A programmatic advertisement delivery method and device based on big data and a medium

Abstract

The embodiment of the specification discloses a programmatic advertisement putting method and device based on big data, equipment and medium, which relates to the technical field of Internet, and the method comprises the following steps: receiving advertisement putting requests of a plurality of advertisement putting users through an advertisement transaction platform, collecting basic data and behavior data of a plurality of target users through the advertisement transaction platform and big data collection technology; generating attribute labels corresponding to each target user in advance according to the basic data through a user portrait generation module, and generating operation labels corresponding to each target user according to the behavior data and a preset real-time label algorithm, so as to generate a user portrait of each target user based on the attribute labels and the operation labels; determining a specified putting user among the plurality of target users according to the plurality of advertisement putting requests and the user portrait of each target user through the advertisement transaction platform, and determining a specified putting advertisement among a plurality of to-be-put advertisements, so as to put the specified putting advertisement to the specified putting user.

Description

Technical Field

[0001] This specification relates to the field of Internet technology, and in particular to a method, device and medium for programmatic advertising based on big data. Background Technology

[0002] Throughout the development of the internet, advertising has always been a crucial business model and remains the primary and most direct profit model for websites. It is precisely the continuous impetus from internet advertising that has enabled the internet industry to flourish. With the advancement of internet technology, digital marketing methods and tools have constantly evolved, representing significant progress from early online advertising to social marketing.

[0003] Current ad delivery methods typically match user characteristics using user tags. These tags are calculated offline, and their real-time accuracy cannot be guaranteed. Therefore, existing ad delivery methods lack real-time user tags, compromising ad accuracy, leading to issues like duplicate ad delivery, and resulting in low delivery efficiency. Summary of the Invention

[0004] This specification provides one or more embodiments of a programmatic advertising delivery method, device, and medium based on big data, which is used to solve the following technical problems: existing advertising delivery methods lack real-time user tags, cannot guarantee the accuracy of advertising delivery, are prone to duplicate delivery, and have low delivery efficiency.

[0005] One or more embodiments of this specification employ the following technical solutions:

[0006] This specification provides one or more embodiments of a big data-based programmatic advertising delivery method, applied to a programmatic advertising delivery system. The programmatic advertising delivery system includes an ad exchange platform and a user profile generation module. The method includes: receiving ad delivery requests from multiple ad delivery users through the ad exchange platform, wherein each ad delivery request includes multiple ads to be delivered and ad information for each ad; collecting basic data and behavioral data of multiple target users through the ad exchange platform and big data acquisition technology; generating attribute tags for each target user in advance based on the basic data, and generating operational tags for each target user based on the behavioral data and a preset real-time tagging algorithm, thereby generating a user profile for each target user based on the attribute tags and the operational tags; and determining a designated user among the multiple target users and a designated ad among the multiple ads to be delivered through the ad exchange platform, so as to deliver the designated ad to the designated user.

[0007] Further, based on the behavioral data and a preset real-time tagging algorithm, an operational tag corresponding to each target user is generated. Specifically, this includes: acquiring the traffic-driving data already generated by the target user from the behavioral data, and specified behavioral data meeting preset requirements within a preset time period; determining non-interest category information in the traffic-driving data, and generating exclusion tags for the target user based on the non-interest category information, wherein the exclusion tags are used to exclude products within the same category based on the non-interest category information; determining interest category information in the specified behavioral data, and generating intention tags for the target user based on the interest category information, wherein the intention tags are used to recommend products within the same category based on the interest category information; and generating an operational tag corresponding to each target user using the exclusion tags and the intention tags.

[0008] Furthermore, based on the attribute tags and the operational tags, a user profile for each target user is generated, specifically including: horizontally and vertically stratifying the attribute tags and operational tags corresponding to each target user to generate a user tag matrix for each target user; and generating a user profile for each target user based on the user tag matrix for each target user.

[0009] Furthermore, after collecting basic data and behavioral data of multiple target users through an advertising exchange platform, the method further includes: obtaining device information of multiple target devices corresponding to the behavioral data of each target user, wherein the device information includes a device identifier; determining a specified target device that meets the requirements among the multiple target devices based on the device identifier in each device information, and determining the specified device information of the specified target device; establishing an association relationship between the specified device information of the specified target device and the target user, and binding the target user and the specified target device according to the association relationship, so as to send the specified advertisement to the specified target device of the specified target user.

