Advertisement delivery method and device, storage medium, and electronic device
By obtaining and matching advertising delivery data, automatically allocating virtual resources and pushing advertisements to matching user terminals, the problem of low advertising planning efficiency is solved and the accuracy and return of advertising delivery is improved.
Patent Information
- Application Number
- CN202111592429.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-12-23
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2041-12-23
AI Technical Summary
The efficiency of advertising planning during the existing advertising delivery process is low, resulting in inaccurate budget allocation, low return rate and lack of effective solutions.
By obtaining relevant data of advertisements that have been placed on multiple contacts, allocating virtual resources in proportion, and using ad browsing historical data to extract the contact feature vectors to match the user feature vectors, automatically pushing advertisements to the user terminal with the highest matching degree to ensure accurate resources distribute.
It realizes the precise allocation of advertising budget, improves advertising delivery efficiency and return rate, and solves the problem of low advertising planning efficiency.
Smart Images

Figure CN114399328B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of the Internet, and more specifically, to an advertisement delivery method and device, a storage medium, and an electronic device. Background Art
[0002] With the rapid development of Internet technology, Internet advertising has become an important channel for the public to understand brands. How companies can use limited budgets to carry out accurate brand marketing is a very hot topic. Advertising budget allocation is to help companies solve the budget allocation problem of various delivery channels during the advertising process, so that limited budgets can get the maximum return through reasonable budget planning. The current solution is usually configured based on experience, requiring users to manually collect relevant information, organize and analyze it, which has low planning efficiency and low budget return rate.
[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention
[0004] The embodiments of the present application provide a method and device for delivering advertisements, a storage medium, and an electronic device, so as to at least solve the technical problem of low efficiency of advertisement planning in the related art.
[0005] According to one aspect of an embodiment of the present application, a method for delivering advertisements is provided, comprising: obtaining a data set, wherein the data set includes relevant data of advertisements delivered at multiple touch points; allocating total virtual resources configured for a target advertisement to each of the multiple touch points in proportion according to the data set, wherein each time a target advertisement is pushed to a user terminal at a touch point, virtual resources allocated to the touch point need to be consumed; and pushing the target advertisement to a matched target user terminal at a target touch point of the multiple touch points, wherein the target touch point is any one of the multiple touch points.
[0006] Optionally, the data set includes historical data of advertisement browsing, and on a target touch point of multiple touch points, the target advertisement is pushed to a matched target user terminal, including: extracting a touch feature vector from the historical data of advertisement browsing, wherein the touch feature vector is a feature vector of a reference user facing the target touch point; when advertisement requests from multiple user terminals are received on the target touch point, matching the user feature vectors of the multiple user terminals with the touch feature vector to obtain a matching degree between the user feature vector of each user terminal and the touch feature vector; and pushing the target advertisement to the target user terminal with the highest matching degree among the multiple user terminals.
[0007] Optionally, user feature vectors of multiple user terminals are matched with contact feature vectors to obtain a matching degree between the user feature vectors of each user terminal and the contact feature vector, including: calculating the Euclidean distance between the user feature vectors of multiple user terminals and the contact feature vector, and using the obtained Euclidean distance between the user feature vectors of each user terminal and the contact feature vector as the matching degree.
[0008] Optionally, before pushing the target advertisement to the target user terminal with the highest matching degree among multiple user terminals, the method also includes: obtaining the amount of available virtual resources allocated to the target contact; after pushing the target advertisement to the target user terminal with the highest matching degree among multiple user terminals, the method also includes: subtracting the amount of specified resources from the amount of available virtual resources allocated to the target contact, wherein the specified amount of resources is the amount of resources required to push the target advertisement to the user terminal once.
[0009] Optionally, after obtaining the available virtual resource amount allocated to the target contact, the method further includes: if the available virtual resource amount allocated to the target contact is less than a specified resource amount, stopping pushing the target advertisement on the target contact.
