Advertisement pushing method, device and equipment, and storage medium

Abstract

The application discloses an advertisement pushing method and device, equipment and a storage medium, and belongs to the computer technical field. In the process of pushing the advertisement, the pushing effect information of the target advertisement is obtained, and the pushing effect information can reflect the pushing effect of the target advertisement pushed by the first pushing mode. The second pushing mode is determined based on the pushing guide information and the pushing effect information. Since the pushing guide information can guide the pushing of the target advertisement according to the pushing effect, that is, the corresponding relationship between the pushing effect and the pushing mode is provided, the second pushing mode determined is more matched with the current pushing effect of the target advertisement, and the target advertisement pushed by the second pushing mode can obtain a better pushing effect.

Description

Technical Field

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

[0002] With the development of computer technology, more and more advertisers will push advertisements to users through advertising push platforms. For example, merchants will push product advertisements to customers through advertising push platforms, and live streamers will push live advertisements to viewers through advertising push platforms.

[0003] In related technologies, during the ad delivery process, advertisers need to adjust the ad delivery method according to different situations. For example, advertisers can stop ad delivery at a certain time, or they can increase the scope of the delivery at a certain time. However, the choice of delivery method is often determined by the advertiser based on intuition, which may lead to a negative impact on ad delivery and thus a decrease in the effectiveness of ad delivery. Summary of the Invention

[0004] This application provides an advertising push method, apparatus, device, and storage medium, which can improve the effectiveness of advertising push. The technical solution is as follows:

[0005] On the one hand, an advertising push method is provided, the method comprising:

[0006] Obtain the push effect information of the target advertisement, wherein the push effect information is used to indicate the push effect of pushing the target advertisement based on the first push method;

[0007] Parse the push guidance information to obtain the structured information corresponding to the push guidance information. The push guidance information is generated based on the push effect information of multiple reference advertisements and the operation of the target object on the multiple reference advertisements. The push guidance information is used to guide the push of advertisements based on the push effect information.

[0008] Based on the push effect information and the structured information, a second push method for the target advertisement is determined;

[0009] The method of pushing the target advertisement is changed from the first method to the second method.

[0010] On the one hand, an advertising push device is provided, the device comprising:

[0011] The push effect information acquisition module is used to acquire push effect information of the target advertisement, wherein the push effect information is used to indicate the push effect of pushing the target advertisement based on the first push method;

[0012] The push method determination module is used to parse the push guidance information to obtain the structured information corresponding to the push guidance information. The push guidance information is generated based on the push effect information of multiple reference advertisements and the operation of the target object on the multiple reference advertisements. The push guidance information is used to guide the push of advertisements based on the push effect information. Based on the push effect information and the structured information, the second push method of the target advertisement is determined.

[0013] The push module is used to change the push method of the target advertisement from the first push method to the second push method.

[0014] In one possible implementation, the push method determination module is used to input the push guidance information into a syntax parser, and to structure the push guidance information through the syntax parser to obtain the structured information corresponding to the push guidance information.

[0015] In one possible implementation, the push method determination module is used to perform lexical analysis on the push guidance information through the syntax parser to obtain multiple words in the push guidance information and the types of the multiple words; and to perform grammatical analysis on the multiple words based on the types of the multiple words to obtain the structured information corresponding to the push guidance information.

[0016] In one possible implementation, the push method determination module is used to segment the push guidance information using the syntax parser to obtain multiple words in the push guidance information; and compare the multiple words with a word type table to obtain the type of the multiple words.

[0017] In one possible implementation, the push method determination module is used to determine the hierarchy among the multiple words based on their types; and rearrange the multiple words based on their hierarchy to obtain structured information corresponding to the push guidance information.

[0018] In one possible implementation, the push method determination module is configured to obtain at least one of the effect parameters and attribute parameters corresponding to the structured information from the push effect information, wherein the effect parameters are parameters that change when the target advertisement is pushed, and the attribute parameters are parameters that do not change when the target advertisement is pushed; and based on the structured information, process at least one of the effect parameters and the attribute parameters to obtain the second push method of the target advertisement.

