Advertisement request processing method, apparatus, device, and storage medium

Abstract

Embodiments of the present application disclose an advertisement request processing method and device, equipment and a storage medium, which can be applied to the fields of computer technology, block chain technology and cloud computing technology. The method comprises the following steps: obtaining a target advertisement request, and determining a request identifier of the target advertisement request; in response to the target advertisement request being a repeated advertisement request, determining a time interval between a current visit and a previous visit of the target advertisement request; in response to the time interval between the current visit and the previous visit of the target advertisement request being less than a preset time interval, and the first cache space including advertisement information associated with the request identifier, obtaining at least one historical advertisement list generated in a previous processing process of the target advertisement request from a second cache space; determining target advertisement information based on the at least one historical advertisement list, and returning the target advertisement information. By using the embodiments of the present application, the processing efficiency of the advertisement request can be improved, the computing resources can be saved, and the applicability is high.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to an advertising request processing method, apparatus, device, and storage medium. Background Technology

[0002] As the demand for media information continues to grow, advertising platforms are also needing to process more and more advertising requests. Consequently, advertising platforms need to further improve their advertising request processing capabilities and efficiency to handle a large number of repetitive advertising requests.

[0003] Existing advertising platforms primarily use pre-trained evaluation models to determine whether to return ad information to an ad request and, if so, which ad information to return. Alternatively, they may differentiate the ad queue length or simplify processing steps based on business scenarios. However, pre-trained evaluation model-based ad request processing methods often involve complex processes, consuming significant computational resources and processing time, and cannot accurately identify duplicate ad requests. Business scenario-based ad request processing methods, on the other hand, still treat duplicate ad requests the same way, offering no significant improvement in processing efficiency.

[0004] Therefore, improving the processing efficiency of ad requests and reducing the consumption of computing resources has become an urgent problem to be solved. Summary of the Invention

[0005] This application provides an advertising request processing method, apparatus, device, and storage medium, which can improve the processing efficiency of advertising requests and has high applicability.

[0006] On one hand, embodiments of this application provide an advertising request processing method, the method comprising:

[0007] Obtain the target ad request and determine the request identifier of the target ad request;

[0008] In response to the above target ad request being a duplicate ad request, the time interval between the current access to the above target ad request and the previous access is determined;

[0009] In response to the above target ad request, where the time interval between the current access and the previous access is less than a preset time interval, and the first cache space includes ad information stored in association with the above request identifier, at least one historical ad list generated during the previous processing of the above target ad request is obtained from the second cache space.

[0010] The target advertising information is determined based on at least one of the above historical advertising lists, and the target advertising information is returned.

[0011] On the other hand, embodiments of this application provide an advertising request processing apparatus, which includes:

[0012] The acquisition module is used to acquire the target advertisement request and determine the request identifier of the target advertisement request.

[0013] The processing module is used to respond to the above target advertisement request being a duplicate advertisement request and to determine the time interval between the current access and the previous access of the above target advertisement request;

[0014] The above processing module is used to respond to the fact that the time interval between the current access to the target advertisement request and the previous access is less than a preset time interval, and the first cache space includes advertisement information stored in association with the request identifier, and to obtain at least one historical advertisement list generated during the previous processing of the target advertisement request from the second cache space.

[0015] The return module is used to determine the target advertisement information based on at least one of the above-mentioned historical advertisement lists and return the target advertisement information.

[0016] On the other hand, embodiments of this application provide an electronic device, including a processor and a memory, which are interconnected;

[0017] The aforementioned memory is used to store computer programs;

[0018] The processor described above is configured to execute the advertising request processing method provided in the embodiments of this application when the computer program described above is invoked.

[0019] On the other hand, embodiments of this application provide a computer-readable storage medium storing a computer program that is executed by a processor to implement the advertising request processing method provided in embodiments of this application.

[0020] On the other hand, embodiments of this application provide a computer program product, which includes a computer program that, when executed by a processor, implements the advertising request processing method provided in embodiments of this application.

[0021] Based on the advertising request processing method provided in this application embodiment, after receiving a target advertising request, if the target advertising request is a repeated advertising request and the time interval between repeated requests is less than a preset threshold, then when determining the corresponding advertising information returned for the previous target advertising request based on the first cache space, the target advertising information corresponding to this target advertising request can be determined based on the corresponding historical advertising list in the second cache space. This saves time in determining the target advertising information to improve the efficiency of advertising request processing, while reducing the consumption of computing resources, and has high applicability. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the 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.

[0023] Figure 1 This is a schematic diagram illustrating the advertising request processing principle provided in the embodiments of this application;

[0024] Figure 2 This is a flowchart illustrating an advertising request processing method provided in an embodiment of this application;

[0025] Figure 3 This is a schematic diagram of a scenario of the advertising request processing method provided in the embodiments of this application;

[0026] Figure 4 This is another flowchart illustrating the advertising request processing method provided in the embodiments of this application;

[0027] Figure 5 This is another scenario illustration of the advertising request processing method provided in the embodiments of this application;

[0028] Figure 6 This is another flowchart illustrating the advertising request processing method provided in the embodiments of this application;

[0029] Figure 7 This is another scenario illustration of the advertising request processing method provided in the embodiments of this application;

[0030] Figure 8 This is another scenario illustration of the advertising request processing method provided in the embodiments of this application;

[0031] Figure 9 This is a schematic diagram of the structure of the sorting device provided in the embodiments of this application;

[0032] Figure 10 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0033] 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 of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0034] See Figure 1 , Figure 1This is a schematic diagram illustrating the advertising request processing principle provided in an embodiment of this application. For example... Figure 1 As shown, the ad slot sends an ad request to the ad platform to request the playback of the ad. After receiving the ad request, the ad platform needs to return a certain number of ad information from a large number of candidate ad information to the ad request so that the ad slot can play the ad based on the received ad.

[0035] During the recall phase, the advertising platform can initially select a certain number of candidate advertising information from a massive amount of candidate advertising information to form an advertising list 1. The purpose is to reduce the number of candidate advertising information (e.g., keep it within 1000 as much as possible) so as to accurately determine the advertising information that needs to be returned from the advertising list 1.

[0036] Specifically, different strategies, features, or simple models can be used to recall a portion of candidate ad information, and then the recalled candidate ad information is used as ad list 1. For example, a certain number of candidate ad information can be determined by scoring and ranking based on ad placement type, ad type, business scenario, keywords, geographic information, and historical behavior corresponding to the ad request, or a certain number of candidate ad information can be determined based on the matching degree between each candidate ad information and the ad request, such as calculating the relevance between the ad request and each candidate ad information through methods such as cosine similarity or Euclidean distance, etc., without any restrictions.

[0037] Furthermore, if the number of candidate ad information in ad list 1 obtained during the recall phase is large, a coarse ranking process can be performed on each candidate ad information in ad list 1 to filter out candidate ad information that further matches the ad request through a simple screening method, resulting in ad list 2. For ad list 2 or ad list 1 with a smaller number of candidate ad information, more features and feature combinations can be used, and a complex neural network model can be employed to perform fine ranking on each candidate ad information in ad list 1 or ad list 2, i.e., to perform unified evaluation, scoring, and sorting, and select a portion of the candidate ad information from the sorting results as ad list 3.

[0038] The aforementioned neural network model can be trained using machine learning techniques within the field of artificial intelligence. Artificial intelligence utilizes digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceiving the environment, acquiring knowledge, and using that knowledge to achieve optimal results. In other words, artificial intelligence is a comprehensive technology within computer science that attempts to understand the essence of intelligence and produce a new type of intelligent machine that can react in a way similar to human intelligence. Artificial intelligence studies the design principles and implementation methods of various intelligent machines, enabling them to possess perception, reasoning, and decision-making capabilities. Machine learning is a multidisciplinary field involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory, and many other disciplines. It specifically studies how computers can simulate or implement human learning behavior to acquire new knowledge or skills, reorganize existing knowledge structures to continuously improve their performance, such as training neural network models with scoring and ranking capabilities for candidate advertising information through artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and deep learning.

