A method, device, equipment and storage medium for predicting operation response result

Abstract

The application provides a method, device and equipment for predicting operation response results and a storage medium, which can be applied to the field of cloud computing or the field of intelligent transportation, and is used to solve the problem of low accuracy and reliability of predicting operation response results. The method comprises the following steps: in response to a target operation triggered for target promotion content, obtaining a plurality of historical operation data associated with the target promotion content; determining the matching degree between the target operation and each target historical operation based on the relative distance between the target trigger position of the target operation and the historical trigger position contained in each of the plurality of historical operation data, and the historical trigger times contained in each of the plurality of historical operation data; and predicting the response result of the target operation based on the obtained matching degrees. The prediction is based on the target historical operation of the target conversion task that has been performed, thereby improving the accuracy and reliability of predicting the response result of the target operation.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, device, and storage medium for predicting operational response results. Background Technology

[0002] With the continuous development of technology, more and more devices can perform intelligent promotion tasks on traffic platforms.

[0003] Within a traffic platform, when presenting target content to a target audience, the device can overlay promotional content on top of the target content for a preset duration, allowing the target audience to view the promotional content through the traffic platform. The device can also respond to the target audience's access to the promotional content by displaying a details page of the promotional content, enabling the target audience to perform corresponding promotional tasks on the details page, thereby achieving the promotional goal. Furthermore, the device can also respond to the target audience's close operation of the promotional content, canceling its display.

[0004] When performing the close operation, due to the small trigger range of the close button, the operation may be mistakenly executed, leading to the details page of the promotional content.

[0005] In related technologies, it can be predicted that the response result of the entry operation will not achieve the promotion goal if the trigger position of the entry operation is near the trigger range of the close button; or it can be predicted that the response result of the entry operation will achieve the promotion goal if the trigger position of the entry operation is not near the trigger range of the close button.

[0006] However, there are several reasons why erroneous entry operations might occur. For example, when promotional content flashes frequently over target content, a selection action performed by the target object on the target content might be identified as an entry operation on the promotional content, resulting in an erroneous entry operation. Simply relying on whether the entry operation is triggered near the trigger range of the close button is insufficient to accurately predict the response of the entry operation.

[0007] It is evident that the accuracy and reliability of the response results of predictive operations in related technologies are relatively low. As a result, content promoters will be unable to accurately determine the effective promotion methods that can achieve their promotion goals, leading to blind promotion and unnecessary waste of resources. Summary of the Invention

[0008] This application provides a method, apparatus, computer device, and storage medium for predicting operation response results, which addresses the problem of low accuracy and reliability of predicted operation response results.

[0009] Firstly, a method for predicting operational response results is provided, including:

[0010] In response to a target operation triggered for a target promotional content, a promotional interface associated with the target promotional content is presented, and multiple historical operation data associated with the target promotional content are obtained. Each historical operation data represents that the response result of the corresponding target historical operation is that the target conversion task has been executed in the promotional interface. Each historical operation data includes at least the historical triggering position and the historical triggering number of the corresponding target historical operation.

[0011] Based on the historical trigger positions contained in each of the multiple historical operation data, the relative distance between them and the target trigger position of the target operation, and the number of historical triggers contained in each of the multiple historical operation data, the matching degree between the target operation and each target historical operation is determined respectively.

[0012] Based on the obtained matching degrees, the response result of the target operation is predicted.

[0013] Secondly, an apparatus for pre-storing operation response results is provided, comprising:

[0014] Acquisition module: In response to a target operation triggered for the target promotion content, presents the promotion interface associated with the target promotion content, and acquires multiple historical operation data associated with the target promotion content. Each historical operation data represents that the response result of the corresponding target historical operation is that the target conversion task has been executed in the promotion interface. Each historical operation data includes at least the historical trigger position and historical trigger number of the corresponding target historical operation.

[0015] Processing module: used to determine the matching degree between the target operation and each target historical operation based on the historical trigger position contained in each of the multiple historical operation data, the relative distance between the target operation and the target trigger position, and the number of historical triggers contained in each of the multiple historical operation data;

[0016] The processing module is also used to: predict the response result of the target operation based on the obtained matching degrees.

[0017] Optionally, the target promotion content is provided with a content identifier, which is used to uniquely identify the target promotion content;

[0018] The obtaining module is specifically used for:

[0019] Acquire heatmap data of each historical operation generated within a historical time period. Each heatmap data of a historical operation includes the content identifier of the corresponding candidate promotion content, as well as the candidate trigger coordinates and the number of candidate triggers for the corresponding candidate historical operation.

[0020] Based on the content identifier of the target promotion content, the alternative trigger coordinates and alternative trigger counts of each target historical operation are determined from the heatmap data of each historical operation.

[0021] Based on the candidate trigger coordinates of each target historical operation, the historical trigger position of each target historical operation is determined, and based on the candidate trigger count of each target historical operation, the historical trigger count of each target historical operation is determined, so as to generate the multiple historical operation data.

[0022] Optionally, each historical operation heatmap data also includes the promotion content size of the corresponding alternative promotion content;

[0023] The processing module is specifically used for:

[0024] Based on the historical operation heatmap data, the size of the target promotion content is determined;

[0025] Based on the size of the target promotion content, the candidate trigger coordinates of each target historical operation are normalized to obtain the historical trigger position of each target historical operation.

[0026] Optionally, the processing module is specifically used for:

[0027] The total number of triggers is obtained by summing the number of alternative triggers for each target's historical operation.

[0028] Based on the total number of triggers, the candidate trigger counts for each target historical operation are normalized to obtain the historical trigger counts for each target historical operation.

[0029] Optionally, the processing module is specifically used for:

[0030] Determine the relative distance between the historical trigger positions contained in each of the plurality of historical operation data and the target trigger position of the target operation;

[0031] The ratio between the number of historical triggers contained in each of the multiple historical operation data and the corresponding relative distance is used as the matching degree between the target operation and each target historical operation.

[0032] Optionally, the processing module is specifically used for:

[0033] Based on preset weighting coefficients, the various matching degrees are weighted and summed to determine the overall matching degree;

[0034] When the overall matching degree is less than the preset matching degree threshold, the predicted response result of the target operation is that the target conversion task is not executed in the promotion interface;

[0035] When the overall matching degree is greater than or equal to the preset matching degree threshold, the predicted response result of the target operation is that the target conversion task has been executed in the promotion interface.