[0019] In one possible implementation, the push method determination module is used to obtain at least one of the effect parameters and the attribute parameters from the push effect information based on a reflection mechanism.

[0020] In one possible implementation, the push method determination module is used to perform a Boolean operation on at least one of the effect parameters and the attribute parameters based on the target relationship data to obtain the push method identifier of the target advertisement;

[0021] Based on the push method identifier, the second push method of the target advertisement is determined.

[0022] In one possible implementation, the device further includes:

[0023] The push guidance information generation module is used to obtain push effect information of multiple reference advertisements and the operations performed by the target object on the multiple reference advertisements respectively. The operations are used to adjust the push method of the reference advertisements, and the target object is the object corresponding to the target advertisement. Based on the push effect information of the multiple reference advertisements and the operations performed by the target object on the multiple reference advertisements, the push guidance information is generated.

[0024] In one possible implementation, the push guidance information generation module is used to cluster the push effect information of the plurality of reference advertisements and the operations performed by the target object on the plurality of reference advertisements to generate the push guidance information.

[0025] In one possible implementation, the target advertisement's push effect information includes effect parameters and attribute parameters. The push effect information acquisition module is used to acquire the target advertisement's effect parameters based on a target business, where the target business is the push service for which the target advertisement is pushed, and the effect parameters are parameters that describe the effect of pushing the target advertisement and are parameters that change during the push process. Based on the target business, the module also acquires the target business's attribute parameters, where the attribute parameters are parameters that do not change during the push process for the target advertisement.

[0026] On one hand, a computer device is provided, the computer device including one or more processors and one or more memories, the one or more memories storing at least one computer program, the computer program being loaded and executed by the one or more processors to implement the advertising push method.

[0027] On one hand, a computer-readable storage medium is provided, wherein at least one computer program is stored in the computer-readable storage medium, the computer program being loaded and executed by a processor to implement the advertising push method.

[0028] On one hand, a computer program product or computer program is provided, which includes program code stored in a computer-readable storage medium, wherein a processor of a computer device reads the program code from the computer-readable storage medium and executes the program code, causing the computer device to perform an advertising push method.

[0029] Using the technical solution provided in this application, during the advertising push process, the push effect information of the target advertisement is obtained. The push effect information can reflect the quality of the push effect when the target advertisement is pushed using the first push method. Subsequently, a second push method is determined based on the push guidance information and the push effect information. Since the push guidance information can guide the push of the target advertisement according to the quality of the push effect, that is, it provides a correspondence between the push effect and the push method, the determined second push method is more matched with the current push effect of the target advertisement. Using the second push method to push the target advertisement can achieve a better push effect. Attached Figure Description

[0030] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0031] Figure 1 This is a schematic diagram of the implementation environment of an advertising push method provided in an embodiment of this application;

[0032] Figure 2 This is a flowchart of an advertising push method provided in an embodiment of this application;

[0033] Figure 3 This is a flowchart of an advertising push method provided in an embodiment of this application;

[0034] Figure 4 This is a flowchart of a push strategy engine provided in an embodiment of this application;

[0035] Figure 5 This is a flowchart of a push strategy engine provided in an embodiment of this application;

[0036] Figure 6 This is a schematic diagram of an advertising push page provided in an embodiment of this application;

[0037] Figure 7 This is a schematic diagram of an advertising push device provided in an embodiment of this application;

[0038] Figure 8This is a schematic diagram of the structure of a terminal provided in an embodiment of this application;

[0039] Figure 9 This is a schematic diagram of the structure of a server provided in an embodiment of this application. Detailed Implementation

[0040] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0041] In this application, the terms "first," "second," etc., are used to distinguish identical or similar items with essentially the same function. It should be understood that there is no logical or temporal dependency between "first," "second," and "nth," nor are there any restrictions on quantity or execution order.

[0042] In this application, the term "at least one" means one or more, and "multiple" means two or more.

[0043] The following is a description of some terms used in the embodiments of this application.

[0044] Advertiser: The company that places the advertisement.

[0045] Promotion plan: A collection of advertisements with the same promotional goal and a certain time limit.

