the forced confirmation pop-up window.

[0010] Optionally, the pre-processing of each advertisement in the set of advertisements that need to be displayed includes generating feature information of the advertisement, which includes:

[0011] read the target device ID in the advertisement request received by the advertisement backend service; wherein, when the monitoring SDK is initialized, the device feature information of the current device is obtained and reported to the backend service plug-in; the backend service plug-in generates the target device ID according to the device feature information of the current device and feeds back to the monitoring SDK; when the advertisement SDK initiates an advertisement request, the target device ID is added to the advertisement request, and then the advertisement request is sent to the advertisement backend service;

[0012] combine the advertisement ID and the target device ID to obtain a combined ID of the advertisement and the device for each advertisement in the set of advertisements that need to be displayed.

[0013] Optionally, the feature information of the advertisement further includes a jump success rate of the advertisement, and the pre-processing of each advertisement in the set of advertisements that need to be displayed includes generating feature information of the advertisement, which includes:

[0014] obtain historical data of the advertisement for each advertisement in the set of advertisements that need to be displayed;

[0015] read the target device ID in the advertisement request received by the advertisement backend service;

[0016] determine the user portrait corresponding to the target device ID according to the target device ID;

[0017] input the historical data of the advertisement and the user portrait corresponding to the target device ID into a jump success rate prediction model to output the jump success rate of the advertisement;

[0018] combine the advertisement ID and the target device ID to obtain a combined ID of the advertisement and the device.

[0019] Optionally, the monitoring method of the advertisement further includes:

[0020] receive the target monitoring file fed back by the monitoring SDK; wherein, the target monitoring file includes: the combined ID of the target advertisement and the device, the time when the current application switches to the background, and the time when the current application switches back to the foreground;

[0021] determining whether a difference between a time when the current application switches back to the foreground and a time when the current application switches to the background is greater than a time threshold value;

[0022] if it is determined that the difference between the time when the current application switches back to the foreground and the time when the current application switches to the background is not greater than the time threshold value, determining that the target advertisement fails to jump;

[0023] if it is determined that the difference between the time when the current application switches back to the foreground and the time when the current application switches to the background is greater than the time threshold value, determining whether the target advertisement fails to jump by using a historical jump success rate of the advertisement corresponding to the combination ID of the advertisement and the device.

[0024] Optionally, after receiving the report information returned by the monitoring SDK, the method further comprises:

[0025] if there is the combination ID of the target advertisement and the device in the attribution report set, determining that the target advertisement succeeds in jumping; wherein the attribution report set comprises at least one attribution report information; the target advertisement attempts to access the attribution SDK after successfully jumping; after the target advertisement accesses the attribution SDK, the attribution SDK reports the combination ID of the target advertisement and the device to the backend service plug-in; the backend service plug-in takes the combination ID of the target advertisement and the device as the attribution report information.

[0026] The second aspect of the present application provides an advertisement monitoring method applied to a monitoring SDK, wherein the monitoring SDK runs in the form of a plug-in in an advertisement SDK, and the advertisement monitoring method comprises:

[0027] obtaining feedback information received by the advertisement SDK; wherein the feedback information is obtained by an advertisement backend service according to an advertisement request sent by the advertisement SDK after determining a set of advertisements to be displayed; a backend service plug-in pre-processes each advertisement in the set of advertisements to be displayed to generate feature information of the advertisement, adds the feature information of all the advertisements to the feedback information, and feeds back the feedback information to the advertisement SDK by the advertisement backend service; the backend service plug-in runs in the form of a plug-in in the advertisement backend service; the feature information of the advertisement comprises a combination ID of the advertisement and the device;

[0028] when receiving advertisement click information reported by the advertisement SDK, determining the combination ID of the target advertisement and the device according to a target advertisement ID; wherein the advertisement click information comprises the target advertisement ID; the target advertisement ID is an ID of an advertisement clicked by a user;

[0029] generating report information by using the target advertisement ID, the combination ID of the target advertisement and the device, and a click time, and reporting the report information to a backend service plug-in;

[0030] feedback the operation information of the user to the backend service plug-in; wherein, after receiving the report information and the operation information of the user to the forced confirmation pop-up window, the backend service plug-in generates a monitoring result of the advertisement according to the report information and the operation information of the user to the forced confirmation pop-up window.

[0031] Optionally, the monitoring method of the advertisement further comprises:

[0032] record the combination ID of the target advertisement and the device and the time when the current application switches to the background, to obtain a monitoring file;

[0033] when the current application switches to the foreground again, add the time when the current application switches to the foreground to the monitoring file, to obtain a target monitoring file;

[0034] feedback the target monitoring file to the backend service plug-in; wherein, after receiving the target monitoring file, if the backend service plug-in judges that the difference between the time when the current application switches to the foreground and the time when the current application switches to the background is not greater than a time threshold, it determines that the target advertisement fails to jump; if the backend service plug-in judges that the difference between the time when the current application switches to the foreground and the time when the current application switches to the background is greater than the time threshold, it determines whether the target advertisement fails to jump by using the historical jump success rate of the advertisement corresponding to the combination ID of the advertisement and the device.

[0035] Optionally, the feature information of the advertisement further comprises a jump success rate of the advertisement, and after the feedback information received by the advertisement SDK is obtained, the method further comprises:

[0036] generate a target advertisement set according to the jump success rate of all advertisements and the combination ID of the advertisement and the device; wherein, the advertisement SDK renders and displays the target advertisement set.

[0037] The third aspect of the present application provides an advertisement monitoring device applied to a backend service plug-in, wherein the backend service plug-in runs in the form of a plug-in in an advertisement backend service, and the advertisement monitoring device comprises:

[0038] a first generating unit for preprocessing each advertisement in a target advertisement set to be displayed to generate feature information of the advertisement; wherein, the feature information of the advertisement comprises a combination ID of the advertisement and the device; the target advertisement set to be displayed is determined by the advertisement backend service according to an advertisement request sent by an advertisement SDK;

[0039] The first adding unit is configured to add feature information of all advertisements to feedback information, wherein the advertisement backend service feeds back the feedback information to the advertisement SDK; the monitoring SDK acquires the feedback information received by the advertisement SDK, and when the monitoring SDK receives advertisement click information reported by the advertisement SDK, determines a combination ID of a target advertisement and a device according to a target advertisement ID; the advertisement click information includes the target advertisement ID; the target advertisement ID is an ID of an advertisement clicked by a user; the monitoring SDK generates report information including the target advertisement ID, the combination ID of the target advertisement and the device, and a click time, and reports the report information to the backend service plug-in; the monitoring SDK feeds back operation information of the user for a forced confirmation pop-up window to the backend service plug-in; and the monitoring SDK runs in the form of a plug-in in the advertisement SDK.