[0036] Thirdly, a computer program product is provided, including a computer program that, when executed by a processor, implements the method described in the first aspect.

[0037] Fourthly, a computer device is provided, comprising:

[0038] Memory, used to store program instructions;

[0039] A processor is configured to invoke program instructions stored in the memory and execute the method described in the first aspect according to the obtained program instructions.

[0040] Fifthly, a computer-readable storage medium is provided, the computer-readable storage medium storing computer-executable instructions for causing a computer to perform the method as described in the first aspect.

[0041] In this embodiment, after presenting a promotional interface associated with the target promotional content in response to a target operation triggered by the target promotional content, multiple historical operation data associated with this target promotional content can be obtained. The historical operation data indicates that the response result of the corresponding target historical operation is that the target conversion task has been executed in the promotional interface. Based on the target trigger position of the target operation, the relative distance between it and the historical trigger positions of each target historical operation, and the historical trigger count of each target historical operation, the matching degree between the target operation and each target historical operation can be determined. Based on each matching degree, it can be predicted whether the response result of the target operation is that the target conversion task has been executed in the promotional interface.

[0042] Compared to prediction methods based on the target trigger location of the target operation, such as whether it is near the close button of the target promotional content or at the edge of the target promotional content, this embodiment uses the target historical operations that have already executed the target conversion task in the promotion interface as a basis to determine the matching degree between the target operation and the target historical operations, thereby predicting the response result of the target operation. This avoids misjudging some target operations whose target trigger location is far from the close button of the target promotional content as having executed the target conversion task, making the accuracy and reliability of predicting the response result of the target operation higher.

[0043] Furthermore, when judging the matching degree between the target operation and the target historical operation, it not only considers the relative distance between the historical trigger position and the target trigger position, but also the number of historical triggers. This allows for the measurement of the matching degree between the target operation and the target historical operation from multiple perspectives, further improving the accuracy and reliability of predicting the response results of the target operation. Attached Figure Description

[0044] Figure 1a A schematic diagram of an interface for presenting target promotional content provided in an embodiment of this application;

[0045] Figure 1b A schematic diagram of an interface for presenting a promotional interface associated with target promotional content, provided in an embodiment of this application;

[0046] Figure 1c This is one application scenario of the method for predicting operation response results provided in the embodiments of this application;

[0047] Figure 2 A flowchart illustrating a method for predicting operational response results provided in an embodiment of this application;

[0048] Figure 3a A schematic diagram of an interface for a method of predicting operation response results provided in an embodiment of this application;

[0049] Figure 3b A schematic diagram illustrating the principle of a method for predicting operational response results provided in this application embodiment;

[0050] Figure 4 A schematic diagram of the principle of the method for predicting operation response results provided in the embodiments of this application. Figure 2 ;

[0051] Figure 5 A schematic diagram three illustrating the principle of a method for predicting operational response results provided in this application embodiment;

[0052] Figure 6 A schematic diagram of the principle of the method for predicting operation response results provided in the embodiments of this application. Figure 4 ;

[0053] Figure 7 A schematic diagram of the principle of the method for predicting operation response results provided in the embodiments of this application. Figure 5 ;

[0054] Figure 8 A schematic diagram of a device for predicting operation response results provided in an embodiment of this application;

[0055] Figure 9A schematic diagram of the structure of the apparatus for predicting operation response results provided in the embodiments of this application. Figure 2 . Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0057] The following explanations of some terms used in the embodiments of this application are provided to facilitate understanding by those skilled in the art.

[0058] (1) Cost Per Click (CPC):

[0059] Cost-per-click (CPC) advertising represents the cost per ad click. Advertisers pay for the user's action of clicking the ad, not for ad impressions. For advertisers, CPC advertising avoids the risk of impressions without clicks and is currently one of the mainstream advertising pricing methods.

[0060] (2) Advertisers and traffic owners:

[0061] Advertisers refer to users or service providers who pay to place advertisements. For advertisers, each paid ad click can only effectively achieve promotional goals if it is a valid click from a real user. If it is a fraudulent click, it will result in a waste of funds and other resources.

[0062] A traffic owner is a provider of user traffic, typically referring to media outlets, websites, or software. In instant messaging advertising platforms, a traffic owner refers to a public account with a certain number of followers. Traffic owners can participate in profit sharing from advertising; for the same ad exposure, the higher the click-through rate, the higher the profit they receive.

[0063] The embodiments of this application are designed with technologies in the fields of Artificial Intelligence (AI) and cloud computing, and can be applied to fields such as intelligent transportation, assisted driving, or mapping.

[0064] Artificial intelligence (AI) is the theory, methods, technology, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, 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 studies the design principles and implementation methods of various machines, attempting to understand the essence of intelligence and produce new intelligent machines that can react in a way similar to human intelligence, enabling machines to have perception, reasoning, and decision-making functions.

[0065] Artificial intelligence (AI) is a comprehensive discipline encompassing a wide range of fields, including both hardware and software technologies. Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, interactive operating systems, and mechatronics. AI software technologies primarily include computer vision, speech processing, natural language processing, machine learning / deep learning, autonomous driving, and intelligent transportation. With the development and progress of AI, it has been researched and applied in numerous fields, such as smart homes, intelligent customer service, virtual assistants, smart speakers, intelligent marketing, wearable devices, autonomous driving, drones, robots, smart healthcare, vehicle networking, and intelligent transportation. It is believed that with further technological advancements, AI will be applied in even more fields, playing an increasingly important role. The solutions provided in this application's embodiments relate to deep learning and augmented reality technologies in AI, which are further illustrated by the following examples.

[0066] Cloud computing refers to the delivery and usage model of IT infrastructure, meaning obtaining necessary resources in an on-demand and easily scalable manner through a network. In a broader sense, cloud computing refers to the delivery and usage model of services, meaning obtaining necessary services in an on-demand and easily scalable manner through a network. These services can be IT and software related, internet-related, or other services. Cloud computing is a product of the development and integration of traditional computer and network technologies such as grid computing, distributed computing, parallel computing, utility computing, network storage technologies, virtualization, and load balancing.