[0046] Advertising: Internet media display methods used to promote specific products to a specific group of people.

[0047] Pitcher: The person in charge of the actual operation of the advertising system.

[0048] Strategy: A method to win in advertising competition when a large number of ads are running simultaneously.

[0049] DSL (Domain Specific Language): A dedicated language used to describe specific problems in a specific domain.

[0050] A Boolean expression is a code declaration that has two values: True and False. The simplest Boolean expression is equality, which is used to test whether one value is the same as another.

[0051] It is understood that in the specific implementation of this application, data related to user clicks, views, and operations are involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions.

[0052] Figure 1 This is a schematic diagram illustrating the implementation environment of an advertising push method provided in this application embodiment. See also... Figure 1 The implementation environment may include terminal 110 and server 140.

[0053] Terminal 110 is connected to server 140 via a wireless or wired network. Optionally, terminal 110 may be a smartphone, tablet, laptop, desktop computer, smartwatch, etc., but is not limited to these. Terminal 110 has an application installed and running that supports ad delivery.

[0054] Server 140 is a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms. Server 140 provides background services for the application that supports ad push running on terminal 110.

[0055] Those skilled in the art will understand that the number of terminals 110 described above can be more or less. For example, there may be only one terminal, or there may be dozens or hundreds of terminals, or even more, in which case other terminals may also be included in the above implementation environment. This application does not limit the number of terminals or the type of device in its embodiments.

[0056] After introducing the implementation environment of the embodiments of this application, the application scenarios of the embodiments of this application will be described below in conjunction with the above implementation environment. In the following description, the terminal is the terminal 110 mentioned above, and the server is the server 140 mentioned above.

[0057] The advertising push method provided in this application can be applied to various advertising scenarios, such as pushing live streaming ads or pushing product ads.

[0058] In the scenario of pushing application ads, advertisers can use an ad push platform to push application ads. This means the advertiser uploads the application ads they want to push to the ad push platform, which then pushes the ads to application ad display positions. Users can then view the ads through these display positions, thus achieving the push of application ads. In some embodiments, the application ad display position is an application ad display position on a webpage, an application ad display position within the application interface, or a recommendation pop-up, etc. This process of advertisers pushing application ads through an ad push platform can also be called the application ad placement process. In some embodiments, during the application ad push process, advertisers need to consume a certain amount of virtual assets, that is, they need to pay a certain amount of virtual assets to the ad push platform. In this case, advertisers can adjust the application ad push method based on the application ad push effect. For example, the push method may include continuing to push application ads, stopping push applications ads, or expanding the push scope of application ads. In some embodiments, advertisers can perform corresponding operations on the terminal to adjust the application ad push method. However, advertisers often rely on intuition when adjusting the push method for application ads, which can lead to misjudgments and worsen the push effect. In this case, advertisers can use a terminal to execute the application ad push method provided in this application embodiment. That is, the terminal obtains the push effect information of the application ads, which indicates the push effect of pushing application ads based on the first push method. The terminal determines a second push method based on the application ad push effect information and push guidance information, which guides the push of ads based on the push effect information. In some embodiments, the push guidance information is also referred to as a push strategy. The terminal adjusts the first push method of the application ads to the second push method, that is, pushes the application ads using the second push method. Alternatively, the application ad push method provided in this application embodiment can be executed by an ad push platform. That is, when advertisers push application ads through an ad push platform, they can also choose to enable the automatic push function. When the advertiser selects the automatic push function, the ad push platform can obtain the push effect information of the application ads, which indicates the push effect of pushing application ads based on the first push method. The ad delivery platform determines the second delivery method based on the application ad delivery performance information and delivery guidance information. This guidance information is used to guide ad delivery based on the performance information. The ad delivery platform then adjusts the application ad delivery method from the first to the second method, meaning the application ads are delivered using the second method.In some embodiments, the advertising push platform runs on server 140 in the above-described implementation environment.

