Content processing method, apparatus and computer readable storage medium

Abstract

Embodiments of the present application disclose a content processing method and device and a computer readable storage medium, which can be applied to various scenes such as cloud technology, artificial intelligence, intelligent transportation and auxiliary driving. The historical content request log is acquired, and the content area corresponding to each historical content request is identified in the historical content request log. The content areas are aggregated according to the attribute information of the historical content requests to obtain a content area set. The content area set is merged based on the set relationship between the content area sets to obtain at least one target content area set, and a set identifier of the target content area set is generated. The set identifier is associated with each content area in the target content area set to obtain association information of the content area. The to-be-processed content request is processed based on the association information of the content area. In this way, the accuracy of the relationship between the obtained content area and the corresponding physical advertising position is improved, and the efficiency of content processing is improved.

Description

Technical Field

[0001] This application relates to the field of Internet technology, specifically to a content processing method, apparatus, and computer-readable storage medium. Background Technology

[0002] In recent years, with the rapid development of internet technology, content promotion via the internet has become a new and widely used form of information dissemination. Among these, internet advertising (hereinafter referred to as advertising content), as a common method of content promotion on the internet, has become an important channel for users to obtain information and for advertisers to enhance brand awareness and promote products. In practical applications, developers often use a waterfall layout mechanism to create multiple virtual ad slots corresponding to a single physical ad slot in an application (APP), thereby requesting more precise content through these multiple content slots. To facilitate content processing, it is necessary to obtain the relationship between content slots and their corresponding physical ad slots. In existing content processing methods, the relationship between content slots and their corresponding physical ad slots is generally collected manually by developers.

[0003] In the process of researching and practicing existing technologies, the inventors of this invention discovered that the existing content processing methods, which rely on manually collecting the relationship between content areas and corresponding physical advertising spaces, are prone to errors, resulting in low accuracy of the obtained relationship between content areas and corresponding physical advertising spaces. Consequently, this leads to low efficiency in content processing. Summary of the Invention

[0004] This application provides a content processing method, apparatus, and computer-readable storage medium, which can improve the accuracy of the relationship between the obtained content area and the corresponding physical advertising space, thereby improving content processing efficiency.

[0005] This application provides a content processing method, including:

[0006] Obtain historical content request logs and identify the content area corresponding to each historical content request in the historical content request logs;

[0007] Based on the attribute information of the historical content requests, the content regions are aggregated to obtain at least one set of content regions;

[0008] Based on the set relationships between the content region sets, the content region sets are merged to obtain at least one target content region set, and a set identifier for the target content region set is generated;

[0009] Associating the set identifier with each content region in the target content region set yields the association information of the content regions;

[0010] Based on the association information of the content area, the request for the content to be processed is processed.

[0011] Accordingly, embodiments of this application provide a content processing apparatus, including:

[0012] The acquisition unit is used to acquire historical content request logs and identify the content area corresponding to each historical content request in the historical content request logs.

[0013] An aggregation unit is used to aggregate the content regions based on the attribute information of the historical content requests to obtain at least one set of content regions.

[0014] The merging unit is used to merge the content region sets based on the set relationships between the content region sets to obtain at least one target content region set, and generate a set identifier for the target content region set;

[0015] The association unit is used to associate the set identifier with each content region in the target content region set to obtain the association information of the content region;

[0016] The processing unit is used to process the content request to be processed based on the association information of the content area.

[0017] In one embodiment, the aggregation unit includes:

[0018] An aggregation subunit is used to aggregate the content areas based on the attribute information of the historical content requests to obtain at least one initial set of content areas.

[0019] An abnormal content region filtering subunit is used to filter out abnormal content regions in the content regions of the initial content region set based on the content region attributes corresponding to the content region.

[0020] The deletion sub-unit is used to delete the abnormal content region from the initial content region set to obtain a content region set.

[0021] In one embodiment, the aggregation subunit includes:

[0022] The attribute information acquisition module is used to acquire the attribute information of the historical content request;

[0023] The time information recognition module is used to identify the time information corresponding to the historical content request from the attribute information;

[0024] The content region set extraction module is used to extract at least one initial content region set from the content region based on the time information.

[0025] In one embodiment, the content region set extraction module includes:

[0026] The object identifier acquisition submodule is used to acquire the object identifier corresponding to the historical content request;

[0027] The classification submodule is used to classify the content region according to the object identifier to obtain at least one candidate content region set;

[0028] The time information filtering submodule is used to filter out target content regions whose time information falls within a preset time interval from the candidate content region set, thereby obtaining an initial content region set.

[0029] In one embodiment, the merging unit includes:

[0030] The content area combination subunit is used to combine the content areas in each content area set based on a preset step size to obtain the combined content area.

[0031] An undirected graph construction subunit is used to construct an undirected graph corresponding to each set of content regions based on the combined content regions.

[0032] A connected subgraph combination subunit is used to generate at least one connected subgraph based on the undirected graph, and combine the content regions corresponding to the connected subgraphs to obtain a set of target content regions.

[0033] In one embodiment, the associated unit includes:

[0034] The content region identifier acquisition subunit is used to acquire the content region identifier of the content region.

[0035] The mapping relationship construction subunit is used to construct a mapping relationship between the set identifier and each content region in the target content region set based on the content region identifier, and store the mapping relationship in a preset mapping relationship set;

[0036] A storage subunit is used to store the set identifier and the content region identifier of each content region in the target content region set into a preset identifier database according to the mapping relationship;

[0037] The assignment subunit is used to use the preset mapping relationship set and the preset identifier database as the association information of the content area.

[0038] In one embodiment, the content processing apparatus further includes:

[0039] The current target content region set determination unit is used to obtain the current content request log and determine the current target content region set based on the current content request log;

[0040] The association information update unit is used to update the association information based on the current target content region set to obtain the updated association information.

[0041] In one embodiment, the associated information update unit includes:

[0042] The historical set identifier query subunit is used to query the historical set identifier that matches the current content region identifier corresponding to the content region in the current target content region set in the preset mapping relationship set;

[0043] The first association information update subunit is used to add the current content area identifier to the association information based on the historical set identifier when the historical set identifier is found, so as to obtain the updated association information.

[0044] The second association information update subunit is used to generate a current set identifier corresponding to the current target content region set when the historical set identifier is not found, and to add the current content region identifier to the association information according to the current set identifier to obtain the updated association information.

[0045] In one embodiment, the second association information update subunit includes:

[0046] The preset mapping relationship set update module is used to construct the current mapping relationship between the current set identifier and each content region in the current target content region set based on the current content region identifier, and add the current mapping relationship to the preset mapping relationship set to obtain the updated preset mapping relationship set;

[0047] The preset identifier database update module is used to add the current set identifier and the current content area identifier of each content area in the current target content area set to the preset identifier database according to the current mapping relationship, so as to obtain the updated preset identifier database.

[0048] The update assignment module is used to use the updated preset mapping relationship set and the updated preset identifier database as the updated association information.

[0049] In one embodiment, the processing unit includes:

[0050] The pending content region identifier acquisition subunit is used to acquire the pending content region identifier corresponding to the pending content request when a pending content request is received.

[0051] The verification subunit is used to verify the content request to be processed based on the identifier of the content region to be processed and the associated information;

[0052] The content return sub-unit is used to return the target content corresponding to the content request to be processed based on the verification result.

[0053] In one embodiment, the verification subunit is configured to:

[0054] Query the target set identifier corresponding to the identifier of the content region to be processed in the associated information;

[0055] Obtain the reference resource information corresponding to the target set identifier and the target resource information corresponding to the content request to be processed;

[0056] Based on the reference resource information, the target resource information is matched;

[0057] The content is returned to the sub-unit for:

[0058] When the target resource information matches the reference resource information, the target content corresponding to the content request to be processed is returned.

[0059] Furthermore, embodiments of this application also provide a computer-readable storage medium storing a plurality of instructions adapted for loading by a processor to execute steps in any of the content processing methods provided in embodiments of this application.

[0060] Furthermore, this application also provides a computer device, including a processor and a memory, wherein the memory stores an application program, and the processor is used to run the application program in the memory to implement the content processing method provided in this application.

[0061] This application also provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps in the content processing method provided in this application.