[0067] With the development of the internet, real-time data streams, and the diversification of connected devices, as well as the demands for search services, social networks, mobile commerce, and open collaboration, cloud computing has rapidly developed. Unlike previous parallel distributed computing, cloud computing will fundamentally revolutionize the entire internet model and enterprise management model.

[0068] It should be noted that in the embodiments of this application, data such as historical operation data are involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required each time data is obtained, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0069] The application areas of the method for predicting operational response results provided in the embodiments of this application will be briefly introduced below.

[0070] With the continuous development of technology, more and more devices can perform intelligent promotion tasks on traffic platforms.

[0071] Within a traffic platform, when a device presents target content to a target audience, it can overlay promotional content on top of the target content for a preset duration, allowing the target audience to view the promotional content through the traffic platform. Please refer to [link / reference]. Figure 1a Taking promotional content as an example, the target audience can access the game interface and play the game through their device. Please refer to [the relevant documentation / reference]. Figure 1a (1). When the device presents the game interface to the target audience, it can overlay the promotional content for promoting WeChat Official Account A onto the target content within a preset duration of 5 seconds. Please refer to [the relevant documentation]. Figure 1a (2) This allows the target content to view the promotional content for promoting WeChat Official Account A when entering the game interface.

[0072] The device can respond to a target user's access to promoted content, presenting the promoted content's interface to the target user so that the target user can perform corresponding promotional tasks on the details page, thereby achieving the promotional goal. The device can also respond to a target user's close operation of the promoted content, canceling the presentation of the promoted content. Please refer to [reference needed]. Figure 1b Taking the promotional content as an example, when displaying promotional content for WeChat Official Account A, in response to the "Follow Official Account" click action within the promotional content, please refer to... Figure 1b (1) The device can display a detailed interface of the promotional content to the target audience, i.e., the promotional interface of WeChat Official Account A. Please refer to [reference needed]. Figure 1b (2) Target audiences can complete the conversion task and achieve the promotion goal by clicking the "Follow" button on the promotion interface. Target audiences can also cancel the display of promotional content and the promotion interface by clicking the "Back" button on the promotion interface.

[0073] When performing the close operation, the close button may have a small trigger range, or the swipe to return along the edge of the promotional content may be mistakenly identified as a click on the promotional content, resulting in an accidental entry into the details page of the promotional content.

[0074] In related technologies, it is possible to predict whether the response result of an entry operation will fail to achieve the promotion goal based on whether the trigger position of the entry operation is near the trigger range of the close button, or whether the trigger position of the entry operation is at the edge of the promotional content; conversely, it is possible to predict whether the response result of an entry operation will achieve the promotion goal based on whether the trigger position of the entry operation is not near the trigger range of the close button, or whether the trigger position of the entry operation is not at the edge of the promotional content.

[0075] However, there are several reasons why accidental entry operations might occur. For example, when promotional content flashes frequently over target content, a selection action performed by the target user on the target content might be identified as an entry operation on the promotional content, resulting in an accidental entry operation. Another example is when the close button on the promotional content is placed in a concealed location, allowing the target user to click randomly within the promotional content, thus causing an accidental entry operation.

[0076] It is impossible to accurately predict the response result of an entry operation based solely on whether the trigger location of the entry operation is near the trigger range of the close button or at the edge of the promotional content.

[0077] It is evident that the accuracy and reliability of the response results of predictive operations in related technologies are relatively low. As a result, content promoters will be unable to accurately determine the effective promotion methods that can achieve their promotion goals, leading to blind promotion and unnecessary waste of resources.

[0078] For example, taking content promotion as an example, the content promoter is the advertiser, who can be a user or service provider. To place ads on a traffic platform, the advertiser needs to pay a fee to the traffic owner, who can be a carrier providing user traffic, such as media, websites, or software. The advertiser and traffic owner typically use a cost-per-click (CPC) billing method, meaning the advertiser pays the traffic owner for each user click on the ad.

[0079] From an advertiser's perspective, it's best if each user click on an ad results in a conversion. For example, when promoting a public WeChat account, it's ideal if users click on the ad and then follow the account to achieve the promotion goal.

[0080] From the perspective of traffic owners, the more users click on ads, the more profit they can earn. Therefore, traffic owners often use click fraud methods to increase click-through rates and thus increase their profit share. For example, by setting the close button of an ad to a very small trigger range, users may accidentally trigger an area outside the trigger range when clicking the close button to close the ad, causing them to click on the ad again.

[0081] However, with the continuous advancement of technology, the methods of click fraud are becoming more and more diverse. For example, some methods include placing advertisements on top of content that users originally intended to click, such as placing them on top of the start button of a game, and making them flash frequently so that users accidentally click on the advertisement when they are trying to click on the content they originally intended to click.

[0082] In related technologies, predictions typically only rely on whether a user's click is near the trigger range of the ad's close button to determine whether a click will lead to an ad conversion and achieve promotional goals. This results in low accuracy and reliability of the prediction results, causing advertisers to pay large, unnecessary fees to traffic owners without generating corresponding ad conversions to achieve their promotional objectives.

[0083] To address the issue of low accuracy and reliability in predicting the response results of operations, this application proposes a method for predicting operation response results. In this method, when a promotional interface associated with the target promotional content is presented in response to a target operation triggered by the target promotional content, multiple historical operation data associated with the target promotional content can be obtained. Each historical operation data point represents the response result of the corresponding target historical operation as the execution of a target conversion task within the promotional interface. Each historical operation data point at least includes the historical trigger position and the historical trigger count of the corresponding target historical operation. Therefore, based on the relative distance between the historical trigger positions contained in each of the multiple historical operation data points and the target trigger position of the target operation, as well as the historical trigger count contained in each of the multiple historical operation data points, the matching degree between the target operation and each target historical operation can be determined. Based on the obtained matching degrees, the response result of the target operation can be predicted.

[0084] In this embodiment, after presenting a promotional interface associated with the target promotional content in response to a target operation triggered by the target promotional content, multiple historical operation data associated with this target promotional content can be obtained. The historical operation data indicates that the response result of the corresponding target historical operation is that the target conversion task has been executed in the promotional interface. Based on the target trigger position of the target operation, the relative distance between it and the historical trigger positions of each target historical operation, and the historical trigger count of each target historical operation, the matching degree between the target operation and each target historical operation can be determined. Based on each matching degree, it can be predicted whether the response result of the target operation is that the target conversion task has been executed in the promotional interface.