[0039] After obtaining the ad list 3, a certain number of candidate ad information can be determined from the ad list 3 as the final ad information returned to the ad slot, so that the ad slot can play the ad based on the received ad information.

[0040] The aforementioned ad placements include, but are not limited to, designated locations or program nodes on applications and terminal devices used to play advertisements. For example, if a user triggers an advertisement while using an application, the application can initiate an ad request through the ad placement to obtain the ad information.

[0041] The advertising request processing method provided in this application can be implemented based on the server corresponding to the advertising platform. The server corresponding to the advertising platform can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services; this application does not impose any restrictions here.

[0042] See Figure 2 , Figure 2 This is a flowchart illustrating an advertising request processing method provided in an embodiment of this application. Figure 2 As shown, the advertising request processing method provided in this application embodiment may include the following steps:

[0043] Step S21: Obtain the target ad request and determine the request identifier of the target ad request.

[0044] In some feasible implementations, a target ad request is an ad request sent by any ad slot to request ad information. After obtaining the target ad request, the request identifier of the target ad request can be determined so as to further process the target ad request based on the target ad request identifier.

[0045] Specifically, the request identifier of a target ad request can be determined by at least one of the following: the ad slot identifier corresponding to the target ad request, the requester identifier, the ad slot type identifier, or the request time.

[0046] The ad slot identifier is used to uniquely identify the ad slot that initiated the target ad request.

[0047] The requester identifier corresponding to the target ad request is used to uniquely identify the ad requester who initiates the target ad request through the ad slot or by triggering the ad slot. For example, the identification information of the administrator who initiates the target ad request through the ad slot, or the identification information of the ad requester who triggers the ad slot and initiates the target ad request during the use of the application, etc., are not restricted here.

[0048] The ad placement type identifier uniquely identifies the type of ad placement that initiated the target ad request. This type can be categorized based on the ad placement's usage environment, such as application type or webpage type. Alternatively, it can be categorized based on the type of ad to be displayed, such as household goods or digital products. It should be noted that the specific ad placement type categorization described above can be determined based on the actual application scenario requirements and is not limited here.

[0049] The request identifier of the target ad request can be used to uniquely identify the target ad request, that is, the determined request identifier of the target ad request can uniquely represent the target ad request. When determining the request identifier of the target ad request, at least one of the following can be concatenated: the ad placement identifier, the requester identifier, the ad placement type identifier, or the request time corresponding to the target ad request, or a portion of the length can be truncated and concatenated, etc., to obtain the request identifier of the target ad request.

[0050] As an example, after obtaining the target ad request, the ad slot identifier and the requester identifier corresponding to the target ad request can be determined. The determined ad slot identifier and the requester identifier are then concatenated to obtain the request identifier corresponding to the target ad request.

[0051] As an example, after obtaining the target ad request, the ad slot identifier, requester identifier, and ad slot type identifier corresponding to the target ad request can be determined. The determined ad slot identifier, requester identifier, and ad slot type identifier are then concatenated to obtain the request identifier corresponding to the target ad request.

[0052] In some feasible implementations, before determining the request identifier of the target ad request, it can be determined whether further processing of the target ad request is needed based on the ad request processing conditions. That is, after obtaining the target ad request, it can be determined whether the target ad request meets the ad request processing conditions. If the target ad request meets the ad request processing conditions, the request identifier of the target ad request is further determined so that further processing of the target ad request can be performed based on the request identifier. If the target ad request does not meet the ad request processing conditions, then no processing of the target ad request is required, and there is no need to determine the request identifier of the target ad request.

[0053] Specifically, the conditions for processing an ad request include at least one of the following:

[0054] When an ad is played in the corresponding ad slot, the first resource quantity sent to the corresponding ad slot is less than the first resource quantity threshold.

[0055] When the advertisement is played a preset number of times in the corresponding ad slot, the predicted second resource quantity is greater than or equal to the second resource quantity threshold.

[0056] For any given ad slot, a certain amount of resources is required to play an ad. For example, when an ad needs to be played through the ad slot, a certain amount of virtual resources must be paid to the ad slot (or the ad slot administrator corresponding to the ad slot) in order for the ad slot to play the ad.

[0057] The first resource quantity corresponding to the target ad request can be the minimum resource quantity required for the ad slot corresponding to the target ad request to play the ad, or it can be the average resource quantity of the historical resource quantity sent to each ad slot when playing ads in all ad slots, etc. The specific amount can be determined based on the actual application scenario requirements, and there are no restrictions here.

[0058] As an example, after obtaining the target ad request, the first resource amount required for the ad slot corresponding to the target ad request to play the ad can be determined. If the first resource amount is less than the first resource amount threshold, the request identifier of the target ad request can be determined so as to further process the target ad request based on the request identifier.

[0059] The second resource quantity predicted to be obtained when the ad slot corresponding to the target ad request plays an ad a preset number of times is the revenue that can be obtained by playing an ad a preset number of times through the ad slot corresponding to the target ad request.

[0060] The second resource quantity predicted can be the one predicted based on the evaluation model, or the average of the actual resource quantities obtained by the ad slot corresponding to the target ad request or by the ads in all ad slots for a preset number of historical plays, or the resource quantity obtained by the most recently returned ad information for a predicted number of plays, such as the Effective Cost per Mille (ECPM) corresponding to the ad information. The specific amount can be determined based on the actual application scenario requirements and is not limited here.

[0061] As an example, after obtaining the target ad request, it is possible to predict the second resource quantity to be obtained when the ad slot corresponding to the target ad request plays an ad a preset number of times. If the second resource quantity is greater than or equal to the second resource quantity threshold, the request identifier of the target ad request can be determined so as to further process the target ad request based on the request identifier.

[0062] As an example, after obtaining a target ad request, the first resource amount required for the ad slot corresponding to the target ad request to play the ad can be determined, and the second resource amount predicted to be obtained when the ad slot corresponding to the target ad request plays the ad a preset number of times. If the first resource amount is less than the first resource amount threshold and / or the second resource amount is greater than or equal to the second resource amount threshold, the request identifier of the target ad request can be determined so as to further process the target ad request based on the request identifier.

[0063] The first resource quantity threshold, the second resource quantity threshold, and the preset number of times mentioned above can be determined based on the actual application scenario requirements, and are not restricted here.

[0064] Based on this, when a target ad request or multiple ad requests are obtained, ad requests that do not meet the ad request processing requirements can be pre-filtered out, thereby ensuring that the ad space needs to pay less resources and / or receive more resources when playing the ad based on the final returned ad information.

[0065] Step S22: In response to the target ad request being a duplicate ad request, determine the time interval between the current visit to the target ad request and the previous visit.

[0066] In some feasible implementations, after determining the request identifier of the target ad request, it can be determined whether the target ad request is a first-time ad request based on the request identifier of the target ad request, that is, whether the same target ad request has been received before.

[0067] Specifically, for any previously received advertising request, if the advertising information corresponding to the advertising request is determined and the corresponding advertising information is returned for the advertising request, the request identifier of the advertising request and the corresponding advertising information will be associated and stored in the first cache space.

[0068] If the advertising information corresponding to the advertising request is ultimately not determined, the request identifier of the advertising request and the first indication information will be associated and stored in the first cache space. The first indication information is used to indicate that the advertising information corresponding to the advertising request has not been determined. Alternatively, only the request identifier of the advertising request may be stored in the first cache space. If only the request identifier of the advertising request is stored in the first cache space, it can be considered that the advertising information corresponding to the advertising request has not been determined before.