[0010] Furthermore, based on the multiple ad delivery requests and the user profile of each target user, a designated user is identified from among the multiple target users, and a designated ad is identified from among the multiple ads to be delivered. Specifically, this includes: determining the target profile of the target user for each ad to be delivered based on the ad information in the multiple ad delivery requests; comparing the target profile of the target user for each ad to be delivered with the user profile of each target user to identify the designated user who meets preset requirements from among the multiple target users; determining the ad revenue data in each ad information; and based on the ad revenue data, identifying the designated ad with the highest ad revenue from among the multiple preset ads to be delivered.

[0011] Furthermore, after delivering the designated advertisement to the designated user, the method further includes: monitoring the actions of the designated user within a preset time period to obtain the action data of the designated user; generating additional interest tags for the designated user based on the action data of the designated user and the advertising information of the designated advertisement; and updating the user profile of the designated user through the additional interest tags.

[0012] Furthermore, the programmatic advertising system also includes a user demand management platform and a media traffic management platform. After receiving advertising requests from multiple advertising users through the advertising exchange platform, the method further includes: when the advertising exchange platform receives the advertising request, it sends an ad slot query request to the media traffic management platform; through the media traffic management platform and the ad slot query request, it generates ad slot information, wherein the ad slot information includes the ad slot's activation status and ad slot size data; through the advertising exchange platform, it sends the ad slot information to the user demand management platform, so that the user demand management platform can obtain advertising information for available ad slots, wherein the advertising information includes the ad slot address, advertising user identifier, and advertising price.

[0013] Furthermore, after delivering the designated advertisement to the designated user, the method further includes: obtaining the exposure data of the designated advertisement and sending the exposure data to the advertising exchange platform; and calculating the exposure data through the advertising exchange platform to complete the cost deduction operation for the designated advertisement.

[0014] This specification provides one or more embodiments of a programmatic advertising delivery device based on big data, including:

[0015] At least one processor; and,

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to:

[0018] The system receives ad delivery requests from multiple ad delivery users through an ad exchange platform. Each ad delivery request includes multiple ads to be delivered and ad information for each ad. The system also collects basic and behavioral data from multiple target users using the ad exchange platform and big data acquisition technology. A user profile generation module pre-generates attribute tags for each target user based on the basic data and generates operational tags for each target user based on the behavioral data and a preset real-time tagging algorithm. Based on these attribute tags and operational tags, a user profile for each target user is generated. Finally, the ad exchange platform identifies a designated user among the multiple target users and a designated ad among the multiple ads to be delivered, allowing the designated ad to be delivered to the designated user.

[0019] This specification provides one or more embodiments of a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured as follows:

[0020] The system receives ad delivery requests from multiple ad delivery users through an ad exchange platform. Each ad delivery request includes multiple ads to be delivered and ad information for each ad. The system also collects basic and behavioral data from multiple target users using the ad exchange platform and big data acquisition technology. A user profile generation module pre-generates attribute tags for each target user based on the basic data and generates operational tags for each target user based on the behavioral data and a preset real-time tagging algorithm. Based on these attribute tags and operational tags, a user profile for each target user is generated. Finally, the ad exchange platform identifies a designated user among the multiple target users and a designated ad among the multiple ads to be delivered, allowing the designated ad to be delivered to the designated user.

[0021] The above-mentioned at least one technical solution adopted in the embodiments of this specification can achieve the following beneficial effects: Through the above technical solution, basic user data and behavioral data are obtained through big data collection, a real-time algorithm tag system is introduced, and offline tag calculation and real-time tag calculation are performed on the tags, ensuring the accuracy of user tags, further improving the accuracy of user profiles, improving advertising efficiency, reducing duplicate and invalid pushes, and advertising users can also programmatically purchase media resources to automatically achieve accurate target audience targeting, thereby improving the accuracy of advertising. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0023] Figure 1 A flowchart illustrating a programmatic advertising delivery method based on big data, provided as an embodiment of this specification;

[0024] Figure 2 A schematic diagram of the workflow of a programmatic advertising delivery system provided in the embodiments of this specification;

[0025] Figure 3 A schematic diagram illustrating a layered example of an operational label provided in this specification.