[0010] Optionally, the data set includes historical data of advertising delivery, and based on the data set, the total virtual resources configured for the target advertisement are allocated to each of the multiple touch points in proportion, including: determining the allocation ratio of each of the multiple touch points in the total virtual resources based on the historical data of advertising delivery; allocating virtual resources in the total virtual resources to each of the multiple touch points according to the allocation ratio.
[0011] Optionally, based on historical data of advertising delivery, the allocation ratio of each of the multiple touch points in the total virtual resources is determined, including: using the historical data of advertising delivery to determine the return on investment (ROI) of each touch point; normalizing the obtained ROI of each touch point to obtain the contribution value of each touch point in a push; and using the proportion of the contribution value of each touch point in the sum of the contribution values of all touch points as the allocation ratio of each touch point in the total virtual resources.
[0012] According to another aspect of an embodiment of the present application, there is also provided an advertisement delivery device, comprising: an acquisition unit, for acquiring a data set, wherein the data set includes relevant data of advertisements delivered at multiple touch points; an allocation unit, for allocating the total virtual resources configured for the target advertisement to each of the multiple touch points in proportion according to the data set, wherein each time the target advertisement is pushed to a user terminal at a touch point, the virtual resources allocated to the touch point need to be consumed; and a pushing unit, for pushing the target advertisement to the matched target user terminal at a target touch point of the multiple touch points, wherein the target touch point is any one of the multiple touch points.
[0013] According to another aspect of an embodiment of the present application, a storage medium is further provided, which includes a stored program, and the above method is executed when the program is run.
[0014] According to another aspect of an embodiment of the present application, an electronic device is further provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the above method through the computer program.
[0015] According to one aspect of the present application, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps of any one of the embodiments of the above method.
[0016] This application can be used to provide operational optimization technical support for EIP products, such as mathematical programming. In an embodiment of the present application, a data set is obtained, which includes relevant data on advertisements that have been delivered at multiple touch points; based on the data set, the total virtual resources configured for the target advertisement are allocated to each of the multiple touch points in proportion, and each time the target advertisement is pushed to a user terminal at a touch point, the virtual resources allocated to the touch point need to be consumed; at the target touch point of the multiple touch points, the target advertisement is pushed to the matched target user terminal, and the target touch point is any touch point among the multiple touch points. The entire solution can be automatically executed, and the solution can accurately allocate the budget allocated on the touch point to the person, which can solve the technical problem of low efficiency of advertising planning in related technologies. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0018] Figure 1 is a schematic diagram of a hardware environment of an advertisement delivery method according to an embodiment of the present application;
[0019] Figure 2 is a flow chart of an optional method for delivering advertisements according to an embodiment of the present application;
[0020] Figure 3 is a schematic diagram of an optional advertisement delivery solution according to an embodiment of the present application;
[0021] Figure 4 is a schematic diagram of an optional advertisement delivery device according to an embodiment of the present application; and,
[0022] Figure 5 It is a structural block diagram of a terminal according to an embodiment of the present application. DETAILED DESCRIPTION
[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.
[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0025] According to one aspect of the embodiments of the present application, a method embodiment of a method for delivering advertisements is provided.
[0026] Optionally, in this embodiment, the above advertisement delivery method can be applied to: Figure 1 In the hardware environment composed of the terminal 101 and the server 103 shown in FIG. Figure 1 As shown, the server 103 is connected to the terminal 101 via a network, and can be used to provide advertising services for the terminal or a client installed on the terminal. A database 105 can be set on the server or independently of the server to provide data storage services for the server 103. The above-mentioned network includes but is not limited to: a wide area network, a metropolitan area network or a local area network, and the terminal 101 is not limited to a PC, a mobile phone, a tablet computer, etc.