[0040] The first receiving unit is configured to receive report information returned by the monitoring SDK and operation information of the user for a forced confirmation pop-up window.

[0041] The second generating unit is configured to generate a monitoring result of an advertisement according to the report information and the operation information of the user for the forced confirmation pop-up window.

[0042] Optionally, the first generating unit includes:

[0043] The first reading unit is configured to read a target device ID in an advertisement request received by an advertisement backend service; wherein when the monitoring SDK is initialized, device feature information of a current device is acquired and reported to the backend service plug-in; the backend service plug-in generates a target device ID according to the device feature information of the current device and feeds back the target device ID to the monitoring SDK; when the advertisement SDK is about to initiate an advertisement request, the target device ID is added to the advertisement request, and then the advertisement request is sent to the advertisement backend service.

[0044] The first combination unit is configured to combine the advertisement ID and the target device ID for each advertisement in a set of advertisements that need to be displayed, to obtain a combination ID of an advertisement and a device.

[0045] Optionally, the feature information of the advertisement further includes a jump success rate of the advertisement, and the first generating unit includes:

[0046] The first acquiring unit is configured to acquire historical data of each advertisement in the set of advertisements that need to be displayed.

[0047] The second reading unit is configured to read a target device ID in an advertisement request received by an advertisement backend service.

[0048] The first determining unit is configured to determine a user portrait corresponding to the target device ID according to the target device ID.

[0049] a prediction unit configured to input the historical data of the advertisement and a user portrait corresponding to the target device ID into a jump success rate prediction model, and output a jump success rate of the advertisement;

[0050] a second combination unit configured to combine the advertisement ID and the target device ID to obtain a combined ID of the advertisement and the device.

[0051] Optionally, the advertisement monitoring device further comprises:

[0052] a first receiving unit configured to receive a target monitoring file fed back by a monitoring SDK; wherein the target monitoring file comprises a combined ID of a target advertisement and a device, a time at which a current application switches to the background, and a time at which the current application switches back to the foreground;

[0053] a judging unit configured to judge whether a difference between the time at which the current application switches back to the foreground and the time at which the current application switches to the background is greater than a time threshold value;

[0054] a triggering unit configured to determine that the target advertisement fails to jump if the judging unit judges that the difference between the time at which the current application switches back to the foreground and the time at which the current application switches to the background is not greater than the time threshold value;

[0055] a second determining unit configured to determine whether the target advertisement fails to jump by using a historical jump success rate of the advertisement corresponding to the combined ID of the advertisement and the device if the judging unit judges that the difference between the time at which the current application switches back to the foreground and the time at which the current application switches to the background is greater than the time threshold value.

[0056] Optionally, the advertisement monitoring device further comprises:

[0057] a third determining unit configured to determine that the target advertisement succeeds to jump if the combined ID of the target advertisement and the device in the report information is in an attribution reporting set; wherein the attribution reporting set comprises at least one attribution report information; the target advertisement attempts to access an attribution SDK after successfully jumping; the attribution SDK reports the combined ID of the target advertisement and the device of the target advertisement to a backend service plug-in after the target advertisement accesses the attribution SDK; and the backend service plug-in takes the combined ID of the target advertisement and the device of the target advertisement as the attribution report information.

[0058] The fourth aspect of the present application provides an advertisement monitoring device applied to a monitoring SDK, wherein the monitoring SDK runs in the form of a plug-in in an advertisement SDK, and the advertisement monitoring device comprises:

[0059] The second acquisition unit is configured to acquire feedback information received by the advertising SDK; wherein the feedback information is fed back by the advertising backend service to the advertising SDK after the advertising backend service determines a set of advertisements to be displayed according to an advertising request sent by the advertising SDK, the backend service plug-in pre-processes each advertisement in the set of advertisements to be displayed to generate feature information of the advertisement, and adds the feature information of all the advertisements to the feedback information.

[0060] The second receiving unit is configured to determine a combination ID of a target advertisement and a device according to a target advertisement ID when receiving advertising click information reported by the advertising SDK; wherein the advertising click information includes the target advertisement ID; and the target advertisement ID is an ID of an advertisement clicked by a user.

[0061] The third generation unit is configured to generate report information by using the target advertisement ID, the combination ID of the target advertisement and the device, and a click time, and report the report information to the backend service plug-in.

[0062] The first feedback unit is configured to feed back operation information of the user to the backend service plug-in in response to a forced confirmation pop-up window; wherein the backend service plug-in generates a monitoring result of the advertisement according to the report information and the operation information of the user to the forced confirmation pop-up window after receiving the report information and the operation information of the user to the forced confirmation pop-up window.

[0063] Optionally, the advertisement monitoring device further includes:

[0064] The recording unit is configured to record the combination ID of the target advertisement and the device and a time when the current application switches to the background to obtain a monitoring file.

[0065] The second adding unit is configured to add a time when the current application switches back to the foreground to the monitoring file to obtain a target monitoring file when the current application switches back to the foreground.

[0066] The second feedback unit is configured to feed back the target monitoring file to the backend service plug-in; wherein the backend service plug-in determines whether the target advertisement fails to jump if it is determined that a difference between the time when the current application switches back to the foreground and the time when the current application switches to the background is not greater than a time threshold, or determines whether the target advertisement fails to jump by using a historical jump success rate of the advertisement corresponding to the combination ID of the advertisement if it is determined that the difference between the time when the current application switches back to the foreground and the time when the current application switches to the background is greater than the time threshold.

[0067] Optionally, the advertisement monitoring device further includes:

[0068] The fourth generating unit is configured to generate a target advertisement set according to the jump success rate of all the advertisements and the combination ID of the advertisements and the device; and the advertisement SDK renders and displays the target advertisement set.

[0069] From the above solution, the application provides an advertisement monitoring method and device. Each advertisement in an advertisement set to be displayed is preprocessed by a backend service plug-in. After generating the feature information of the advertisements, the feature information of all the advertisements is added to feedback information. The feedback information is fed back to an advertisement SDK by an advertisement backend service. The monitoring SDK acquires the feedback information received by the advertisement SDK. When the monitoring SDK receives the advertisement click information reported by the advertisement SDK, the combination ID of a target advertisement and a device is determined according to a target advertisement ID. Report information is generated from the target advertisement ID, the combination ID of the target advertisement and the device, and a click time. The report information is reported to the backend service plug-in. The operation information of a user on a forced confirmation pop-up window is fed back to the backend service plug-in. The backend service plug-in generates an advertisement monitoring result according to the report information and the operation information of the user on the forced confirmation pop-up window. Thus, whether the advertisement after the forced confirmation pop-up window jumps successfully can be accurately and timely monitored. BRIEF DESCRIPTION OF DRAWINGS

[0070] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only belong to the embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of the provided drawings.