[0059] In scenarios involving live streaming advertising, broadcasters can push live stream ads through an advertising platform. This means the broadcaster uploads the desired live stream ad to the platform, which then pushes it to a designated live stream ad display area. Users can then view the ad through this display area, thus achieving ad delivery. In some embodiments, this display area may be a webpage ad display area, a live stream application interface ad display area, or a recommendation pop-up. This process of broadcasters pushing live stream ads through an advertising platform can also be called live stream ad placement. In some embodiments, broadcasters need to consume a certain amount of virtual assets during the live stream ad push process; that is, they need to pay a certain amount of virtual assets to the advertising platform. In this case, broadcasters can adjust the live stream ad push method based on the ad's performance. For example, the push method may include continuing to push the live stream ad, stopping the push, or expanding the push scope. In some embodiments, broadcasters can perform corresponding operations on their devices to adjust the live stream ad push method. However, when adjusting the push method for live stream ads, broadcasters often rely on intuition, which can lead to misjudgments and a decrease in the effectiveness of the live stream ad push. In this case, the broadcaster can use a terminal to execute the ad push method provided in this application embodiment. That is, the terminal obtains the push effect information of the live stream ads, which can indicate the push effect of pushing live stream ads based on the first push method. The terminal determines a second push method based on the push effect information of the live stream ads and push guidance information, which is used to guide the push of ads based on the push effect information. In some embodiments, the push guidance information is also referred to as a push strategy. The terminal adjusts the first push method of the live stream ads to the second push method, that is, pushes the live stream ads using the second push method. Alternatively, the ad push method provided in this application embodiment is executed by an ad push platform. That is, when the broadcaster pushes live stream ads through the ad push platform, they can also choose to enable the automatic push function. When the broadcaster selects the automatic push function, the ad push platform can obtain the push effect information of the live stream ads, which can indicate the push effect of pushing live stream ads based on the first push method. The advertising platform determines the second push method based on the performance information and guidance information of the live stream ads. This guidance information is used to guide the ad delivery based on the performance information. The advertising platform then adjusts the first push method for live stream ads to the second push method, meaning that live stream ads are pushed using the second push method.

[0060] In scenarios involving product advertising, merchants can use advertising push platforms to push product ads. Merchants upload the desired product ads to the platform, which then pushes them to designated ad display areas. Users can then view these ads through these display areas, thus achieving ad delivery. In some embodiments, these ad display areas are on web pages, within shopping application interfaces, or as recommendation pop-ups. This process of merchants pushing product ads through advertising push platforms can also be referred to as product ad placement. In some embodiments, merchants need to consume a certain amount of virtual assets during ad delivery, meaning they need to pay the advertising push platform a certain amount of virtual assets. In this case, merchants can adjust the ad delivery method based on the ad's performance, such as continuing to push ads, stopping ad delivery, or expanding the ad's reach. In some embodiments, merchants can perform corresponding operations on their devices to adjust the ad delivery method. However, when adjusting the way product advertisements are pushed, merchants often rely on intuition, which may lead to misjudgments and a decrease in the effectiveness of the product advertisement push. In this case, merchants can use a terminal to execute the advertising push method provided in this application embodiment. That is, the terminal obtains the product advertisement push effect information, which can indicate the push effect of pushing product advertisements based on the first push method. The terminal determines a second push method based on the product advertisement push effect information and push guidance information, which is used to guide the push of advertisements based on the push effect information. In some embodiments, the push guidance information is also referred to as a push strategy. The terminal adjusts the first push method of the product advertisement to the second push method, that is, pushes the product advertisement using the second push method. Alternatively, the advertising push method provided in this application embodiment is executed by an advertising push platform. That is, when merchants push product advertisements through an advertising push platform, they can also choose to enable the automatic push function. When the merchant selects the automatic push function, the advertising push platform can obtain the product advertisement push effect information, which can indicate the push effect of pushing product advertisements based on the first push method. The advertising platform determines the second push method based on the product advertising push performance information and push guidance information. This push guidance information is used to guide the push of advertisements based on the push performance information. The advertising platform adjusts the product advertising push method from the first push method to the second push method, that is, it uses the second push method to push product advertisements.