[0026] Figure 4 This is a schematic diagram of a programmatic advertising delivery device based on big data, provided as an embodiment of this specification. Detailed Implementation

[0027] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0028] Throughout the development of the internet, advertising has always been a crucial business model and remains the primary and most direct profit model for websites. It is precisely the continuous impetus from internet advertising that has enabled the internet industry to flourish. With the advancement of internet technology, digital marketing methods and tools have constantly evolved, representing significant progress from early online advertising to social marketing.

[0029] Current ad delivery methods typically match user characteristics using user tags. These tags are calculated offline, and their real-time accuracy cannot be guaranteed. Therefore, existing ad delivery methods lack real-time user tags, compromising ad accuracy, leading to issues like duplicate ad delivery, and resulting in low delivery efficiency.

[0030] This specification provides a programmatic advertising delivery method based on big data. The execution entity in this specification can be a server or any device with data processing capabilities. It should be noted that this specification applies to a programmatic advertising delivery system, which includes an ad exchange platform and a user profile generation module. The ad exchange platform receives delivery requests from ad delivery users and collects user information from end users; these ad delivery users can be referred to as advertisers. Figure 1 A flowchart illustrating a programmatic advertising delivery method based on big data, provided as an embodiment of this specification, is shown below. Figure 1 As shown, the main steps include the following:

[0031] Step S101: Receive advertising placement requests from multiple advertising users through the advertising exchange platform.

[0032] In one embodiment of this specification, an advertising exchange platform receives advertising placement requests from multiple advertising users. Each advertising placement request includes multiple advertisements to be placed and advertising information for each advertisement. This advertising information may include the target audience, the placement strategy, and the cost of the advertisement. It should be noted that in practical applications, there may be multiple advertisers requiring ad exposure, such as advertisers for food, vehicles, and clothing. Different advertisers can apply to the system for ad exposure, i.e., send advertising placement requests, also known as ad exposure requests.

[0033] The programmatic advertising system also includes a user demand management platform and a media traffic management platform. After receiving advertising requests from multiple advertising users through the advertising exchange platform, the method further includes: when the advertising exchange platform receives the advertising request, it sends an ad slot query request to the media traffic management platform; through the media traffic management platform and the ad slot query request, it generates ad slot information, wherein the ad slot information includes the ad slot's activation status and ad slot size data; through the advertising exchange platform, it sends the ad slot information to the user demand management platform, so that the user demand management platform can obtain advertising information for available ad slots, wherein the advertising information includes the ad slot address, advertising user identifier, and advertising price.

[0034] In one embodiment of this specification, a user demand management platform is constructed for advertisers to register and upload advertising material information, and a media traffic management platform is constructed for media terminals to maintain advertising space information. An advertising trading platform is also constructed, which connects to both the user demand management platform and the media traffic management platform. Figure 2This specification provides a schematic diagram of the workflow of a programmatic advertising delivery system, as illustrated in the embodiments herein. Figure 2 As shown,

[0035] After receiving an ad impression request, the ad exchange platform first queries the media traffic management platform for ad placement details, such as ad placement activation status and size. Then, it requests the user demand management platform, along with the ad placement information, to obtain available ad placement information for that ad placement. The user demand management platform will then return ad creative addresses, advertisers, ad quotes, and other placement data.

[0036] After the designated ad is delivered to the designated user, the method further includes: obtaining the exposure data of the designated ad and sending the exposure data to the ad exchange platform; and calculating the exposure data through the ad exchange platform to complete the cost deduction operation for the designated ad.

[0037] In one embodiment of this specification, after an advertisement is placed, advertisement exposure data will be generated and sent to the advertising trading platform. The advertising trading platform will then calculate the exposure data and complete the cost deduction operation for the designated advertisement, thereby realizing the advertisement placement transaction.

[0038] Step S102: Collect basic and behavioral data of multiple target users through advertising exchange platforms and big data collection technology.

[0039] In one embodiment of this specification, basic data and behavioral data of each target user are collected through an advertising exchange platform. It should be noted that the basic data here refers to basic data such as the user's gender and age, while the behavioral data refers to data corresponding to the user's actions over a period of time, such as receiving coupons, recharging, liking, commenting, and forwarding.

[0040] In one embodiment of this specification, a big data platform can be built to collect basic user data from multiple channels, and then perform data cleaning and aggregation to obtain basic data for each target user. Behavioral data can be obtained from user behavior data on smart terminals, which can be mobile phones, tablets, or other terminal devices.