[0062] This application embodiment obtains historical content request logs and identifies the content region corresponding to each historical content request in the logs. Based on the attribute information of the historical content requests, the content regions are aggregated to obtain at least one set of content regions. Based on the set relationships between the content region sets, these sets are merged to obtain at least one target content region set, and a set identifier for the target content region set is generated. The set identifier is associated with each content region in the target content region set to obtain the association information of the content regions. Based on the association information of the content regions, the content request to be processed is processed. In this way, the association relationship between content regions in the same target content region set is extracted through historical content request logs, and multiple virtual ad slots corresponding to actual physical ad slots are represented based on multiple content regions in the target content region set. This yields the association relationship between each content region and its corresponding physical ad slot, thus improving the accuracy of the obtained relationship between content regions and their corresponding physical ad slots, and consequently increasing the efficiency of content processing. Attached Figure Description

[0063] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0064] Figure 1 This is a schematic diagram illustrating an implementation scenario of a content processing method provided in an embodiment of this application;

[0065] Figure 2 This is a flowchart illustrating a content processing method provided in an embodiment of this application;

[0066] Figure 3 This is a schematic flowchart illustrating a content processing method provided in an embodiment of this application;

[0067] Figure 4 This is a schematic diagram of a connected subgraph of a content processing method provided in an embodiment of this application;

[0068] Figure 5 This is another specific flowchart illustrating a content processing method provided in an embodiment of this application;

[0069] Figure 6 This is another schematic flowchart of a content processing method provided in an embodiment of this application;

[0070] Figure 7This is a schematic diagram of the structure of the content processing device provided in the embodiments of this application;

[0071] Figure 8 This is a schematic diagram of the structure of the computer device provided in the embodiments of this application. Detailed Implementation

[0072] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0073] This application provides a content processing method, apparatus, and computer-readable storage medium. The content processing apparatus can be integrated into a computer device, which may be a server or a terminal, etc.

[0074] Please see Figure 1 Taking the integration of content processing devices into computer equipment as an example, Figure 1 This is a schematic diagram illustrating an implementation scenario of the content processing method provided in this application. It includes server A and terminal B. Server A can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms. Server A can obtain historical content request logs and identify the content region corresponding to each historical content request in the logs. Based on the attribute information of the historical content requests, it aggregates the content regions to obtain at least one set of content regions. Based on the set relationships between the content region sets, it merges the content region sets to obtain at least one target content region set and generates a set identifier for the target content region set. It associates the set identifier with each content region in the target content region set to obtain the association information of the content regions. Based on the association information of the content regions, it processes the content requests to be processed.

[0075] Terminal B may include, but is not limited to, mobile phones, computers, smart voice interaction devices, smart home appliances, vehicle terminals, aircraft, and other devices.

[0076] Terminal B and server A can be connected directly or indirectly via wired or wireless communication. Server A can obtain data uploaded by terminal B to perform corresponding content processing operations. This application does not impose any restrictions on this.

[0077] It should be noted that the embodiments of the present invention can be applied to various scenarios, including but not limited to cloud technology, artificial intelligence, smart transportation, and assisted driving. Figure 1 The illustrated implementation environment scenario of the content processing method is merely an example. The implementation environment scenario of the content processing method described in this application embodiment is for the purpose of more clearly illustrating the technical solution of this application embodiment and does not constitute a limitation on the technical solution provided in this application embodiment. Those skilled in the art will understand that with the evolution of content processing and the emergence of new business scenarios, the technical solution provided in this application is also applicable to similar technical problems.

[0078] The following sections provide detailed descriptions of each example. It should be noted that the order in which the embodiments are described is not intended to limit the preferred order of the embodiments.

[0079] This embodiment will be described from the perspective of a content processing device, which can be integrated into a computer device, which can be a server, and this application does not limit it.

[0080] Please see Figure 2 , Figure 2 This is a flowchart illustrating the content processing method provided in an embodiment of this application. The content processing method includes:

[0081] In step 101, the historical content request log is obtained, and the content area corresponding to each historical content request is identified in the historical content request log.

[0082] The content can be a carrier for transmitting relevant information for a specific purpose, such as an internet advertisement (referred to as an advertisement). The historical content request log can be a log recording the events corresponding to historical content requests. The historical content request can be a request to the content provider to obtain content generated before the current moment, such as an advertisement request. The content area can be an area that carries content, used to place content on the page. Taking an advertisement as an example, the content area can be an advertisement slot, which can be used to place an advertisement on the page.

[0083] There are several ways to identify the content area corresponding to each historical content request in the historical content request log. For example, please refer to... Figure 3 , Figure 3This is a schematic diagram of a specific process of a content processing method provided in an embodiment of this application. It can parse historical content request logs, obtain the log corresponding to each historical content request based on the parsing result, and extract the content area corresponding to each historical content request from the log corresponding to each historical content request.

[0084] When developers need to acquire ads, they request ads from advertising systems through software development kits (SDKs) and application programming interfaces (APIs). Currently, the mainstream request method is the Waterfall request. Waterfall, also known as ad tiering, refers to developers creating a series of virtual ad slots with identical configurations but different target prices for a given physical ad slot. These virtual ad slots are then used to request ads from the advertising system in descending order of target price. These physical ad slots can be different types of ad slots located in different positions on an application or webpage. When monetizing ads, requesting ads from only one advertising platform often fails to acquire a sufficient number of ads. Therefore, developers can use the Waterfall mechanism to set multiple target prices (effective cost per mille, eCPM, the revenue generated per thousand impressions) for a given physical ad slot and make tiered requests to different ad providers within the advertising system. This ad tiering approach maximizes fill rate and increases revenue, thereby improving the ad request experience for the requesting party.

[0085] Therefore, in practical applications, developers often use a waterfall layout mechanism to create multiple virtual ad slots (i.e., content areas) for a single real physical ad slot in an application (APP), thereby requesting more precise content through multiple content areas. The application of the waterfall layout mechanism makes it impossible for the advertising system to obtain the relationship between content areas and their corresponding physical ad slots during actual content processing. To facilitate content processing, it is necessary to obtain the relationship between content areas and their corresponding physical ad slots. In existing content processing methods, this relationship is generally collected manually by developers. However, this method of manually collecting the relationship between content areas and their corresponding physical ad slots is prone to errors; developers may not fill in the information according to requirements or may fill it in incorrectly, resulting in low accuracy of the obtained relationship between content areas and their corresponding physical ad slots, thus leading to low efficiency in content processing.

[0086] To address these issues, this application provides a content processing method that obtains historical content request logs and extracts the relationship between content areas and corresponding physical ad slots based on these logs. This improves the accuracy of the obtained relationship between content areas and corresponding physical ad slots, thereby enhancing content processing efficiency. The specific details are as follows.

[0087] In step 102, the content regions are aggregated based on the attribute information of historical content requests to obtain at least one set of content regions.

[0088] The attribute information can be information characterizing the nature and relationship of historical content requests. For example, it can include the name, time information, request parameters, request method, and protocol used in the historical content request. The time information can include the time when the historical content request was generated. The content area set can be a whole consisting of at least one content area, or it can be at least one set obtained by aggregating content areas based on the attribute information of historical content requests. The content areas in each content area set belong to the same waterfall flow, that is, they correspond to the same physical ad space.

[0089] There are several ways to aggregate content regions based on the attribute information of historical content requests. For example, the content regions can be aggregated based on the attribute information of the historical content requests to obtain at least one initial set of content regions. Based on the content region attributes corresponding to the content regions, abnormal content regions can be filtered out from the content regions of the initial set of content regions. The abnormal content regions can then be deleted from the initial set of content regions to obtain a set of content regions.

[0090] The initial content region set can be at least one set obtained by aggregating content regions based on attribute information from historical content requests. The content region attributes can be information characterizing the nature and relationships of the content regions; for example, they can include the type of content region, the material specifications supported by the content region, and the location of the content region on the page. The abnormal content region can be a content region whose attributes differ from other content regions in the initial content region set.

[0091] For example, the content area can be categorized as an ad placement type, which may include splash screen ads, rewarded video ads, native ads, interstitial ads, banner ads, etc. The supported creative specifications for this content area, i.e., the creative specifications supported by the ad placement, can include the style, format, size, aspect ratio, etc., of the ad creative. The format can include image or video formats, etc. The position of this content area on the page can include the coordinates of the ad placement container on the screen, such as the horizontal and vertical coordinates of the top-left corner of the ad placement container relative to the top-left corner of the screen when the ad is displayed.