[0071] Figure 1 A specific flowchart of an advertisement monitoring method provided by an embodiment of the present application is provided.

[0072] Figure 2 A flowchart of a method for generating feature information of an advertisement provided by another embodiment of the present application is provided.

[0073] Figure 3 A flowchart of a method for generating feature information of an advertisement provided by another embodiment of the present application is provided.

[0074] Figure 4 A flowchart of an advertisement monitoring method provided by another embodiment of the present application is provided.

[0075] Figure 5 A specific flowchart of an advertisement monitoring device (applied to a backend service plug-in) provided by another embodiment of the present application is provided.

[0076] Figure 6The specific flow chart of the monitoring device (application to the monitoring SDK) of the advertisement is provided for another embodiment of the present application. DETAILED DESCRIPTION

[0077] The technical solutions in the embodiments of the present application will be clearly and completely described in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0078] The term "comprising" and variations thereof as used in the present application are open, i.e., "including, but not limited to". The term "based on" is "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Related definitions of other terms will be given in the following description.

[0079] It should be noted that the information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0080] It should be noted that the "first", "second" and other concepts mentioned in the present application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0081] It should be noted that the modification of "one" and "multiple" in the present application is illustrative and not limiting, and those skilled in the art should understand that unless otherwise explicitly indicated in the context, it should be understood as "one or more".

[0082] First, the technical terms appearing in the present application are explained and described:

[0083] ID: is the abbreviation of Identity document, i.e., identity card identification number.

[0084] SDK: is the abbreviation of Software Development Kit, i.e., software development kit.

[0085] Hook: the Chinese interpretation is hook, which is a technical means mainly used by developers to intercept, modify or extend the original behavior.

[0086] The embodiment of the application provides a kind of advertisement monitoring method, as shown in Figure 1 Specifically, it includes the following steps:

[0087] S101, the back-end service plug-in pre-processes each advertisement in the set of advertisements that need to be displayed, and generates the feature information of the advertisement.

[0088] Wherein, the back-end service plug-in runs in the form of plug-in in the advertisement back-end service, non-invasive, the original advertisement system does not need to be modified;The feature information of the advertisement includes: the combination ID of the advertisement and the device;The set of advertisements that need to be displayed is determined by the advertisement back-end service according to the advertisement request sent by the advertisement SDK.

[0089] In the specific implementation process of the application, the advertisement back-end service determines the set of advertisements that need to be displayed according to the advertisement request sent by the advertisement SDK, which includes but is not limited to that the advertisement back-end service will analyze the request data in the advertisement SDK, determine the corresponding device information, and obtain the set of advertisements suitable for the current device from the current advertisement system, which is not limited here.

[0090] Optionally, in the specific implementation process of the application, one embodiment of step S101 includes: Figure 2 As shown in

[0091] S201, read the target device ID in the advertisement request received by the advertisement back-end service.

[0092] Wherein, when the advertisement SDK is initialized, the monitoring SDK is initialized synchronously, when the monitoring SDK is initialized, the device feature information of the current device is obtained by the monitoring SDK, and is reported to the back-end service plug-in;The back-end service plug-in generates the target device ID according to the device feature information of the current device and feeds back to the monitoring SDK;When the advertisement SDK initiates an advertisement request, the target device ID is added to the advertisement request, and the advertisement request is sent to the advertisement back-end service.

[0093] It should be noted that the device feature information includes but is not limited to the device feature (OAID and AndroidID) of the current device, which is not limited here.

[0094] Wherein, when the advertisement SDK initiates an advertisement request, the target device ID can be added to the advertisement request by Hook, and then the advertisement request is sent to the advertisement back-end service, which is not limited here.

[0095] In the specific implementation process of the application, when the advertisement back-end service receives the advertisement request, the back-end service plug-in can read the target device ID in the advertisement request received by the advertisement back-end service by Hook, which is not limited here.

[0096] S202, for each advertisement in the set of advertisements that needs to be displayed, combine the advertisement ID and the target device ID to obtain the combined ID of the advertisement and the device.

[0097] In the specific implementation process of the present application, the combined ID of the advertisement and the device can be generated by binding the advertisement ID and the target device ID, which is not limited here.

[0098] S102, the backend service plug-in adds the feature information of all advertisements to the feedback information.

[0099] Among them, the advertisement backend service feeds back the feedback information to the advertisement SDK. After receiving the feedback information fed back by the backend service plug-in, the advertisement SDK renders and displays the advertisement set in the feedback information.

[0100] S103, the monitoring SDK obtains the feedback information received by the advertisement SDK.

[0101] Among them, the monitoring SDK runs in the form of a plug-in in the advertisement SDK, which is non-intrusive and does not need to modify the original advertisement SDK.

[0102] In the specific implementation process of the present application, when the advertisement SDK receives the feedback information, the monitoring SDK can read all the feature information of the advertisements in the feedback information received by the advertisement SDK through the Hook method, which is not limited here.

[0103] S104, when the monitoring SDK receives the advertisement click information reported by the advertisement SDK, the combined ID of the target advertisement and the device is determined according to the target advertisement ID.

[0104] Among them, the advertisement click information includes the target advertisement ID; the target advertisement ID is the ID of the advertisement clicked by the user.

[0105] In the specific implementation process of the present application, the advertisement SDK monitors the advertisement set in real time, when the user clicks on a certain advertisement, the advertisement is taken as the target advertisement, and the target advertisement ID is added to the advertisement click information and reported to the monitoring SDK, and the monitoring SDK determines the combined ID of the target advertisement and the device according to the target advertisement ID.

[0106] S105, the monitoring SDK generates report information including the target advertisement ID, the combined ID of the target advertisement and the device, and the click time, and reports it to the backend service plug-in.

[0107] In the specific implementation process of the present application, when the monitoring SDK generates report information including the target advertisement ID, the combined ID of the target advertisement and the device, and the click time, and reports it to the backend service plug-in, the advertisement SDK will initiate a jump, at this time the operating system will forcibly pop up a forced confirmation pop-up window, the current application will be switched to the background state, and wait for the user to make a choice in the forced confirmation pop-up window.

[0108] Optionally, in another embodiment of the application, after receiving the report information returned by the monitoring SDK, an embodiment of the advertisement monitoring method further comprises:

[0109] If the target advertisement in the report information is combined with the device ID in the attribution report set, it is determined that the target advertisement jump is successful.