[0069] The first cache space can be a server used to provide key-value (KV) storage services. In this server, the request identifier of any advertising request is stored in the form of an identifier key, and the corresponding first instruction information or advertising information is stored in the form of a record value corresponding to the identifier key, thereby realizing the associated storage of the request identifier and the corresponding first instruction information or advertising information.

[0070] Furthermore, it can be determined whether the first cache space stores the request identifier of the target advertisement request. If it is determined that the first cache space stores the request identifier of the target advertisement request, it can be determined that the target advertisement request is not the first visit advertisement request, that is, the target advertisement request is a duplicate advertisement request received at different times.

[0071] Furthermore, if the target ad request is determined to be a duplicate ad request, the time interval between the current visit and the previous visit of the target ad request can be determined, so as to determine the processing method for the target ad request based on the time interval between the current visit and the previous visit of the target ad request.

[0072] In this context, the access time of each ad request can also be associated with the request identifier of the ad request and stored in the first cache space. For example, when the request identifier of the ad request is stored as the key in the KV database, the corresponding access time can be stored as part of the corresponding value field.

[0073] In this case, the access time of the last access to the target ad request can be determined based on the first cache space, and then the time interval between the current access to the target ad request and the last access can be determined.

[0074] Step S23: In response to the target ad request, the time interval between the current access and the previous access is less than a preset time interval, and the first cache space includes ad information stored in association with the request identifier, retrieve at least one historical ad list generated during the processing of the previous target ad request from the second cache space.

[0075] If the time interval between the current access to the target ad request and the previous access is less than a preset time interval, at least one historical ad list generated during the previous processing of the target ad request can be obtained.

[0076] For any previously processed ad request, at least one historical ad list generated during the processing of that ad request can be one or more ad lists generated during the recall phase, coarse ranking phase, or fine ranking phase when processing that ad request. Alternatively, it can be an ad list generated during any ad ranking phase, such as an ad list generated during the fine ranking phase where each ad information corresponds to the predicted click-through rate (PCTR) or predicted conversion rate (PCVR). There are no restrictions on this.

[0077] In this context, at least one historical ad list corresponding to any ad request can also be associated with the request identifier of the ad request and stored in the second cache space. For example, the request identifier of the ad request and the corresponding historical ad list can also be stored in a KV database in key-value format.

[0078] In the embodiments of this application, the first cache space and the second cache space can be cache spaces used to cache different information in the same storage space, or they can be different storage spaces in the same device, or they can be storage spaces corresponding to different independent devices. The specific location can be determined based on the actual application scenario requirements, and no restrictions are imposed here.

[0079] For example, the first cache space and the second cache space can correspond to different storage spaces of the same server, database, cloud storage space, or blockchain, such as different storage spaces of the same key-value database or different blocks of the same blockchain. Alternatively, the first cache space and the second cache space can correspond to different servers, databases, cloud storage spaces, or blockchains, such as different key-value databases or different cloud storage spaces, etc., without any restrictions.

[0080] In short, the database can be viewed as an electronic filing cabinet—a place to store electronic files. In this application, it can be used to store the request identifier of each advertising request, as well as the first instruction information and advertising information associated with the request identifier, and / or the historical advertising list generated during the processing of each advertising request.

[0081] Blockchain, in particular, is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. In this application, each data block in the blockchain can store the request identifier of each advertising request, as well as the first indication information and advertising information associated with the request identifier, and / or a historical list of advertisements generated during the processing of each advertising request.

[0082] Cloud storage is a new concept that extends and develops from the concept of cloud computing. It refers to the use of cluster applications, grid technology, and distributed storage file systems to bring together a large number of storage devices of various types (storage devices are also called storage nodes) in the network to work together through application software or application interfaces to jointly store the request identifier of each advertising request, as well as the first indication information and advertising information associated with the request identifier, and / or the historical advertising list generated during the processing of each advertising request.

[0083] Optionally, to further improve the processing efficiency of ad requests, the first cache space and the second cache space can be deployed in the form of multi-level caching. That is, the second cache space can only be accessed after the first cache space is accessed. In other words, the second cache space is only accessed to obtain the historical ad list generated during the previous processing of the target ad request if the target ad is determined to be a duplicate ad request based on the first cache space and the time interval between the current access and the previous access is less than a preset time interval.

[0084] Step S24: Determine the target ad information based on at least one historical ad list and return the target ad information.

[0085] In some feasible implementations, for at least one historical ad list corresponding to the target ad request, the ad information in each historical ad list can be filtered based on preset filtering rules to obtain the target ad list.

[0086] Any piece of advertising information may include the advertising content of the corresponding advertisement, the access address corresponding to the advertising content, etc., without any restrictions.

[0087] Specifically, the advertising conditions corresponding to the target advertising request can be determined, such as product type, advertising style, target audience and advertising area. Based on the advertising conditions, the advertising information in the historical advertising list is filtered to obtain the target advertising list.

[0088] For example, if the target ad's delivery conditions determine that the ad type to be played in the corresponding ad slot is a maternal and infant ad, then non-maternal and infant ad information in the historical ad list can be filtered to obtain the target ad list.

[0089] Optionally, resource budgeting can also be controlled for each ad in the historical ad list. For example, if the amount of resources sent to the advertiser of the ad is less than the amount of resources obtained from the ad slot when the ad is placed in the ad slot corresponding to the target ad request, then additional resources will be required when the ad is placed in the ad slot corresponding to the target ad request. In this case, the ad can be removed from the historical ad list.

[0090] It should be noted that the above method of filtering advertising information in the historical advertising list based on preset filtering rules is only an example. For example, it can also filter out advertising information whose advertising duration does not meet the duration requirement. The specific method can be determined based on the actual application scenario requirements, and there are no restrictions here.

[0091] Furthermore, after obtaining the target ad list, the intersection of the target ad list and each historical ad list can be determined. A certain number of ad messages are then identified from this intersection as target ad messages; that is, if the target ad list is not empty, at least one target ad message is identified from it. This target ad message can then be used as the ad message corresponding to the target ad request and returned, such as by returning the target ad message to the ad slot corresponding to the target ad request, so that the ad slot can play the ad using the target ad message.

[0092] After identifying the target ad message, the third resource quantity corresponding to the target ad message can be further adjusted, and then the target ad message can be returned after adjustment. The third resource quantity corresponding to the target ad message is the amount of resources obtained from the advertiser corresponding to the target ad message for each preset number of ad playbacks based on the target ad message, or the amount of resources obtained from the advertiser corresponding to the target ad message for each time an ad viewer transfers resources through the target ad message (such as making a purchase). For example, by increasing the third resource quantity, more resources can be obtained from the advertiser while increasing the exposure opportunities of the target ad message.

[0093] Alternatively, after identifying multiple target ad messages, the third resource quantity corresponding to each target ad message can be adjusted, and at least one target ad message with the highest third resource quantity can be used as the final returned target ad message, without any restrictions.

[0094] Optionally, after obtaining the target ad list, if the target ad list includes ad information stored in the preset storage space that is associated with the request identifier of the target ad request, then the ad information stored in the preset storage space that is associated with the request identifier of the target ad request can be used as the target ad information. If the target ad list does not include ad information stored in the preset storage space that is associated with the request identifier of the target ad request, then the target ad information can be determined from the target ad list based on any of the above implementation methods.

[0095] Optionally, after obtaining the target ad list, if the target ad list does not include the ad information stored in the preset storage space that is associated with the request identifier of the target ad request, the ad information can be added to the target ad list, and then the target ad information can be determined from the target ad list based on any of the above implementation methods.

[0096] In some feasible implementations, after returning the target advertising information, the advertising information stored in the first cache space associated with the request identifier of the target advertising request can be updated based on the target advertising information. That is, the advertising information previously returned for the target advertising request and stored in the first cache space associated with the request identifier of the target advertising request is replaced with the target advertising information returned for the current target advertising request, thereby realizing the continuous updating of the first cache space.