[0092] There are several ways to aggregate the historical content request in the content area based on the attribute information of the historical content request to obtain at least one initial content area set. For example, the attribute information of the historical content request can be obtained, the time information corresponding to the historical content request can be identified in the attribute information, and at least one initial content area set can be extracted in the content area based on the time information.

[0093] There are several ways to extract at least one initial content region set from the content area based on the time information. For example, the object identifier corresponding to the historical content request can be obtained, the content area can be classified according to the object identifier to obtain at least one candidate content region set, and the target content region in which the time information is within a preset time interval can be selected from the candidate content region set to obtain the initial content region set.

[0094] The object identifier can be information used to uniquely identify a specific object, thus distinguishing each object. For example, the object identifier can be the identifier (IdentityDocument, or ID) of the client that triggered the historical content request. Based on the object identifier, the client corresponding to each historical content request can be determined. The candidate content area set can be the entire set of content areas corresponding to each object identifier. The target content area can be the content area in the candidate content area set whose time information falls within a preset time interval. The preset time interval can be a pre-defined time interval. Since in practical applications, each client will make tiered requests in the advertising system through a waterfall mechanism, according to the waterfall advertising request mechanism, historical content requests triggered by the same client within a certain time period can be regarded as content requests triggered by the same physical ad slot. Therefore, the content areas in the candidate content area set corresponding to each object identifier whose time information falls within the preset time interval can be filtered out, thereby obtaining at least one initial content area set.

[0095] There are several ways to classify the content region based on the object identifier. For example, suppose content regions a, b, c, d, and e are identified from historical content request logs. The object identifiers for content region a and c are X, d and e are X, and e is Z. Then, the content regions can be classified according to the object identifiers to obtain the candidate content region set (a, d) for object identifier X, (b, c) for object identifier Y, and (e) for object identifier Z.

[0096] After classifying the content area based on the object identifier, the target content area whose time information falls within a preset time interval can be filtered from the candidate content area set. There are several ways to filter the target content area whose time information falls within the preset time interval from the candidate content area set; for example, please refer to [link / reference]. Figure 3 A time-based window mechanism can be used to aggregate content regions in the candidate content region set. Specifically, a sliding time window can be constructed based on a preset time interval. This sliding time window can filter out content regions in each candidate content region set whose time information falls within the preset time interval, resulting in an initial content region set. For example, assuming the preset time interval is t, the time window can be set to t, and assuming the current time is T, then when the time information of historical content requests corresponding to content regions in the candidate content region set corresponding to the same object identifier is within the time interval [T, T+t], they can be considered to belong to the same waterfall flow content region and integrated into the same initial content region set.

[0097] In this embodiment, a physical ad slot refers to the actual ad slot corresponding to a waterfall layout. Specifically, different physical ad slots can be distinguished based on dimensions such as physical location and time. For example, ad slots located in different physical locations on the actual page can be considered different physical ad slots based on physical location. When a physical location on the page is split into two or more waterfall layouts, each waterfall layout in that physical location can be associated with a different physical ad slot based on the time dimension. That is, an ad slot in one physical location can be divided into multiple different physical ad slots. For example, different refreshes of a waterfall layout in one physical location can be associated with different physical ad slots. In this way, each physical ad slot can correspond to one waterfall layout, and the content area of ​​the same waterfall layout can be mapped to the corresponding physical ad slot to obtain the relationship between the content area and the corresponding physical ad slot, thereby improving the efficiency of content processing.

[0098] Since content areas within the same waterfall layout share the same attributes, after selecting target content areas whose time information falls within a preset time interval from the candidate content area set, the content area attributes can be used to filter out content areas that do not belong to the same waterfall layout. Thus, based on the content area attributes and the majority principle, abnormal content areas with different attributes from other content areas can be selected from the initial content area set. These abnormal content areas can then be deleted from the initial content area set, resulting in the final content area set.

[0099] Optionally, after classifying the content area according to the object identifier, the target content area in which the time information is within a preset time interval can be selected from the candidate content area set. Alternatively, after selecting the content area in which the time information is within a preset time interval, the content area can be classified according to the object identifier. This application does not limit this.

[0100] In step 103, based on the set relationships between content region sets, the content region sets are merged to obtain at least one target content region set, and a set identifier for the target content region set is generated.

[0101] The set relationship can be a connection between sets, such as whether the sets intersect or not. A set relationship exists when two sets contain at least one common element. The target content region set can be a set obtained by merging the initial content sets based on the set relationship. For example, it can be a whole composed of multiple initial content sets that intersect. The set identifier can be identification information generated based on the target content region set, used to uniquely identify a target content region set, thereby distinguishing content regions in different waterfall layouts.

[0102] The waterfall flow mechanism ensures that a physical ad placement will not request other content areas within the same waterfall flow once a request for a content area is successful. Therefore, the set of content areas aggregated based on time information can be a subset of different waterfall flows. In order to aggregate content areas within the same waterfall flow, the sets of content areas that have intersections can be merged into a target content area set based on the set relationships between the content area sets. In this way, a physical ad placement can be represented based on each target content area set, and the content areas in the target content area set are the content areas within the same waterfall flow.

[0103] For example, we can assume the existence of initial content sets f, g, h, i, and j, where initial content set f includes (content region 1, content region 2), initial content set g includes (content region 2, content region 3), initial content set h includes (content region 1, content region 4), initial content set i includes (content region 5, content region 6), and initial content set j includes (content region 6, content region 7). Then, based on the set relationships between the content region sets, we can merge the content region sets that have intersections. Since there is content region 2 between the initial content set f and the initial content set g, and there is content region 1 between the initial content set f and the initial content set h, the initial content sets f, g, and h can be merged to obtain the target content region set (f, g, h). Since there is content region 6 between the initial content sets i and j, that is, there is an intersection between the initial content sets i and j, the initial content sets i and j can be merged to obtain the target content region set (i, j).

[0104] Based on the set relationships between these content regions, there are several ways to merge them. For example, to improve merging efficiency, a connected subgraph can be constructed to merge the content regions. For details, please refer to [link / reference]. Figure 3 The system can combine the content regions in each content region set based on a preset step size to obtain the combined content region. Based on the combined content region, an undirected graph corresponding to each content region set is constructed. The system traverses the undirected graph to generate at least one connected subgraph. The content regions corresponding to the connected subgraph are then combined to obtain the target content region set.

[0105] The preset step size can be a pre-defined step size used to construct edges. The combined content region can be the content region in the content region set that is combined based on the preset step size. The undirected graph can be a graph composed of at least one undirected edge. The connected subgraph can be an undirected graph in which there is a path between any pair of vertices.

[0106] There are several ways to combine the content regions in each content region set based on a preset step size. For example, the preset step size can be set to 2, so that any two content regions in each content region set can be combined based on the preset step size, so that the combined content regions in each content region set can be obtained, and an undirected edge can be formed based on the two content regions.

[0107] After combining the content regions in each content region set based on a preset step size, an undirected graph corresponding to each content region set can be constructed based on the combined content regions. In other words, each content region set corresponds to an undirected graph, and each content region in the content region set is a vertex in the undirected graph. Each combination of two content regions can form an undirected edge in the undirected graph.

[0108] After constructing an undirected graph corresponding to each set of content regions based on the combined content regions, at least one connected subgraph can be generated based on the undirected graph. Each connected subgraph corresponds to a waterfall flow, and each vertex in the connected subgraph is a content region in the same waterfall flow. In this way, the content regions corresponding to each vertex in the connected subgraph can be combined to obtain the target content region set.