[0061] It should be noted that in the above description, the technical solutions provided in the embodiments of this application are used as examples in the scenarios of pushing advertisements, pushing live broadcast information, and pushing product information. In other possible implementations, the technical solutions provided in the embodiments of this application can also be applied to scenarios of pushing other content, and the embodiments of this application do not limit this.

[0062] Furthermore, in the following description of the technical solutions provided in this application, a server is used as the execution subject. In other possible implementations, a terminal may also be used as the execution subject to execute the technical solutions provided in this application. The embodiments of this application do not limit the type of execution subject.

[0063] Figure 2 This is a flowchart of an advertising push method provided in an embodiment of this application. See also... Figure 2 Executed by the server, the methods include:

[0064] 201. The server obtains the push effect information of the target advertisement, which is used to indicate the push effect of pushing the target advertisement based on the first push method.

[0065] In different application scenarios, targeted advertising has different meanings. In the scenario of pushing application ads, targeted advertising is the application ad being pushed; in the scenario of pushing live streaming ads, targeted advertising is the live streaming ad being pushed. In some embodiments, the effectiveness of targeted advertising is determined based on the interaction behavior between the user and the targeted ad. For example, the number of times a user views the targeted ad can be used as one of the indicators for evaluating the effectiveness of targeted advertising.

[0066] 202. The server parses the push guidance information to obtain the structured information corresponding to the push guidance information. The push guidance information is generated based on the push effect information of multiple reference advertisements and the target object's operation on the multiple reference advertisements. The push guidance information is used to guide the push of advertisements based on the push effect information.

[0067] The push guidance information, also known as the push strategy, is used to guide the delivery of advertisements. Here, guiding advertisement delivery refers to determining the corresponding push method based on push performance information. Structured information is the information obtained after structuring the push guidance information. Structuring refers to splitting and reorganizing the push guidance information according to its hierarchical relationship, making it easier for the server to utilize the push guidance information. In some embodiments, the structured information corresponding to the push guidance information is also referred to as the syntax tree of the push guidance information.

[0068] 203. Based on the push effect information and the structured information, the server determines the second push method for the target advertisement.

[0069] The second push method is the push method to be switched, and the first push method is the historical push method.

[0070] 204. The server adjusts the push method of the target advertisement from the first push method to the second push method.

[0071] Using the technical solution provided in this application, during the advertising push process, the push effect information of the target advertisement is obtained. The push effect information can reflect the quality of the push effect when the target advertisement is pushed using the first push method. Subsequently, a second push method is determined based on the push guidance information and the push effect information. Since the push guidance information can guide the push of the target advertisement according to the quality of the push effect, that is, it provides a correspondence between the push effect and the push method, the determined second push method is more matched with the current push effect of the target advertisement. Using the second push method to push the target advertisement can achieve a better push effect.

[0072] Steps 201-203 above are a simplified description of the advertising push method provided in the embodiments of this application. The following will provide a more detailed description of the advertising push method provided in the embodiments of this application, using examples where the executing entity is a server. (See below for further details.) Figure 3 The terms include:

[0073] 301. The server obtains the push effect information of the target advertisement, which is used to indicate the push effect of pushing the target advertisement based on the first push method.

[0074] The first push method refers to the push method for the current target advertisement. This first push method can be the push method selected by the content creator, the default push method configured on the server, or the push method selected by the advertising push personnel of the advertising push platform. This application embodiment does not limit this. In some embodiments, the advertising push platform runs on the server. In some embodiments, push effect information is also referred to as push metrics.

[0075] In one possible implementation, the target ad push performance information includes performance parameters and attribute parameters. The server obtains the performance parameters of the target ad based on a target service, where the target service is the push service for pushing the target ad, and the performance parameters are parameters that describe the effect of pushing the target ad; these performance parameters are parameters that change during the push process. The server also obtains the attribute parameters of the target service based on the target service; these attribute parameters are parameters that do not change during the push process for pushing the target ad.

