Information Processing Method, Apparatus, Medium and Electronic Device

Abstract

The present application belongs to the field of computer technology, and specifically relates to an information processing method, an information processing device, a computer-readable medium, and an electronic device. The information processing method includes: obtaining trigger position information of multiple content triggering operations on a content display subject, wherein the multiple content triggering operations act on the content display subject and are used to trigger content display of content display information on the content display subject; dividing the content display subject into regions to obtain multiple triggering regions, and determining the triggering region information of the multiple content triggering operations on the content display subject based on the triggering position information; determining the distribution dispersion information of the content triggering operations on the content display subject based on the triggering region information; determining the content triggering state of the content display subject based on the distribution dispersion information, and the content triggering state includes a normal triggering state and an abnormal triggering state. Based on this method, cheating behavior of the content display subject can be effectively detected.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an information processing method, an information processing device, a computer-readable medium, and an electronic device. Background Art

[0002] With the development of computers and the internet, information can be disseminated quickly and widely through the internet. For example, online advertising allows advertisers to insert online ads into various web pages or software application pages. When users browse web pages or use applications, they can click on these ads to view them. Data such as the impressions and click-through rates of online ads generally influence the advertising placement fees paid by advertisers to online platforms.

[0003] To increase exposure and clickthrough rates for various online information, such as online advertisements, some online platforms use software scripts or other fraudulent tools to automatically manipulate clicks on related information. This fraudulently generated exposure is completely ineffective and can cause serious losses to advertisers and other publishers. False exposure can generally be detected through manual verification, but this method is often costly, inefficient, and inaccurate.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of this application, and therefore may include information that does not constitute prior art known to ordinary technicians in this field. Summary of the Invention

[0005] The purpose of this application is to provide an information processing method, an information processing device, a computer-readable medium and an electronic device, which can at least to some extent overcome the technical problems of high cost, low efficiency and poor accuracy in detecting invalid exposure data in the related art.

[0006] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by practice of the present application.

[0007] According to one aspect of an embodiment of the present application, there is provided an information processing method, the method comprising:

[0008] Acquiring trigger position information of multiple content triggering operations on a content display subject, wherein the multiple content triggering operations act on the content display subject and are used to trigger content display information on the content display subject to be displayed;

[0009] Divide the content display body into regions to obtain a plurality of trigger regions, and determine trigger region information of the plurality of content trigger operations on the content display body according to the trigger position information, wherein the trigger region information is used to indicate distribution information of the content trigger operations on each trigger region;

[0010] Determining distribution dispersion information of the content triggering operation on the content display subject according to the triggering area information;

[0011] The content triggering state of the content display subject is determined according to the distribution dispersion information, where the content triggering state includes a normal triggering state and an abnormal triggering state.

[0012] According to one aspect of an embodiment of the present application, there is provided an information processing device, the device comprising:

[0013] an information acquisition module configured to acquire trigger position information of a plurality of content triggering operations on a content display subject, wherein the plurality of content triggering operations act on the content display subject and are used to trigger content display information on the content display subject to be displayed;

[0014] a region division module configured to divide the content display body into regions to obtain a plurality of trigger regions, and determine trigger region information of the plurality of content triggering operations on the content display body according to the trigger position information, wherein the trigger region information is used to indicate distribution information of the content triggering operations on each trigger region;

[0015] an information determination module configured to determine distribution dispersion information of the content triggering operation on the content display subject according to the triggering area information;

[0016] The state determination module is configured to determine the content trigger state of the content display body according to the distribution dispersion information, and the content trigger state includes a normal trigger state and an abnormal trigger state.

[0017] In some embodiments of the present application, based on the above technical solution, the information acquisition module includes:

[0018] a coordinate acquisition unit configured to acquire trigger position coordinates of a plurality of content triggering operations on a content visualization page corresponding to the content display subject, wherein the content visualization page is used to display the content display information and receive the content triggering operations;

[0019] The position determination unit is configured to determine the trigger position information of each content triggering operation on the content display body according to the trigger position coordinates.

[0020] In some embodiments of the present application, based on the above technical solution, the position determination unit includes:

[0021] a size acquisition subunit, configured to acquire page size information of the content visualization page and acquire normalized size information related to the content display body;

[0022] The normalization processing subunit is configured to normalize the trigger position coordinates according to the page size information and the normalized size information to obtain the normalized position coordinates of each content trigger operation, wherein the normalized position coordinates represent the trigger position information of the content trigger operation on the content display body.

[0023] In some embodiments of the present application, based on the above technical solution, the region division module includes:

[0024] A first quantity acquisition unit is configured to acquire a subject trigger quantity of content triggering operations on the content display subject, wherein the subject trigger quantity is a total number of content triggering operations acting on the content display subject;

[0025] a second quantity acquisition unit configured to determine, according to the trigger position information, a region trigger quantity of content triggering operations on each of the triggering regions, wherein the region trigger quantity is the number of content triggering operations respectively acting on each of the triggering regions;

[0026] The trigger frequency determination unit is configured to determine the area trigger frequency of each trigger area according to the proportion of the area trigger quantity in the main body trigger quantity, wherein the area trigger frequency represents the trigger area information of the multiple content trigger operations on the content display main body.

[0027] In some embodiments of the present application, based on the above technical solution, the region division module includes:

[0028] a parameter acquisition unit configured to acquire area division parameters for dividing each trigger position on the content display body into areas;

[0029] The area division unit is configured to divide the content visualization page corresponding to the content display body into areas according to the area division parameters to obtain multiple trigger areas, wherein the content visualization page is used to display the content display information and receive the content trigger operation.

[0030] In some embodiments of the present application, based on the above technical solution, the area division unit includes:

[0031] a number determination subunit, configured to determine a first number of divisions for area division along the first direction and a second number of divisions for area division along the second direction according to the area division parameter;

[0032] The grid division subunit is configured to divide the content visualization page corresponding to the content display body into regions according to the first division number and the second division number to obtain a plurality of trigger regions in a grid shape.

[0033] In some embodiments of the present application, based on the above technical solution, the parameter acquisition unit includes:

[0034] A first sample determination subunit is configured to determine at least one content display subject in a normal trigger state as a positive sample subject, and to determine at least one content display subject in an abnormal trigger state as a negative sample subject;

[0035] A first parameter acquisition subunit is configured to acquire at least two candidate segmentation parameters for performing region segmentation on the positive sample body and the negative sample body;

[0036] A first information determination subunit is configured to determine, based on each candidate partition parameter, the positive sample distribution dispersion information of the content-triggered operation on the positive sample subject and the negative sample distribution dispersion information of the content-triggered operation on the negative sample subject;

[0037] The first parameter determination subunit is configured to select a candidate partition parameter as a region partition parameter for partitioning each trigger position on the content display body according to the discreteness difference between the positive sample distribution discreteness information and the negative sample distribution discreteness information.