[0110] The attribution report set includes at least one attribution report information; the target advertisement attempts to access the attribution SDK after the jump is successful, and the attribution SDK reports the target advertisement and the combination ID of the target advertisement of the device to the backend service plug-in after the target advertisement accesses the attribution SDK; the backend service plug-in takes the target advertisement and the combination ID of the target advertisement of the device as the attribution report information.

[0111] S106, the monitoring SDK feeds back the operation information of the user to the backend service plug-in.

[0112] The forced confirmation pop-up window is used to confirm with the user whether to jump to the application corresponding to the target advertisement, which can be realized by providing two options "agree" and "refuse" to the user, which is not limited here,

[0113] Specifically, after the user completes the click, the operation information of the user to the forced confirmation pop-up window will be generated according to the click condition, for example: the user clicks "agree", then jumps to the application corresponding to the target advertisement, and the operation information of the user to the forced confirmation pop-up window is that the user agrees to jump to the application corresponding to the target advertisement; when the user clicks "refuse", the current application will switch back to the foreground from the background in a short time, and the operation information of the forced confirmation pop-up window is that the user refuses to jump to the application corresponding to the target advertisement, which is not limited here.

[0114] In the specific implementation process of the application, after the APP corresponding to the target advertisement is started, the jump success information can also be directly reported to the advertisement backend service, including but not limited to the ID of the target advertisement, the user ID and other related data.

[0115] S107, the backend service plug-in receives the report information returned by the monitoring SDK and the operation information of the user to the forced confirmation pop-up window.

[0116] S108, the backend service plug-in generates the monitoring result of the advertisement according to the report information and the operation information of the user to the forced confirmation pop-up window.

[0117] For example, the report information includes 123 (target advertisement ID), 123-mn (target advertisement and device combined ID), and click time (17:00 on January 1, 2000), the operation information for the mandatory confirmation pop-up window is that the user clicks "Agree", and the generated advertisement monitoring result is that the user device mn wakes up the advertisement with the advertisement ID 123 at 17:00 on January 1, 2000.

[0118] Optionally, in another embodiment of the present application, the feature information of the advertisement further includes the jump success rate of the advertisement. The jump success rate of the advertisement in the set of advertisements to be displayed is predicted by a separate machine learning model in the backend service plug-in, the jump success rate of the advertisement is obtained, and the monitoring SDK is provided. The monitoring SDK generates a target advertisement set according to the jump success rates of all advertisements and the combined ID of the advertisement and the device; the target advertisement set is rendered and displayed by the advertisement SDK, so as to further improve the probability of user clicking the advertisement, such as Figure 3 As shown in the figure, an embodiment of generating feature information of an advertisement by a backend service plug-in includes:

[0119] S301, for each advertisement in the set of advertisements to be displayed, obtaining the historical data of the advertisement.

[0120] The historical data of the advertisement includes but is not limited to the jump success rate of the corresponding user portrait group of the advertisement, which is not limited here.

[0121] S302, reading the target device ID in the advertisement request received by the advertisement backend service.

[0122] It should be noted that the specific implementation of step S302 can refer to the specific implementation of step S201, which will not be repeated here.

[0123] S303, determining the user portrait corresponding to the target device ID according to the target device ID.

[0124] The user portrait corresponding to the target device ID can be obtained by the historical behavior of the user corresponding to the target device ID, but is not limited to this. The main dimensions are time, click rate, jump success rate, etc., which are not limited here.

[0125] S304, inputting the historical data of the advertisement and the user portrait corresponding to the target device ID into the jump success rate prediction model, and outputting to obtain the jump success rate of the advertisement.

[0126] The jump success rate prediction model is obtained by pre-training through a training sample set. The type of the jump success rate prediction model includes but is not limited to a time series prediction model, which is not limited here.

[0127] S305, combine the advertisement ID and the target device ID to obtain a combined ID of the advertisement and the device.

[0128] It should be noted that the specific implementation of step S305 can refer to the specific implementation of step S202, which will not be repeated here.

[0129] In the specific implementation of the present application, the jump success rate of the advertisement and the combined ID of the advertisement and the device are taken as the feature information of the advertisement and added to the feedback information. The advertisement backend service feeds back the feedback information to the advertisement SDK. After receiving the feedback information fed back by the backend service plug-in, the monitoring SDK obtains the feedback information received by the advertisement SDK. The monitoring SDK generates a target advertisement set according to the jump success rate of all advertisements and the combined ID of the advertisement and the device. The advertisement SDK renders and displays the target advertisement set.

[0130] For example, the monitoring SDK sorts all advertisements according to the jump success rate from high to low, records all original advertisement IDs and newly added combined IDs of the advertisement and the device, obtains a target advertisement set, and returns the target advertisement set to the advertisement SDK. The advertisement SDK renders and displays the target advertisement set.

[0131] In the specific implementation of the present application, the user conversion behavior in the APP corresponding to the target advertisement can also be monitored. The user conversion behavior includes but is not limited to the user's operation in the APP corresponding to the target advertisement, such as registration, purchase or completion of other predefined conversion behaviors, which are not limited here. When the user completes the conversion, the APP corresponding to the target advertisement will report the conversion behavior to the advertisement backend service and associate the previous jump record. At this time, the advertisement backend service will update the state of this target advertisement delivery to “successful conversion”.

[0132] It can be understood that after the user completes the operation in the APP corresponding to the target advertisement, the user will usually return to the original advertisement APP (i.e. the current application described above). When the current application detects that it is switched from the background to the foreground, it will judge the time elapsed since the last switching to the background (i.e. the difference between the time when the current application is switched back to the foreground and the time when the current application is switched to the background). If the time exceeds the preset threshold (i.e. exceeds the reasonable jump and use time), the monitoring SDK will request the advertisement backend service to query whether the jump produces an effective conversion.

[0133] However, in actual application, the advertisement SDK initiates jump, at which time the operating system will forcibly pop up a pop-up window, and the current application will be switched to the background state. In the background state, it may not be possible to report the time when the current application is switched to the background due to operating system settings, permissions and other reasons. Therefore, in another embodiment of the present application, one implementation of the advertisement monitoring method is as follows: Figure 4Also shown, and including:

[0134] S401, monitoring the SDK records the target advertisement and the combination ID of the device and the time when the current application switches to the background, to obtain a monitoring file.

[0135] Specifically, the target advertisement and the combination ID of the device and the time when the current application switches to the background are recorded in the monitoring SDK locally to obtain a monitoring file.

[0136] S402, when the current application switches to the foreground again, the monitoring SDK adds the time when the current application switches back to the foreground to the monitoring file to obtain a target monitoring file.

[0137] S403, the monitoring SDK feeds back the target monitoring file to the backend service plug-in.