[0027] The advertisement delivery method of the embodiment of the present application may be executed by the server 103 , or may be executed jointly by the server 103 and the terminal 101 . Figure 2 is a flow chart of an optional method for delivering advertisements according to an embodiment of the present application, such as Figure 2 As shown, the method may include the following steps:
[0028] In step S202, the server obtains a data set, which includes relevant data on advertisements delivered at multiple touch points, such as historical data on advertisement delivery and historical data on advertisement browsing, so that part of the data is used for budget allocation and part of the data is used for advertisement recommendation.
[0029] Touch Point (TP), a concept that often appears in the advertising field, refers to a delivery unit defined by fields such as brand, city, target group, media, and device. For example, Brand = XX, City = Shanghai, Target Group = Women aged 18-30, Media = YY, Device = Mobile Phone, such values define a TP, while Brand = XX, City = Shanghai, Target Group = Women aged 18-30, Media = ZZ, Device = Mobile Phone, defines another TP.
[0030] In step S204, the server allocates the total virtual resources configured for the target advertisement to each of the multiple touch points in proportion according to the data set. Each time the target advertisement is pushed to a user terminal on a touch point, the virtual resources allocated to the touch point need to be consumed. The virtual resources can be virtual currency, digital currency, gold coins, etc.
[0031] Optionally, the allocation ratio of each of the multiple touchpoints in the total virtual resources can be determined according to the historical data of advertising delivery in the following manner: the total budget for this time, the budget allocated to each touchpoint, the cost of advertising (such as cost per thousand CPM, a method of advertising billing, i.e., the cost of one thousand ad impressions), and the revenue of advertising are recorded in the historical data of advertising delivery. The return on investment (ROI) of each touchpoint is determined using the historical data of advertising delivery, which refers to the ratio of the cost to revenue of advertising; the ROI of each touchpoint is normalized to obtain the contribution value of each touchpoint in a push; the proportion of the contribution value of each touchpoint in the sum of the contribution values of all touchpoints is used as the allocation ratio of each touchpoint in the total virtual resources.
[0032] Then, a virtual resource is allocated among the total virtual resources for each of the plurality of touch points according to the allocation ratio.
[0033] Step S206: At a target touch point among the multiple touch points, the server pushes the target advertisement to the matched target user terminal, where the target touch point is any one of the multiple touch points.
[0034] Optionally, step S206 may be implemented in the following manner:
[0035] Step S2062, obtain the available virtual resource amount allocated to the target contact, and stop pushing the target advertisement on the target contact when the available virtual resource amount allocated to the target contact is less than the specified resource amount. If the available virtual resource amount allocated to the target contact is not less than the specified resource amount, continue to perform the following steps. The specified resource amount is the virtual resource required for a single touch.
[0036] Step S2064, extracting a touch feature vector from the historical data of advertisement browsing. The touch feature vector is a feature vector of a reference user to which the target touch is directed, such as a vector of dimensions such as brand, city, target population, media, and device.
[0037] Step S2066, when receiving advertisement requests from multiple user terminals on the target touch point, the user feature vectors of the multiple user terminals are matched with the touch feature vector to obtain the matching degree between the user feature vector of each user terminal and the touch feature vector. The user feature vector may include information on the user's gender, the user's location, keywords of the content being watched, the duration of watching, and whether the content is forwarded, commented, or liked.
[0038] Optionally, the Euclidean distances between the user feature vectors of the plurality of user terminals and the touch feature vectors are calculated, and the obtained Euclidean distances between the user feature vectors of the respective user terminals and the touch feature vectors are used as the matching degree.
[0039] Step S2068: Push the target advertisement to the target user terminal with the highest matching degree among the multiple user terminals. Then subtract the specified resource amount from the available virtual resource amount allocated to the target touch point, where the specified resource amount is the resource amount consumed to push the target advertisement to the user terminal once.
[0040] When allocating the budget, it can be based on the logic of static allocation, and determine how much budget should be allocated to each TP according to the return on investment ROI. This allocation method is particularly suitable for advance implementation. It is essentially a global optimization problem, in which the decision variable of the optimization problem is the budget of each TP, the goal of the optimization problem is to maximize the global ROI, and the constraint of the optimization problem is the total budget. This type of method does not consider how to accurately deliver the budget allocated to TP to people, but only achieves the optimal level of touch points, and may not necessarily achieve the global optimality of the entire advertising budget allocation process.