[0038] In some embodiments of the present application, based on the above technical solution, the parameter acquisition unit includes:

[0039] The second sample determination subunit is configured to form a training sample set from at least two content display entities in different content triggering states;

[0040] A second parameter acquisition subunit is configured to acquire at least two candidate partitioning parameters for performing regional partitioning on the content presentation subject in the training sample set;

[0041] a model training subunit, configured to train a parameter selection model for selecting a region partition parameter from the at least two candidate partition parameters using the training sample set;

[0042] The second information determination subunit is configured to input the content display body that needs to be divided into regions into the parameter selection model to obtain the region division parameters output by the parameter selection model for dividing each trigger position on the content display body into regions.

[0043] In some embodiments of the present application, based on the above technical solution, the distribution dispersion information is a trigger area heat map drawn based on the trigger area information to represent the distribution state of the content triggering operation on the content display body; the state determination module includes:

[0044] a heat map input unit configured to input a trigger area heat map of the content display subject into a pre-trained state recognition model;

[0045] The heat map analysis unit is configured to perform image analysis and state recognition on the trigger area heat map through the state recognition model to obtain the content trigger state of the content display body output by the image recognition model.

[0046] In some embodiments of the present application, based on the above technical solution, the distribution dispersion information is the regional distribution information entropy determined according to the trigger area information; and the state determination module includes:

[0047] a subject sorting unit, configured to sort the content display subjects used to carry the content display information according to the regional distribution information entropy;

[0048] The state determination unit is configured to determine the content triggering state of each of the content display entities according to the sorting result.

[0049] In some embodiments of the present application, based on the above technical solution, the information processing device further includes:

[0050] a duration acquisition unit configured to acquire an actual display duration of content display information in each content display subject and a standard display duration associated with the content display information;

[0051] A completion rate determination unit is configured to determine a content display completion rate of the content display subject according to a proportion of content display information whose actual display duration is greater than or equal to the standard display duration;

[0052] an average duration determining unit, configured to determine an average content display duration of the content display subject according to an actual display duration of the content display information;

[0053] The display subject screening unit is configured to screen and obtain content display subjects in a normal triggering state according to the content display completion rate and the average content display duration.

[0054] In some embodiments of the present application, based on the above technical solution, the display subject screening unit includes:

[0055] A threshold acquisition subunit is configured to acquire a display completion rate threshold and a display duration threshold for screening content display subjects;

[0056] The subject screening subunit is configured to screen content display subjects whose content display completion rate is greater than the display completion rate threshold and whose average content display duration is greater than the display duration threshold as content display subjects in a normal triggering state.

[0057] According to one aspect of an embodiment of the present application, a computer-readable medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the information processing method in the above technical solution is implemented.

[0058] According to one aspect of an embodiment of the present application, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the information processing method in the above technical solution by executing the executable instructions.

[0059] In the technical solution provided in the embodiments of this application, by statistically analyzing content triggering operations on a content display entity, the distribution dispersion information of the content triggering operations can be determined based on the triggering position, and thus the content triggering state of the content display entity can be determined based on the distribution dispersion information. This method can effectively detect cheating behavior of the content display entity and efficiently and accurately discover invalid exposure data for content display information.

[0060] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] The accompanying drawings are incorporated into and constitute a part of the specification, illustrating embodiments consistent with the present application and, together with the specification, explaining the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and those skilled in the art can derive other drawings based on these drawings without inventive effort. In the drawings:

[0062] Figure 1 The following schematically shows an exemplary system architecture diagram applying the technical solution of the present application.

[0063] Figure 2 The following schematically illustrates the steps of the information processing method provided in the embodiment of the present application.

[0064] Figure 3 The diagram schematically shows the visualization effect of the content display information in the content display body being triggered to be displayed.

[0065] Figure 4 The figure schematically shows the comparative effects of heat maps of two triggers with different distribution discreteness.

[0066] Figure 5 The following schematically illustrates the steps of triggering the statistical content operation in an embodiment of the present application.

[0067] Figure 6 The following schematically illustrates the steps for determining distribution dispersion information based on a trigger area in an embodiment of the present application.

[0068] Figure 7 The visualization effect of dividing the content display subject into regions in an application scenario according to an embodiment of the present application is schematically shown.

[0069] Figure 8 The following schematically illustrates the steps for determining region division parameters based on sample analysis in an embodiment of the present application.

[0070] Figure 9 The following schematically illustrates the steps for determining the region division parameters based on the parameter selection model in an embodiment of the present application.

[0071] Figure 10 The display effect of a content display body including multiple content display information is schematically shown.

[0072] Figure 11 The following schematically shows a structural block diagram of the information processing device in an embodiment of the present application.

[0073] Figure 12 A schematic diagram of the structure of a computer system suitable for implementing an electronic device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0074] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art.

[0075] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner.In the following description, many specific details are provided so as to provide a full understanding of the embodiments of the present application. However, it will be appreciated by those skilled in the art that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps etc. can be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0076] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0077] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, while others may be combined or partially combined. Therefore, the actual execution order may vary depending on the actual situation.

[0078] In the following embodiments of the present application, the information processing method for detecting false exposure of network information is mainly described by taking online advertisements as an example. However, the present application is also applicable to other forms of network information such as video, audio, image, text, etc., and the present application is not limited to them.

[0079] Before providing a detailed description of the information processing methods, information processing devices and other technical solutions provided in the embodiments of this application, a brief introduction to the artificial intelligence technology involved in some embodiments of this application is first given.

[0080] Artificial Intelligence (AI) refers to the theories, methods, techniques, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, to perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results. In other words, AI is a comprehensive technology within computer science that seeks to understand the essence of intelligence and produce new intelligent machines that can respond in a manner similar to human intelligence. AI also studies the design principles and implementation methods of various intelligent machines, enabling them to possess the capabilities of perception, reasoning, and decision-making.

[0081] Artificial intelligence (AI) technology is a comprehensive discipline encompassing a wide range of fields, encompassing both hardware and software technologies. Foundational AI technologies generally include sensors, specialized AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, speech processing, natural language processing, and machine learning / deep learning.

[0082] Computer vision (CV) is the science of making machines "see." Specifically, it refers to machine vision techniques such as using cameras and computers to replace the human eye in identifying, tracking, and measuring objects. Further image processing is performed to transform the computer-generated images into images more suitable for human observation or transmission to instrumentation. As a scientific discipline, computer vision studies related theories and technologies, aiming to build artificial intelligence systems capable of extracting information from images or multidimensional data. Computer vision technologies typically include image processing, image recognition, image semantic understanding, image retrieval, optical character recognition (OCR), video processing, video semantic understanding, video content / behavior recognition, three-dimensional object reconstruction, 3D technology, virtual reality, augmented reality, simultaneous localization and mapping, and common biometric recognition technologies such as facial recognition and fingerprint recognition.

[0083] Machine learning (ML) is a multidisciplinary field that encompasses probability theory, statistics, approximation theory, convex analysis, and algorithmic complexity theory. It specifically studies how computers can simulate or implement human learning behaviors to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Machine learning is at the core of artificial intelligence and the fundamental way to make computers intelligent. Its applications span all areas of AI. Machine learning and deep learning typically include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and self-learning.