[0138] S404, after the backend service plug-in receives the target monitoring file, it judges whether the difference between the time when the current application switches back to the foreground and the time when the current application switches to the background is greater than a time threshold.

[0139] The time threshold is pre-set by technicians, experts, etc., and is not limited here.

[0140] S405, if it is determined that the difference between the time when the current application switches back to the foreground and the time when the current application switches to the background is not greater than the time threshold, it is determined that the target advertisement fails to jump.

[0141] It can be understood that in actual application process, the user may misoperate or switch to the target APP, and then find that the target APP does not have what he is interested in and switch back to the foreground. At this time, the target advertisement does not occur effective conversion, and therefore, it is determined that the advertisement fails to jump.

[0142] S406, if it is determined that the difference between the time when the current application switches back to the foreground and the time when the current application switches to the background is greater than the time threshold, the historical jump success rate of the advertisement corresponding to the combination ID of the advertisement and the device is used to determine whether the target advertisement fails to jump.

[0143] Specifically, the difference between the time when the current application switches back to the foreground and the time when the current application switches to the background is taken as time A; the current device model is determined according to the combination ID of the target advertisement and the device, the historical jump time of the application corresponding to the target advertisement is obtained as B according to the current device model, the target advertisement is determined according to the combination ID of the target advertisement and the device, and the historical jump success rate C of the application corresponding to the target advertisement. Then, if A<1 and B>1, it is directly determined that the target advertisement fails to jump, if A>B, it is directly determined that the target advertisement succeeds to jump, if A>B-(B*0.3) and C>0.5, it is determined that the target advertisement succeeds to jump, otherwise, it is determined that the target advertisement fails to jump, and if B<=10, B is added to the historical data.

[0144] In another embodiment of the present application, if it is determined that the target advertisement jump fails or does not produce effective conversion (for example: the user does not complete the registration or purchase behavior, etc.), a bottom mechanism is triggered, which includes but is not limited to displaying backup content, providing coupons or reward points to encourage users to continue using, guiding users to perform other operations, such as filling out a questionnaire or participating in an interactive activity, etc., which are not limited here.

[0145] In another embodiment of the present application, if the target advertisement jump is successful or produces effective conversion, a corresponding feedback mechanism is triggered, for example: different feedback mechanisms will be used according to different types of advertisements. Assuming that it is an incentive type of advertisement, the user will be given corresponding incentives after the display is completed, which is not limited here.

[0146] In another embodiment of the present application, during the jump process of the advertisement, if the data cannot be normally reported or feedback cannot be obtained due to network problems, a timeout mechanism is designed in the present application. When the feedback is not received after the preset time is exceeded, the system will automatically trigger the bottom-up solution to ensure that the user experience is not affected.

[0147] In another embodiment of the present application, during the jump process of the advertisement, if it is found that the target APP is not installed, the user is guided to the application store to download the application. In this case, if the user eventually downloads and installs the target APP, it can be considered as "indirect success", and the chain of this behavior is recorded in the background.

[0148] In another embodiment of the present application, for other situations that may cause jump failure or data reporting failure (such as system permission restrictions, device compatibility problems, etc.), the present application can also capture related error information and upload it to the background for analysis, so that the developer can further optimize the system compatibility and stability.

[0149] From the above scheme, the application provides an advertisement monitoring method, which pre-processes each advertisement in a set of advertisements to be displayed through a backend service plug-in, generates feature information of the advertisements, adds the feature information of all the advertisements to feedback information, feeds back the feedback information to an advertisement SDK by an advertisement backend service, acquires the feedback information received by the advertisement SDK by a monitoring SDK, determines a target advertisement and a combination ID of the target advertisement and a device according to a target advertisement ID when the monitoring SDK receives advertisement click information reported by the advertisement SDK, generates report information including the target advertisement ID, the combination ID of the target advertisement and the device, and a click time, reports the report information to the backend service plug-in, feeds back operation information of a user on a forced confirmation pop-up window to the backend service plug-in, and generates a monitoring result of the advertisement according to the report information and the operation information of the user on the forced confirmation pop-up window by the backend service plug-in. Thus, whether the advertisement after the forced confirmation pop-up window jumps successfully can be accurately and timely monitored, and the advertisement owner is helped to optimize a delivery strategy, improve a return on investment (ROI), and improve overall user experience.

[0150] The application embodiment provides an advertisement monitoring device, which is applied to a backend service plug-in, the backend service plug-in runs in the form of a plug-in in an advertisement backend service, and one embodiment of the advertisement monitoring device specifically includes: Figure 5

[0151] A first generation unit 501 is configured to pre-process each advertisement in a set of advertisements to be displayed and generate feature information of the advertisements.

[0152] The feature information of the advertisements includes a combination ID of the advertisements and devices, and the set of advertisements to be displayed is determined by the advertisement backend service according to an advertisement request sent by an advertisement SDK.

[0153] Optionally, in another embodiment of the application, one embodiment of the first generation unit 501 includes:

[0154] A first reading unit is configured to read a target device ID in an advertisement request received by the advertisement backend service.

[0155] When the monitoring SDK is initialized, device feature information of a current device is acquired and reported to the backend service plug-in, the backend service plug-in generates a target device ID according to the device feature information of the current device and feeds back the target device ID to the monitoring SDK, and when the advertisement SDK initiates an advertisement request, the target device ID is added to the advertisement request, and the advertisement request is sent to the advertisement backend service.

[0156] A first combination unit is configured to combine the advertisement ID and the target device ID for each advertisement in the set of advertisements to be displayed to obtain a combination ID of the advertisements and devices.​

[0157] The specific working processes of the units disclosed in the above embodiments of the application can be seen from the corresponding method embodiment contents, such as Figure 2 as shown, which will not be described here again.

[0158] Optionally, in another embodiment of the application, the feature information of the advertisement further includes a jump success rate of the advertisement, and one embodiment of the first generating unit 501 includes:

[0159] The first obtaining unit is configured to obtain historical data of each advertisement in the set of advertisements that need to be displayed.

[0160] The second reading unit is configured to read a target device ID in an advertisement request received by an advertisement backend service.

[0161] The first determining unit is configured to determine a user portrait corresponding to the target device ID according to the target device ID.

[0162] The predicting unit is configured to input the historical data of the advertisement and the user portrait corresponding to the target device ID into a jump success rate prediction model, and output a jump success rate of the advertisement.

[0163] The second combining unit is configured to combine the advertisement ID and the target device ID to obtain a combined ID of the advertisement and the device.

[0164] The specific working processes of the units disclosed in the above embodiments of the application can be seen from the corresponding method embodiment contents, such as Figure 3 as shown, which will not be described here again.

[0165] The first adding unit 502 is configured to add the feature information of all the advertisements to the feedback information.