[0085] Compared to prediction methods based on the target trigger location of the target operation, such as whether it is near the close button of the target promotional content or at the edge of the target promotional content, this embodiment uses the target historical operations that have already executed the target conversion task in the promotion interface as a basis to determine the matching degree between the target operation and the target historical operations, thereby predicting the response result of the target operation. This avoids misjudging some target operations whose target trigger location is far from the close button of the target promotional content as having executed the target conversion task, making the accuracy and reliability of predicting the response result of the target operation higher.

[0086] Furthermore, when judging the matching degree between the target operation and the target historical operation, it not only considers the relative distance between the historical trigger position and the target trigger position, but also the number of historical triggers. This allows for the measurement of the matching degree between the target operation and the target historical operation from multiple perspectives, further improving the accuracy and reliability of predicting the response results of the target operation.

[0087] The following describes the application scenarios of the method for predicting operational response results provided in this application.

[0088] Please refer to Figure 1c This is a schematic diagram illustrating an application scenario of the method for predicting operation response results provided in this application. The application scenario includes a client 101 and a server 102. The client 101 and the server 102 can communicate with each other. The communication method can be wired, such as through a network cable or serial cable; or wireless, such as through Bluetooth or Wireless Fidelity (WIFI), etc., without limitation.

[0089] Client 101 generally refers to devices that can trigger target operations, such as terminal devices, third-party applications accessible by terminal devices, or web pages accessible by terminal devices. Terminal devices include, but are not limited to, mobile phones, computers, intelligent transportation equipment, and smart appliances. Server 102 generally refers to devices that can predict the response result of an operation, such as terminal devices or servers. Servers include, but are not limited to, cloud servers, local servers, or associated third-party servers. Both client 101 and server 102 can utilize cloud computing to reduce the consumption of local computing resources; similarly, they can also utilize cloud storage to reduce the consumption of local storage resources.

[0090] As one embodiment, the client 101 and the server 102 can be the same device. For example, this embodiment can be implemented using only the client 101 or only the server 102, etc., without any specific limitation. In this embodiment, the client 101 and the server 102 are described as different devices.

[0091] The following is based on Figure 1c This application provides a detailed description of the method for predicting operational response results according to embodiments. Please refer to... Figure 2 This is a flowchart illustrating a method for predicting operational response results provided in an embodiment of this application.

[0092] S201, in response to a target operation triggered for the target promotional content, presents the promotional interface associated with the target promotional content and obtains multiple historical operation data associated with the target promotional content.

[0093] When a target object displays target content on a client-side application, if the target promotional content is displayed in the client, the target object can trigger a close operation or a target operation on the target promotional content. The close operation is used to cancel the display of the target promotional content, while the target operation is used to display the promotional interface associated with the target promotional content.

[0094] Please refer to Figure 3a When the target audience is using a client to view the introduction interface of game A, the client can display promotional content for game B on top of the introduction interface, with the promotional content for game B overlapping the introduction of game A. In this case, the client can be configured to not respond to the target audience's attempts to trigger the "Share" and "Start" buttons on the introduction interface of game A. The target audience can trigger a close operation by clicking the "Close" button within the promotional content, thus canceling the display of the promotional content, and then perform operations on the introduction interface of game A; alternatively, they can click on an area within the promotional content other than the close button to trigger their target action and enter the introduction interface of game B.

[0095] When the server cancels the display of the target promotional content in response to a close operation triggered by the target promotional content, it means that the server accurately identified the close operation performed by the target object. Therefore, the response result of the close operation can be that the target conversion task was not executed in the promotional interface.

[0096] When a promotional interface associated with a target promotional content is displayed in response to a target action triggered by that content, it indicates that the client's identification of the target object's action to display the promotional interface may be due to a misexecution or a requirement for the target object to perform such an action. Therefore, the server can further predict whether the response to the target action will result in the promotional interface not executing the target conversion task or having already executed it.

[0097] Target conversion tasks are tasks executed within the promotion interface to achieve promotional goals. For example, to promote content from a WeChat official account, a conversion task to confirm following the account can be executed within the promotion interface associated with the content, thus achieving the promotional goal. Similarly, to promote content from an application, a conversion task to confirm downloading the application can be executed within the promotion interface associated with the content, and so on. Specific conversion tasks are not limited.

[0098] When the server further predicts the response result of the target operation, it can obtain multiple historical operation data associated with the target promotion content after presenting the promotion interface related to the target promotion content in response to the target operation triggered by the target promotion content. Each historical operation data represents the response result of the corresponding target historical operation, which is that the target conversion task has been executed in the promotion interface.

[0099] Multiple historical operation data records can be the relevant data of each target historical operation that has been executed in the promotion interface within a preset time period with the current time as the end point. For example, if the preset time period is seven days, then the server can obtain the relevant data of each target historical operation that has been executed in the promotion interface in the past seven days.

[0100] Historical operation data can be recorded when an object, in the case of an object permission record, continues to execute the target conversion task on the promotion interface associated with the target promotion content after the object triggers the target operation for the target promotion content; or it can be recorded when the response result of the target operation is predicted using the method provided in the embodiments of this application, etc., and there are no specific limitations.

[0101] Each historical operation data point must contain at least the historical trigger location and the number of times the corresponding target historical operation was triggered. The historical trigger location can be the relative position between the trigger point of the target historical operation and a specified edge of the client's display screen; it can also be the coordinate position of the trigger point of the target historical operation in a coordinate system formed by two specified edges of the client's display screen; or it can be the relative position between the trigger point of the target historical operation and a specified edge of the display range of the target promotional content, etc., and there are no specific restrictions.

[0102] Historical operations with the same trigger location can be considered as the same operation. Therefore, the number of historical triggers can represent the number of times the target historical operation has been executed.

[0103] As one embodiment, historical operation data can also be obtained from the historical operation heatmap data of each alternative promotional content recorded by the server. This historical operation heatmap data can be used to create heatmaps. Please refer to [link / reference]. Figure 3b (1) As an alternative promotional content Figure 3b (2) A heatmap for triggering alternative historical operations for alternative promotional content. In the heatmap, the center surrounded by multiple circles is brighter than the surrounding area. The more circles there are, the brighter the center becomes. The brighter the point, the more alternative historical operations are triggered for that location.