[0084] With the research and advancement of artificial intelligence technology, artificial intelligence technology has been studied and applied in many fields, such as common smart homes, smart wearable devices, virtual assistants, smart speakers, smart marketing, unmanned driving, autonomous driving, drones, robots, smart medical care, smart customer service, etc. It is believed that with the development of technology, artificial intelligence technology will be applied in more fields and play an increasingly important role.

[0085] The technical solutions provided in the embodiments of the present application are described in detail below in conjunction with specific application scenarios.

[0086] Figure 1 The following schematically shows an exemplary system architecture diagram applying the technical solution of the present application.

[0087] like Figure 1 As shown, system architecture 100 may include client 110, network 120, and server 130. Client 110 may include various terminal devices such as smartphones, tablet computers, laptop computers, and desktop computers. Server 130 may include various server devices such as network servers, application servers, and database servers. Network 120 may be a communication medium of various connection types capable of providing a communication link between client 110 and server 130, such as a wired communication link, a wireless communication link, and the like.

[0088] Depending on implementation needs, the system architecture in the embodiments of the present application can have any number of clients, networks, and servers. For example, the server 130 can be a server group consisting of multiple server devices. In addition, the technical solutions provided in the embodiments of the present application can be applied to the client 110, can also be applied to the server 130, or can be implemented by both the client 110 and the server 130, and this application does not make any special restrictions on this.

[0089] For example, client 110 can install an advertising platform acting as a traffic provider to host and display online advertisements. A traffic provider is a carrier that provides user traffic, typically referring to a website owner. In social media-based advertising platforms, traffic providers primarily refer to mini-programs or official accounts that have enabled the display of advertisements. When a trigger action for an online advertisement is generated on client 110, advertising data can be retrieved from server 130, acting as the advertiser, via network 120, thereby displaying the corresponding online advertisement on client 110.

[0090] Traffic owners can participate in the sharing of advertising revenue. The greater the traffic owner's advertising exposure and click volume, the higher the revenue from the share, so traffic owners have a strong motivation to cheat. Creating invalid exposures in an illegal manner can increase the traffic owner's advertising revenue, but the resulting advertising effect is very poor, which will harm the interests of advertisers (advertisers). In order to avoid losses caused by invalid exposures, the information processing method provided in this application can be executed on the client 110 or the server 130, and the normal and abnormal states of the traffic owner can be evaluated by statistics and analysis of triggering operations for online advertisements. For traffic owners with abnormalities, their invalid exposure behavior can be stopped in a timely manner.

[0091] Figure 2 The steps of the information processing method provided in the embodiment of the present application are schematically shown. The execution subject of the information processing method can be a terminal device or a server. Figure 2 As shown, the information processing method may mainly include the following steps S210 to S240:

[0092] Step S210: Acquire trigger position information of multiple content triggering operations on the content display subject, wherein the multiple content triggering operations act on the content display subject and are used to trigger content display of content display information on the content display subject.

[0093] Content display information is online information that can be disseminated and displayed online. Examples include online advertisements, as well as various other information such as video, audio, images, and text. The content display subject is the main object used to carry the content display information. Examples include web pages displaying online advertisements, applications embedded with online advertisements, mini-programs based on application platforms, and official accounts.

[0094] The content display information can be expressed in various forms such as virtual controls or jump links on the content display body. When the user applies a content triggering operation to the content display body, the content display information carried therein can be triggered to achieve the effect of visual display of the content display information. The content triggering operation can be any triggering operation such as clicking, double-clicking, long pressing, etc. This step can obtain the content triggering operation applied to the content display body within a certain period of time (such as one day, one week, one month, etc.), and record the triggering position of each content triggering operation on the content display body. The triggering position information is used to represent the distribution information of each content triggering operation at each position point of the content display body. For example, when the content triggering operation is a click operation, this step can record the click position coordinates of the click operation on the content display body, thereby determining the triggering position information representing the distribution of the click operation based on the click position coordinates.

[0095] Figure 3 The figure schematically shows the visualization effect of the content display information in the content display body being triggered to display. Figure 3 As shown, in the interactive interface 310 provided by the content display entity, there is an incentive advertisement 320 as content display information. Incentive advertisements are advertisements that users can actively watch and interact with, and they can get certain rewards after completing the advertisement playback. The main feature of this type of advertisement is that users actively trigger it and receive certain incentives. Figure 3 As shown in , in a small program installed on a social software, users can obtain daily income by clicking the income collection button 330, such as 4.4M virtual gold coins. In addition, users can also obtain additional rewards in addition to daily income by clicking on the incentive advertisement 320. When the user clicks on the incentive advertisement 320, the content display page 340, that is, the advertisement playback page, can be displayed on the interactive interface 310. The content display page 340 can be a web page with a certain display time. When the user plays the advertisement in the content display page 340 completely, he can get 3 times the income reward, such as 13.2M virtual gold coins.

[0096] Step S220. Divide the content display body into regions to obtain multiple trigger regions, and determine trigger region information of multiple content trigger operations on the content display body based on the trigger position information. The trigger region information is used to represent the distribution information of the content trigger operations on each trigger region.

[0097] The number of position points on the content display subject that can respond to content triggering operations is generally very large. For example, the number of position points on a certain content display subject that can be clicked and triggered is about 200,000. For the content display subject, the number of content triggering operations generated in a period such as a day or a week is much smaller than the number of position points available for triggering. This results in a very sparse distribution of the number of content triggering operations on the content display subject. Even a content display subject in a normal state will have the problem of insufficient concentration of content triggering operations. Therefore, this step can obtain multiple triggering areas by dividing the content display subject into regions. The number of triggering areas can be, for example, dozens or hundreds, which is specifically related to the regional division rules. After regional division, the triggering area information corresponding to each content triggering operation can be determined based on the triggering position information of the content triggering operation, thereby characterizing the distribution of the content triggering operation in the dimension of the triggering area. A triggering area can correspond to a group of triggering position points, thereby improving the distribution concentration of the content triggering operation between the various triggering areas. The trigger area information is used to represent the distribution information of the content trigger operation in each trigger area. For example, each click operation of the user can determine a position coordinate on the content display body. Based on the position coordinate, the trigger area where it is located can be determined, thereby establishing a correspondence between the content trigger operation and the trigger area. Based on this correspondence, the distribution of each content trigger operation in each trigger area can be determined.

[0098] Step S230: Determine the distribution dispersion information of the content triggering operation on the content display body according to the triggering area information.

[0099] Distribution dispersion information is information used to represent the distribution of various content triggering operations on the content display subject. In some optional embodiments, the distribution dispersion information can be presented as visual information based on a heat map. A heat map is a graphic representation of areas frequently clicked or visited by users in a highlighted form, which can quickly identify more important triggering areas. The distribution dispersion information can be obtained by drawing a heat map of the content triggering operations based on the triggering area information. In other optional embodiments, the distribution dispersion information can be presented as data quantification information based on information entropy. Information entropy is a parameter used to measure the degree of order in a system. The distribution dispersion information is obtained by inputting the triggering area information into a preset information entropy calculation model. Taking the content display subject containing a large number of content triggering operations as a system, the more concentrated and orderly the distribution of the triggering areas of the content triggering operations is, the lower the information entropy of the system will be; conversely, if the distribution of the triggering areas of the content triggering operations is more discrete and disordered, the higher the information entropy of the system will be.