[0109] For example, please refer to Figure 4 , Figure 4 This is a schematic diagram of a connected subgraph of a content processing method provided in an embodiment of this application. It can be assumed that there exist initial content sets k, l, m, and n, where initial content set k includes (content region 1, content region 2, content region 3), initial content set l includes (content region 2, content region 4, content region 8), initial content set m includes (content region 5, content region 6, content region 7), and initial content set n includes (content region 6, content region 9). Assuming a preset step size of 2, the content regions in each content region set can be combined based on the preset step size, resulting in the combined content regions corresponding to initial content set k as [(content region 1, content region 2), (content region 2, content region 3)]. Initial content set l... The combined content regions are [(content region 2, content region 4), (content region 4, content region 8)], the combined content regions corresponding to the initial content set m are [(content region 5, content region 6), (content region 6, content region 7)], and the combined content regions corresponding to the initial content set m are [(content region 6, content region 9)]. Based on these combined content regions, an undirected graph corresponding to each content region set can be constructed. Then, all connected vertices in the undirected graph can be connected, thus generating connected subgraph A and connected subgraph B based on this undirected graph. Please refer to the diagram further. Thus, the content regions corresponding to each connected subgraph can be combined to obtain the target content region set (k, l) corresponding to connected subgraph A and the target content region set (m, n) corresponding to connected subgraph B.

[0110] After merging the content region sets based on the set relationships between them, a set identifier for the target content region set can be generated. There are several ways to generate the set identifier for the target content region set. For example, the set identifier for the target content region set can be generated based on the time information of the historical content request logs corresponding to the target content region set and the merging time of the target content region set. Alternatively, the Snowflake algorithm can be used to generate a corresponding set identifier for each target content region set, so as to uniquely identify a target content region set based on the set identifier.

[0111] In step 104, the set identifier is associated with each content region in the target content region set to obtain the association information of the content regions.

[0112] The association information can be information representing the association relationship between each content region in the set of target content regions and the set of identifiers.

[0113] There are several ways to associate the set identifier with each content area in the target content area set. For example, the content area identifier of the content area can be obtained, and based on the content area identifier, a mapping relationship between the set identifier and each content area in the target content area set can be constructed and stored in a preset mapping relationship set. According to the mapping relationship, the set identifier and the content area identifier of each content area in the target content area set can be stored in a preset identifier database. The preset mapping relationship set and the preset identifier database can be used as the association information of the content area.

[0114] The content area identifier can be the identification information corresponding to a content area, used to uniquely identify a content area. For example, it can be an ad slot ID, which can uniquely identify an ad slot. The mapping relationship can be a relationship representing the correspondence between the set identifier and each content area in the corresponding target content area set. The preset mapping relationship set can be a pre-defined set used to store the mapping relationships between the set identifier and each content area in the target content area set. The preset identifier database can be a pre-defined database used to store the set identifier and the content area identifier of each content area in the corresponding target content area set.

[0115] There are several ways to construct a mapping relationship between the set identifier and each content region in the target content region set based on the content region identifier, and store the mapping relationship in a preset mapping relationship set. For example, in order to improve the subsequent query speed and query efficiency, an inverted index can be used to construct a mapping relationship between the set identifier and the content region identifier corresponding to each content region in the target content region set, so that the preset mapping relationship set can be obtained based on the constructed inverted index.

[0116] Optionally, after constructing the mapping relationship between the set identifier and each content region in the target content region set, the current content request log can be retrieved to update this association information. For details, please refer to... Figure 5 , Figure 5 Another specific flowchart of a content processing method provided in this application embodiment can be obtained by acquiring the current content request log, determining the current target content region set based on the current content request log, updating the associated information based on the current target content region set, and obtaining the updated associated information.

[0117] Among them, the current content request log is the content request log obtained at present, the current target content area set can be the target content area set determined based on the current content request, and the updated association information can be the association information obtained after updating the association information based on the current target content set.

[0118] There are several ways to update the associated information based on the current target content region set. For example, you can query the historical set identifier that matches the current content region identifier corresponding to the content region in the current target content region set in the preset mapping relationship set. When the historical set identifier is found, the current content region identifier is added to the associated information based on the historical set identifier to obtain the updated associated information. When the historical set identifier is not found, the current set identifier corresponding to the current target content region set is generated, and the current content region identifier is added to the associated information based on the current set identifier to obtain the updated associated information.

[0119] The historical set identifier can be a set identifier that matches the current content region identifier in the current target content region set within the preset mapping relationship set, and the current set identifier can be the set identifier corresponding to the current target content region set.

[0120] There are several ways to query historical set identifiers that match the current content region identifier corresponding to the content region in the current target content region set within the preset mapping relationship set. For example, since there is a mapping relationship between the set identifier and each content region in the corresponding target content region set in the association information, it is also possible to query the content region identifier that is the same as the current content region identifier corresponding to the content region in the current target content region set within the preset mapping relationship set. Thus, based on the same content region identifier, it is possible to query the historical set identifier that matches the current content region identifier corresponding to the content region in the current target content region set within the preset mapping relationship set.

[0121] When the historical set identifier is found, there are several ways to add the current content region identifier to the associated information based on that historical set identifier. For example, please refer to [link / reference]. Figure 5 Specifically, when the current content region identifier is found in the preset mapping relationship set (i.e., when the historical set identifier is found), the current content region identifier can be added to the corresponding position of the historical set identifier in the preset mapping relationship set, and the current content region identifier can also be added to the preset identifier database. Optional, please refer to [further details]. Figure 5 Alternatively, when a content region identifier in the preset mapping relationship set matches the current content region identifier in the current target content region set, the current content region identifier corresponding to each content region in the current target content region set is added to the corresponding position of the historical set identifier in the preset mapping relationship set. Furthermore, the current content region identifier corresponding to each content region in the current target content region set can be merged into the preset identifier database. If duplicate content region identifiers exist in the preset identifier database, they can be deleted. Therefore, updated association information can be obtained based on the updated preset mapping relationship set and the updated preset identifier database.

[0122] When the historical set identifier is not found, there are several ways to add the current content region identifier to the associated information based on the current set identifier. For example, based on the current content region identifier, a current mapping relationship between the current set identifier and each content region in the current target content region set can be constructed, and the current mapping relationship can be added to the preset mapping relationship set to obtain an updated preset mapping relationship set. Based on the current mapping relationship, the current set identifier and the current content region identifier of each content region in the current target content region set can be added to the preset identifier database to obtain an updated preset identifier database. The updated preset mapping relationship set and the updated preset identifier database can be used as the updated associated information.

[0123] The current mapping relationship can be the mapping relationship between the current set identifier and each content area in the current target content area set. The updated preset mapping relationship set can be the preset mapping relationship set updated based on the current mapping relationship. The updated preset identifier database can be the preset identifier database obtained by adding the current set identifier and the current content area identifier of each content area in the current target content area set to the preset identifier database based on the current mapping relationship. The updated association information can be obtained based on the updated preset mapping relationship set and the updated preset identifier database.

[0124] In step 105, the content request to be processed is processed based on the association information of the content area.

[0125] The pending content request can be a content request that has been obtained and is waiting to be processed.

[0126] There are several ways to process the content request based on the association information of the content area. For example, when a content request is received, the identifier of the content area to be processed corresponding to the content request can be obtained. Based on the identifier of the content area to be processed and the association information, the content request can be verified. Based on the verification result, the target content corresponding to the content request can be returned.

[0127] The identifier of the content area to be processed can be the content area identifier corresponding to the content area to be processed in the content request to be processed. The verification result can be the result of verifying the content request to be processed based on the identifier of the content area to be processed and the associated information. The target content can be the content corresponding to the content request to be processed.

[0128] There are several ways to verify the content request based on the content region identifier and the associated information. For example, the target set identifier corresponding to the content region identifier can be queried in the associated information, the reference resource information corresponding to the target set identifier and the target resource information corresponding to the content request can be obtained, and the target resource information can be matched based on the reference resource information.

[0129] The target set identifier can be the set identifier corresponding to the content area identifier to be processed. The reference resource information can be the resource information determined based on the average value of the resource information obtained by the waterfall corresponding to the target set identifier in the historical content request process. The resource information can be information that characterizes the value of the content, such as the target price (ecpm) corresponding to the advertisement. Correspondingly, the reference resource information can be the historical average price corresponding to a content area in a certain waterfall. The target resource information can be the expected resource information set by the developer for the content area corresponding to the content request to be processed.