[0041] After collecting basic and behavioral data of multiple target users through an advertising exchange platform, the method further includes: obtaining device information of multiple target devices corresponding to the behavioral data of each target user, wherein the device information includes a device identifier; determining a specified target device that meets the requirements among the multiple target devices based on the device identifier in each device information, and determining the specified device information of the specified target device; establishing an association between the specified device information of the specified target device and the target user, and binding the target user to the specified target device based on the association, so as to send the specified advertisement to the specified target device of the specified target user.

[0042] In real-world applications, existing methods for ad delivery may involve one user across multiple devices or one account used by multiple users. In such cases, the resulting user data cannot accurately represent the user's characteristics, leading to inaccurate user profiles and inaccurate ad delivery.

[0043] In one embodiment of this specification, device information of multiple target devices corresponding to the generated behavioral data is obtained. This device information includes device identifiers, which can be unique identification information such as device serial numbers or mobile phone numbers. Among the multiple target devices, the most frequently used designated target device is identified, and its designated device information is determined. An association relationship is established between the designated device information of the designated target device and the target user. Based on this association relationship, the target user is bound to the designated target device. After binding the user to the designated target device, a specific advertisement can be sent to the designated target device of the designated target user, or the behavioral data generated on the designated target device can be used as the user's behavioral data. This ensures both the accuracy of advertisement delivery and the authenticity of user data.

[0044] Step S103: The user profile generation module generates attribute tags for each target user in advance based on basic data, and generates operational tags for each target user based on behavioral data and a preset real-time tagging algorithm, so as to generate a user profile for each target user based on the attribute tags and the operational tags.

[0045] In one embodiment of this specification, a user profile generation module performs offline data aggregation and cleaning on basic data. Based on the basic data, attribute tags are generated for each target user. It should be noted that these attribute tags are basic attribute tags such as user interests and preferences. Based on behavioral data and a preset real-time tagging algorithm, operational tags are generated for each target user. A user profile for each target user is then generated based on these attribute tags and operational tags. It should be noted that these operational tags are generated based on user behavioral data and are used to indicate the likelihood of a user performing a certain action within a given timeframe.

[0046] Based on the behavioral data and a preset real-time tagging algorithm, an operational tag is generated for each target user. Specifically, this includes: acquiring the traffic-driving data already generated by the target user within the behavioral data, and specified behavioral data meeting preset requirements within a preset time period; determining non-interest category information in the traffic-driving data, and generating an exclusion tag for the target user based on this non-interest category information, wherein the exclusion tag is used to exclude products within the same category based on the non-interest category information; determining interest category information in the specified behavioral data, and generating an intention tag for the target user based on this interest category information, wherein the intention tag is used to recommend products within the same category based on the interest category information; and generating an operational tag for each target user using the exclusion tag and the intention tag.

[0047] In one embodiment of this specification, the behavioral data includes generated referral data, such as having purchased a product, downloaded an app, or registered for a game, as well as specified behavioral data within a preset time period that meets preset requirements. Meeting preset requirements refers to high-frequency behaviors within a recent period, such as searching for multiple car models, claiming coupons for a specific category, or repeatedly forwarding articles of a certain category. Non-interest category information is determined from the referral data. Since the referral data represents actions already generated, generally, after performing this action, users will not subsequently select similar products or engage in similar behaviors. Therefore, exclusion tags for target users can be generated based on the non-interest category information in the referral data. These exclusion tags are used to exclude products within the same category based on the non-interest category information. Additionally, interest category information is determined from the specified behavioral data. For example, claiming coupons for a specific category. If a user frequently claims coupons for a specific category within a recent period, it indicates that the user is interested in that category and may subsequently make purchases in that category. In other words, intention tags for target users can be generated based on the interest category information in the specified behavioral data. These intention tags are used to recommend products within the same category based on the interest category information. By excluding category tags and intention category tags, operational tags are generated for each target user.

[0048] Based on the attribute tag and the operation tag, a user profile for each target user is generated, specifically including: horizontally and vertically stratifying the attribute tag and the operation tag corresponding to each target user to generate a user tag matrix for each target user; and generating a user profile for each target user based on the user tag matrix for each target user.

[0049] In one embodiment of this specification, the tag system is layered horizontally (attribute tags) and vertically (operational tags) to form a user tag matrix. In addition to traditional category-based push notifications, the vertical flow of users can also be observed, thereby enabling the understanding of the user lifecycle.