[0041] In the technical solution of the present application, a data set is obtained, which includes relevant data on advertisements that have been delivered on multiple touch points; based on the data set, the total virtual resources configured for the target advertisement are allocated to each of the multiple touch points in proportion, and each time the target advertisement is pushed to a user terminal on a touch point, the virtual resources allocated to the touch point need to be consumed; on the target touch point of the multiple touch points, the target advertisement is pushed to the matched target user terminal, and the target touch point is any touch point among the multiple touch points. The entire solution can be executed automatically, and the solution can accurately allocate the budget allocated on the touch point to the person, which can solve the technical problem of low efficiency of advertising planning in related technologies.
[0042] The present application provides a complete budget allocation framework, which includes two parts: traditional budget allocation and recommendation system. By combining these two parts, the framework can achieve the optimal allocation of the advertiser's total budget to each user. It first uses a budget allocation method to allocate the total budget to each touch point; it provides a general budget allocation framework. The proposed general budget framework is different from the budget allocation method in the related technology. Its allocation granularity is user level rather than touch point level. Intelligent recommendation technology can be used to stream the budget allocated to each touch point to each user. This opens up the entire advertising delivery process, achieves the global optimality of the entire advertising budget allocation, and brings maximum benefits to advertisers. As an optional embodiment, Figure 3 As shown, the technical solution of the present application is further described in detail below in conjunction with specific implementation methods:
[0043] Step 1: Obtain a data set. The acquired data includes two parts: one is a data set used for budget allocation, and the other is a data set used for advertising recommendation.
[0044] The budget allocation data set can collect historical data of an advertising campaign. Each piece of data may include more detailed information such as brand, city, target population, media, device, advertising format, and frequency of advertising, as well as the spending and reward generated by the advertisement.
[0045] The cost of an ad is the CPM / 1000 of the ad. The revenue of an ad system generally refers to the user conversion rate (forward, comment, like, etc.), reach rate (the proportion of the population reached by the ad to the target population), etc. The recommendation data set needs to collect the user's browsing history data. For example, each browsing history data may include: user gender, user region, keywords of the content viewed, viewing time, whether to forward, comment, like, etc. Collecting this information can help better mine user characteristics.
[0046] Step 2: Mining touchpoint features on the budget allocation dataset and using any budget allocation method to allocate the total budget to each touchpoint.
[0047] There are many ways to allocate budgets for touchpoints. This application uses the method of calculating the ROI of the touchpoints. The total budget is allocated to each touchpoint based on the ROI. The ROI calculation method for each touchpoint is as follows:
[0048]
[0049] Each advertisement has a cost. j refers to all advertisements placed on this touch point. One touch point can place multiple advertisements. Some advertisements can bring conversion revenue, while others do not. The numerator of the first formula is to calculate the conversion revenue brought by all advertisements placed on this touch point. The denominator describes all the expenses of the advertisements placed on this touch point, because there is a cost for advertising every day.
[0050] After statistics, we can get the roi (tp i ), and after normalization, we can get the contribution value w(tp) of each touch point in an advertising delivery process. i ):
[0051]
[0052] The numerator of the above formula is the input-output ratio of touch point i calculated by the previous formula, and the denominator is the total input-output ratio of all touch points in a single delivery process. Multiple touch points will be delivered in one campaign, and multiple advertisements will be delivered on each touch point.
[0053] Based on w(tp i ) can divide the total advertising budget into each touch point in proportion, and use S to represent the total budget for this campaign. Then the budget for each touch point is s(tp i )=w(tp i )*S.
[0054] Step 3: Mining user features on the ad recommendation dataset and using any recommendation matching method to distribute the ads one by one to interested users.