[0166] The advertisement backend service feeds back the feedback information to the advertisement SDK; the monitoring SDK obtains the feedback information received by the advertisement SDK, and when the monitoring SDK receives the advertisement click information reported by the advertisement SDK, determines a combined ID of a target advertisement and a device according to a target advertisement ID; the advertisement click information includes the target advertisement ID; the target advertisement ID is an ID of an advertisement clicked by a user; the monitoring SDK generates report information including the target advertisement ID, the combined ID of the target advertisement and the device, and a click time, and reports the report information to a backend service plug-in; the monitoring SDK feeds back operation information of the user to the backend service plug-in in response to a forced confirmation pop-up window; and the monitoring SDK runs in the form of a plug-in in the advertisement SDK.

[0167] The first receiving unit 503 is configured to receive the report information returned by the monitoring SDK and the operation information of the user to the forced confirmation pop-up window.

[0168] The second generating unit 504 is configured to generate a monitoring result of the advertisement according to the report information and the operation information of the user for the forced confirmation pop-up window.

[0169] The specific working process of the units disclosed in the above embodiments of the application can be referred to the corresponding method embodiment contents, such as Figure 1 shown, and will not be described here.

[0170] Optionally, in another embodiment of the application, an embodiment method of the advertisement monitoring device further includes:

[0171] The first receiving unit is configured to receive a target monitoring file fed back by the monitoring SDK.

[0172] The target monitoring file includes a combination ID of a target advertisement and a device, a time when a current application switches to the background, and a time when the current application switches back to the foreground.

[0173] The judging unit is configured to judge whether a difference between the time when the current application switches back to the foreground and the time when the current application switches to the background is greater than a time threshold.

[0174] The triggering unit is configured to determine that the target advertisement fails to jump if the judging unit judges that the difference between the time when the current application switches back to the foreground and the time when the current application switches to the background is not greater than the time threshold.

[0175] The second determining unit is configured to determine whether the target advertisement fails to jump by using a historical jump success rate of the advertisement corresponding to the combination ID of the advertisement if the judging unit judges that the difference between the time when the current application switches back to the foreground and the time when the current application switches to the background is greater than the time threshold.

[0176] The specific working process of the units disclosed in the above embodiments of the application can be referred to the corresponding method embodiment contents, such as Figure 4 shown, and will not be described here.

[0177] The application embodiment provides an advertisement monitoring device applied to a monitoring SDK, the monitoring SDK runs in the form of a plug-in in an advertisement SDK, and an embodiment of the advertisement monitoring device is shown in Figure 6 specifically includes:

[0178] The second obtaining unit 601 is configured to obtain feedback information received by the advertisement SDK.

[0179] The feedback information is fed back to the advertisement SDK by the advertisement backend service after the advertisement backend service determines the set of advertisements to be displayed according to an advertisement request sent by the advertisement SDK, and the backend service plug-in pre-processes each advertisement in the set of advertisements to be displayed to generate feature information of the advertisement, adds the feature information of all the advertisements to the feedback information, and feeds back the feedback information to the advertisement SDK by the advertisement backend service; the backend service plug-in runs in the form of a plug-in in the advertisement backend service; the feature information of the advertisement includes a combination ID of the advertisement and a device.

[0180] The second receiving unit 602 is configured to determine a combination ID of a target advertisement and a device according to a target advertisement ID when receiving advertisement click information reported by the advertisement SDK.

[0181] The advertisement click information includes the target advertisement ID; and the target advertisement ID is an ID of an advertisement clicked by a user.

[0182] The third generating unit 603 is configured to generate report information including the target advertisement ID, the combination ID of the target advertisement and the device, and a click time, and report the report information to the backend service plug-in.

[0183] The first feedback unit 604 is configured to feed back operation information of the user on the forced confirmation pop-up window to the backend service plug-in.

[0184] The backend service plug-in generates an advertisement monitoring result according to the report information and the operation information of the user on the forced confirmation pop-up window after receiving the report information and the operation information of the user on the forced confirmation pop-up window.

[0185] The specific working processes of the units disclosed in the above embodiments of the application can be referred to the corresponding method embodiments, for example, as shown in the above method embodiments, and details are not described herein. Figure 1

[0186] Optionally, in another embodiment of the application, an embodiment of the advertisement monitoring device further includes:

[0187] The recording unit is configured to record the combination ID of the target advertisement and the device and a time when the current application switches to the background to obtain a monitoring file.

[0188] The second adding unit is configured to add a time when the current application switches back to the foreground to the monitoring file to obtain a target monitoring file when the current application switches to the foreground again.

[0189] The second feedback unit is configured to feed back the target monitoring file to the backend service plug-in.

[0190] ​The backend service plug-in receives the target monitoring file, and if it is determined that the time when the current application switches back to the foreground and the time when the current application switches to the background differ by no more than a time threshold, it is determined that the target advertisement fails to jump; if it is determined that the time when the current application switches back to the foreground and the time when the current application switches to the background differ by more than the time threshold, the historical jump success rate of the advertisement corresponding to the combination ID of the advertisement and the device is used to determine whether the target advertisement fails to jump.

[0191] The specific working process of the units disclosed in the above embodiments of the application can be referred to the corresponding method embodiment contents, for example, as shown in the above embodiments, and details are not described herein. Figure 4

[0192] Optionally, in another embodiment of the application, an embodiment of the advertisement monitoring device further includes:

[0193] The fourth generation unit is configured to generate a target advertisement set according to the jump success rates of all the advertisements and the combination ID of the advertisement and the device.

[0194] The advertisement SDK renders and displays the target advertisement set.

[0195] The specific working process of the units disclosed in the above embodiments of the application can be referred to the corresponding method embodiment contents, for example, as shown in the above embodiments, and details are not described herein.

[0196] As can be seen from the above solutions, the application provides an advertisement monitoring device. The backend service plug-in pre-processes each advertisement in the advertisement set to be displayed, generates feature information of the advertisement, adds the feature information of all the advertisements to feedback information, feeds back the feedback information to the advertisement SDK by the advertisement backend service, acquires the feedback information received by the advertisement SDK by the monitoring SDK, determines the combination ID of the target advertisement and the device according to the target advertisement ID when the monitoring SDK receives the advertisement click information reported by the advertisement SDK, generates report information including the target advertisement ID, the combination ID of the target advertisement and the device, and the click time, reports to the backend service plug-in, feeds back the operation information of the user to the forced confirmation pop-up window to the backend service plug-in, and generates the monitoring result of the advertisement according to the report information and the operation information of the user to the forced confirmation pop-up window by the backend service plug-in. Thus, the advertisement whether jumps successfully after the forced confirmation pop-up window is accurately and timely monitored, which helps the advertisement owner to optimize the delivery strategy, improve the return on investment (ROI), and improve the overall user experience.