[0050] Figure 3 A schematic diagram illustrating a layered example of an operational label provided in this specification, such as... Figure 3 As shown, operational tags can be layered into primary, secondary, and tertiary tags. Primary tags include platform behavior, marketing behavior, and brand and product preferences. Each primary tag includes at least one secondary tag. Each secondary tag includes at least one tertiary tag. For example, when the primary tag is platform behavior, its secondary tag is behavior path, and the corresponding tertiary tags are search-oriented users and browsing-oriented users. Search-oriented users are defined as having performed 5 searches sequentially within the past 30 days; browsing-oriented users are defined as having viewed product details more than 10 times sequentially within the past 30 days. It should be noted that the definition rules can also be set according to actual needs. When the primary tag is brand and product preferences, the corresponding secondary tag is brand / product preferences, and the corresponding tertiary tags include product preferences and brand preferences. The definition rules for product preference are as follows: Product preference is tagged using the number of times a user's product name appears most frequently on the product details page within a preset time period (e.g., the top 5). Brand preference is tagged using the number of times a user's current price appears most frequently on the product details page within a preset time period (e.g., the top 20). The preset time period can be 30 days. When the primary tag is a marketing activity, the corresponding secondary tags include price range, marketing activities, recharge, coupons, and points. The tertiary tag for price range is price-sensitive user; the tertiary tag for marketing activities is marketing activity enthusiast; the tertiary tags for recharge are new recharge user, high-spending user, large-spending user, and average recharger; the tertiary tags for coupons are high-sensitivity user, medium-sensitivity user, and low-sensitivity user; the tertiary tags for points are high-level user, medium-level user, and low-level user. The definition rules for each tertiary tag are as follows: Figure 3 As shown.

[0051] Step S104: Through the advertising exchange platform, based on multiple advertising requests and the user profile of each target user, the designated target user is identified among the multiple target users, and the designated advertising is identified among the multiple advertisements to be placed, so as to place the designated advertising on the designated target user.

[0052] Based on the multiple ad delivery requests and the user profile of each target user, a designated user is identified from among the multiple target users, and a designated ad is identified from among the multiple ads to be delivered. Specifically, this includes: determining the target user profile of each ad to be delivered based on the ad information in the multiple ad delivery requests; comparing the target user profile of each ad to be delivered with the user profile of each target user to identify the designated user who meets preset requirements from among the multiple target users; determining the ad revenue data in each ad information; and based on the ad revenue data, identifying the designated ad with the highest ad revenue from among the multiple ads to be delivered.

[0053] In one embodiment of this specification, based on the advertising information in each advertising request, a target user profile for each advertisement to be delivered is determined. Each target profile is then compared with the user profile of each target user to identify designated users who meet preset requirements from among multiple target users. It should be noted that user profiles whose profile comparison results exceed a preset threshold can be used as the target audience for the advertisements to be delivered. Furthermore, since there are multiple advertisements to be delivered, advertising revenue data for each advertisement is determined based on the advertiser's delivery strategy and advertising bidding data. Based on the advertising revenue data, the designated advertisement with the highest advertising revenue is identified from among the multiple advertisements to be delivered.

[0054] After the designated ad is delivered to the designated user, the method further includes: monitoring the actions of the designated user within a preset time period to obtain the user's action data; generating additional interest tags for the designated user based on the user's action data and the ad information of the designated ad; and updating the user profile of the designated user using the additional interest tags.

[0055] In one embodiment of this specification, after the user receives the advertising material information, the user's actions within a preset time period are recorded, and their action data is obtained. The preset time period may be the dwell time on the user terminal interface of the advertisement, and the action data may be actions such as skipping, clicking, and forwarding. Based on the user's action data and the advertising information of the advertising material, additional interest tags for the user are generated. The additional interest tags are then updated in the user profile generation module to make the user profile easier to use next time.

[0056] Through the above technical solutions, basic user data and behavioral data are obtained through big data collection. A real-time algorithm tagging system is introduced to perform offline and real-time tag calculations, ensuring the accuracy of user tags and further improving the accuracy of user profiles. This enhances advertising efficiency, reduces duplicate and ineffective push notifications, and allows advertisers to programmatically purchase media resources and automatically achieve precise target audience targeting, thereby improving the accuracy of advertising.