[0100] Generally speaking, the distribution of content display information within a content display entity is relatively fixed. Therefore, when a user triggers the content display information by performing a content triggering operation, the triggering area will also be relatively concentrated. However, if the content display entity utilizes automated scripts or other cheating tools to automatically trigger and display content display information (such as automatically playing ads) without the user actively triggering the content display information, the corresponding content triggering operations will be distributed discretely and disorderly across the triggering areas. Figure 4 The diagram schematically shows the comparative effects of two types of heat maps with different distribution discreteness of triggers. Part 4A shows the heat map of the main trigger click of normal traffic. It can be seen that the click areas of the heat map are concentrated in multiple areas, with relatively fixed trigger positions. The heat map shown in part 4B is the heat map of automatically playing ads (not triggered by users). It can be seen that the clicks are very scattered and disordered, with no pattern to follow. It should be noted that in actual use, the trigger heat of each area in the heat map can be characterized by the brightness and depth of the color.

[0101] Step S240: Determine the content triggering state of the content display subject according to the distribution dispersion information. The content triggering state includes a normal triggering state and an abnormal triggering state.

[0102] according to Figure 4From the visual effect, we can clearly see that the degree of distribution dispersion of the content triggering operation on the content display subject can reflect the content triggering status of the content display subject. The content triggering status is used to indicate whether the content display subject displays the content display information normally. If the distribution dispersion information determines that the triggering area of the content triggering operation is distributed in a concentrated and orderly manner, then the content triggering status of the content display subject can be determined to be a normal triggering status; and if the distribution dispersion information determines that the triggering area of the content triggering operation is distributed discretely and disorderly, then the content triggering status of the content display subject can be determined to be an abnormal triggering status. A content display subject in an abnormal triggering status is very likely to have generated a content triggering operation through an automated script or other cheating tools, rather than being actively triggered by humans.

[0103] In the information processing method provided in the embodiments of the present application, by counting the content triggering operations acting on the content display subject and dividing the content display subject into regions, the distribution dispersion information of the content triggering operations can be determined based on the distribution of the content triggering operations in each triggering region, and thus the content triggering state of the content display subject can be determined based on the distribution dispersion information. Based on this method, cheating behavior of the content display subject can be effectively detected, and invalid exposure data for content display information can be efficiently and accurately discovered.

[0104] The following combination Figures 5 to 10 Some steps in the above embodiments are described in detail.

[0105] Figure 5 The steps of the statistical content triggering operation in the embodiment of the present application are schematically shown. Figure 5 As shown, based on the above embodiment, obtaining trigger position information of multiple content triggering operations on the content display body in step S210 may further include the following steps S510 to S520:

[0106] Step S510: Acquire trigger position coordinates of multiple content triggering operations on a content visualization page corresponding to the content display body, wherein the content visualization page is used to display content display information and receive content triggering operations.

[0107] The content visualization page is a content page on the content display body used to visualize the content display information. The content page can be a new page opened by jumping through the main page of the content display body, or it can be a sub-page (such as a floating window page) that pops up on the main page of the content display body.

[0108] A coordinate system can be pre-established based on the content visualization page, and the trigger position coordinates of each content trigger action can be determined based on the trigger position on the content visualization page. On the content visualization page, the coordinate system can be established directly using each pixel as a coordinate point, or a set of pixels consisting of several adjacent pixels can be used as a coordinate point.

[0109] Step S520: Determine the trigger position information of each content triggering operation on the content display body according to the trigger position coordinates.

[0110] In some optional implementations, the trigger position coordinates of each content triggering operation can be directly used as the trigger position information of the content triggering operation on the content display body. In other optional implementations, the trigger position coordinates of each content triggering operation can also be converted to obtain more accurate trigger position information.

[0111] For example, this step may first obtain the page size information of the content visualization page and the normalized size information related to the content display body. Then, the trigger position coordinates are normalized based on the page size information and the normalized size information to obtain the normalized position coordinates of each content triggering operation, and the normalized position coordinates are determined as the trigger position information of the content triggering operation on the content display body.

[0112] On different types of terminal devices, the display effects of the content visualization page will vary to some extent. Therefore, normalizing the trigger position coordinates can reduce the coordinate differences caused by display size differences, thereby obtaining more accurate trigger position information. For example, for a content display subject, n content trigger operations can be counted, and the trigger position coordinates of these content trigger operations can form a coordinate set {(x1, y1), (x2, y2), ..., (x n ,y n )}, after normalizing each trigger position coordinate, we can obtain a coordinate set consisting of the corresponding normalized position coordinates {(nx1,ny1),(nx2,ny2),……,(nx n ,ny n In some optional implementations, the trigger position coordinates may be normalized according to the following formula:

[0113]

[0114]

[0115] Among them, w i and h iis the page size information of the content visualization page, that is, the original width and original height of the content visualization page; W and H are the normalized size information, that is, the unified fixed width and fixed height obtained after normalization processing, for example, W can be 360 and H can be 720.

[0116] By executing steps S510 to S520, the trigger position coordinates of the content triggering operation can be obtained using the content visualization page carried by the content display body, thereby obtaining the trigger position information of the content triggering operation on the content display body. This information acquisition method can be applied to different types of content display bodies and has strong universal applicability. In particular, by normalizing the trigger position coordinates, it can be more universally applied to content visualization pages of different sizes, improving the efficiency and accuracy of obtaining trigger position information.

[0117] When there are a large number of trigger locations on the content display body, there is a problem that the distribution of each content trigger operation is too discrete, resulting in a poor representation of the location distribution. Based on this, the embodiment of the present application can obtain distribution dispersion information with stronger representation capabilities by dividing the content display body into regions. Figure 6 The following schematically illustrates the steps of determining trigger area information based on trigger position information in an embodiment of the present application. Figure 6 As shown, based on the above embodiment, determining the triggering area information of multiple content triggering operations on the content display body according to the triggering position information in step S220 can further include the following steps S610 to S630:

[0118] Step S610: Obtain the subject trigger quantity of the content trigger operation on the content display subject, where the subject trigger quantity is the total number of content trigger operations acting on the content display subject.

[0119] The subject trigger count is the total number of content trigger operations that affect the content display subject. The subject trigger count can be a periodic number calculated over a certain period of time, or a number that increases continuously over time within a certain time range.

[0120] Step S620: Determine the area trigger quantity of the content trigger operation on each trigger area according to the trigger position information, wherein the area trigger quantity is the number of content trigger operations acting on each trigger area.

[0121] The number of area triggers is the number of content trigger operations that act on each trigger area of the content display body. According to the trigger position information of each content trigger operation, the trigger area where each content trigger operation is located can be determined, so that the number of content trigger operations on each trigger area can be counted.