[0076] In some embodiments, push performance parameters include the number of views, clicks, cost, and conversions of the target ad. The number of views refers to the number of times a user sees the target ad; more views indicate greater ad exposure. The number of clicks refers to the number of times a user clicks on the target ad; more clicks indicate higher user interest. Cost refers to the amount of virtual assets consumed in pushing the target ad. In some embodiments, given the same push range, a longer push duration results in more virtual assets being consumed; similarly, a larger push range results in more virtual assets being consumed. Conversions refer to the number of conversions based on the target ad; for example, if the target ad is an advertisement, the conversion count is the number of orders placed based on that advertisement.

[0077] In some embodiments, the attribute parameters include the user identifier that pushes the target advertisement; in the context of pushing advertisements, this user identifier is also the advertiser ID. The attribute parameters also include the identifier of the content set to which the target advertisement belongs (Group ID), the identifier of the push plan corresponding to the target advertisement (Campaign ID), the type of the target advertisement (Promoted Object Type), the identifier of the target advertisement (Promoted Object ID), the daily budget for pushing the target advertisement, the start time, the end time, the optimization goal, and the bid amount. The optimization goal refers to an optimistic estimate of the target advertisement's target using the first push method, including the number of clicks, views, and conversions. The bid amount refers to the total amount of virtual assets that can be consumed in pushing the target advertisement.

[0078] For example, the server uses a data crawler to retrieve the performance parameters of the target advertisement from the performance parameter service of the target business. This performance parameter service is used to retrieve the performance storage of the target advertisement from external sources, specifically the devices that push the target advertisement. The server also uses the data crawler to retrieve the attribute parameters corresponding to the performance parameters from the attribute parameter service of the target business. This attribute parameter service is used to maintain the attribute parameters of the target business. In some embodiments, performance parameters are also referred to as metrics, and the performance parameter service of the target business is also referred to as a metrics service; attribute parameters are also simply referred to as attributes, and the attribute parameter service of the target business is also referred to as an attribute service.

[0079] In one possible implementation, the server sends a request to the ad push server to obtain push performance information. This request carries the identifier of the target ad. The ad push server is also the server that pushes the target ad; in the context of push advertising, it is also called the ad delivery server or ad serving server. Upon receiving the request, the ad push server retrieves the identifier of the target ad from the request, performs a query based on the identifier, and obtains the push performance information of the target ad. The ad push server then sends this push performance information to the server, which then retrieves the push performance information of the target ad.

[0080] 302. The server parses the push guidance information to obtain the structured information corresponding to the push guidance information. This push guidance information is used to guide the push of advertisements based on the push effect information.

[0081] The push guidance information, also known as push strategy or push rule, guides the delivery of advertisements based on push performance information. In other words, the server can control the delivery of target advertisements based on the acquired push performance information and push guidance information. The number of push guidance messages can be one or more, and this application embodiment does not limit this.

[0082] In one possible implementation, the server inputs the push notification guidance information into a syntax parser, which then structures the information to obtain structured information corresponding to the push notification guidance information. In some embodiments, the structured information corresponding to the push notification guidance information is also referred to as the syntax tree of the push notification guidance information.

[0083] For example, the server uses the parser to perform lexical analysis on the push notification guidance information, obtaining multiple words and their types. The server then uses the parser to perform syntactic analysis on these words based on their types, obtaining the structured information corresponding to the push notification guidance information. In some embodiments, the parser is an AST (Abstract Syntax Tree) parser, and the server uses this AST parser to perform the following steps: segmenting the push notification guidance information to obtain multiple words; comparing these words with a word type table to obtain their types; determining the hierarchy between the words based on their types; and rearranging the words based on their hierarchy to obtain the structured information corresponding to the push notification guidance information.

[0084] To provide a clearer explanation of the process by which the server parses the push notification information using an AST parser, the following sections will describe the steps performed by the AST parser in several parts.

[0085] Part 1: The server uses the AST parser to segment the push notification information into words, obtaining multiple words from the push notification information.

[0086] In one possible implementation, the server scans multiple characters in the push notification information using the AST parser and combines these characters into multiple words according to their types. The character types include characters belonging to keywords, characters belonging to custom names, and characters belonging to operators or logical operators, etc.

[0087] The second part involves the server using the AST parser to compare the multiple words with the word type table to obtain the types of the multiple words.