[0104] Each historical operation heatmap can contain the content identifier of the corresponding candidate promotional content, as well as the candidate trigger coordinates and the number of times the corresponding candidate historical operation was triggered. The content identifier of the candidate promotional content can uniquely identify each candidate promotional content.

[0105] The alternative trigger coordinates for alternative historical operations can be the coordinates corresponding to the alternative historical operations on the heatmap, and the alternative trigger count can be the number of times the alternative historical operations are triggered for the same alternative trigger coordinates.

[0106] Please refer to Table 1 for a record of the historical operation heatmap data for each candidate promotion content.

[0107] Table 1

[0108]

[0109] If the target promotional content has a content identifier, which uniquely identifies the target promotional content, then the server can obtain historical operation heatmap data generated within a historical time period. Based on the content identifier of the target promotional content, the server selects historical operation heatmap data associated with the target promotional content from the various historical operation heatmap data, thereby determining the alternative trigger coordinates and alternative trigger counts for each target historical operation.

[0110] Based on the alternative trigger coordinates of each target's historical operations, the historical trigger position of each target's historical operations is determined, and based on the alternative trigger counts of each target's historical operations, the historical trigger count of each target's historical operations is determined, so as to generate multiple historical operation data.

[0111] The server can use the alternative trigger coordinates of each target's historical operation as the historical trigger position of each target's historical operation, and use the alternative trigger count of each target's historical operation as the historical trigger count of each target's historical operation, thereby obtaining multiple historical operation data.

[0112] As one example, if the historical operation heatmap data also includes the size of the corresponding candidate promotion content, the server can normalize the coordinates of each candidate trigger based on the size of the target recommended content, and use the result of the normalization as the corresponding historical trigger position.

[0113] Please refer to Table 2 for a record of the historical operation heatmap data for each candidate promotion content.

[0114] Table 2

[0115]

[0116] The server can determine the size of the target promotional content based on the heatmap data of each historical operation. Based on the size of the target promotional content, the candidate trigger coordinates of each target historical operation are normalized to obtain the historical trigger position of each target historical operation.

[0117] Calculate historical trigger locations (X) ′ Y ′ Please refer to formulas (1) and (2).

[0118]

[0119]

[0120] Where (X, Y) represents the alternative trigger coordinates, W represents the width of the target promotion content, and H represents the height of the target promotion content.

[0121] As one example, since the number of alternative triggers for alternative historical operations may differ for different alternative promotional content, some alternative promotional content may have a very high number of alternative triggers for alternative historical operations, while others may have a very low number of alternative triggers for alternative historical operations. To facilitate unified calculation, the server can normalize the number of alternative triggers based on the sum of the number of alternative triggers for the target historical operations.

[0122] The server can sum the number of candidate triggers for each target's historical operation to obtain the total number of triggers. Based on the total number of triggers, the number of candidate triggers for each target's historical operation is normalized to obtain the historical trigger count for each target's historical operation.

[0123] To calculate the total number of triggers N_sum, refer to formula (3).

[0124]

[0125] Among them, CLK n This indicates the number of alternative triggers for the nth target's historical operation. The recommended content includes a total of N target historical operations.

[0126] To calculate the historical trigger count (PV), please refer to formula (4).

[0127]

[0128] Wherein, CLK represents the number of alternative triggers for a target historical operation, and N_sum represents the total number of triggers.

[0129] Based on formulas (1) to (4), please refer to Table 3 for a record format of each historical operation data.

[0130] Table 3

[0131]

[0132] S202, based on the historical trigger positions contained in each of the multiple historical operation data, the relative distance between them and the target trigger position of the target operation, and the number of historical triggers contained in each of the multiple historical operation data, determine the matching degree between the target operation and each target historical operation.

[0133] After obtaining multiple historical operation data associated with the target promotion content, the server can determine the matching degree between the target operation and each target historical operation based on the historical trigger location contained in each of the multiple historical operation data, the relative distance between the target trigger location and the target operation, and the number of historical triggers contained in each of the multiple historical operation data.

[0134] There are several methods to determine the matching degree. Two of them are introduced below as examples, without any restrictions.

[0135] Method 1:

[0136] In the heatmap, each target's historical operation is used as a light source, the historical trigger count of the target's historical operation is used as the light intensity, and the illuminance of each light source on the target operation is used as the matching degree between the target operation and each target's historical operation.

[0137] The server can determine the relative distance between the historical trigger locations contained in each of the multiple historical operation data sets and the target trigger location of the target operation. The ratio of the number of historical triggers contained in each of the multiple historical operation data sets to their respective relative distances is used as the matching degree E between the target operation and each target historical operation. i Please refer to formula (5).

[0138]

[0139] Among them, pv i This represents the number of times the historical operation of the i-th target has been triggered in history, (x i -x p ) 2 +(y i -y p ) 2 Indicates the target trigger position (x) of the target operation. p yp ) and the historical trigger position (x) of the i-th target historical operation i y i The relative distance between them is calculated by adding 1 to the relative distance to prevent the denominator from being 0.

[0140] Please refer to Figure 4 (1) The content presented is the target promotion content for promoting the public account A. The target audience can enter the details interface of public account A by clicking the "Follow Public Account" button. In the details interface, they can follow public account A.

[0141] Please refer to Figure 4 (2) is a diagram illustrating the historical operations performed on the content promoted for this target. Figure 4 (2) The area containing the target promotional content is magnified. The "Follow Official Account" button contains ten target historical operations, numbered 0-9. The area containing the target promotional content also includes one target operation, numbered 10.

[0142] Please refer to Figure 4 (3) Each target historical operation is used as a light source, and the historical trigger count of the target historical operation is used as the light intensity. The historical trigger counts of the target historical operations labeled 0 to 9 are 1, 5, 6, 4, 3, 4, 1, 2, 7, and 3, respectively. When the target historical operation is used as a light source, there is illuminance for the target operation labeled 10. The illuminance produced by light sources with different intensities and at different distances is different. The greater the relative distance between the target historical operations and the target operation, the lower the illuminance produced by the target historical operation on the target operation. The closer the relative distance between the target historical operations and the target operation, the higher the illuminance produced by the target historical operation on the target operation. The higher the light intensity of the target historical operation, the higher the illuminance produced by the target historical operation on the target operation. The lower the light intensity of the target historical operation, the lower the illuminance produced by the target historical operation on the target operation.