[0055] User-level budget allocation: User-level budget allocation is mainly based on the budget s(tp allocated to the touchpoints) allocated by intelligent recommendation technology. i) and then to each user. This allocation process is streaming, it allocates the budget of the touchpoints in the form of one advertisement after another. When facing advertising requests from multiple users at the same time, each time the advertisement is allocated to the user who is most likely to convert. The most likely conversion requires calculating the similarity between the user feature vector and the touchpoint feature vector. The user feature vector can be mined from the dimensions of [user gender, user region, keywords of the content viewed, viewing time, whether to forward, comment or like] in the recommendation data set. The touchpoint feature vector is actually the dimension that defines the touchpoint [brand, city, target population, media, device]. After similarity calculation, the similarity between the user and the advertisement can be estimated, and then the user with the highest similarity can be found for push.
[0056] Step 4: Every time an ad is sent, the CPM of the ad is subtracted from the budget of the corresponding touchpoint, and the process of step 3 is repeated until the budget of the touchpoint is exhausted.
[0057] The above process is equivalent to greedy allocation. According to the process in step 3, each time we select the user who is most likely to convert and deliver the ad to that user. This is a greedy strategy, which can ensure that we make the best decision at the moment for each ad we deliver. We iterate the strategy in step 3 again and again until the budget on the touchpoint is exhausted, and then the budget for the touchpoint is optimally allocated.
[0058] This application proposes a universal advertising budget allocation framework, which combines traditional budget allocation methods and intelligent recommendation system technology, comprehensively considers the entire process of budget allocation, and realizes the precise delivery of advertising budgets from coarse to fine. The traditional budget allocation method is mainly responsible for completing the allocation at the touch point level. This is a static allocation logic that can allocate the budget of each touch point in advance. This allocation method can make the allocation at the touch point level reach the global optimal. The recommendation system is responsible for accurately allocating the budget allocated at the touch point to the person. This is a greedy allocation logic. It is necessary to allocate the budget of each touch point in real time, dynamically, and streamingly according to the user's preferences. The traditional budget allocation method combined with the intelligent recommendation system can optimize the entire advertising delivery process and maximize the interests of advertisers.
[0059] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.
[0060] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.
[0061] According to another aspect of the embodiments of the present application, an advertisement delivery device for implementing the above-mentioned advertisement delivery method is also provided. Figure 4 is a schematic diagram of an optional advertisement delivery device according to an embodiment of the present application, such as Figure 4 As shown, the device may include:
[0062] An acquisition unit 41 is used to acquire a data set, wherein the data set includes relevant data of advertisements delivered at multiple touch points;
[0063] an allocating unit 43, configured to allocate the total virtual resources configured for the target advertisement to each of the multiple touch points in proportion according to the data set, wherein each time the target advertisement is pushed to a user terminal on a touch point, the virtual resources allocated to the touch point need to be consumed;
[0064] The pushing unit 45 is configured to push the target advertisement to a matched target user terminal at a target touch point among the multiple touch points, wherein the target touch point is any touch point among the multiple touch points.
[0065] It should be noted that the acquisition unit 41 in this embodiment can be used to execute step S202 in the embodiment of the present application, the allocation unit 43 in this embodiment can be used to execute step S204 in the embodiment of the present application, and the push unit 45 in this embodiment can be used to execute step S206 in the embodiment of the present application.
[0066] It should be noted that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments. It should be noted that the above modules as part of the device can be run in Figure 1 In the hardware environment shown, it can be implemented by software or by hardware.
[0067] Through the above module, a data set is obtained, wherein the data set includes relevant data on advertisements delivered at multiple touch points; based on the data set, the total virtual resources configured for the target advertisement are allocated to each of the multiple touch points in proportion, and each time the target advertisement is pushed to a user terminal at a touch point, the virtual resources allocated to the touch point need to be consumed; at the target touch point of the multiple touch points, the target advertisement is pushed to the matched target user terminal, and the target touch point is any touch point of the multiple touch points. The entire solution can be automatically executed, and the solution can accurately allocate the budget allocated to the touch points to people, and can solve the technical problem of low efficiency of advertising planning in related technologies.