[0097] In some feasible implementations, after obtaining the target ad list, if the target ad information to be returned is not determined based on the target ad list, a first indication information can be returned to indicate that the target ad information corresponding to the target ad request has not been determined, so that the ad slot corresponding to the target ad request can re-initiate the ad request.

[0098] Furthermore, after returning the first indication information, the advertising information stored in the first cache space associated with the request identifier of the target advertising request can be updated based on the first indication information to indicate that the target advertising information corresponding to the target advertising request was not determined this time. Based on this, if a target advertising request is received again in the future, and it is determined that the first cache space includes the first indication information stored with the request identifier of the target advertising, it is determined that the first cache space does not include the advertising information stored with the request identifier of the target advertising, that is, the advertising information corresponding to the target advertising request was not determined in the previous instance.

[0099] Optionally, after returning the first indication information, the advertising information associated with the request identifier of the target advertising request in the first cache space can also be deleted. Based on this, if the target advertising request is received again in the next instance, it can be directly determined that the first cache space does not contain the advertising information stored associated with the request identifier of the target advertising, that is, the advertising information corresponding to the target advertising request was not determined in the previous instance.

[0100] The following is combined Figure 3 right Figure 2 The advertising request processing method shown will be further explained. Figure 3 This is a schematic diagram of a scenario for the advertising request processing method provided in this application embodiment. After obtaining a target advertising request, the request identifier of the target advertising request is determined, and based on the request identifier, it is determined whether the target advertising request is a first-time visit advertising request.

[0101] If the target ad request is a repeated ad request, the time interval between the current access and the previous access of the target ad request is determined. If the time interval between the current access and the previous access is less than the preset time interval T, it is further determined whether the first cache space includes ad information stored in association with the target ad request.

[0102] If the first cache space includes advertising information stored in association with the target advertising request, at least one historical advertising list generated during the previous processing of the target advertising request is obtained from the second cache space. The target advertising information is obtained by performing operations such as targeting filtering and budget control on the historical advertising list. The target advertising information is then returned to the advertising position corresponding to the target advertising request so that the advertising position plays the advertisement based on the target advertising information.

[0103] See Figure 4 , Figure 4 This is another flowchart illustrating the advertising request processing method provided in this application embodiment. For example... Figure 4 As shown, the advertising request processing method provided in this application embodiment may include the following steps:

[0104] Step S41: Obtain the target ad request and determine the request identifier of the target ad request.

[0105] In some feasible implementations, the specific implementation of step S41 can be found in [reference needed]. Figure 2 The implementation method shown in step S21 will not be described again here.

[0106] Step S42: In response to the target advertisement request, if the time interval between the current visit and the previous visit is less than a preset time interval, and the first cache space does not contain the advertisement information stored with the request identifier, return the first indication information.

[0107] In some feasible implementations, after determining the request identifier of the target ad request, it can be determined whether the target ad request is a first-time ad request based on the request identifier of the target ad request, that is, whether the same target ad request has been received before.

[0108] If it is determined that the first cache space stores the request identifier of the target advertisement request, then it can be determined that the target advertisement request is not the first advertisement request, that is, the target advertisement request is an advertisement request that is repeatedly received at different times.

[0109] In this case, the time interval between the current access to the target ad request and the previous access can be further determined. If the time interval is less than the preset time interval and the first cache space does not contain the ad information stored in association with the request identifier of the target ad request, it is determined that no ad information was returned for the target ad request in the previous access. At this time, the first indication information can be returned for the current target ad request to indicate that the target ad information corresponding to the target ad request has not been determined, or no processing is performed on the current target ad request.

[0110] If the first cache space includes first indication information stored in association with the request identifier of the target ad request, or only includes the request identifier of the target ad request, it can be considered that the first cache space does not include ad information stored in association with the request identifier of the target ad request, that is, it is determined that no ad information was returned for the target ad request in the last time.

[0111] In some feasible implementations, the first indication information corresponding to any advertisement information may also include the access time of the corresponding advertisement request, so as to indicate that the advertisement information corresponding to the advertisement request received at that access time has not been determined.

[0112] Based on this, after returning the first indication information, the first indication information stored in the first cache space associated with the request identifier of the target advertisement request can be updated based on the first indication information returned this time. That is, the first indication information returned last time for the target advertisement request is updated based on the first indication information returned this time, so as to indicate that the target advertisement information corresponding to the target advertisement request received this time has not been determined.

[0113] The following is combined Figure 5 right Figure 4 The advertising request processing method shown will be further explained. Figure 5 This is another scenario illustration of the advertising request processing method provided in the embodiments of this application. After obtaining the target advertising request, the request identifier of the target advertising request is determined, and based on the request identifier of the target advertising request, it is determined whether the target advertising request is an advertising request accessed for the first time.

[0114] If the target ad request is a repeated ad request, the time interval between the current access and the previous access of the target ad request is determined. If the time interval between the current access and the previous access is less than the preset time interval T, it is further determined whether the first cache space includes ad information stored in association with the target ad request.

[0115] If the first cache space does not contain advertising information stored in association with the target advertising request, but includes first indication information stored in association with the request identifier of the target advertising request or only includes the request identifier of the target advertising request, it means that the request identifier corresponding to the target advertising request was not determined last time, and the request identifier corresponding to the target request will not be determined this time either. Therefore, the first indication information can be returned directly to indicate that the corresponding target advertising information cannot be determined this time, so that the advertising slot corresponding to the target advertising request will not play the advertisement.

[0116] based on Figure 4 The advertising request processing method shown can, when receiving a duplicate advertising request, if the time interval between the current access and the previous access is less than a preset time interval and the previous access did not return the corresponding advertising information, then no further processing is required for the received advertising request, thus saving computing resources and improving the processing efficiency of advertising requests.

[0117] See Figure 6 , Figure 6 This is another flowchart illustrating the advertising request processing method provided in the embodiments of this application. Figure 6 As shown, the advertising request processing method provided in this application embodiment may include the following steps:

[0118] Step S61: Obtain the target ad request and determine the request identifier of the target ad request.

[0119] Step S62: In response to a target ad request that is a first-time ad request, or a target ad request that is a repeated ad request and the time interval between the current visit and the previous visit is greater than or equal to a preset time interval, process the target ad request.

[0120] In some feasible implementations, after determining the request identifier of the target ad request, it can be determined whether the target ad request is a first-time ad request based on the request identifier of the target ad request, that is, whether the same target ad request has been received before.

[0121] If it is determined that the first cache space stores the request identifier of the target advertisement request, then it can be determined that the target advertisement request is not the first advertisement request, that is, the target advertisement request is an advertisement request that is repeatedly received at different times.

[0122] In this case, the time interval between the current visit and the previous visit for the target advertisement request can be further determined. If the time interval is greater than or equal to the preset time interval, the target advertisement request can be processed.

[0123] In some feasible implementations, if the request identifier of the target ad request is not stored in the first cache space, the target ad request can be determined to be a first-time ad request. In this case, the target ad request can be further processed in the same way.

[0124] In some feasible implementations, when processing target ad requests, different strategies, features, or simple models can be used to recall a portion of candidate ad information. Further, a coarse-ranking method can be used to score and sort the ad slot type, ad type, business scenario, keywords, geographic information, and historical behavior corresponding to the target ad request to determine a smaller number of candidate ad information. Alternatively, a coarse-ranking method can be used to determine the matching degree between each candidate ad information and the ad request, such as calculating the relevance between the ad request and each candidate ad information through methods like cosine similarity or Euclidean distance. No restrictions are imposed here.