[0130] Therefore, the resource information range can be determined based on the reference resource information corresponding to the target set identifier. For example, assuming the reference resource information corresponding to the target set identifier is 15, the corresponding resource information range can be determined as [13, 17]. When the target resource information corresponding to the content request to be processed is within this resource information range, the content request to be processed can be considered a reasonable content request. Thus, the reference resource information corresponding to the target set identifier can be used to verify whether the target resource information corresponding to the content request to be processed is within a reasonable resource information range of the waterfall flow corresponding to the content request to be processed. When the target resource information corresponding to the content request to be processed is within a reasonable resource information range of the waterfall flow corresponding to the content request to be processed, it indicates that the target resource information matches the reference resource information, and the content request to be processed can be responded to, thereby returning the target content corresponding to the content request to be processed to the corresponding client.

[0131] When the target resource information corresponding to the pending content request is not within the reasonable resource information range of the waterfall flow corresponding to the pending content request, that is, the target resource information corresponding to the pending content request is unreasonable resource information, it indicates that the target resource information does not match the reference resource information. In this case, the pending content request can be blocked to reduce the number of content requests corresponding to unreasonable content areas in the same waterfall flow.

[0132] In practical applications, based on the waterfall layout mechanism, developers can achieve higher revenue by setting up more content areas to explore higher-value advertising content. Therefore, developers tend to create more ad slots, resulting in dozens or even hundreds of content requests for a single ad exposure, leading to significant waste of server resources. The content processing method provided in this application can accurately obtain the relationship between content areas, corresponding physical ad slots, and the waterfall layout. This allows for the determination of the waterfall layout corresponding to each content request, filtering out content requests with unreasonable target resource information. It also effectively eliminates the incentive for developers to create a large number of content areas, thereby reducing the number of content requests and improving server resource utilization. Furthermore, it avoids the phenomenon of large differences in the eCPM (eligible click-through rate) of ad requests corresponding to the same waterfall layout content area, thus improving the accuracy and stability of content prediction. In addition, determining the relationship between content areas, corresponding physical ad slots, and the waterfall layout helps improve the accuracy of prediction models in predicting content (e.g., predicting click-through rate, conversion rate, etc.), further improving the accuracy and efficiency of content processing.

[0133] In one embodiment, upon receiving a request for content to be processed, the content region identifier corresponding to the request can be obtained. Then, based on this association information, a target set identifier corresponding to the content region identifier can be queried, and reference resource information corresponding to the target set identifier can be obtained. Based on this reference resource information, matching target content can be filtered from the content to be returned, and the target content can be returned to the client corresponding to the request. The content to be returned can be content provided by a content provider. In this way, upon receiving a request for content to be processed, the matching content can be returned directly, avoiding the resource waste caused by multiple content requests and improving the efficiency of content processing.

[0134] As described above, this embodiment of the application obtains historical content request logs and identifies the content region corresponding to each historical content request in the historical content request logs; aggregates the content regions according to the attribute information of the historical content requests to obtain at least one set of content regions; merges the content region sets based on the set relationships between the content region sets to obtain at least one set of target content regions, and generates a set identifier for the target content region set; associates the set identifier with each content region in the target content region set to obtain the association information of the content regions; and processes the content request to be processed based on the association information of the content regions. In this way, the association relationship between content regions in the same set of target content regions is extracted through historical content request logs, and multiple virtual ad slots corresponding to actual physical ad slots are represented based on multiple content regions in the set of target content regions. This yields the association relationship between each content region and its corresponding physical ad slot, and the content request to be processed is then processed based on the association information between the content region and its corresponding physical ad slot. This improves the accuracy of the obtained relationship between the content region and its corresponding physical ad slot, thereby increasing the efficiency of content processing.

[0135] Based on the method described in the above embodiments, the following examples will provide further detailed explanations.

[0136] In this embodiment, the content processing device will be specifically integrated into a computer device as an example for explanation. The content processing method will be specifically described using a server as the executing entity. For details, please refer to... Figure 5 , Figure 5 This is a schematic diagram illustrating the specific process of a content processing method provided in an embodiment of this application.

[0137] For a better description of the embodiments of this application, please refer to Figure 6 .like Figure 6 As shown, Figure 6 Another flowchart illustrating the content processing method provided in this application embodiment. The specific process is as follows:

[0138] In step 201, the server obtains historical content request logs and identifies the content area corresponding to each historical content request in the historical content request logs.

[0139] In this application, the embodiment is described in detail using the content as an advertisement and the content area as an advertisement slot as an example.

[0140] There are several ways a server can identify the content area corresponding to each historical content request in the historical content request log. For example, please refer to [reference needed]. Figure 3 The server can parse the historical content request logs and, based on the parsing results, obtain the log corresponding to each historical content request from the historical content request logs. Thus, the content area corresponding to each historical content request can be extracted from the log corresponding to each historical content request.

[0141] In step 202, the server obtains the attribute information of the historical content request, identifies the time information corresponding to the historical content request in the attribute information, obtains the object identifier corresponding to the historical content request, classifies the content area according to the object identifier, and obtains at least one candidate content area set.

[0142] In practical applications, each client makes tiered requests within the advertising system via a waterfall mechanism. Therefore, based on the waterfall advertising request mechanism, historical content requests triggered by the same client within a certain time period can be considered as content requests triggered by ad slots within the same physical ad slot. Consequently, content areas whose time information falls within a preset time interval can be filtered out from the candidate content area set corresponding to each object identifier, thus obtaining at least one initial content area set.

[0143] There are several ways for the server to classify the content region based on the object identifier. For example, suppose content regions a, b, c, d, and e are identified from the historical content request logs. The object identifiers for content regions a, b, and c are Y, d and e are X, and e is Z. Then, the content regions can be classified according to the object identifiers to obtain the candidate content region set (a, d) for object identifier X, the candidate content region set (b, c) for object identifier Y, and the candidate content region set (e) for object identifier Z.

[0144] In step 203, the server filters out the target content area where the time information is within a preset time interval from the candidate content area set to obtain the initial content area set.

[0145] There are several ways for the server to filter the target content area from the candidate content area set, where the time information falls within a preset time interval. For example, please refer to [link / reference needed]. Figure 3 The server can employ a time-based window mechanism to aggregate content regions within the candidate content region set. Specifically, a sliding time window can be constructed based on a preset time interval. This sliding time window can filter out content regions in each candidate content region set whose time information falls within the preset time interval, resulting in an initial content region set. For example, assuming the preset time interval is t, the time window can be set to t, and assuming the current time is T, then when the time information of historical content requests corresponding to content regions in the candidate content region set of the same object identifier falls within the time interval [T, T+t], they can be considered to belong to the same waterfall flow content region and integrated into the same initial content region set.

[0146] Optionally, the server may classify the content area according to the object identifier and then filter out the target content area whose time information is within a preset time interval from the candidate content area set. Alternatively, it may classify the content area according to the object identifier after filtering out the content area whose time information is within the preset time interval. This application does not limit this.

[0147] In step 204, the server filters out abnormal content regions from the content regions of the initial content region set based on the content region attributes corresponding to the content region, and deletes the abnormal content regions from the initial content region set to obtain a content region set.

[0148] In this embodiment, a physical ad slot refers to the actual ad slot corresponding to a waterfall layout. Specifically, different physical ad slots can be distinguished based on dimensions such as physical location and time. For example, ad slots located in different physical locations on the actual page can be considered different physical ad slots based on physical location. When a physical location on the page is split into two or more waterfall layouts, each waterfall layout in that physical location can be associated with a different physical ad slot based on the time dimension. That is, an ad slot in one physical location can be divided into multiple different physical ad slots. For example, different refreshes of a waterfall layout in one physical location can be associated with different physical ad slots. In this way, each physical ad slot can correspond to one waterfall layout, and the content area of ​​the same waterfall layout can be mapped to the corresponding physical ad slot to obtain the relationship between the content area and the corresponding physical ad slot, thereby improving the efficiency of content processing.

[0149] Since content areas within the same waterfall layout share the same attributes, after the server selects the target content area whose time information falls within a preset time interval from the candidate content area set, it can use the content area attributes to filter out content areas that do not belong to the same waterfall layout. Thus, based on the content area attributes and the majority principle, the server can filter out abnormal content areas in the initial content area set whose attributes differ from other content areas. These abnormal content areas can then be deleted from the initial content area set, resulting in the final content area set.