[0057] This specification also provides another programmatic advertising method based on big data. First, a big data platform is built to offline aggregate user data collected from multiple channels, obtaining and saving basic attribute tags such as user interests and preferences. Next, online user behavior data (e.g., claiming certain coupons) is analyzed to generate user operation tags, used to mark the likelihood of users performing a certain action in the near future. The tag system is layered horizontally (attribute tags) and vertically (operation tags) to form a user tag matrix. In addition to traditional category-based push notifications, the vertical flow of users can be observed, thus allowing for the understanding of the user lifecycle. Furthermore, a user demand management platform is built for advertisers to register and upload advertising material information, and a media traffic management platform is built for media terminals to maintain advertising space information. An advertising transaction platform is built, simultaneously connecting to the user demand management platform and the media traffic management platform. By analyzing media traffic to obtain user identification information, user algorithm tags are combined with basic attribute tags to filter out target customers belonging to advertisers and deliver advertisements, completing the advertising transaction. Finally, user action information regarding advertising materials is fed back, and the user's algorithm tags and basic tags are improved and supplemented based on further user actions.

[0058] In one embodiment of this specification, the user profiling system collects user data through offline or online activities, performs preliminary data cleaning, filters and analyzes user behavior data generated within the app (e.g., likes, comments, shares), converts it into structured user interest tags (e.g., cars, real estate), and binds them to unique identification information such as frequently used device serial numbers or mobile phone numbers. When a user launches the app on a smart terminal, a pre-set advertising space (e.g., a splash screen ad) sends an ad request to the advertising exchange platform, carrying user account and other identification information.

[0059] After receiving an ad impression request, the ad exchange platform first queries the media traffic management platform for ad placement details, such as ad placement activation status and size. Then, it requests the user demand management platform, along with the ad placement information, to obtain available ad placement information for that ad placement. The user demand management platform then returns ad creative URLs, advertisers, ad quotes, and other placement data.

[0060] The user profiling system extracts user data as follows after receiving it: First, it uses the user's existing traffic generation effects as the highest weight (e.g., having purchased a product, downloaded an app, or registered for a game) to exclude similar products; second, it uses the user's high-frequency behaviors in recent times as the second weight (e.g., searching for multiple car models, claiming coupons for a certain category, or repeatedly forwarding articles of a certain category) to recommend and label similar products; finally, it combines the user's basic attribute tags calculated offline to generate user identification features (e.g., middle-aged male, has a family, purchased women's clothing yesterday) and returns them to the advertising exchange platform.

[0061] After acquiring the ad creative information, the ad exchange calculates the most relevant and profitable creative based on different advertisers' strategies and bidding data, and returns it to the user. The user receives the creative and displays it, while simultaneously recording user actions (e.g., skipping, clicking, sharing). The user then pushes the ad exposure data back to the ad exchange, which performs calculations, deducts costs, and supplements and refines the user profile system with relevant user interest characteristics.

[0062] This specification also provides an embodiment of a programmatic advertising delivery device based on big data, such as... Figure 4 As shown, the device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to:

[0063] The system receives ad delivery requests from multiple ad delivery users through an ad exchange platform. Each ad delivery request includes multiple ads to be delivered and the ad information for each ad. The system then collects basic and behavioral data from multiple target users using the ad exchange platform and big data collection technology. A user profile generation module pre-generates attribute tags for each target user based on the basic data and generates operational tags for each target user based on the behavioral data and a pre-set real-time tagging algorithm. Based on these attribute tags and operational tags, a user profile for each target user is generated. Finally, the ad exchange platform identifies a designated user from among the multiple target users and a designated ad from among the multiple ads to be delivered, allowing the designated ad to be delivered to that designated user.

[0064] This specification also provides a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured as follows:

[0065] The system receives ad delivery requests from multiple ad delivery users through an ad exchange platform. Each ad delivery request includes multiple ads to be delivered and the ad information for each ad. The system then collects basic and behavioral data from multiple target users using the ad exchange platform and big data collection technology. A user profile generation module pre-generates attribute tags for each target user based on the basic data and generates operational tags for each target user based on the behavioral data and a pre-set real-time tagging algorithm. Based on these attribute tags and operational tags, a user profile for each target user is generated. Finally, the ad exchange platform identifies a designated user from among the multiple target users and a designated ad from among the multiple ads to be delivered, allowing the designated ad to be delivered to that designated user.