[0125] Furthermore, more features and feature combinations can be used to refine the candidate ad information in the ad list determined in the coarse ranking stage through a complex neural network model. This involves uniformly evaluating, scoring, and ranking the ad information, and selecting a portion of the candidate ad information from the ranking results as the candidate ad list, thereby determining the target ad information from the candidate ads.

[0126] In some feasible implementations, after determining the candidate ad list, the ad information in the candidate ad list can be filtered based on preset filtering rules to obtain the target ad list.

[0127] Specifically, the advertising conditions corresponding to the target advertising request can be determined, such as product type, advertising style, target audience, etc. Based on the advertising conditions, the advertising information in the candidate advertising list can be filtered to obtain the target advertising list.

[0128] Optionally, resource budgets can be controlled for each ad in the historical ad list. For example, ad information that meets the preset resource budget when placed in the ad slot corresponding to the target ad request can be selected from the candidate ad list to obtain the target ad list.

[0129] Furthermore, after obtaining the target ad list, the intersection of the target ad list and each historical ad list can be determined. A certain number of ad messages are then identified from this intersection as target ad messages. That is, if the target ad list is not empty, at least one target ad message is identified from it. If the target ad list is empty, it means that no target ad message corresponding to the target ad request has been identified.

[0130] Step S63: In response to determining the target ad information corresponding to the target ad request, return the target ad information.

[0131] In some feasible implementations, if the target advertising information corresponding to the target advertising request is determined, the target advertising information can be returned, such as returning the target advertising information to the advertising space corresponding to the target advertising request, so that the advertising space can play the advertisement based on the target advertising information.

[0132] After identifying the target ad message, the third resource quantity corresponding to the target ad message can be further adjusted, and then the target ad message can be returned after adjustment. The third resource quantity corresponding to the target ad message is the amount of resources obtained from the advertiser corresponding to the target ad message for each preset number of ad playbacks based on the target ad message, or the amount of resources obtained from the advertiser corresponding to the target ad message for each time an ad viewer transfers resources through the target ad message (such as making a purchase). For example, by increasing the third resource quantity, more resources can be obtained from the advertiser while increasing the exposure opportunities of the target ad message.

[0133] Alternatively, after identifying multiple target ad messages, the third resource quantity corresponding to each target ad message can be adjusted, and at least one target ad message with the highest third resource quantity can be used as the final returned target ad message, without any restrictions.

[0134] In some feasible implementations, when the target ad information corresponding to the target ad request is determined, one or more ad lists generated during the recall, coarse ranking, or fine ranking stages of the target ad processing can be associated with the request identifier of the target ad request and stored in a preset storage space. Alternatively, the ad list generated in any ad ranking stage can be associated with the request identifier of the target ad request and stored in a first cache space. For example, the ad list corresponding to PCTR or PCVR of each ad information in the ad list generated in the fine ranking stage can be associated with the request identifier of the target ad request and stored in the first cache space. No limitation is imposed here.

[0135] In some feasible implementations, when the target ad request is a first-time ad request, if the target ad information corresponding to the target ad request is determined, then after returning the target ad information, the request identifier of the target ad request and the target ad information are associated and stored in the first cache space. Thus, when the target ad request is received again, if the time interval between repeated accesses of the target ad request is less than a preset time interval, at least one historical ad list generated during the current processing of the target ad is retrieved from the second cache space, and then the corresponding target ad information is determined based on each historical ad list.

[0136] Optionally, if the target ad request is a repeatedly accessed ad request and the time interval between the current access and the previous access is greater than or equal to a preset time interval, if the target ad information corresponding to the target ad request is determined, then after returning the target ad information, the first indication information or ad information stored in the first cache space associated with the request identifier of the target ad request is updated based on the target ad information.

[0137] Based on this, when a target ad request is received again, if the time interval between repeated accesses to the target ad request is less than a preset time interval, at least one historical ad list generated during the current processing of the target ad is obtained from the second cache space, and then the corresponding target ad information is determined based on each historical ad list.

[0138] In other words, if the target ad request is a repeated ad request and the time interval between the current access and the previous access is greater than or equal to a preset time interval, if the target ad information corresponding to the target ad request is determined, then after returning the target ad information, if the ad information was returned for the previous target ad request, the ad information stored in the first cache space associated with the request identifier of the target ad request will be updated to the target ad information determined this time.

[0139] If the previous request for the target advertisement did not return the corresponding advertisement information, then if the first indication information is returned to indicate that the corresponding advertisement information was not determined in the previous request, the first indication information stored in the first cache space associated with the request identifier of the target advertisement request will be updated to the target advertisement information that has been determined this time.

[0140] If the previous request for the target ad did not return the corresponding ad information, and no further processing was performed on the target ad request, the target ad information determined this time can be associated with the request identifier of the target ad request included in the first cache space and stored.

[0141] Step S64: In response to the failure to determine the target advertisement information corresponding to the target advertisement request, return the first indication information.

[0142] In some feasible implementations, if the target ad information corresponding to the target ad request is determined, a first indication information can be returned to the ad slot corresponding to the target ad request to indicate that the target ad information corresponding to the target ad request has not been determined.

[0143] In some feasible implementations, when the target ad request is a first-time ad request, if the target ad information corresponding to the target ad request is not determined and a first indication is returned, the request identifier of the target ad request and the first indication can be associated and stored in a first cache space. Therefore, when the target ad request is received again, if the time interval between repeated accesses is less than a preset time interval and the first cache space includes ad information stored in association with the request identifier of the target ad request, the first indication is also returned to indicate that the corresponding target ad information has still not been determined. Alternatively, if the target ad information corresponding to the target ad request is not determined, the request identifier of the target ad request can be stored in the first cache space. Therefore, when the target ad request is received again, if the time interval between repeated accesses is less than a preset time interval and the first cache space only includes the request identifier of the target ad request, no processing is performed on the target ad request.

[0144] Optionally, if the target ad request is a repeatedly accessed ad request and the time interval between the current access and the previous access is greater than or equal to a preset time interval, and if the target ad information corresponding to the target ad request is not determined and the first indication information is returned, then the ad information can be updated to the first indication information when the ad information stored in the first cache space is associated with the request identifier of the target ad request.

[0145] Based on this, when a target ad request is received again, if the time interval between repeated accesses to the target ad request is less than a preset time interval, and if the first cache space includes first indication information stored in association with the request identifier of the target ad request, the first indication information can also be returned to indicate that the corresponding target ad information still cannot be determined this time.

[0146] Optionally, if the target ad request is a repeatedly accessed ad request and the time interval between the current access and the previous access is greater than or equal to a preset time interval, and if the target ad information corresponding to the target ad request is not determined and no indication information is returned, and the first cache space includes ad information stored in association with the request identifier of the target ad request, the ad information stored in association with the request identifier of the target ad request in the first cache space can be deleted.

[0147] Therefore, when a target ad request is received again, if the time interval between repeated accesses of the target ad request is less than a preset time interval, and the first cache space only contains the request identifier of the target ad request, then no processing is performed on the target ad request.

[0148] Optionally, the first indication information corresponding to any advertisement information may further include the access time of the corresponding advertisement request, to indicate that the advertisement information corresponding to the advertisement request received at that access time has not been determined. If the target advertisement request is a repeatedly accessed advertisement request, and the time interval between the current access and the previous access is greater than or equal to a preset time interval, if the target advertisement information corresponding to the target advertisement request has not been determined and the first indication information is returned, and the first cache space includes a first indication stored in association with the request identifier of the target advertisement request, the first indication information stored in association with the request identifier of the target advertisement request in the first cache space may be updated based on the returned first indication information, to indicate that the target advertisement information corresponding to the currently received target advertisement request has not been determined.