[0150] In step 205, the server combines the content regions in each content region set based on a preset step size to obtain combined content regions. Based on the combined content regions, it constructs an undirected graph corresponding to each content region set, generates at least one connected subgraph based on the undirected graph, and combines the content regions corresponding to the connected subgraph to obtain a target content region set, and generates a set identifier for the target content region set.

[0151] There are several ways for the server to combine the content regions in each content region set based on a preset step size. For example, the preset step size can be set to 2, so that the server can combine any two content regions in each content region set based on the preset step size, thereby obtaining the combined content region in each content region set, and an undirected edge can be formed based on the two content regions.

[0152] After the server combines the content regions in each content region set based on a preset step size, it can construct an undirected graph corresponding to each content region set based on the combined content regions. In other words, each content region set corresponds to an undirected graph, and each content region in the content region set is a vertex in the undirected graph. Each combination of two content regions can form an undirected edge in the undirected graph.

[0153] After the server constructs an undirected graph corresponding to each set of content regions based on the combined content regions, it can generate at least one connected subgraph based on the undirected graph. Each connected subgraph corresponds to a waterfall flow, and each vertex in the connected subgraph is a content region in the same waterfall flow. In this way, the server can combine the content regions corresponding to each vertex in the connected subgraph to obtain the target content region set.

[0154] For example, please refer to Figure 4We can assume the existence of initial content sets k, l, m, and n. Initial content set k includes (content region 1, content region 2, content region 3), initial content set l includes (content region 2, content region 4, content region 8), initial content set m includes (content region 5, content region 6, content region 7), and initial content set n includes (content region 6, content region 9). Assuming a preset step size of 2, the server can combine the content regions in each content region set based on the preset step size, resulting in the combined content regions corresponding to initial content set k as [(content region 1, content region 2), (content region 2, content region 3)], and the combined content regions corresponding to initial content set l as [(content region 1, content region 2), (content region 2, content region 3)], and [(content region 1, content region 2), content region 3], respectively. Given content regions 2, 4, 8, and 9, the combined content regions corresponding to the initial content set m are [(content region 5, 6), 7, 6, 9). The server can construct an undirected graph corresponding to each content region set based on these combined content regions. This allows the server to connect all connected vertices in the undirected graph, thus generating connected subgraphs A and B. Referring to the graph, the server can combine the content regions corresponding to each connected subgraph to obtain the target content region set (k, l) for connected subgraph A and the target content region set (m, n) for connected subgraph B.

[0155] After merging the content region sets based on the set relationships between them, the server can generate a set identifier for the target content region set. There are several ways for the server to generate the set identifier for the target content region set. For example, the server can generate the set identifier for the target content region set based on the time information of the historical content request logs corresponding to the target content region set and the merging time of the target content region set. Alternatively, the snowflake algorithm can be used to generate a corresponding set identifier for each target content region set, so as to uniquely identify a target content region set based on the set identifier.

[0156] In step 206, the server obtains the content region identifier of the content region, constructs a mapping relationship between the set identifier and each content region in the target content region set based on the content region identifier, and stores the mapping relationship in a preset mapping relationship set.

[0157] There are several ways for the server to construct a mapping relationship between the set identifier and each content region in the target content region set based on the content region identifier, and store the mapping relationship in a preset mapping relationship set. For example, in order to improve the subsequent query speed and query efficiency, the server can use an inverted table to construct a mapping relationship between the set identifier and the content region identifier corresponding to each content region in the target content region set, so that the preset mapping relationship set can be obtained based on the constructed inverted table.

[0158] In step 207, the server stores the set identifier and the content area identifier of each content area in the target content area set into a preset identifier database according to the mapping relationship, and uses the preset mapping relationship set and the preset identifier database as the association information of the content area.

[0159] Optionally, after the server stores the set identifier and the content area identifier of each content area in the target content area set into a preset identifier database according to the mapping relationship to obtain the association information, it can obtain the current content request log, determine the current target content area set based on the current content request log, and update the association information based on the current target content area set to obtain the updated association information.

[0160] In step 208, when a request for content to be processed is received, the server obtains the identifier of the content region to be processed corresponding to the request, queries the target set identifier corresponding to the identifier of the content region to be processed in the associated information, and obtains the reference resource information corresponding to the target set identifier and the target resource information corresponding to the request for content to be processed.

[0161] Specifically, the server can query the target set identifier corresponding to the content region identifier corresponding to the content request in the associated information's preset mapping relationship set. Optionally, the server can query the content region identifier with the same identifier in the associated information's preset mapping relationship set, and then find the set identifier corresponding to the content region identifier based on the mapping relationship stored in the preset mapping relationship set, thereby obtaining the target set identifier.

[0162] In step 209, the server matches the target resource information based on the reference resource information. When the target resource information matches the reference resource information, the server returns the target content corresponding to the content to be processed request.

[0163] The resource information range can be determined based on the reference resource information corresponding to the target set identifier. For example, assuming the reference resource information corresponding to the target set identifier is 15, the corresponding resource information range can be determined as [13, 17]. When the target resource information corresponding to the content request to be processed falls within this resource information range, the content request to be processed can be considered a reasonable content request. Therefore, the reference resource information corresponding to the target set identifier can be used to verify whether the target resource information corresponding to the content request to be processed falls within a reasonable resource information range of the waterfall flow corresponding to the content request to be processed. When the target resource information corresponding to the content request to be processed falls within a reasonable resource information range of the waterfall flow corresponding to the content request to be processed, it indicates that the target resource information matches the reference resource information. The server can then respond to the content request to be processed, thereby returning the target content corresponding to the content request to the corresponding client.

[0164] When the target resource information corresponding to the pending content request is not within the reasonable resource information range of the waterfall flow corresponding to the pending content request, that is, the target resource information corresponding to the pending content request is unreasonable resource information, indicating that the target resource information does not match the reference resource information, the server can block the pending content request to reduce the content requests corresponding to unreasonable content areas in the same waterfall flow.

[0165] In practical applications, based on the waterfall layout mechanism, developers can achieve higher revenue by setting up more content areas to explore higher-value advertising content. Therefore, developers tend to create more ad slots, resulting in dozens or even hundreds of content requests for a single ad exposure, leading to significant waste of server resources. The content processing method provided in this application can accurately obtain the relationship between content areas, corresponding physical ad slots, and the waterfall layout. This allows for the determination of the waterfall layout corresponding to each content request, filtering out content requests with unreasonable target resource information. It also effectively eliminates the incentive for developers to create a large number of content areas, thereby reducing the number of content requests and improving server resource utilization. Furthermore, it avoids the phenomenon of large differences in the eCPM (eligible click-through rate) of ad requests corresponding to the same waterfall layout content area, thus improving the accuracy and stability of content prediction. In addition, determining the relationship between content areas, corresponding physical ad slots, and the waterfall layout helps improve the accuracy of prediction models in predicting content (e.g., predicting click-through rate, conversion rate, etc.), further improving the accuracy and efficiency of content processing.

[0166] As described above, this embodiment of the application obtains historical content request logs through a server and identifies the content region corresponding to each historical content request in the historical content request logs; the server obtains the attribute information of the historical content request, identifies the time information corresponding to the historical content request in the attribute information, obtains the object identifier corresponding to the historical content request, classifies the content region according to the object identifier, and obtains at least one candidate content region set; the server filters out target content regions whose time information is within a preset time interval from the candidate content region set, and obtains an initial content region set; the server filters out abnormal content regions from the content regions of the initial content region set based on the content region attributes corresponding to the content region, deletes the abnormal content regions from the initial content region set, and obtains a content region set; the server combines the content regions in each content region set according to a preset step size, obtains a combined content region, constructs an undirected graph corresponding to each content region set based on the combined content region, generates at least one connected subgraph based on the undirected graph, and connects the connected subgraph... The server combines the content regions corresponding to the image to obtain a target content region set and generates a set identifier for the target content region set. The server obtains the content region identifier of the content region, constructs a mapping relationship between the set identifier and each content region in the target content region set based on the content region identifier, and stores the mapping relationship in a preset mapping relationship set. The server stores the set identifier and the content region identifier of each content region in the target content region set in a preset identifier database according to the mapping relationship, and uses the preset mapping relationship set and the preset identifier database as the association information of the content region. When a content request to be processed is received, the server obtains the content region identifier corresponding to the content request to be processed, queries the target set identifier corresponding to the content region identifier to be processed in the association information, obtains the reference resource information corresponding to the target set identifier and the target resource information corresponding to the content request to be processed. The server matches the target resource information based on the reference resource information. When the target resource information matches the reference resource information, the server returns the target content corresponding to the content request to be processed.Therefore, by extracting the relationships between content regions within the same target content region set through historical content request logs, and representing multiple virtual ad slots corresponding to actual physical ad slots based on multiple content regions in the target content region set, the relationship between each content region and its corresponding physical ad slot is obtained. This improves the accuracy of the obtained relationship between content regions and their corresponding physical ad slots. At the same time, the relationship information between content regions and their corresponding physical ad slots can be used to verify the content requests to be processed. Based on the verification results, content requests with unreasonable target resource information are filtered out, which can effectively eliminate the incentive for developers to create a large number of content regions, thereby effectively reducing the number of content requests, improving the utilization of server resources, and enhancing the efficiency of content processing.