[0143] Therefore, the matching degree between the target operation and the target historical operation can be determined, which is the illuminance generated by the target historical operation on the target operation. Since illuminance is directly proportional to light intensity and inversely proportional to relative distance, the matching degree is directly proportional to the number of historical triggers and inversely proportional to the relative distance.

[0144] Method 2:

[0145] By pre-storing the correspondence between different relative distances, different historical trigger counts, and matching degrees, the matching degree between the target operation and each target historical operation is determined based on the relative distance between the historical trigger positions contained in multiple historical operation data and the target trigger position of the target operation, as well as the historical trigger counts contained in each of the multiple historical operation data. In the correspondence, the smaller the relative distance and the larger the historical trigger count, the greater the corresponding matching degree.

[0146] For example, the pre-stored correspondences include: Correspondence A: relative distance is 1, historical trigger count is 1, and the corresponding matching degree is 0.3; Correspondence B: relative distance is 1, historical trigger count is 5, and the corresponding matching degree is 0.6; Correspondence C: relative distance is 4, historical trigger count is 1, and the corresponding matching degree is 0.1. Therefore, if the relative distance between the historical trigger position contained in the historical operation data and the target trigger position of the target operation is calculated to be 1, and the historical trigger count contained in the historical operation data is 5, then the matching degree between the target operation and the target historical operation can be determined to be 0.6 from Correspondence B.

[0147] S203, based on the obtained matching degrees, predict the response result of the target operation.

[0148] After obtaining the matching degree between the target operation and each historical target operation, the server can predict the response result of the target operation based on the obtained matching degrees. There are multiple methods to predict the response result of the target operation based on the obtained matching degrees, and the specific prediction method is not limited. The server can predict the response result of the target operation as having executed the target conversion task in the promotion interface when the number of matching degrees greater than the matching degree threshold exceeds the quantity threshold; and predict the response result of the target operation as not having executed the target conversion task in the promotion interface when the number of matching degrees greater than the matching degree threshold does not exceed the quantity threshold.

[0149] The server can also predict the response result of the target operation as the target conversion task has been executed in the promotion interface when all matching degrees are greater than the matching degree threshold; and predict the response result of the target operation as the target conversion task has not been executed in the promotion interface when there is a matching degree among the matching degrees that is not greater than the matching degree threshold.

[0150] The server can also predict the response result of the target operation as the target conversion task has been executed in the promotion interface when the error between any two matching degrees is no greater than the error threshold; and predict the response result of the target operation as the target conversion task has not been executed in the promotion interface when the error between any two matching degrees is greater than the error threshold.

[0151] The server can also perform a weighted summation of each matching degree based on preset weight coefficients to determine the overall matching degree. When the overall matching degree is less than the preset matching degree threshold, the predicted response result for the target operation is that the target conversion task has not been executed in the promotion interface; when the overall matching degree is greater than or equal to the preset matching degree threshold, the predicted response result for the target operation is that the target conversion task has been executed in the promotion interface.

[0152] If the server predicts that the response to a target action will result in the execution of a target conversion task on the promotional interface, then it can be determined that the target action was actively performed by the target user on the target promotional content. In this case, the target user will execute the corresponding target conversion task on the promotional interface associated with the target promotional content, achieving the promotional goal. Therefore, in the advertising field, advertisers can pay traffic owners for target actions whose predicted response result is the execution of a target conversion task on the promotional interface, significantly reducing unnecessary expenses for advertisers and effectively achieving promotional goals with minimal cost.

[0153] After obtaining the response results of the target actions, the server can set processing strategies based on these results. For example, advertisers can use the server to count the number of target actions for each promotional content delivered to each traffic owner where the response result indicates that the target conversion task was not executed on the promotional interface. When the number of actions reaches a specified threshold, the server can reduce the payment to the traffic owner or impose a penalty on the traffic owner. Alternatively, advertisers can use the server to reduce the payment to the traffic owner by a certain percentage after predicting a certain number of response results indicating that the target conversion task was not executed on the promotional interface for each promotional content delivered to each traffic owner. Specific details are not limited.

[0154] The following example uses advertising as the target promotion content to illustrate the method for predicting operation response results provided in this application.

[0155] Please refer to Figure 5 (1) When advertisers place ads through traffic owners on traffic platforms, the traffic owners can display the ads on top of the game interface that the target audience was originally viewing. The target audience can only enter the details page of Official Account A, i.e., the promotional page associated with the target promotional content, by clicking the "Follow Official Account" button in the ad. Please refer to [link / reference]. Figure 5 (2) is a heatmap of the various actions triggered by the advertisement. Only in this way can the user follow the official account A and achieve the promotion goal.

[0156] However, in actual promotion, the locations of the various actions triggered on this advertisement differ. Please refer to [the relevant documentation / reference]. Figure 6(1) A heatmap of the various actions triggered on the advertisement shows that not only are there a large number of actions at the "Follow Official Account" button, but also in other locations on the advertisement. If the advertiser pays the traffic owner for all the actions, the advertiser will spend a lot of unnecessary money without gaining more attention.

[0157] Please refer to Figure 6 (2) Taking the operation in box 601 as an example of each target's historical operation, the response result of the operation in box 601 is that the target followed public account A in the details interface of public account A. If the operations in box 602 and box 603 are each target operation, then the target operation that is closer to the brighter position in box 601 can be predicted to have the response result of following public account A in the details interface of public account A, that is, the response result of the target operation in box 602 is that the target operation followed public account A in the details interface of public account A. The target operation that is farther away from the brighter position in box 601 can be predicted to have the response result of not following public account A in the details interface of public account A, that is, the response result of the target operation in box 603 is that the target operation did not follow public account A in the details interface of public account A.

[0158] The method for predicting operation response results described in this application can detect target operations that are not located near the close button of the target promotional content, or are located at the edge of the target promotional content. The response result of these target operations is that the target conversion task was not executed on the promotional interface. The method for predicting operation response results described in this application has a prediction accuracy that is more than 20 times higher than prediction methods based on the close button of the target promotional content or the edge of the target promotional content.

[0159] Please refer to Table 4, which shows the number of clicks on each target promotional content when each traffic owner presents each target promotional content within a certain time period; the number of false clicks predicted by the method of predicting operation response results described in the embodiments of this application; and the percentage of false clicks.