[0066] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0067] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0068] The devices, media, and methods provided in the embodiments of this specification are one-to-one correspondences. Therefore, the devices and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0069] Those skilled in the art will understand that embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this specification may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0070] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0071] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0072] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0073] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0074] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0075] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0076] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0077] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. A programmatic advertising delivery method based on big data, characterized in that, The method is applied to a programmatic advertising delivery system, wherein the programmatic advertising delivery system includes: an ad exchange platform and a user profile generation module, and the method includes: The advertising exchange platform receives advertising placement requests from multiple advertising users, wherein each advertising placement request includes multiple advertisements to be placed and advertising information for each advertisement to be placed; By using advertising exchange platforms and big data collection technologies, basic and behavioral data of multiple target users can be collected. The user profile generation module generates attribute tags for each target user in advance based on the basic data, and generates operational tags for each target user based on the behavioral data and the preset real-time tag algorithm, so as to generate a user profile for each target user based on the attribute tags and the operational tags. Through the advertising trading platform, based on multiple advertising requests and the user profile of each target user, a designated user is identified from among the multiple target users, and a designated advertisement is identified from among the multiple advertisements to be placed, so as to place the designated advertisement on the designated user. Based on the behavioral data and a preset real-time tagging algorithm, an operational tag is generated for each target user, specifically including: Acquire the traffic generation data generated by the target user in the behavioral data, as well as the specified behavioral data that meets the preset requirements within a preset time period; Identify non-interest category information in the traffic acquisition data, and generate exclusion tags for target users based on the non-interest category information in the traffic acquisition data, wherein the exclusion tags are used to exclude products of the same category based on the non-interest category information; The interest category information in the specified behavioral data is determined, and the intention category tag of the target user is generated based on the interest category information in the specified behavioral data, wherein the intention category tag is used to make recommendations within the same category based on the interest category information; The operation tag corresponding to each target user is generated by using the exclusion category tag and the intention category tag; Based on the attribute tags and the operational tags, a user profile is generated for each target user, specifically including: The attribute tags and operational tags corresponding to each target user are layered horizontally and vertically to generate a user tag matrix for each target user; Based on the user tag matrix of each target user, a user profile for each target user is generated; After delivering the designated advertisement to the designated users, the method further includes: Within a preset time period, the actions of the designated users are monitored to obtain the action data of the designated users. Based on the action data of the designated user and the advertising information of the designated advertisement, generate additional interest tags for the designated user; The user profile of the designated target users is updated using the additional interest tags.

2. The programmatic advertising delivery method based on big data according to claim 1, characterized in that, After collecting basic and behavioral data from multiple target users through an advertising exchange platform, the method further includes: Obtain device information of multiple target devices corresponding to the behavioral data of each target user, wherein the device information includes a device identifier; Based on the device identifier in each device information, a specified target device that meets the requirements is identified from multiple target devices, and the specified device information of the specified target device is determined. Establish an association between the specified device information of the specified target device and the target user, and bind the target user and the specified target device according to the association, so as to send the specified advertisement to the specified target device of the target user.

3. The programmatic advertising delivery method based on big data according to claim 1, characterized in that, Based on the multiple ad delivery requests and the user profile of each target user, a designated user is identified from the multiple target users, and a designated ad is identified from the multiple ads to be delivered, specifically including: Based on the advertising information in the multiple advertising delivery requests, determine the target user profile for each advertisement to be delivered; By comparing the target profile of each target user with the user profile of each target user, the designated target users who meet the preset requirements are identified from multiple target users. Determine the advertising revenue data for each of the aforementioned advertising messages; Based on the advertising revenue data, the designated advertisement with the highest advertising revenue is determined from a plurality of preset advertisements to be placed.

4. The programmatic advertising delivery method based on big data according to claim 1, characterized in that, The programmatic advertising delivery system also includes a user demand management platform and a media traffic management platform. After receiving advertising delivery requests from multiple advertising users through the advertising exchange platform, the method further includes: After receiving the ad delivery request, the ad exchange platform sends an ad slot query request to the media traffic management platform. Ad placement information is generated through the media traffic management platform and the ad placement query request, wherein the ad placement information includes the ad placement's activation status and ad placement size data; The advertising exchange platform sends the advertising space information to the user demand management platform so that the user demand management platform can obtain advertising placement information for available advertising spaces. The advertising placement information includes the advertising space address, the advertising user identifier, and the advertising placement price.