[0068] Optionally, the data set includes historical data of advertising browsing, and at a target touch point of the multiple touch points, when the push unit pushes the target advertisement to the matched target user terminal, the push unit extracts a touch feature vector from the historical data of advertising browsing, wherein the touch feature vector is a feature vector of a reference user facing the target touch point; when receiving advertisement requests from multiple user terminals at the target touch point, the user feature vectors of the multiple user terminals are matched with the touch feature vector to obtain a matching degree between the user feature vectors of each user terminal and the touch feature vector; and the target advertisement is pushed to the target user terminal with the highest matching degree among the multiple user terminals.
[0069] Optionally, when the push unit matches the user feature vectors of the multiple user terminals with the contact feature vector to obtain the matching degree between the user feature vector of each user terminal and the contact feature vector, the push unit calculates the Euclidean distance between the user feature vectors of the multiple user terminals and the contact feature vector, and uses the obtained Euclidean distance between the user feature vector of each user terminal and the contact feature vector as the matching degree.
[0070] Optionally, the pushing unit is also used to: before pushing the target advertisement to the target user terminal with the highest match among the multiple user terminals, obtain the amount of available virtual resources allocated to the target contact; after pushing the target advertisement to the target user terminal with the highest match among the multiple user terminals, subtract a specified amount of resources from the amount of available virtual resources allocated to the target contact, wherein the specified amount of resources is the amount of resources required to push the target advertisement to the user terminal once.
[0071] Optionally, the pushing unit is further configured to: after acquiring the available virtual resource amount allocated to the target contact point, if the available virtual resource amount allocated to the target contact point is less than the specified resource amount, stop pushing the target advertisement on the target contact point.
[0072] Optionally, the data set includes historical data of advertising delivery. When the allocation unit allocates the total virtual resources configured for the target advertisement to each of the multiple touch points in proportion according to the data set, the allocation unit determines the allocation ratio of each of the multiple touch points in the total virtual resources according to the historical data of advertising delivery; and allocates virtual resources in the total virtual resources to each of the multiple touch points according to the allocation ratio.
[0073] Optionally, when the allocation unit determines the allocation ratio of each of the multiple touch points in the total virtual resources based on the historical data of the advertising delivery, the allocation unit uses the historical data of the advertising delivery to determine the return on investment (ROI) of each touch point; normalizes the obtained ROI of each touch point to obtain the contribution value of each touch point in a push; and uses the ratio of the contribution value of each touch point to the sum of the contribution values of all touch points as the allocation ratio of each touch point in the total virtual resources.
[0074] It should be noted that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments. It should be noted that the above modules as part of the device can be run in Figure 1 In the hardware environment shown, it can be implemented by software or by hardware, wherein the hardware environment includes a network environment.
[0075] According to another aspect of the embodiments of the present application, a server or terminal for implementing the above-mentioned advertisement delivery method is also provided.
[0076] Figure 5 is a structural block diagram of a terminal according to an embodiment of the present application, such as Figure 5 As shown, the terminal may include: one or more ( Figure 5 (only one is shown) processor 501, memory 503, and transmission device 505, as shown in Figure 5 As shown, the terminal may also include an input and output device 507.
[0077] Among them, the memory 503 can be used to store software programs and modules, such as the program instructions / modules corresponding to the advertising delivery method and device in the embodiment of the present application. The processor 501 executes various functional applications and data processing by running the software programs and modules stored in the memory 503, that is, realizing the above-mentioned advertising delivery method. The memory 503 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 503 may further include a memory remotely arranged relative to the processor 501, and these remote memories can be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0078] The above-mentioned transmission device 505 is used to receive or send data via a network, and can also be used for data transmission between a processor and a memory. The above-mentioned network specific examples may include wired networks and wireless networks. In one example, the transmission device 505 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers via a network cable so as to communicate with the Internet or a local area network. In one example, the transmission device 505 is a radio frequency (Radio Frequency, RF) module, which is used to communicate with the Internet wirelessly.