[0122] Step S630: Determine the region trigger frequency of each trigger region according to the proportion of the region trigger quantity in the main body trigger quantity, wherein the region trigger frequency represents the trigger region information of multiple content trigger operations on the content display main body.

[0123] The regional trigger frequency is the distribution ratio of multiple content trigger operations in each trigger area, and also represents the probability of generating a content trigger operation in each trigger area. For example, the regional trigger frequency p of the i-th trigger area is area_i It can be calculated according to the following formula:

[0124]

[0125] Among them, click_cnt total It is the main trigger quantity of the content trigger operation on the content display body, click_cnt area_i is the area trigger quantity for the content trigger operation on the i-th trigger area.

[0126] By executing steps S610 to S630, trigger region information represented by region trigger frequency can be obtained. Region distribution information entropy of content trigger operations can be determined based on the region trigger frequency, where the region distribution information entropy represents the distribution dispersion information of content trigger operations on the content display subject.

[0127] Regional distribution information entropy is a parameter used to represent the degree of discretization of the content triggering operation determined based on the triggering area on the content display subject. a It can be calculated according to the following formula:

[0128] E a =-∑p area_i *log(p area_i )

[0129] Regional distribution information entropy E a The larger the value, the more discrete the distribution of content trigger operations in each trigger area.

[0130] Through regional division, the distribution dispersion of content-triggered operations can be reduced to a certain extent, and distribution dispersion information with stronger representation capabilities can be obtained. How to perform regional division and the size of the regional division will have a direct impact on the acquisition of distribution dispersion information.

[0131] In some optional implementations, dividing the content display body into regions to obtain multiple triggering regions in step S220 may further include the following steps:

[0132] Obtaining area division parameters for dividing each trigger position on the content display body into areas;

[0133] The content visualization page corresponding to the content display body is divided into regions according to the region division parameters to obtain at least two trigger regions, wherein the content visualization page is used to display content display information and receive content trigger operations. Based on the above steps, at least two trigger regions corresponding to the content display body can be determined by dividing the content visualization page into regions. Specifically, a first number of region divisions along a first direction and a second number of region divisions along a second direction can be determined according to the region division parameters; then, the content visualization page corresponding to the content display body is divided into regions according to the first number of divisions and the second number of divisions to obtain multiple trigger regions in a grid shape.

[0134] The first number of divisions is, for example, the number of divisions for dividing the content visualization page into regions along the horizontal direction, and the second number of divisions is the number of divisions for dividing the content visualization page into regions along the vertical direction. Figure 7 The following schematically illustrates the visualization effect of dividing the content display subject into regions in an application scenario according to an embodiment of the present application. In this application scenario, the number of first divisions is 6 and the number of second divisions is 13. Figure 7 As shown, the content visualization page 710 of the content display body can be divided into regions in the horizontal and vertical directions based on the region division parameters, wherein the horizontal direction is divided into 6 parts and the vertical direction is divided into 13 parts, thereby obtaining the trigger areas 720 distributed in a grid shape on the content visualization page.

[0135] The region division parameter can be determined according to actual needs and specific application scenarios. If the region division parameter is too large or too small, it will affect the accuracy of the representation of the distribution dispersion information.

[0136] In some optional implementations, content display entities may be collected as samples, and the samples may be analyzed and processed to determine appropriate area division parameters.

[0137] Figure 8 The following schematically illustrates the steps for determining the region division parameters based on sample analysis in an embodiment of the present application. Figure 8 As shown, based on the above embodiment, obtaining the region division parameters for dividing each trigger position on the content display body into regions may further include the following steps S810 to S840:

[0138] Step S810: Determine at least one content display subject in a normal trigger state as a positive sample subject, and determine at least one content display subject in an abnormal trigger state as a negative sample subject;

[0139] Step S820: Obtain at least two candidate partitioning parameters for performing region partitioning on the positive sample body and the negative sample body;

[0140] Step S830. Determine the positive sample distribution dispersion information of the content-triggered operation on the positive sample body and the negative sample distribution dispersion information of the content-triggered operation on the negative sample body based on each candidate partition parameter;

[0141] Step S840: Select a candidate partition parameter as a region partition parameter for partitioning each trigger position on the content display body according to the dispersion difference between the positive sample distribution dispersion information and the negative sample distribution dispersion information.

[0142] The embodiment of the present application is applicable to the situation where the number of samples is small. For example, a content display subject in a normal triggering state can be determined as a positive sample subject. Figure 4 The content display subject corresponding to the heat map of part 4A shown in the figure can be used as the positive sample subject. At the same time, a content display subject in an abnormal trigger state can be determined as a negative sample subject, such as Figure 4 The content display subject corresponding to the heat map of part 4B in can be used as the negative sample subject.

[0143] On this basis, at least two candidate partitioning parameters can be pre-selected, and each candidate partitioning parameter can be a different parameter combination consisting of different horizontal partitioning parameters and / or different vertical partitioning parameters. After the positive sample body and the negative sample body are divided into regions based on each candidate partitioning parameter, the corresponding positive sample distribution discreteness information and negative sample distribution discreteness information can be obtained, and then the discreteness difference between the positive sample distribution discreteness information and the negative sample distribution discreteness information can be determined. If the discreteness difference calculated by one region partitioning parameter is large, it means that the distribution discreteness information obtained after the region partitioning based on the region partitioning parameter has a strong characterization ability. If the discreteness difference calculated by one region partitioning parameter is small, it means that the distribution discreteness information obtained after the region partitioning based on the region partitioning parameter has a weaker characterization ability. In some optional embodiments, the candidate partitioning parameter with the largest discreteness difference can be used as the region partitioning parameter for dividing the various trigger positions on the content display body into regions.

[0144] Figure 9 The following schematically illustrates the steps for determining the region division parameters based on the parameter selection model in the embodiment of the present application. Figure 9 As shown, based on the above embodiment, obtaining the region division parameters for dividing each trigger position on the content display body into regions may further include the following steps S910 to S940:

[0145] Step S910. Form a training sample set with at least two content display entities in different content triggering states;

[0146] Step S920: Obtain at least two candidate partitioning parameters for partitioning the content presentation subject in the training sample set into regions;

[0147] Step S930: Using the training sample set to train a parameter selection model for selecting a region partition parameter from at least two candidate partition parameters;

[0148] Step S940: Input the content display body that needs to be divided into regions into the parameter selection model to obtain the region division parameters output by the parameter selection model for dividing each trigger position on the content display body into regions.

[0149] The embodiment of the present application is applicable to situations where the number of samples is large. When the number of samples is large enough, the content display entities in different content triggering states can be combined into a training sample set, and then supervised learning can be performed using the training sample set to train a parameter selection model. After the content display entity is feature extracted and parameterized, it can be input into the parameter selection model to obtain the area division parameters output by the parameter selection model. Among them, the parameter selection model can be a machine learning model built based on a supervised classification algorithm, such as a logistic regression model, a support vector machine, and the like.