[0149] The following is combined Figure 7 right Figure 6 The advertising request processing method shown will be further explained. Figure 7 This is another scenario illustration of the advertising request processing method provided in this application embodiment. After obtaining the target advertising request, the request identifier of the target advertising request can be determined, and whether the target advertising request is a first-time access advertising request can be determined by determining whether the request identifier of the target advertising is stored in the first cache space.

[0150] When the target ad request is a repeated ad request and the time interval between the current access and the previous access is greater than or equal to a preset time interval T, or when the target ad request is a first-time ad request, the target ad information can be determined through ad processing methods such as recall, coarse ranking, and fine ranking by the ad platform's backend system. The target ad information is then returned to the ad slot corresponding to the target ad request, so that the ad slot plays the ad based on the target ad information, and simultaneously updates the first indication information or ad information stored in the first cache space associated with the request identifier of the target ad request based on the target ad information.

[0151] Furthermore, once the target ad information corresponding to the target ad request is determined, the historical ad list generated during the recall, coarse ranking, and fine ranking stages can be stored in the second cache space. When the target ad request is received again, if the time interval between repeated accesses of the target ad request is less than a preset time interval, the historical ad list stored this time can be retrieved from the second cache space, and the target ad information corresponding to the next received target ad request can be determined based on this.

[0152] If the target ad request is a repeated ad request and the time interval between the current access and the previous access is greater than or equal to a preset time interval T, or if the target ad request is a first-time ad request, and the target ad information cannot be determined through processing methods such as recall, coarse ranking, and fine ranking, then a first indication message can be returned to indicate that the corresponding ad slot has not been identified with the corresponding target ad information. Simultaneously, based on the first indication message, the first indication message or ad information stored in the first cache space associated with the request identifier of the target ad request is updated, so that when the next target ad request is received, if the time interval between repeated accesses of the target ad request is less than the preset time interval, the first indication message will also be returned.

[0153] based on Figure 7 The advertising request processing method shown only processes the advertising request based on the advertising platform's backend system to determine the corresponding advertising information when the time interval between receiving the first access to the advertising request or the repeated access to the received advertising request is greater than or equal to a preset time interval, thereby saving a lot of computing resources.

[0154] The advertising processing methods provided in this application, including advertising processing (such as coarse ranking, recall, and fine ranking) and information processing of the information stored in the first and second cache spaces, can all be implemented based on cloud computing technology. Cloud computing is a product of the integration of traditional computer and network technologies such as grid computing, distributed computing, parallel computing, utility computing, network storage technologies, virtualization, and load balancing. Driven by the development of the Internet, real-time data streams, the diversification of connected devices, and the demands of search services, social networks, mobile commerce, and open collaboration, cloud computing has developed rapidly.

[0155] The following is combined Figure 8 The advertising request processing method provided in the embodiments of this application will be described in general. Figure 8 This is another scenario illustration of the advertising request processing method provided in the embodiments of this application. For example... Figure 8 As shown, after obtaining the target ad request, the request identifier of the target ad request is determined, and the target ad request is determined as a first-time ad request through the preset storage space.

[0156] Scenario 1:

[0157] If the target ad request is determined to be an ad request for the first time based on the first cache space, the ad can be processed through the ad platform's backend system using ad processing methods such as recall, coarse ranking, and fine ranking.

[0158] If the target ad information is determined through the backend system of the advertising platform, the target ad information is returned to the ad slot corresponding to the target ad request, so that the ad slot plays the ad based on the target ad information. At the same time, the request identifier of the target ad request is associated with the target ad information and stored in the first cache space, and the historical ad list generated in the recall stage, coarse ranking stage and fine ranking stage is stored in the second cache space.

[0159] If the target ad information cannot be determined through the advertising platform's backend system, a first indication message can be returned to indicate that the corresponding ad slot has not been found to contain the corresponding target ad information. Simultaneously, the first indication message and the request identifier of the target ad request are associated and stored in the first cache space.

[0160] Scenario 2:

[0161] If the target ad request is a repeated ad request, the time interval between the current access and the previous access of the target ad request is determined. If the time interval between the current access and the previous access is less than the preset time interval T, it is further determined whether the first cache space includes ad information stored in association with the target ad request.

[0162] If the first cache space includes advertising information stored in association with the target advertising request, then at least one historical advertising list generated during the previous processing of the target advertising request is retrieved from the second cache space, and operations such as targeting filtering and budget control are performed on the historical advertising list. If the target advertising information is determined, the target advertising information is returned to the advertising position corresponding to the target advertising request, and the advertising information stored in the first cache space in association with the request identifier of the target advertising request is updated based on the target advertising information. If the target advertising information is not determined, a first indication information can be returned to indicate that the corresponding advertising position has not determined the corresponding target advertising information. At the same time, the advertising information stored in the first cache space in association with the request identifier of the target advertising request is updated based on the first indication information.

[0163] If the first cache space does not contain the advertising information stored in association with the target advertising request, then the first indication information can be returned to indicate that the corresponding advertising slot has not identified the corresponding target advertising information. At the same time, the advertising information or the first indication information stored in the first cache space in association with the request identifier of the target advertising request is updated based on the first indication information.

[0164] If the target ad request is a repeat ad request and the time interval between the current visit and the previous visit is greater than or equal to the preset time interval T, the ad can be processed through the ad platform's backend system using ad processing methods such as recall, coarse ranking, and fine ranking.

[0165] If the target ad information is identified through the advertising platform's backend system, it is returned to the ad slot corresponding to the target ad request. This allows the ad slot to play the ad based on the target ad information, and simultaneously, the ad information or first indication information stored in the first cache space associated with the request identifier of the target ad request is replaced with the target ad information. The historical ad lists generated during the recall, coarse ranking, and fine ranking phases are stored in the second cache space. If the target ad information is not identified through the advertising platform's backend system, the first indication information is returned to indicate that the corresponding ad slot did not have the corresponding target ad information. Simultaneously, the ad information or first indication information stored in the first cache space associated with the request identifier of the target ad request is replaced with the returned first indication information.

[0166] Based on the advertising request processing method provided in this application embodiment, for a received repeatedly accessed advertising request, if the time interval between repeated accesses of the advertising request is less than a preset time interval, the processing method for the advertising request can be quickly determined based on the first cache space and / or the second cache space. For example, an indication message indicating that no advertising information has been determined can be returned, or the advertising information to be returned can be quickly determined based on the historical advertising list of the advertising request, thereby saving computing resources. For an advertising request that is received for the first time and the time interval between repeated accesses is greater than or equal to the preset time interval, after processing the advertising request, the processing result (returned advertising information or indication message) can be stored in the first cache space, and the historical advertising list generated during the processing can be stored in the second cache space. Therefore, after receiving the corresponding advertising request again, the processing efficiency of the advertising request can be further improved based on the first cache space and the second cache space.

[0167] Furthermore, the process of handling duplicate advertising requests does not involve complex model training, which makes the advertising request processing method provided in this application applicable to any advertising platform. The use of the first cache space and the second cache space can reduce the impact of excessive caching on the performance and revenue of the advertising platform, thus having a wide range of applications.

[0168] See Figure 9 , Figure 9 This is a schematic diagram of the structure of the advertising request processing apparatus provided in this application embodiment. The apparatus provided in this application embodiment includes:

[0169] The acquisition module 91 is used to acquire the target advertisement request and determine the request identifier of the target advertisement request.

[0170] Processing module 92 is used to respond to the above target advertisement request being a duplicate advertisement request and determine the time interval between the current access and the previous access of the above target advertisement request;

[0171] The aforementioned processing module 92 is used to respond to the fact that the time interval between the current access to the target advertisement request and the previous access is less than a preset time interval, and the first cache space includes advertisement information stored in association with the request identifier, and to obtain at least one historical advertisement list generated during the previous processing of the target advertisement request from the second cache space.

[0172] Return module 93 is used to determine target advertising information based on at least one of the above-mentioned historical advertising lists and return the target advertising information.