[0197] ​The functionality described herein above can be performed, at least in part, by one or more hardware logic components. For example, and without limitation, illustrative types of hardware logic components that can be used include Field-programmable Gate Arrays (FPGAs), Application-specific Integrated Circuits (ASICs), Application-specific Standard Products (ASSPs), System-on-a-chip systems (SOCs), Complex Programmable Logic Devices (CPLDs), etc.

[0198] Another embodiment of the present application provides an electronic device, comprising:

[0199] one or more processors.

[0200] a storage storing one or more programs.

[0201] The one or more programs, when executed by the one or more processors, enable the one or more processors to implement a method for monitoring advertisement according to any one of the above embodiments.

[0202] Another embodiment of the present application provides a computer storage medium storing a computer program, wherein the computer program, when executed by a processor, implements a method for monitoring advertisement according to any one of the above embodiments.

[0203] In the context of the present application, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0204] It should be noted that the computer readable medium in the present application can be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium may, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or apparatus. In the present application, the computer readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer readable program code. Such a propagated data signal can take many forms, including but not limited to an electromagnetic signal, an optical signal or any suitable combination of the above. The computer readable signal medium can also be any computer readable medium other than the computer readable storage medium, which can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or apparatus. The program code contained in the computer readable medium can be transmitted by any suitable medium, including but not limited to a wire, a cable, an RF (radio frequency) or the like, or any suitable combination of the above.

[0205] The computer readable medium described above can be contained in the electronic device described above; or can exist separately and not be assembled into the electronic device.

[0206] Another embodiment of the present application provides a computer program product for executing the above-described advertisement monitoring method when the computer program product is executed.

[0207] In particular, according to embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, embodiments of the present application include a computer program product comprising a computer program carried on a non-transitory computer readable medium, the computer program comprising program code for executing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by a communication device, or installed from a storage device, or installed from a ROM. When the computer program is executed by a processing device, the above-described functions defined in the methods of the embodiments of the present application are executed.

[0208] Although the subject matter has been described in language specific to structural features and / or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

[0209] Although specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the application. Some features described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment can also be implemented separately or in any appropriate subcombination. For the sake of clarity, the numerous embodiments of the application have not been illustrated in every possible combination. It is therefore to be understood that numerous other modifications, in addition to those described herein, can be effected. Accordingly, no limitation is placed on the scope of the application apart from the applications defined in the claims.

[0210] The above description is merely illustrative of the exemplary embodiments of this application and the principles thereof. It is understood that numerous other modifications and adaptations were apparent to those skilled in the art in view of the above description. Accordingly, the scope of the application should be determined not with reference to the above description but instead with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled. It is therefore to be understood that numerous modifications can be made to the illustrative embodiments described herein, and that other arrangements can be devised without departing from the scope of the present application as defined by the appended claims.

Claims

1. An advertising monitoring method characterized by, The application is applied to a backend service plug-in, which runs in the form of a plug-in in an advertisement backend service, and the monitoring method of the advertisement comprises: Preprocessing each advertisement in a set of advertisements that need to be displayed to generate feature information of the advertisement; wherein the feature information of the advertisement comprises a combination ID of the advertisement and a device and a jump success rate of the advertisement; the set of advertisements that need to be displayed is determined by an advertisement backend service according to an advertisement request sent by an advertisement SDK, and the jump success rate is obtained by inputting historical data of the advertisement and a user portrait corresponding to the target device ID into a jump success rate prediction model; Adding the feature information of all advertisements to feedback information; wherein the advertisement backend service feeds back the feedback information to the advertisement SDK; a monitoring SDK acquires the feedback information received by the advertisement SDK, and when the monitoring SDK receives advertisement click information reported by the advertisement SDK, determines a combination ID of a target advertisement and a device according to a target advertisement ID; the advertisement click information comprises the target advertisement ID; the target advertisement ID is the ID of an advertisement clicked by a user; the monitoring SDK generates report information of the target advertisement ID, the combination ID of the target advertisement and the device, and a click time, and reports the report information to a backend service plug-in; the monitoring SDK feeds back operation information of the user to a forced confirmation pop-up window to the backend service plug-in; the monitoring SDK runs in the form of a plug-in in the advertisement SDK; Receiving report information returned by the monitoring SDK and operation information of the user to a forced confirmation pop-up window; Generating a monitoring result of the advertisement according to the report information and the operation information of the user to the forced confirmation pop-up window.

2. The method of claim 1, wherein The preprocessing of each advertisement in the set of advertisements that need to be displayed to generate the feature information of the advertisement comprises: Reading a target device ID in an advertisement request received by an advertisement backend service; wherein when the monitoring SDK is initialized, device feature information of a current device is acquired and reported to the backend service plug-in; the backend service plug-in generates the target device ID according to the device feature information of the current device and feeds back the target device ID to the monitoring SDK; when the advertisement SDK initiates an advertisement request, the target device ID is added to the advertisement request, and the advertisement request is sent to the advertisement backend service; For each advertisement in the set of advertisements that need to be displayed, combining the ID of the advertisement and the target device ID to obtain a combination ID of the advertisement and the device.

3. The method of claim 1, wherein The preprocessing of each advertisement in the set of advertisements that need to be displayed to generate the feature information of the advertisement comprises: For each advertisement in the set of advertisements that need to be displayed, acquiring historical data of the advertisement; Reading a target device ID in an advertisement request received by an advertisement backend service; Determining a user portrait corresponding to the target device ID according to the target device ID; Inputting the historical data of the advertisement and the user portrait corresponding to the target device ID into a jump success rate prediction model to output the jump success rate of the advertisement; Combine the ID of the advertisement and the target device ID to obtain an advertisement-device combined ID.

4. The method of claim 3, wherein Also include: Receiving a target monitoring file for monitoring SDK feedback; wherein the target monitoring file includes: a target advertisement-device combined ID, a time when the current application switches to the background, and a time when the current application switches back to the foreground; Determine whether the difference between the time when the current application switches back to the foreground and the time when the current application switches to the background is greater than a time threshold; If it is determined that the difference between the time when the current application switches back to the foreground and the time when the current application switches to the background is not greater than the time threshold, it is determined that the target advertisement fails to jump; If it is determined that the difference between the time when the current application switches back to the foreground and the time when the current application switches to the background is greater than the time threshold, the historical jump success rate of the advertisement corresponding to the advertisement-device combined ID is used to determine whether the target advertisement fails to jump.