[0150] In the above embodiments, the discreteness information of the content triggering operation is mainly represented by the numerically quantified regional distribution information entropy. On this basis, the content triggering status of the content display subject determined based on the distribution discreteness information can also be obtained by sorting according to the numerical quantification results. In view of this, in step S240, the content triggering status of the content display subject determined based on the distribution discreteness information can further include the following steps:

[0151] Sorting the content display entities used to carry content display information according to regional distribution information entropy;

[0152] The content triggering status of each content display subject is determined respectively according to the sorting results.

[0153] For example, the same content display information can be carried by at least two different content display entities, such as the same online advertisement is simultaneously implanted in 30 mini-programs. In an embodiment of the present application, the information entropy of the content triggering operation can be calculated for each of these content display entities, and then these content display entities can be sorted according to the numerical value of the information entropy. For example, when the information entropy is arranged in descending order, the content display entity with a higher ranking indicates that the trigger position distribution of its content triggering operation is highly discrete, and it is very likely that the exposure of the content display information is obtained by cheating.

[0154] The premise for information entropy to detect the status of a content display entity is that the content display information is concentrated and uniformly distributed within the content display entity. If a large amount of content display information is dispersed within the content display entity, the triggering locations of the corresponding content triggering actions will also be highly dispersed, negatively impacting the status detection results.

[0155] Figure 10 The display effect of a content display body including multiple content display information is schematically shown. Figure 10 As shown, since multiple virtual controls 1020 for triggering content display information are evenly distributed on the interactive interface 1010 of the content display body, when the user actually views the content display body, they may click on any of the virtual controls to trigger an advertisement or other content display form. Therefore, before sorting the content display bodies used to carry content display information based on the distribution dispersion information, the embodiment of the present application can first perform a preliminary screening of the content display bodies.

[0156] For example, statistical data on the display results of the content display information in each content display subject can be first obtained, and then the content display subjects in a normal triggering state can be filtered based on the statistical data on the display results. The statistical data on the display results can include at least one of statistical data such as the content display completion rate and the average content display duration of the content display information.

[0157] In some embodiments of the present application, the actual display duration of the content display information in each content display entity and the standard display duration associated with the content display information can be first obtained. The actual display duration is the length of time from the start to the end of the display of the content display information after the content triggering operation triggers the display of the content display information. For example, it can be the actual playback duration of a network advertisement after it is clicked to play. The standard display duration is the total duration of the complete display of the content display information. For example, it can be the playback duration of a complete network advertisement.

[0158] The content display completion rate of the content display subject is determined based on the proportion of content display information whose actual display duration is greater than or equal to the standard display duration. When a user triggers a content display information to be displayed, the user can end its display process at any time thereafter. For example, the user can close it at any time during the playback of the online advertisement. If the display process of a content display information is interrupted in the middle, then its actual display duration will be less than its standard display duration. The proportion of content display information that is fully displayed on the content display subject to all content display information is the content display completion rate of the content display subject. For example, on an advertising platform, a total of 1,000 online advertisements were played in one day, of which 300 online advertisements were played in full, and the other 700 online advertisements were actively closed after only a portion of the advertisements were played. In this case, the content display completion rate of the advertising platform can be calculated as 30%.

[0159] The average content display duration of the content display body is determined according to the actual display duration of the content display information. The average display duration is the average value of the actual display duration of each content display information.

[0160] The content display subjects in the normal triggering state are screened based on the content display completion rate and the average content display duration. When screening the content display information, the display completion rate threshold and the display duration threshold for screening the content display subjects can be obtained. For example, the display completion rate threshold can be selected as 40%, and the display duration threshold can be selected as 10 seconds. The content display subjects whose content display completion rate is greater than the display completion rate threshold and whose content display average duration is greater than the display duration threshold are screened as content display subjects in the normal triggering state. If the display completion rate of a content display subject is greater than 40% and its content display average duration is greater than 10 seconds, then the content display subject can be determined to be a content display subject in the normal triggering state. For other content display subjects whose display completion rate is less than or equal to 40% or whose content display average duration is less than or equal to 10 seconds, their content triggering status can continue to be detected by information entropy sorting.

[0161] In addition to the information entropy based on numerical quantification, the embodiment of the present application can also use a heat map with a visualization effect as distribution dispersion information. For example, a trigger position heat map can be drawn based on the trigger position information to represent the distribution state of the content trigger operation on the content display subject, and the trigger position heat map can be used as the distribution dispersion information of the content trigger operation on the content display subject. At the same time, the embodiment of the present application can pre-select and train a state recognition model that uses the trigger position heat map as input data to directly output the content trigger state of the content display subject based on the trigger position heat map. For example, the embodiment of the present application can input the trigger position heat map of the content display subject into a pre-trained state recognition model, and then perform image analysis and state recognition on the trigger position heat map through the state recognition model to obtain the content trigger state of the content display subject output by the image recognition model. Among them, the state recognition model can be a machine learning model based on a convolutional neural network, a recurrent neural network or other algorithms, and the embodiment of the present application does not make special restrictions on this.

[0162] It should be noted that although the steps of the method of the present application are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all steps must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0163] The following introduces an embodiment of the device of the present application, which can be used to execute the information processing method in the above-mentioned embodiment of the present application.

[0164] Figure 11 The following schematically shows a structural block diagram of the information processing device in an embodiment of the present application. Figure 11 As shown, the information processing device 1100 may include:

[0165] An information acquisition module 1110 is configured to acquire trigger position information of multiple content triggering operations on a content display subject, wherein the multiple content triggering operations act on the content display subject and are used to trigger content display information on the content display subject to be displayed;

[0166] The region division module 1120 is configured to divide the content display body into regions to obtain multiple trigger regions, and determine trigger region information for multiple content trigger operations on the content display body based on the trigger position information. The trigger region information is used to indicate the distribution information of the content trigger operations on each trigger region.

[0167] The information determination module 1130 is configured to determine the distribution dispersion information of the content triggering operation on the content display subject according to the triggering position information;

[0168] The state determination module 1140 is configured to determine the content trigger state of the content display subject according to the distribution dispersion information. The content trigger state includes a normal trigger state and an abnormal trigger state.

[0169] In some embodiments of the present application, based on the above embodiments, the information acquisition module 1110 includes:

[0170] a coordinate acquisition unit configured to acquire trigger position coordinates of a plurality of content triggering operations on a content visualization page corresponding to a content display subject, wherein the content visualization page is used to display content display information and receive content triggering operations;

[0171] The position determination unit is configured to determine trigger position information of each content triggering operation on the content display body according to the trigger position coordinates.

[0172] In some embodiments of the present application, based on the above embodiments, the position determination unit includes:

[0173] A size acquisition subunit is configured to acquire page size information of the content visualization page and acquire normalized size information related to the content display body;

[0174] The normalization processing subunit is configured to normalize the trigger position coordinates according to the page size information and the normalized size information to obtain the normalized position coordinates of each content trigger operation, wherein the normalized position coordinates represent the trigger position information of the content trigger operation on the content display body.