[0173] In some feasible implementations, the aforementioned return module 93 is further configured to:

[0174] In response to the above target advertisement request, if the time interval between the current access and the previous access is less than the above preset time interval, and the above first cache space does not contain the advertisement information stored in association with the above request identifier, the first indication information is returned. The first indication information is used to indicate that the target advertisement information corresponding to the above target advertisement request has not been determined.

[0175] In some feasible implementations, the aforementioned return module 93 is further configured to:

[0176] In response to the above target ad request being a first-time ad request, or the above target ad request being a repeated ad request and the time interval between the current visit and the previous visit being greater than or equal to the above preset time interval, the above target ad request is processed.

[0177] In response to determining the target ad information corresponding to the above target ad request, the above target ad information is returned; or

[0178] In response to the failure to determine the target advertisement information corresponding to the above target advertisement request, a first indication information is returned, which is used to indicate that the target advertisement information corresponding to the above target advertisement request has not been determined.

[0179] In some feasible implementations, the processing module 92 described above is used for:

[0180] Based on preset filtering rules, at least one of the above-mentioned historical advertising lists is filtered to obtain a target advertising list, and the target advertising information is determined based on the above-mentioned target advertising list.

[0181] In some feasible implementations, the processing module 92 is further configured to:

[0182] In response to the failure to determine the target advertisement information based on at least one of the aforementioned historical advertisement lists, a first indication is returned, wherein the first indication is used to indicate that the target advertisement information corresponding to the target advertisement request has not been determined.

[0183] Based on the first instruction information mentioned above, update the advertising information stored in the first cache space that is associated with the request identifier.

[0184] In some feasible implementations, after returning the aforementioned target advertising information, the processing module 92 is further configured to:

[0185] Based on the aforementioned target advertising information, update the advertising information stored in the first cache space that is associated with the aforementioned request identifier.

[0186] In some feasible implementations, the aforementioned target advertisement request is an advertisement request for the first visit, and the aforementioned processing module 92 is further configured to:

[0187] In response to the return of the aforementioned target advertising information, the aforementioned request identifier and the aforementioned target advertising information are associated and stored in the aforementioned first cache space; or

[0188] In response to the return of the first instruction information, the request identifier and the first instruction information are associated and stored in the first cache space.

[0189] In some feasible implementations, where the target advertisement request is a duplicate advertisement request and the time interval between the current visit and the previous visit is greater than or equal to the preset time interval, the processing module 92 is further configured to:

[0190] In response to returning the aforementioned target advertising information, update the first indication information or advertising information stored in the first cache space associated with the aforementioned request identifier based on the aforementioned target advertising information; or

[0191] In response to the return of the first instruction information and the inclusion of advertising information stored in the first cache space associated with the request identifier, the advertising information stored in the first cache space associated with the request identifier is updated based on the first instruction information.

[0192] In some feasible implementations, the processing module 92 is further configured to:

[0193] At least one list of advertisements generated during the processing of the aforementioned target advertisement requests will be stored in the aforementioned second cache space.

[0194] In some feasible implementations, the aforementioned request identifier is determined by at least one of the following: the ad slot identifier corresponding to the aforementioned target ad request, the requester identifier, the ad slot type identifier, or the request time.

[0195] In some feasible implementations, the processing module 92 is further configured to:

[0196] In response to the aforementioned target ad request satisfying the ad request processing conditions, the request identifier of the aforementioned target ad request is determined, wherein the aforementioned ad request processing conditions include at least one of the following:

[0197] When an ad is played in the corresponding ad slot, the first resource quantity sent to the corresponding ad slot is less than the first resource quantity threshold; or

[0198] When the advertisement is played a preset number of times in the corresponding ad slot, the predicted second resource quantity is greater than or equal to the second resource quantity threshold.

[0199] In specific implementation, the above-mentioned device can perform the above-described actions through its built-in functional modules. Figure 2 , Figure 4 and / or Figure 6 The implementation methods provided for each step are detailed in the above-mentioned implementation methods, and will not be repeated here.

[0200] See Figure 10 , Figure 10 This is a schematic diagram of the structure of the electronic device provided in an embodiment of this application. For example... Figure 10 As shown, the electronic device 1000 in this embodiment may include: a processor 1001, a network interface 1004, and a memory 1005. Furthermore, the electronic device 1000 may also include: a user interface 1003, and at least one communication bus 1002. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen and a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be a high-speed RAM or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory 1005 may also be at least one storage device located remotely from the aforementioned processor 1001. Figure 10 As shown, the memory 1005, which is a computer-readable storage medium, may include an operating system, a network communication module, a user interface module, and a device control application.

[0201] exist Figure 10In the illustrated electronic device 1000, the network interface 1004 provides network communication functionality; the user interface 1003 is primarily used to provide an input interface for the user; and the processor 1001 can be used to call the device control application stored in the memory 1005 to achieve:

[0202] Obtain the target ad request and determine the request identifier of the target ad request;

[0203] In response to the above target ad request being a duplicate ad request, the time interval between the current access to the above target ad request and the previous access is determined;

[0204] In response to the above target ad request, where the time interval between the current access and the previous access is less than a preset time interval, and the first cache space includes ad information stored in association with the above request identifier, at least one historical ad list generated during the previous processing of the above target ad request is obtained from the second cache space.

[0205] The target advertising information is determined based on at least one of the above historical advertising lists, and the target advertising information is returned.

[0206] In some feasible implementations, the processor 1001 is further configured to:

[0207] In response to the above target advertisement request, if the time interval between the current access and the previous access is less than the above preset time interval, and the above first cache space does not contain the advertisement information stored in association with the above request identifier, the first indication information is returned. The first indication information is used to indicate that the target advertisement information corresponding to the above target advertisement request has not been determined.

[0208] In some feasible implementations, the processor 1001 is further configured to:

[0209] In response to the above target ad request being a first-time ad request, or the above target ad request being a repeated ad request and the time interval between the current visit and the previous visit being greater than or equal to the above preset time interval, the above target ad request is processed.

[0210] In response to determining the target ad information corresponding to the above target ad request, the above target ad information is returned; or

[0211] In response to the failure to determine the target advertisement information corresponding to the above target advertisement request, a first indication information is returned, which is used to indicate that the target advertisement information corresponding to the above target advertisement request has not been determined.

[0212] In some feasible implementations, the processor 1001 described above is used for:

[0213] Based on preset filtering rules, at least one of the above-mentioned historical advertising lists is filtered to obtain a target advertising list, and the target advertising information is determined based on the above-mentioned target advertising list.

[0214] In some feasible implementations, the processor 1001 is further configured to:

[0215] In response to the failure to determine the target advertisement information based on at least one of the aforementioned historical advertisement lists, a first indication is returned, wherein the first indication is used to indicate that the target advertisement information corresponding to the target advertisement request has not been determined.

[0216] Based on the first instruction information mentioned above, update the advertising information stored in the first cache space that is associated with the request identifier.

[0217] In some feasible implementations, after returning the aforementioned target advertising information, the processor 1001 is further configured to:

[0218] Based on the aforementioned target advertising information, update the advertising information stored in the first cache space that is associated with the aforementioned request identifier.

[0219] In some feasible implementations, the aforementioned target advertisement request is an advertisement request for the first visit, and the processor 1001 is further configured to:

[0220] In response to the return of the aforementioned target advertising information, the aforementioned request identifier and the aforementioned target advertising information are associated and stored in the aforementioned first cache space; or

[0221] In response to the return of the first instruction information, the request identifier and the first instruction information are associated and stored in the first cache space.