5. The programmatic advertising delivery method based on big data according to claim 4, characterized in that, After delivering the designated advertisement to the designated users, the method further includes: Obtain the exposure data of the designated advertisement and send the exposure data to the advertising exchange platform; The advertising trading platform is used to calculate the exposure data and complete the cost deduction operation for the designated advertising placement.

6. A programmatic advertising delivery device based on big data, characterized in that, The device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to: The advertising exchange platform receives advertising placement requests from multiple advertising users, wherein each advertising placement request includes multiple advertisements to be placed and advertising information for each advertisement to be placed; By using advertising exchange platforms and big data collection technologies, basic and behavioral data of multiple target users can be collected. The user profile generation module generates attribute tags for each target user in advance based on the basic data, and generates operational tags for each target user based on the behavioral data and the preset real-time tag algorithm, so as to generate a user profile for each target user based on the attribute tags and the operational tags. Through the advertising trading platform, based on multiple advertising requests and the user profile of each target user, a designated user is identified from among the multiple target users, and a designated advertisement is identified from among the multiple advertisements to be placed, so as to place the designated advertisement on the designated user. Based on the behavioral data and a preset real-time tagging algorithm, an operational tag is generated for each target user, specifically including: Acquire the traffic generation data generated by the target user in the behavioral data, as well as the specified behavioral data that meets the preset requirements within a preset time period; Identify non-interest category information in the traffic acquisition data, and generate exclusion tags for target users based on the non-interest category information in the traffic acquisition data, wherein the exclusion tags are used to exclude products of the same category based on the non-interest category information; The interest category information in the specified behavioral data is determined, and the intention category tag of the target user is generated based on the interest category information in the specified behavioral data, wherein the intention category tag is used to make recommendations within the same category based on the interest category information; The operation tag corresponding to each target user is generated by using the exclusion category tag and the intention category tag; Based on the attribute tags and the operational tags, a user profile is generated for each target user, specifically including: The attribute tags and operational tags corresponding to each target user are layered horizontally and vertically to generate a user tag matrix for each target user; Based on the user tag matrix of each target user, a user profile for each target user is generated; After delivering the designated advertisement to the designated users, the process further includes: Within a preset time period, the actions of the designated users are monitored to obtain the action data of the designated users. Based on the action data of the designated user and the advertising information of the designated advertisement, generate additional interest tags for the designated user; The user profile of the designated target users is updated using the additional interest tags.

7. A non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured as follows: Through the advertising exchange platform, we receive advertising placement requests from multiple advertising users. The ad delivery request includes multiple ads to be delivered and ad information for each ad to be delivered; By using advertising exchange platforms and big data collection technologies, basic and behavioral data of multiple target users can be collected. The user profile generation module generates attribute tags for each target user in advance based on the basic data, and generates operational tags for each target user based on the behavioral data and the preset real-time tag algorithm, so as to generate a user profile for each target user based on the attribute tags and the operational tags. Through the advertising trading platform, based on multiple advertising requests and the user profile of each target user, a designated user is identified from among the multiple target users, and a designated advertisement is identified from among the multiple advertisements to be placed, so as to place the designated advertisement on the designated user. Based on the behavioral data and a preset real-time tagging algorithm, an operational tag is generated for each target user, specifically including: Acquire the traffic generation data generated by the target user in the behavioral data, as well as the specified behavioral data that meets the preset requirements within a preset time period; Identify non-interest category information in the traffic acquisition data, and generate exclusion tags for target users based on the non-interest category information in the traffic acquisition data, wherein the exclusion tags are used to exclude products of the same category based on the non-interest category information; The interest category information in the specified behavioral data is determined, and the intention category tag of the target user is generated based on the interest category information in the specified behavioral data, wherein the intention category tag is used to make recommendations within the same category based on the interest category information; The operation tag corresponding to each target user is generated by using the exclusion category tag and the intention category tag; Based on the attribute tags and the operational tags, a user profile is generated for each target user, specifically including: The attribute tags and operational tags corresponding to each target user are layered horizontally and vertically to generate a user tag matrix for each target user; Based on the user tag matrix of each target user, a user profile for each target user is generated; After delivering the designated advertisement to the designated users, the process further includes: Within a preset time period, the actions of the designated users are monitored to obtain the action data of the designated users. Based on the action data of the designated user and the advertising information of the designated advertisement, generate additional interest tags for the designated user; The user profile of the designated target users is updated using the additional interest tags.

Images