[0175] In some embodiments of the present application, based on the above embodiments, the region division module 1120 includes:

[0176] A first quantity acquisition unit is configured to acquire a subject trigger quantity of content triggering operations on a content display subject, wherein the subject trigger quantity is a total number of content triggering operations acting on the content display subject;

[0177] a second quantity obtaining unit configured to determine the area trigger quantity of the content triggering operation on each trigger area according to the trigger position information;

[0178] The trigger frequency determination unit is configured to determine the regional trigger frequency of each trigger area according to the proportion of the regional trigger quantity in the main body trigger quantity, wherein the regional trigger frequency represents the trigger area information of multiple content trigger operations on the content display main body.

[0179] In some embodiments of the present application, based on the above embodiments, the region division module 1120 includes:

[0180] A parameter acquisition unit configured to acquire area division parameters for dividing each trigger position on the content display body into areas;

[0181] The area division unit is configured to divide the content visualization page corresponding to the content display body into areas according to the area division parameters to obtain multiple trigger areas, wherein the content visualization page is used to display content display information and receive content trigger operations.

[0182] In some embodiments of the present application, based on the above technical solution, the area division unit includes:

[0183] a number determination subunit, configured to determine a first number of divisions for area division along the first direction and a second number of divisions for area division along the second direction according to the area division parameter;

[0184] The grid division subunit is configured to divide the content visualization page corresponding to the content display body into regions according to the first division number and the second division number to obtain a plurality of trigger regions in a grid shape.

[0185] In some embodiments of the present application, based on the above embodiments, the parameter acquisition unit includes:

[0186] A first sample determination subunit is configured to determine at least one content display subject in a normal trigger state as a positive sample subject, and to determine at least one content display subject in an abnormal trigger state as a negative sample subject;

[0187] A first parameter acquisition subunit is configured to acquire at least two candidate segmentation parameters for performing regional segmentation on the positive sample body and the negative sample body;

[0188] A first information determination subunit is configured to determine, based on each candidate partition parameter, the positive sample distribution dispersion information of the content-triggered operation on the positive sample body and the negative sample distribution dispersion information of the content-triggered operation on the negative sample body;

[0189] The first parameter determination subunit is configured to select a candidate partition parameter as a region partition parameter for partitioning each trigger position on the content display body according to the discreteness difference between the positive sample distribution discreteness information and the negative sample distribution discreteness information.

[0190] In some embodiments of the present application, based on the above embodiments, the parameter acquisition unit includes:

[0191] The second sample determination subunit is configured to form a training sample set from at least two content display entities in different content triggering states;

[0192] A second parameter acquisition subunit is configured to acquire at least two candidate partitioning parameters for performing regional partitioning on the content presentation subject in the training sample set;

[0193] a model training subunit configured to train a parameter selection model for selecting a region partition parameter from at least two candidate partition parameters using a training sample set;

[0194] The second information determination subunit is configured to input the content display body that needs to be divided into regions into a parameter selection model to obtain region division parameters output by the parameter selection model for dividing each trigger position on the content display body into regions.

[0195] In some embodiments of the present application, based on the above embodiments, the distribution dispersion information is a trigger area heat map drawn based on the trigger area information to represent the distribution state of the content triggering operation on the content display body; the state determination module 1140 includes:

[0196] a heat map input unit configured to input a trigger area heat map of a content display subject into a pre-trained state recognition model;

[0197] The heat map analysis unit is configured to perform image analysis and state recognition on the trigger area heat map through a state recognition model to obtain the content trigger state of the content display subject output by the image recognition model.

[0198] In some embodiments of the present application, based on the above embodiments, the distribution dispersion information is the regional distribution information entropy determined according to the trigger region information; the state determination module 1140 includes:

[0199] a subject sorting unit configured to sort the content display subjects used to carry content display information according to the regional distribution information entropy;

[0200] The state determination unit is configured to determine the content triggering state of each content display subject according to the sorting result.

[0201] In some embodiments of the present application, based on the above embodiments, the information processing device further includes:

[0202] a duration acquisition unit configured to acquire the actual display duration of the content display information in each content display subject and a standard display duration associated with the content display information;

[0203] A completion rate determination unit is configured to determine a content display completion rate of a content display subject according to a proportion of content display information whose actual display duration is greater than or equal to a standard display duration;

[0204] An average duration determining unit configured to determine an average content display duration of the content display subject according to the actual display duration of the content display information;

[0205] The display subject screening unit is configured to screen and obtain content display subjects in a normal triggering state according to the content display completion rate and the average content display duration.

[0206] In some embodiments of the present application, based on the above embodiments, the display subject screening unit includes:

[0207] A threshold acquisition subunit is configured to acquire a display completion rate threshold and a display duration threshold for screening content display subjects;

[0208] The subject screening subunit is configured to screen content display subjects whose content display completion rate is greater than a display completion rate threshold and whose average content display duration is greater than a display duration threshold as content display subjects in a normal triggering state.

[0209] The specific details of the information processing device provided in each embodiment of the present application have been described in detail in the corresponding method embodiments and will not be repeated here.

[0210] Figure 12 A schematic diagram of the structure of a computer system suitable for implementing an electronic device according to an embodiment of the present application is shown.

[0211] It should be noted that Figure 12 The computer system 1200 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0212] like Figure 12 As shown, computer system 1200 includes a central processing unit (CPU) 1201, which can perform various appropriate actions and processes according to programs stored in read-only memory (ROM) 1202 or programs loaded from storage 1208 into random access memory (RAM) 1203. Various programs and data required for system operation are also stored in RAM 1203. CPU 1201, ROM 1202, and RAM 1203 are connected to each other via bus 1204. Input / output (I / O) interface 1205 is also connected to bus 1204.

[0213] The following components are connected to the I / O interface 1205: an input section 1206 including a keyboard, a mouse, and the like; an output section 1207 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 1208 including a hard disk; and a communication section 1209 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 1209 performs communication processing via a network such as the Internet. A drive 1210 is also connected to the I / O interface 1205 as needed. Removable media 1211, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 1210 as needed, so that computer programs read from the removable media can be installed in the storage section 1208 as needed.

[0214] In particular, according to an embodiment of the present application, the processes described in the various method flow charts can be implemented as computer software programs. For example, an embodiment of the present application includes a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the methods shown in the flow charts. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 1209, and / or installed from a removable medium 1211. When the computer program is executed by the central processing unit (CPU) 1201, the various functions defined in the system of the present application are executed.

[0215] It should be noted that the computer-readable medium shown in the embodiments of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a 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, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0216] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the above-mentioned module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of the boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0217] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiment of the application, the features and functions of two or more modules or units described above can be concretized in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0218] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present application.

[0219] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of this application and include common knowledge or customary techniques in the art that are not disclosed herein.