[0222] In some feasible implementations, where the target advertisement request is a repeat advertisement request and the time interval between the current visit and the previous visit is greater than or equal to the preset time interval, the processor 1001 is further configured to:

[0223] In response to returning the aforementioned target advertising information, update the first indication information or advertising information stored in the first cache space associated with the aforementioned request identifier based on the aforementioned target advertising information; or

[0224] In response to the return of the first instruction information and the inclusion of advertising information stored in the first cache space associated with the request identifier, the advertising information stored in the first cache space associated with the request identifier is updated based on the first instruction information.

[0225] In some feasible implementations, the processor 1001 is further configured to:

[0226] At least one list of advertisements generated during the processing of the aforementioned target advertisement requests will be stored in the aforementioned second cache space.

[0227] In some feasible implementations, the aforementioned request identifier is determined by at least one of the following: the ad slot identifier corresponding to the aforementioned target ad request, the requester identifier, the ad slot type identifier, or the request time.

[0228] In some feasible implementations, the processor 1001 described above is used for:

[0229] In response to the aforementioned target ad request satisfying the ad request processing conditions, the request identifier of the aforementioned target ad request is determined, wherein the aforementioned ad request processing conditions include at least one of the following:

[0230] When an ad is played in the corresponding ad slot, the first resource quantity sent to the corresponding ad slot is less than the first resource quantity threshold; or

[0231] When the advertisement is played a preset number of times in the corresponding ad slot, the predicted second resource quantity is greater than or equal to the second resource quantity threshold.

[0232] It should be understood that in some feasible implementations, the processor 1001 described above may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor. The memory may include read-only memory and random access memory, and provides instructions and data to the processor. A portion of the memory may also include non-volatile random access memory. For example, the memory may also store device type information.

[0233] In specific implementation, the aforementioned electronic device 1000 can perform the above-described actions through its built-in functional modules. Figure 2 , Figure 4 and / or Figure 6 The implementation methods provided for each step are detailed in the above-mentioned implementation methods, and will not be repeated here.

[0234] This application also provides a computer-readable storage medium storing a computer program that is executed by a processor to perform... Figure 2 , Figure 4 and / or Figure 6 The methods provided in each step are detailed in the implementation methods provided in the above steps, and will not be repeated here.

[0235] The aforementioned computer-readable storage medium can be an internal storage unit of the apparatus or electronic device provided in any of the foregoing embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the electronic device. The aforementioned computer-readable storage medium can also include magnetic disks, optical disks, read-only memory (ROM), or random access memory (RAM), etc. Furthermore, the computer-readable storage medium can include both internal storage units and external storage devices of the electronic device. The computer-readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0236] This application provides a computer program product, which includes a computer program that is executed by a processor. Figure 2 , Figure 4 and / or Figure 6 The methods provided for each step in the process.

[0237] The terms "first," "second," etc., used in the claims, description, and drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or electronic device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or electronic devices. References to "embodiment" herein mean that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The presentation of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments. The term "and / or" as used in this application's description and appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0238] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Those skilled in the art can implement the described functions using different methods for each specific application, but such implementations should not be considered beyond the scope of this application.

[0239] The above-disclosed embodiments are merely preferred embodiments of this application and should not be construed as limiting the scope of this application. Therefore, any equivalent variations made in accordance with the claims of this application shall still fall within the scope of this application.

Claims

1. A method for processing advertising requests, characterized in that, The method includes: Obtain the target advertisement request and determine the request identifier of the target advertisement request; In response to the fact that the target ad request is a duplicate ad request, the time interval between the current access to the target ad request and the previous access is determined; In response to the target ad request, if the time interval between the current access and the previous access is less than a preset time interval, and the first cache space includes ad information stored in association with the request identifier, at least one historical ad list generated during the previous processing of the target ad request is obtained from the second cache space. The target advertising information is determined based on at least one of the historical advertising lists, and the target advertising information is returned.

2. The method according to claim 1, characterized in that, The method further includes: In response to the fact that the time interval between the current access and the previous access to the target advertisement request is less than the preset time interval, and the first cache space does not contain the advertisement information stored in association with the request identifier, a first indication is returned. The first indication is used to indicate that the target advertisement information corresponding to the target advertisement request has not been determined.

3. The method according to claim 1, characterized in that, The method further includes: In response to the target ad request being a first-time ad request, or the target ad request being a repeated ad request and the time interval between the current visit and the previous visit being greater than or equal to the preset time interval, the target ad request is processed. In response to determining the target advertisement information corresponding to the target advertisement request, the target advertisement information is returned; or In response to the failure to determine the target advertisement information corresponding to the target advertisement request, a first indication is returned, which indicates that the target advertisement information corresponding to the target advertisement request has not been determined.

4. The method according to claim 1, characterized in that, Determining the target advertisement information based on at least one of the historical advertisement lists includes: The advertising information in at least one of the historical advertising lists is filtered based on preset filtering rules to obtain a target advertising list, and the target advertising information is determined based on the target advertising list.

5. The method according to claim 1, characterized in that, The method further includes: In response to the failure to identify the target advertisement information based on at least one of the historical advertisement lists, a first indication is returned, the first indication indicating that the target advertisement information corresponding to the target advertisement request has not been identified. Based on the first indication information, update the advertising information stored in the first cache space that is associated with the request identifier.

6. The method according to claim 1, characterized in that, After returning the target advertisement information, the method further includes: Based on the target advertising information, update the advertising information stored in the first cache space that is associated with the request identifier.

7. The method according to claim 3, characterized in that, The target ad request is an ad request for the first visit, and the method further includes: In response to returning the target advertising information, the request identifier and the target advertising information are associated and stored in the first cache space; or In response to the return of the first indication information, the request identifier and the first indication information are associated and stored in the first cache space.

8. The method according to claim 3, characterized in that, The target ad request is a duplicate ad request and the time interval between the current visit and the previous visit is greater than or equal to the preset time interval. The method further includes: In response to returning the target advertising information, update the first indication information or advertising information stored in the first cache space associated with the request identifier based on the target advertising information; or In response to the return of the first indication information and the inclusion of advertising information stored in the first cache space associated with the request identifier, the advertising information stored in the first cache space associated with the request identifier is updated based on the first indication information.

9. The method according to claim 3, characterized in that, The method further includes: At least one list of advertisements generated during the processing of the target advertisement request is stored in the second cache space.

10. The method according to claim 1, characterized in that, The request identifier is determined by at least one of the following: the ad slot identifier corresponding to the target ad request, the requester identifier, the ad slot type identifier, or the request time.

11. The method according to claim 1, characterized in that, The step of determining the request identifier for the target advertisement request includes: In response to the target ad request satisfying the ad request processing conditions, the request identifier of the target ad request is determined, and the ad request processing conditions include at least one of the following: When an ad is played in the corresponding ad slot, the first resource quantity sent to the corresponding ad slot is less than the first resource quantity threshold; or When the advertisement is played a preset number of times in the corresponding ad slot, the predicted second resource quantity is greater than or equal to the second resource quantity threshold.

12. An advertising request processing device, characterized in that, The device includes: The acquisition module is used to acquire the target advertisement request and determine the request identifier of the target advertisement request; The processing module is used to respond to the fact that the target advertisement request is a duplicate advertisement request and determine the time interval between the current access and the previous access of the target advertisement request; The processing module is configured to, in response to the fact that the time interval between the current access to the target advertisement request and the previous access is less than a preset time interval, and the first cache space includes advertisement information stored in association with the request identifier, retrieve at least one historical advertisement list generated during the previous processing of the target advertisement request from the second cache space. The return module is used to determine the target advertisement information based on at least one of the historical advertisement lists and return the target advertisement information.

13. An electronic device, characterized in that, It includes a processor and a memory, which are interconnected; The memory is used to store computer programs; The processor is configured to perform the method as described in any one of claims 1 to 11 when the computer program is invoked.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that is executed by a processor to implement the method of any one of claims 1 to 11.

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

Images