[0167] To better implement the above methods, embodiments of the present invention also provide a content processing apparatus that can be integrated into a computer device, which can be a server.

[0168] For example, such as Figure 7 The diagram shown is a structural schematic of a content processing device provided in an embodiment of this application. The content processing device may include an acquisition unit 301, an aggregation unit 302, a merging unit 303, an association unit 304, and a processing unit 305, as follows:

[0169] The acquisition unit 301 is used to acquire historical content request logs and identify the content area corresponding to each historical content request in the historical content request logs.

[0170] Aggregation unit 302 is used to aggregate the content area according to the attribute information of the historical content request to obtain at least one set of content areas;

[0171] The merging unit 303 is used to merge the content region set based on the set relationship between the content region sets to obtain at least one target content region set, and generate a set identifier for the target content region set.

[0172] The association unit 304 is used to associate the set identifier with each content area in the target content area set to obtain the association information of the content area;

[0173] The processing unit 305 is used to process the content request to be processed based on the association information of the content area.

[0174] In one embodiment, the aggregation unit 302 includes:

[0175] An aggregation subunit is used to aggregate the content area based on the attribute information of the historical content request to obtain at least one initial set of content areas.

[0176] The abnormal content region filtering subunit is used to filter out abnormal content regions from the content regions of the initial content region set based on the content region attributes corresponding to the content region.

[0177] The delete sub-unit is used to delete the abnormal content region from the initial content region set, thus obtaining the content region set.

[0178] In one embodiment, the polymer subunit includes:

[0179] The attribute information acquisition module is used to obtain the attribute information of the historical content request;

[0180] The time information recognition module is used to identify the time information corresponding to the historical content request in the attribute information;

[0181] The content region set extraction module is used to extract at least one initial content region set from the content region based on the time information.

[0182] In one embodiment, the content region set extraction module includes:

[0183] The object identifier retrieval submodule is used to retrieve the object identifier corresponding to the historical content request;

[0184] The classification submodule is used to classify the content region according to the object identifier to obtain at least one set of candidate content regions;

[0185] The time information filtering submodule is used to filter out target content areas whose time information falls within a preset time interval from the candidate content area set, thus obtaining an initial content area set.

[0186] In one embodiment, the merging unit 303 includes:

[0187] The content area combination subunit is used to combine the content areas in each content area set based on a preset step size to obtain the combined content area.

[0188] An undirected graph construction subunit is used to construct an undirected graph corresponding to each set of content regions based on the combined content regions.

[0189] The connected subgraph combination subunit is used to generate at least one connected subgraph based on the undirected graph, and combine the content regions corresponding to the connected subgraph to obtain a set of target content regions.

[0190] In one embodiment, the association unit 304 includes:

[0191] The content region identifier acquisition sub-unit is used to acquire the content region identifier of the content region.

[0192] The mapping relationship construction subunit is used to construct a mapping relationship between the set identifier and each content region in the target content region set based on the content region identifier, and store the mapping relationship in a preset mapping relationship set;

[0193] A storage subunit is used to store the set identifier and the content area identifier of each content area in the target content area set into a preset identifier database according to the mapping relationship;

[0194] The assignment subunit is used to use the preset mapping relationship set and the preset identifier database as the association information of the content area.

[0195] In one embodiment, the content processing apparatus further includes:

[0196] The current target content region set determination unit is used to obtain the current content request log and determine the current target content region set based on the current content request log;

[0197] The associated information update unit is used to update the associated information based on the current target content area set to obtain the updated associated information.

[0198] In one embodiment, the association information update unit includes:

[0199] The historical set identifier query subunit is used to query the historical set identifier that matches the current content area identifier corresponding to the content area in the current target content area set in the preset mapping relationship set.

[0200] The first related information update subunit is used to add the current content area identifier to the related information based on the historical set identifier when the historical set identifier is found, so as to obtain the updated related information;

[0201] The second association information update subunit is used to generate the current set identifier corresponding to the current target content area set when the current set identifier is not found in the historical set identifier, and add the current content area identifier to the association information according to the current set identifier to obtain the updated association information.

[0202] In one embodiment, the second association information update subunit includes:

[0203] The preset mapping relationship set update module is used to construct the current mapping relationship between the current set identifier and each content region in the current target content region set based on the current content region identifier, and add the current mapping relationship to the preset mapping relationship set to obtain the updated preset mapping relationship set;

[0204] The preset identifier database update module is used to add the current set identifier and the current content area identifier of each content area in the current target content area set to the preset identifier database according to the current mapping relationship, so as to obtain the updated preset identifier database.

[0205] The update assignment module is used to use the updated preset mapping relationship set and the updated preset identifier database as the updated association information.

[0206] In one embodiment, the processing unit 305 includes:

[0207] The pending content area identifier acquisition subunit is used to acquire the pending content area identifier corresponding to the pending content request when a pending content request is received.

[0208] The verification subunit is used to verify the request for the content to be processed based on the identifier of the content region to be processed and the associated information.

[0209] The content return sub-unit is used to return the target content corresponding to the request for the content to be processed, based on the verification result.

[0210] In one embodiment, the verification subunit is used for:

[0211] Search the associated information for the target set identifier corresponding to the region identifier of the content to be processed;

[0212] Obtain the reference resource information corresponding to the target set identifier and the target resource information corresponding to the content request to be processed;

[0213] Based on this reference resource information, the target resource information is matched;

[0214] This content returns a sub-unit, used for:

[0215] When the target resource information matches the reference resource information, the target content corresponding to the content to be processed request is returned.

[0216] In practice, each of the above units can be implemented as an independent entity or can be arbitrarily combined to be implemented as the same or several entities. For the specific implementation of each of the above units, please refer to the previous method embodiments, which will not be repeated here.

[0217] As can be seen from the above, in this embodiment of the application, the acquisition unit 301 acquires historical content request logs and identifies the content area corresponding to each historical content request in the historical content request logs; the aggregation unit 302 aggregates the content areas according to the attribute information of the historical content requests to obtain at least one set of content areas; the merging unit 303 merges the content area sets based on the set relationships between the content area sets to obtain at least one target content area set and generates a set identifier for the target content area set; the association unit 304 associates the set identifier with each content area in the target content area set to obtain the association information of the content area; and the processing unit 305 processes the content request to be processed based on the association information of the content area. In this way, the relationship between content regions in the same target content region set is extracted by using historical content request logs, and multiple virtual ad positions corresponding to the actual physical ad positions are represented by multiple content regions in the target content region set. Thus, the relationship between each content region and the corresponding physical ad position is obtained. Based on the relationship information between the content region and the corresponding physical ad position, the content request to be processed is processed, thereby improving the accuracy of the obtained relationship between the content region and the corresponding physical ad position and thus improving the efficiency of content processing.

[0218] This application also provides a computer device, such as... Figure 8 As shown, it illustrates a structural diagram of a computer device involved in an embodiment of this application. This computer device may be a server, specifically:

[0219] The computer device may include components such as a processor 401 with one or more processing cores, a memory 402 with one or more computer-readable storage media, a power supply 403, and an input unit 404. Those skilled in the art will understand that... Figure 8 The computer device structure shown does not constitute a limitation on the computer device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0220] Processor 401 is the control center of the computer device, connecting various parts of the computer device through various interfaces and lines. It performs various functions and processes data by running or executing software programs and / or modules stored in memory 402, and by calling data stored in memory 402. Optionally, processor 401 may include one or more processing cores; preferably, processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into processor 401.