[0160] Table 4

[0161]

[0162]

[0163] As one example, please refer to Figure 7The target object can present target content through the target client 701, and then present target promotional content on top of that target content. In response to a target action triggered by the target object through the target client 701 regarding the target promotional content, the target client 701 can send data such as the current time, the target object's object identifier, the target promotional content's content identifier, and the traffic owner identifier to the access layer server 702. The access layer server 702 receives the data sent by the target client 701 and stores it in the database 703. After storing the data in the database 703, the access layer server 702 can send a request to the real-time computing server 704 regarding the relevant data of the target action, requesting the real-time computing server 704 to predict the response result of the target action. Upon receiving the request, the real-time computing server 704 retrieves the relevant data of the target action and the relevant historical action data of the target promotional content from the database 703. After obtaining all the relevant data and the relevant historical action data, the real-time computing server 704 can calculate the matching degree between the target action and each of the target historical actions based on the obtained data, and thus predict the response result of the target action based on the calculated matching degrees.

[0164] Based on the same inventive concept, embodiments of this application provide an apparatus for predicting operation response results, capable of achieving the functions corresponding to the aforementioned method for predicting operation response results. Please refer to... Figure 8 The device includes an acquisition module 801 and a processing module 802, wherein:

[0165] Acquisition module 801: In response to the target operation triggered for the target promotion content, it presents the promotion interface associated with the target promotion content and acquires multiple historical operation data associated with the target promotion content. Each historical operation data represents that the response result of the corresponding target historical operation is that the target conversion task has been executed in the promotion interface. Each historical operation data includes at least the historical trigger position and historical trigger number of the corresponding target historical operation.

[0166] Processing module 802: is used to determine the matching degree between the target operation and each target historical operation based on the historical trigger positions contained in each of the multiple historical operation data, the relative distance between them and the target trigger position of the target operation, and the number of historical triggers contained in each of the multiple historical operation data.

[0167] The processing module 802 is also used to: predict the response result of the target operation based on the obtained matching degrees.

[0168] In one possible embodiment, the target promotional content is provided with a content identifier, which is used to uniquely identify the target promotional content.

[0169] The module is then specifically used for:

[0170] Acquire heatmap data of each historical operation generated within a historical time period. Each heatmap data of a historical operation includes the content identifier of the corresponding candidate promotion content, as well as the candidate trigger coordinates and the number of candidate triggers for the corresponding candidate historical operation.

[0171] Based on the content identifier of the target promotion content, the alternative trigger coordinates and alternative trigger counts of each target historical operation are determined from the heatmap data of each historical operation.

[0172] Based on the alternative trigger coordinates of each target's historical operations, the historical trigger position of each target's historical operations is determined, and based on the alternative trigger counts of each target's historical operations, the historical trigger count of each target's historical operations is determined, so as to generate multiple historical operation data.

[0173] In one possible embodiment, each historical operation heatmap data also includes the promotion content size of the corresponding alternative promotion content;

[0174] The processing module 802 is specifically used for:

[0175] Based on historical operation heatmap data, determine the size of the target promotion content;

[0176] Based on the size of the target promotion content, the alternative trigger coordinates of each target's historical operation are normalized to obtain the historical trigger position of each target's historical operation.

[0177] In one possible embodiment, the processing module 802 is specifically used for:

[0178] The total number of triggers is obtained by summing the number of alternative triggers for each target's historical operations.

[0179] Based on the total number of triggers, the candidate trigger counts for each target's historical operation are normalized to obtain the historical trigger counts for each target's historical operation.

[0180] In one possible embodiment, the processing module 802 is specifically used for:

[0181] Determine the relative distance between the historical trigger positions contained in each of the multiple historical operation data sets and the target trigger position of the target operation;

[0182] The ratio between the number of historical triggers contained in each of the multiple historical operation data and the corresponding relative distance is used as the matching degree between the target operation and each target historical operation.

[0183] In one possible embodiment, the processing module 802 is specifically used for:

[0184] Based on preset weight coefficients, the matching degrees are weighted and summed to determine the overall matching degree;

[0185] When the overall matching degree is less than the preset matching degree threshold, the predicted response result of the target operation is that the target conversion task is not executed in the promotion interface;

[0186] When the overall matching degree is greater than or equal to the preset matching degree threshold, the predicted response result of the target operation is that the target conversion task has been executed in the promotion interface.

[0187] Please refer to Figure 9 The aforementioned device for predicting operation response results can run on a computer device 900. The current and historical versions of the data storage program, as well as the application software corresponding to the data storage program, can be installed on the computer device 900, which includes a processor 980 and a memory 920. In some embodiments, the computer device 900 may include a display unit 940, which includes a display panel 941 for displaying a user-interactive interface, etc.

[0188] In one possible embodiment, the display panel 941 may be configured in the form of a liquid crystal display (LCD) or an organic light-emitting diode (OLED).

[0189] The processor 980 is used to read a computer program and then execute the methods defined by the computer program. For example, the processor 980 reads a data storage program or file, thereby running the data storage program on the computer device 900 and displaying the corresponding interface on the display unit 940. The processor 980 may include one or more general-purpose processors, and may also include one or more DSPs (Digital Signal Processors) for performing related operations to implement the technical solutions provided in the embodiments of this application.

[0190] The memory 920 generally includes main memory and secondary storage. Main memory can be random access memory (RAM), read-only memory (ROM), and cache, etc. Secondary storage can be a hard disk, optical disk, USB flash drive, floppy disk, or magnetic tape drive, etc. The memory 920 is used to store computer programs and other data. The computer programs include applications corresponding to each client, and other data may include data generated after the operating system or applications are run, including system data (e.g., operating system configuration parameters) and user data. In this embodiment, program instructions are stored in the memory 920, and the processor 980 executes the program instructions in the memory 920 to implement any of the methods described in the preceding figures.

[0191] The aforementioned display unit 940 is used to receive input digital information, character information, or contact touch operations / non-contact gestures, and to generate signal inputs related to user settings and function control of the computer device 900. Specifically, in this embodiment, the display unit 940 may include a display panel 941. The display panel 941, for example, is a touch screen, which can collect touch operations performed by the user on or near it (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or on the display panel 941), and drive corresponding connection devices according to a pre-set program.