[0079] Specifically, the memory 503 is used to store application programs.
[0080] The processor 501 may call the application stored in the memory 503 through the transmission device 505 to perform the following steps:
[0081] Acquire a data set, wherein the data set includes relevant data of advertisements delivered at multiple touch points;
[0082] Allocate the total virtual resources configured for the target advertisement to each of the multiple touch points in proportion according to the data set, wherein each time the target advertisement is pushed to a user terminal on a touch point, the virtual resources allocated to the touch point need to be consumed;
[0083] At a target touch point of the multiple touch points, the target advertisement is pushed to a matched target user terminal, wherein the target touch point is any one of the multiple touch points.
[0084] The processor 501 is further configured to execute the following steps:
[0085] Extracting a touch feature vector from the historical data of advertisement browsing, wherein the touch feature vector is a feature vector of a reference user to which the target touch point is directed;
[0086] In the case where advertisement requests from multiple user terminals are received at the target touch point, user feature vectors of the multiple user terminals are matched with the touch point feature vector to obtain a matching degree between the user feature vector of each user terminal and the touch feature vector;
[0087] The target advertisement is pushed to the target user terminal with the highest matching degree among the multiple user terminals.
[0088] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.
[0089] It can be understood by those skilled in the art that Figure 5 The structure shown is for illustration only, and the terminal may be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, or other terminal devices. Figure 5 It does not limit the structure of the above electronic device. For example, the terminal may also include Figure 5 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 5 Different configurations are shown.
[0090] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.
[0091] The embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to execute the program code of the advertisement delivery method.
[0092] Optionally, in this embodiment, the storage medium may be located on at least one network device among a plurality of network devices in the network shown in the above embodiment.
[0093] Optionally, in this embodiment, the storage medium is configured to store program codes for executing the following steps:
[0094] Acquire a data set, wherein the data set includes relevant data of advertisements delivered at multiple touch points;
[0095] Allocate the total virtual resources configured for the target advertisement to each of the multiple touch points in proportion according to the data set, wherein each time the target advertisement is pushed to a user terminal on a touch point, the virtual resources allocated to the touch point need to be consumed;
[0096] At a target touch point of the multiple touch points, the target advertisement is pushed to a matched target user terminal, wherein the target touch point is any one of the multiple touch points.
[0097] Optionally, the storage medium is further configured to store program codes for executing the following steps:
[0098] Extracting a touch feature vector from the historical data of advertisement browsing, wherein the touch feature vector is a feature vector of a reference user to which the target touch point is directed;
[0099] In the case where advertisement requests from multiple user terminals are received at the target touch point, user feature vectors of the multiple user terminals are matched with the touch point feature vector to obtain a matching degree between the user feature vector of each user terminal and the touch feature vector;
[0100] The target advertisement is pushed to the target user terminal with the highest matching degree among the multiple user terminals.
[0101] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.
[0102] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store program codes.
[0103] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.
[0104] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling one or more computer devices (which may be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.
[0105] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.
[0106] In the several embodiments provided in the present application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.
[0107] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0108] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0109] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.
Claims
1. A method for delivering advertisements, characterized in that: include: Acquire a data set, wherein the data set includes relevant data of advertisements delivered at multiple touch points; Allocate the total virtual resources configured for the target advertisement to each of the multiple touch points in proportion according to the data set, wherein each time the target advertisement is pushed to a user terminal on a touch point, the virtual resources allocated to the touch point need to be consumed; At a target touch point among the multiple touch points, pushing the target advertisement to a matched target user terminal, wherein the target touch point is any one of the multiple touch points; The data set includes historical data of advertisement browsing, and pushing the target advertisement to the matched target user terminal at the target touch point of the multiple touch points includes: Extracting a touch feature vector from the historical data of advertisement browsing, wherein the touch feature vector is a feature vector of a reference user to which the target touch point is directed; In the case where advertisement requests from multiple user terminals are received at the target touch point, user feature vectors of the multiple user terminals are matched with the touch point feature vector to obtain a matching degree between the user feature vector of each user terminal and the touch feature vector; The target advertisement is pushed to the target user terminal with the highest matching degree among the multiple user terminals.