[0221] The memory 402 can be used to store software programs and modules. The processor 401 executes various functional applications and content processing by running the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.

[0222] The computer device also includes a power supply 403 that supplies power to the various components. Preferably, the power supply 403 can be logically connected to the processor 401 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 403 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0223] The computer device may also include an input unit 404, which can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0224] Although not shown, the computer device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 401 in the computer device loads the executable files corresponding to the processes of one or more applications into the memory 402 according to the following instructions, and the processor 401 runs the applications stored in the memory 402 to realize various functions, as follows:

[0225] Retrieve historical content request logs and identify the content region corresponding to each historical content request in the logs; aggregate the content regions based on the attribute information of the historical content requests to obtain at least one set of content regions; merge the content region sets based on the set relationships between them to obtain at least one set of target content regions and generate a set identifier for the target content region set; associate the set identifier with each content region in the target content region set to obtain the association information of the content regions; process the content requests to be processed based on the association information of the content regions.

[0226] The specific implementation of each of the above operations can be found in the preceding embodiments, and will not be repeated here. It should be noted that the computer device provided in this application embodiment and the content processing method in the above embodiments belong to the same concept, and its specific implementation process can be found in the above method embodiments, and will not be repeated here.

[0227] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0228] Therefore, embodiments of this application provide a computer-readable storage medium storing a plurality of instructions that can be loaded by a processor to execute steps in any of the content processing methods provided in embodiments of this application. For example, the instructions can execute the following steps:

[0229] Retrieve historical content request logs and identify the content region corresponding to each historical content request in the logs; aggregate the content regions based on the attribute information of the historical content requests to obtain at least one set of content regions; merge the content region sets based on the set relationships between them to obtain at least one set of target content regions and generate a set identifier for the target content region set; associate the set identifier with each content region in the target content region set to obtain the association information of the content regions; process the content requests to be processed based on the association information of the content regions.

[0230] The computer-readable storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0231] Since the instructions stored in the computer-readable storage medium can execute the steps of any of the content processing methods provided in the embodiments of this application, the beneficial effects that any of the content processing methods provided in the embodiments of this application can achieve can be realized, as detailed in the preceding embodiments, and will not be repeated here.

[0232] According to one aspect of this application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various optional implementations of the above embodiments.

[0233] The foregoing has provided a detailed description of a content processing method, apparatus, and computer-readable storage medium provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A content processing method, characterized in that, include: Obtain historical content request logs and identify the content area corresponding to each historical content request in the historical content request logs; Based on the attribute information of the historical content requests, the content regions are aggregated to obtain at least one set of content regions; Based on the set relationships between the content region sets, the content region sets are merged to obtain at least one target content region set, and a set identifier for the target content region set is generated; Associating the set identifier with each content region in the target content region set yields the association information of the content regions; Based on the association information of the content area, the request for the content to be processed is processed.

2. The content processing method as described in claim 1, characterized in that, The step of aggregating the content regions based on the attribute information of the historical content requests to obtain at least one set of content regions includes: Based on the attribute information of the historical content requests, the content areas are aggregated to obtain at least one initial set of content areas; Based on the content region attributes corresponding to the content region, abnormal content regions are filtered out from the content regions of the initial content region set. The abnormal content regions are deleted from the initial content region set to obtain the content region set.

3. The content processing method as described in claim 2, characterized in that, The aggregation based on the attribute information requested by the historical content in the content area to obtain at least one initial set of content areas includes: Obtain the attribute information of the requested historical content; The time information corresponding to the historical content request is identified from the attribute information; Based on the time information, at least one initial content region set is extracted from the content region.

4. The content processing method as described in claim 3, characterized in that, Extracting at least one initial set of content regions from the content region based on the time information includes: Obtain the object identifier corresponding to the historical content request; The content regions are classified according to the object identifiers to obtain at least one set of candidate content regions; Target content regions whose time information falls within a preset time interval are selected from the candidate content region set to obtain an initial content region set.

5. The content processing method as described in claim 1, characterized in that, The step of merging the content region sets based on the set relationships between the content region sets to obtain at least one target content region set includes: Based on a preset step size, the content regions in each content region set are combined to obtain the combined content region; Construct an undirected graph corresponding to each set of content regions based on the combined content regions; At least one connected subgraph is generated based on the undirected graph, and the content regions corresponding to the connected subgraphs are combined to obtain a set of target content regions.

6. The content processing method as described in claim 1, characterized in that, The step of associating the set identifier with each content region in the target content region set to obtain the association information of the content region includes: Obtain the content region identifier of the content region; Based on the content region identifier, a mapping relationship is constructed between the set identifier and each content region in the target content region set, and the mapping relationship is stored in a preset mapping relationship set; Based on the mapping relationship, the set identifier and the content region identifier of each content region in the target content region set are stored in a preset identifier database; The preset mapping relationship set and the preset identifier database are used as the association information of the content area.

7. The content processing method as described in claim 6, characterized in that, After using the preset mapping relationship set and the preset identifier database as the association information of the content area, the method further includes: Obtain the current content request log, and determine the current target content region set based on the current content request log; The associated information is updated based on the current target content region set to obtain the updated associated information.

8. The content processing method as described in claim 7, characterized in that, The step of updating the associated information based on the current target content region set to obtain the updated associated information includes: Query the preset mapping relationship set for historical set identifiers that match the current content region identifier corresponding to the content region in the current target content region set; When the historical set identifier is found, the current content region identifier is added to the associated information based on the historical set identifier to obtain the updated associated information; When the historical set identifier is not found, a current set identifier corresponding to the current target content region set is generated, and the current content region identifier is added to the association information according to the current set identifier to obtain the updated association information.

9. The content processing method as described in claim 8, characterized in that, The step of adding the current content region identifier to the associated information based on the current set identifier to obtain the updated associated information includes: Based on the current content region identifier, construct the current mapping relationship between the current set identifier and each content region in the current target content region set, and add the current mapping relationship to the preset mapping relationship set to obtain the updated preset mapping relationship set; Based on the current mapping relationship, the current set identifier and the current content region identifier of each content region in the current target content region set are added to the preset identifier database to obtain the updated preset identifier database; The updated preset mapping relationship set and the updated preset identifier database are used as the updated association information.

10. The content processing method according to any one of claims 1 to 9, characterized in that, The process of handling the content request based on the association information of the content region includes: When a request for content to be processed is received, the identifier of the content area to be processed corresponding to the request is obtained; The request for the content to be processed is verified based on the identifier of the content area to be processed and the associated information; Based on the verification result, the target content corresponding to the requested content to be processed is returned.

11. The content processing method as described in claim 10, characterized in that, The step of verifying the content request to be processed based on the region identifier of the content to be processed and the associated information includes: Query the target set identifier corresponding to the identifier of the content region to be processed in the associated information; Obtain the reference resource information corresponding to the target set identifier and the target resource information corresponding to the content request to be processed; Based on the reference resource information, the target resource information is matched; The step of returning the target content corresponding to the content request to be processed based on the verification result includes: When the target resource information matches the reference resource information, the target content corresponding to the content request to be processed is returned.

12. A content processing apparatus, characterized in that, include: The acquisition unit is used to acquire historical content request logs and identify the content area corresponding to each historical content request in the historical content request logs. An aggregation unit is used to aggregate the content regions based on the attribute information of the historical content requests to obtain at least one set of content regions. The merging unit is used to merge the content region sets based on the set relationships between the content region sets to obtain at least one target content region set, and generate a set identifier for the target content region set; The association unit is used to associate the set identifier with each content region in the target content region set to obtain the association information of the content region; The processing unit is used to process the content request to be processed based on the association information of the content area.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a plurality of instructions adapted for loading by a processor to perform the steps of the content processing method according to any one of claims 1 to 11.

14. A computer device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the content processing method according to any one of claims 1 to 11.

15. A computer program product, characterized in that, The computer program product includes a computer program / instruction that, when executed by a processor, implements the steps of the content processing method according to any one of claims 1 to 11.

Images