[0192] In one possible embodiment, the display panel 941 may include two parts: a touch detection device and a touch controller. The touch detection device detects the player's touch position and the signal generated by the touch operation, and transmits the signal to the touch controller. The touch controller receives touch information from the touch detection device, converts it into touch point coordinates, and sends it to the processor 980. It can also receive and execute commands from the processor 980.

[0193] The display panel 941 can be implemented using various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the display unit 940, in some embodiments, the computer device 900 may also include an input unit 930. The input unit 930 may include an image input device 931 and other input devices 932, wherein the other input devices may include, but are not limited to, one or more of the following: a physical keyboard, function keys (such as volume control buttons, power buttons, etc.), a trackball, a mouse, and a joystick.

[0194] In addition to the above, the computer device 900 may also include a power supply 990 for powering other modules, an audio circuit 960, a near-field communication module 970, and an RF circuit 910. The computer device 900 may also include one or more sensors 950, such as an accelerometer, a light sensor, and a pressure sensor. The audio circuit 960 specifically includes a speaker 961 and a microphone 962, for example, the computer device 900 can use the microphone 962 to collect the user's voice and perform corresponding operations.

[0195] As one embodiment, the number of processors 980 can be one or more, and the processors 980 and the memory 920 can be coupled together or relatively independent.

[0196] As one example, Figure 9 The processor 980 in the middle can be used to implement, for example Figure 8 The functions of the acquisition module 801 and the processing module 802 in the process.

[0197] As one example, Figure 9The processor 980 in the text can be used to implement the functions of the server or terminal devices discussed above.

[0198] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0199] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of software products, for example, through a computer program product. This computer program product is stored in a storage medium and includes several instructions to cause a computer device to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

[0200] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for predicting operational response results, characterized in that, include: In response to a target operation triggered for a target promotional content, a promotional interface associated with the target promotional content is presented, and multiple historical operation data associated with the target promotional content are obtained. Each historical operation data represents that the response result of the corresponding target historical operation is that the target conversion task has been executed in the promotional interface. Each historical operation data includes at least the historical triggering position and the historical triggering number of the corresponding target historical operation. Based on the relative distance between the historical trigger locations contained in each of the multiple historical operation data and the target trigger location of the target operation, and the number of historical triggers contained in each of the multiple historical operation data, the matching degree between the target operation and each target historical operation is determined respectively; the relative distance is negatively correlated with the matching degree, and the number of historical triggers is positively correlated with the matching degree; Based on the obtained matching degrees, the response result of the target operation is predicted.

2. The method according to claim 1, characterized in that, The target promotional content is equipped with a content identifier, which is used to uniquely identify the target promotional content. The acquisition of multiple historical operation data associated with the target promotion content includes: Acquire heatmap data of each historical operation generated within a historical time period. Each heatmap data of a historical operation includes the content identifier of the corresponding candidate promotion content, as well as the candidate trigger coordinates and the number of candidate triggers for the corresponding candidate historical operation. Based on the content identifier of the target promotion content, the alternative trigger coordinates and alternative trigger counts of each target historical operation are determined from the heatmap data of each historical operation. Based on the candidate trigger coordinates of each target historical operation, the historical trigger position of each target historical operation is determined, and based on the candidate trigger count of each target historical operation, the historical trigger count of each target historical operation is determined, so as to generate the multiple historical operation data.

3. The method according to claim 2, characterized in that, Each historical operation heatmap data also includes the promotion content size of the corresponding alternative promotion content; The step of determining the historical trigger position of each target historical operation based on the candidate trigger coordinates of each target historical operation includes: Based on the historical operation heatmap data, the size of the target promotion content is determined; Based on the size of the target promotion content, the candidate trigger coordinates of each target historical operation are normalized to obtain the historical trigger position of each target historical operation.

4. The method according to claim 2, characterized in that, The step of determining the historical trigger count of each target historical operation based on the candidate trigger counts of each target historical operation includes: The total number of triggers is obtained by summing the number of alternative triggers for each target's historical operation. Based on the total number of triggers, the candidate trigger counts for each target historical operation are normalized to obtain the historical trigger counts for each target historical operation.

5. The method according to any one of claims 1 to 4, characterized in that, The determination of the matching degree between the target operation and each target historical operation is based on the relative distance between the historical trigger positions contained in each of the multiple historical operation data and the target trigger position of the target operation, and the number of historical triggers contained in each of the multiple historical operation data, including: Determine the relative distance between the historical trigger positions contained in each of the plurality of historical operation data and the target trigger position of the target operation; The ratio between the number of historical triggers contained in each of the multiple historical operation data and the corresponding relative distance is used as the matching degree between the target operation and each target historical operation.

6. The method according to any one of claims 1 to 4, characterized in that, The prediction of the response result of the target operation based on the obtained matching degrees includes: Based on preset weighting coefficients, the various matching degrees are weighted and summed to determine the overall matching degree; When the overall matching degree is less than the preset matching degree threshold, the predicted response result of the target operation is that the target conversion task is not executed in the promotion interface; When the overall matching degree is greater than or equal to the preset matching degree threshold, the predicted response result of the target operation is that the target conversion task has been executed in the promotion interface.

7. An apparatus for predicting operational response results, characterized in that, include: Acquisition module: In response to a target operation triggered for the target promotion content, presents the promotion interface associated with the target promotion content, and acquires multiple historical operation data associated with the target promotion content. Each historical operation data represents that the response result of the corresponding target historical operation is that the target conversion task has been executed in the promotion interface. Each historical operation data includes at least the historical trigger position and historical trigger number of the corresponding target historical operation. Processing module: used to determine the matching degree between the target operation and each target historical operation based on the relative distance between the historical trigger positions contained in each of the multiple historical operation data and the target trigger position of the target operation, and the number of historical triggers contained in each of the multiple historical operation data; Relative distance is negatively correlated with matching degree, while the number of historical triggers is positively correlated with matching degree; The processing module is also used to: predict the response result of the target operation based on the obtained matching degrees.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the method as described in any one of claims 1 to 6.

9. A computer device, characterized in that, include: Memory, used to store program instructions; A processor is configured to invoke program instructions stored in the memory and execute the method as described in any one of claims 1 to 6 according to the obtained program instructions.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions for causing a computer to perform the method as described in any one of claims 1 to 6.

Images