5. The method of claim 1, wherein After receiving the report information returned by the monitoring SDK, it further includes: If there is a target advertisement-device combined ID in the report information in the attribution reporting set, it is determined that the target advertisement jumps successfully; wherein the attribution reporting set includes at least one attribution reporting information; the target advertisement attempts to access the attribution SDK after jumping successfully, and the attribution SDK reports the target advertisement-device combined ID of the target advertisement to the backend service plug-in after the target advertisement accesses the attribution SDK; the backend service plug-in reports the target advertisement-device combined ID of the target advertisement as attribution reporting information.

6. An advertising monitoring method characterized by, Applied to a monitoring SDK, the monitoring SDK runs in the form of a plug-in in an advertisement SDK, and the advertisement monitoring method includes: Obtain feedback information received by the advertisement SDK; wherein the feedback information is determined by the advertisement backend service according to the advertisement request sent by the advertisement SDK after determining the set of advertisements that need to be displayed; the backend service plug-in preprocesses each advertisement in the set of advertisements that need to be displayed to generate feature information of the advertisement, adds the feature information of all advertisements to the feedback information, and feeds back the feedback information to the advertisement SDK by the advertisement backend service; the backend service plug-in runs in the form of a plug-in in the advertisement backend service; the feature information of the advertisement includes an advertisement-device combined ID and a jump success rate of the advertisement, the jump success rate is obtained by inputting historical data of the advertisement and a user portrait corresponding to the target device ID into a jump success rate prediction model, and the user portrait is determined according to the target device ID in the advertisement request; When receiving the advertisement click information reported by the advertisement SDK, determine the target advertisement-device combined ID according to the target advertisement ID; wherein the advertisement click information includes a target advertisement ID; the target advertisement ID is the ID of the advertisement clicked by the user; Generate report information by combining the target advertisement ID, the target advertisement-device combined ID, and the click time, and report it to the backend service plug-in; The operation information of the user for the mandatory confirmation pop-up window is fed back to a backend service plug-in; wherein, after receiving the report information and the operation information of the user for the mandatory confirmation pop-up window, the backend service plug-in generates a monitoring result of the advertisement according to the report information and the operation information of the user for the mandatory confirmation pop-up window.

7. The method of claim 6, wherein Also include: Record the combination ID of the target advertisement and the device and the time when the current application switches to the background to obtain a monitoring file; When the current application switches to the foreground again, add the time when the current application switches back to the foreground to the monitoring file to obtain a target monitoring file; The target monitoring file is fed back to the backend service plug-in; wherein, after receiving the target monitoring file, if it is judged that the difference between the time when the current application switches back to the foreground and the time when the current application switches to the background is not greater than a time threshold, it is determined that the target advertisement fails to jump; if it is judged that the difference between the time when the current application switches back to the foreground and the time when the current application switches to the background is greater than the time threshold, it is determined whether the target advertisement fails to jump by using the historical jump success rate of the advertisement corresponding to the combination ID of the advertisement and the device.

8. The method of claim 6, wherein, The feature information of the advertisement further includes the jump success rate of the advertisement, and after the feedback information received by the advertisement SDK is obtained, the following further includes: Generate a target advertisement set according to the jump success rate of all advertisements and the combination ID of the advertisement and the device; wherein, the advertisement SDK renders and displays the target advertisement set.

9. An apparatus for monitoring advertising, characterized by Applied to a backend service plug-in, the backend service plug-in runs in the form of a plug-in in an advertisement backend service, and the advertisement monitoring device comprises: A first generation unit is configured to preprocess each advertisement in an advertisement set that needs to be displayed to generate feature information of the advertisement; wherein, the feature information of the advertisement includes: a combination ID of the advertisement and the device and a jump success rate of the advertisement; the advertisement set that needs to be displayed is determined by an advertisement backend service according to an advertisement request sent by an advertisement SDK, and the jump success rate is obtained by inputting historical data of the advertisement and a user portrait corresponding to a target device ID into a jump success rate prediction model and outputting; the user portrait is determined according to the target device ID in the advertisement request. A first adding unit is configured to add the feature information of all advertisements to feedback information; wherein, the advertisement backend service feeds back the feedback information to the advertisement SDK; the monitoring SDK obtains the feedback information received by the advertisement SDK, determines the combination ID of the target advertisement and the device according to the target advertisement ID when the monitoring SDK receives the advertisement click information reported by the advertisement SDK; the advertisement click information includes the target advertisement ID; the target advertisement ID is the ID of the advertisement clicked by the user; the monitoring SDK generates report information by combining the target advertisement ID, the combination ID of the target advertisement and the device, and the click time, and reports it to the backend service plug-in; the monitoring SDK feeds back the operation information of the user for the mandatory confirmation pop-up window to the backend service plug-in; the monitoring SDK runs in the form of a plug-in in the advertisement SDK. The first receiving unit is configured to receive the report information returned by the monitoring SDK and the operation information of the user for the forced confirmation pop-up window. The second generating unit is configured to generate the monitoring result of the advertisement according to the report information and the operation information of the user for the forced confirmation pop-up window.

10. An apparatus for monitoring advertising, characterized by The monitoring SDK runs in the form of a plug-in in the advertisement SDK. The second obtaining unit is configured to obtain feedback information received by the advertisement SDK; wherein the feedback information is obtained by the advertisement backend service after determining a set of advertisements to be displayed according to an advertisement request sent by the advertisement SDK; the backend service plug-in pre-processes each advertisement in the set of advertisements to be displayed to generate feature information of the advertisement, adds the feature information of all the advertisements to the feedback information, and feeds back the feedback information to the advertisement SDK by the advertisement backend service; the backend service plug-in runs in the form of a plug-in in the advertisement backend service; the feature information of the advertisement includes a combination ID of the advertisement and a device and a jump success rate of the advertisement; the jump success rate is obtained by inputting historical data of the advertisement and a user portrait corresponding to a target device ID into a jump success rate prediction model; the user portrait is determined according to the target device ID in the advertisement request; The second receiving unit is configured to determine the combination ID of the target advertisement and the device according to the target advertisement ID when receiving the advertisement click information reported by the advertisement SDK; wherein the advertisement click information includes the target advertisement ID; the target advertisement ID is the ID of the advertisement clicked by the user; The third generating unit is configured to generate report information including the target advertisement ID, the combination ID of the target advertisement and the device, and the click time, and report the report information to the backend service plug-in; The first feedback unit is configured to feed back the operation information of the user for the forced confirmation pop-up window to the backend service plug-in; wherein the backend service plug-in generates the monitoring result of the advertisement according to the report information and the operation information of the user for the forced confirmation pop-up window after receiving the report information and the operation information of the user for the forced confirmation pop-up window.

Images