2. The method according to claim 1, characterized in that Matching the user feature vectors of the multiple user terminals with the touch feature vector to obtain a matching degree between the user feature vector of each user terminal and the touch feature vector includes: The Euclidean distance between the user feature vectors of the multiple user terminals and the touch feature vector is calculated, and the obtained Euclidean distance between the user feature vector of each user terminal and the touch feature vector is used as the matching degree.
3. The method according to claim 1, characterized in that Before pushing the target advertisement to the target user terminal with the highest matching degree among the multiple user terminals, the method further includes: acquiring an available virtual resource amount allocated to the target touch point; After pushing the target advertisement to the target user terminal with the highest matching degree among the multiple user terminals, the method further includes: subtracting a specified amount of resources from the available virtual resources allocated to the target contact, wherein the specified amount of resources is the amount of resources required to push the target advertisement to the user terminal once.
4. The method according to claim 3, characterized in that After obtaining the available virtual resource amount allocated to the target touch point, the method further includes: When the available virtual resource amount allocated to the target contact point is less than the designated resource amount, the push of the target advertisement on the target contact point is stopped.
5. The method according to any one of claims 1 to 4, characterized in that The data set includes historical data of advertisement delivery. According to the data set, the total virtual resources configured for the target advertisement are allocated to each of the plurality of touch points in proportion, including: Determining, according to the historical data of the advertisement delivery, a distribution ratio of each of the plurality of touch points in the total virtual resources; Allocate virtual resources from the total virtual resources to each of the plurality of touch points according to the allocation ratio.
6. The method according to claim 5, characterized in that Determining, according to the historical data of the advertisement delivery, a distribution ratio of each of the plurality of touch points in the total virtual resources, including: Determine the ROI of each touch point using the historical data of the advertising; Normalize the ROI of each touch point to get the contribution value of each touch point in a push. The proportion of the contribution value of each contact point to the sum of the contribution values of all contacts is used as the allocation proportion of each contact point in the total virtual resources.
7. An advertisement delivery device, characterized in that: include: An acquisition unit, configured to acquire a data set, wherein the data set includes relevant data on advertisements delivered at multiple touch points; an allocating unit, configured to allocate the total virtual resources configured for the target advertisement to each of the plurality of touch points in proportion according to the data set, wherein each time the target advertisement is pushed to a user terminal on a touch point, the virtual resources allocated to the touch point need to be consumed; A pushing unit, configured to push the target advertisement to a matched target user terminal at a target touch point of the multiple touch points, wherein the target touch point is any touch point of the multiple touch points; The data set includes historical data of advertisement browsing, and the push unit is further used for: Extracting a touch feature vector from the historical data of advertisement browsing, wherein the touch feature vector is a feature vector of a reference user to which the target touch point is directed; In the case where advertisement requests from multiple user terminals are received at the target touch point, user feature vectors of the multiple user terminals are matched with the touch point feature vector to obtain a matching degree between the user feature vector of each user terminal and the touch feature vector; The target advertisement is pushed to the target user terminal with the highest matching degree among the multiple user terminals.
8. A storage medium, characterized in that: The storage medium includes a stored program, wherein the program executes the method described in any one of claims 1 to 6 when executed.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: The processor executes the method described in any one of claims 1 to 6 through the computer program.
Citation Information
Patent Citations
Display object pushing method and device, electronic equipment and storage medium
CN112055235A
Commodity advertisement putting control method and device, computer equipment and storage medium
CN113256337A