[0220] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. An information processing method, characterized in that: include: Acquiring trigger position information of multiple content triggering operations on a content display subject, wherein the multiple content triggering operations act on the content display subject and are used to trigger content display information on the content display subject to be displayed; Determine at least one content display subject in a normal trigger state as a positive sample subject, and determine at least one content display subject in an abnormal trigger state as a negative sample subject; Obtaining at least two candidate segmentation parameters for performing region segmentation on the positive sample subject and the negative sample subject; Determining, based on each candidate partition parameter, the positive sample distribution dispersion information of the content-triggered operation on the positive sample subject and the negative sample distribution dispersion information of the content-triggered operation on the negative sample subject; selecting a candidate partition parameter as a region partition parameter for partitioning each trigger position on the content display body according to a dispersion difference between the positive sample distribution dispersion information and the negative sample distribution dispersion information; Dividing a content visualization page corresponding to the content display subject into regions according to the region division parameters to obtain a plurality of trigger regions, wherein the content visualization page is used to display the content display information and receive the content trigger operation; Determining trigger area information of the multiple content triggering operations on the content display body according to the trigger position information, wherein the trigger area information is used to indicate distribution information of the content triggering operations on each trigger area; Determining distribution dispersion information of the content triggering operation on the content display subject according to the triggering area information; The content triggering state of the content display subject is determined according to the distribution dispersion information, where the content triggering state includes a normal triggering state and an abnormal triggering state.

2. The information processing method according to claim 1, wherein: The obtaining of trigger position information of multiple content triggering operations on the content display body includes: Acquiring trigger position coordinates of a plurality of content triggering operations on a content visualization page corresponding to the content display subject, wherein the content visualization page is used to display the content display information and receive the content triggering operation; The trigger position information of each content triggering operation on the content display body is determined according to the trigger position coordinates.

3. The information processing method according to claim 2, wherein: The determining, according to the trigger position coordinates, the trigger position information of each content triggering operation on the content display body includes: Obtaining page size information of the content visualization page and obtaining normalized size information related to the content display body; The trigger position coordinates are normalized according to the page size information and the normalized size information to obtain normalized position coordinates of each content trigger operation, wherein the normalized position coordinates represent the trigger position information of the content trigger operation on the content display body.

4. The information processing method according to claim 1, wherein: The determining, based on the trigger position information, trigger area information of the multiple content triggering operations on the content display body includes: Obtaining a subject trigger quantity of content triggering operations on the content display subject, wherein the subject trigger quantity is the total number of content triggering operations acting on the content display subject; Determining the area trigger quantity of the content trigger operation in each of the trigger areas according to the trigger position information, wherein the area trigger quantity is the number of content trigger operations respectively acting on each of the trigger areas; The area trigger frequency of each of the trigger areas is determined according to the proportion of the area trigger quantity in the main body trigger quantity, wherein the area trigger frequency represents the trigger area information of the multiple content triggering operations on the content display main body.

5. The information processing method according to claim 1, wherein: Dividing the content visualization page corresponding to the content display body into regions according to the region division parameters to obtain a plurality of trigger regions, including: Determining a first number of divisions for performing regional division along a first direction and a second number of divisions for performing regional division along a second direction according to the regional division parameters; The content visualization page corresponding to the content display body is divided into regions according to the first division number and the second division number to obtain a plurality of trigger regions in a grid shape.

6. The information processing method according to claim 1, wherein: The method further comprises: At least two content display subjects in different content triggering states form a training sample set; Obtaining at least two candidate partitioning parameters for performing regional partitioning on the content presentation subject in the training sample set; Using the training sample set to train a parameter selection model for selecting a region partition parameter from the at least two candidate partition parameters; The content display body that needs to be divided into regions is input into the parameter selection model to obtain region division parameters output by the parameter selection model for dividing each trigger position on the content display body into regions.

7. The information processing method according to claim 1, wherein: The distribution dispersion information is a trigger area heat map drawn according to the trigger area information and used to represent the distribution state of the content triggering operation on the content display body; The determining of the content triggering state of the content display subject according to the distribution dispersion information includes: Inputting the trigger area heat map of the content display subject into a pre-trained state recognition model; The trigger area heat map is subjected to image analysis and state recognition by the state recognition model to obtain the content triggering state of the content display subject output by the image recognition model.

8. The information processing method according to claim 1, wherein: The distribution dispersion information is the regional distribution information entropy determined according to the trigger area information; The determining of the content triggering state of the content display subject according to the distribution dispersion information includes: sorting the content display entities used to carry the content display information according to the regional distribution information entropy; The content triggering status of each of the content display entities is determined respectively according to the sorting results.

9. The information processing method according to claim 8, characterized in that Before sorting the content display entities used to carry the content display information according to the distribution dispersion information, the method further includes: Obtaining the actual display duration of the content display information in each content display subject and the standard display duration associated with the content display information; Determining a content display completion rate of the content display subject according to a proportion of content display information whose actual display duration is greater than or equal to the standard display duration; Determining an average content display duration of the content display subject according to the actual display duration of the content display information; The content display subject in a normal triggering state is obtained by screening according to the content display completion rate and the average content display duration.

10. The information processing method according to claim 9, wherein: The filtering and obtaining of the content display subject in a normal triggering state according to the content display completion rate and the content display average duration includes: Obtain the display completion rate threshold and display duration threshold used to filter content display entities; The content display subjects whose content display completion rate is greater than the display completion rate threshold and whose average content display duration is greater than the display duration threshold are screened as content display subjects in a normal triggering state.

11. An information processing device, characterized in that: include: an information acquisition module configured to acquire trigger position information of a plurality of content triggering operations on a content display subject, wherein the plurality of content triggering operations act on the content display subject and are used to trigger content display information on the content display subject to be displayed; A region division module is configured to determine at least one content display subject in a normal trigger state as a positive sample subject, and to determine at least one content display subject in an abnormal trigger state as a negative sample subject; obtain at least two candidate division parameters for region division of the positive sample subject and the negative sample subject; determine, based on each candidate division parameter, positive sample distribution dispersion information of the content triggering operation on the positive sample subject and negative sample distribution dispersion information of the content triggering operation on the negative sample subject; select a candidate division parameter as a region division parameter for region division of each trigger position on the content display subject according to the dispersion difference between the positive sample distribution dispersion information and the negative sample distribution dispersion information; and divide the content visualization page corresponding to the content display subject into multiple trigger regions according to the region division parameter, wherein the content visualization page is used to display the content display information and receive the content triggering operation; Determining trigger area information of the multiple content triggering operations on the content display body according to the trigger position information, wherein the trigger area information is used to indicate distribution information of the content triggering operations on each trigger area; an information determination module configured to determine distribution dispersion information of the content triggering operation on the content display subject according to the triggering area information; The state determination module is configured to determine the content trigger state of the content display body according to the distribution dispersion information, and the content trigger state includes a normal trigger state and an abnormal trigger state.

12. A computer-readable medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the information processing method according to any one of claims 1 to 10 is implemented.

13. An electronic device, characterized in that: include: processor; as well as a memory for storing executable instructions of the processor; The processor is configured to perform the information processing method according to any one of claims 1 to 10 by executing the executable instructions.

14. A computer program product comprising computer instructions, characterized in that When the computer instructions are executed by a processor, the information processing method according to any one of claims 1 to 10 is implemented.

Images