[0088] The vocabulary types include keywords such as "public", "static", "String", and "int"; custom names such as class names, package names, method names, and variable names; and operators and logical operators such as "+", "-", "*", " / ", and "&&". The vocabulary type table records keywords and operators / logical operators, and it corresponds to the programming language used, updating as the programming language is updated or changed.

[0089] In one possible implementation, during the process of comparing multiple words and a vocabulary type table using the AST parser, if the first word among the multiple words is determined to be a keyword in the vocabulary type table, the type of the first word is marked as a keyword; if the second word among the multiple words is determined to be an operator or logical operator in the vocabulary type table, the type of the second word is marked as an operator or logical operator; if the third word among the multiple words does not exist in the vocabulary type table, the third word is determined as a custom name.

[0090] Part Three: The server uses the AST parser to determine the hierarchy among the multiple words based on their types.

[0091] In one possible implementation, there is a hierarchical relationship between the types of vocabulary. This hierarchical structure is the grammatical structure of the push guidance information. In the case that the push guidance information is in the form of a DSL, this hierarchical structure is also the grammatical structure of the DSL.

[0092] Part Four: The server uses the AST parser to rearrange the multiple words based on the hierarchy between them, and obtains the structured information corresponding to the push guidance information.

[0093] In one possible implementation, the server uses the AST parser to generate multiple nodes based on the hierarchy between the multiple words. According to the word types corresponding to the multiple words, the multiple words are filled into the multiple nodes to obtain the syntax tree corresponding to the push guidance information; this syntax tree is also the structured information.

[0094] After describing the above implementation methods, the form of the push guidance information will be introduced below.

[0095] In some embodiments, the push guidance information is in the form of DSL. The description rules of DSL are set by technicians, and this application embodiment does not limit this. DSL has the characteristics of being simple and easy to understand, and using DSL format facilitates quick understanding and modification of the push guidance information by technicians. Of course, the push guidance information can be in other language forms that are easy to understand and modify besides DSL, and this application embodiment does not limit this. In the following description, the push guidance information is described using DSL format as an example.

[0096] To provide a clearer explanation of the advertising push method provided in the embodiments of this application, the basic syntax of DSL will be explained below.

[0097]

[0098] The parts enclosed in <> are variable content, while the rest are fixed keywords and cannot be formatted.

[0099] RuleName: The name of the push notification guidance message, or strategy name, used to distinguish different push notification guidance messages.

[0100] RuleDescription: A description of the push notification guidance information, or a strategy description, used to describe the specific content of the push notification guidance information.

[0101] boolean expression: A description of the judgment conditions for pushing guidance information, or a description of the policy judgment conditions, used to define the actual executable boolean expression judgment.

[0102] Operation expression: This is a description of the operation for pushing guidance information, or a strategy operation description. It defines the operation to be performed when the judgment conditions for pushing guidance information are met. The operation is used to adjust the content recommendation method. There can be one or more operations; this embodiment does not limit this. When there are multiple operations, they are separated by semicolons.

[0103] The policy judgment condition is a Boolean expression, allowing for the combination of basic Boolean expressions. Tables 1, 2, and 3 below introduce the supported Boolean expressions. Table 1 lists the supported character types, Table 2 lists the supported operator types, and Table 3 lists the supported operator precedence types.

[0104] Table 1

[0105]

[0106] Table 2

[0107] Mathematical operations +，-，*， / ，％ Bitwise operations |，& Logical operations &&，|| Comparison operations <，<＝，>，>＝，＝＝，！＝

[0108] Table 3

[0109] 5 *， / ，％，& 4 +，-，| 3 ＝＝，！＝，<，<＝，>，>＝ 2 && 1 ||

[0110] In a push advertising scenario, a three-layer advertising model entity can be predefined, including Advertiser, Campaign, and Ad Group, along with their respective attributes, metrics, and methods. The Advertiser is the user placing the ad; the Campaign is a collection of ads with the same promotional goal and a time limit; and the Ad Group is the collection to which the ads belong. Attributes are the aforementioned attribute parameters, metrics are the aforementioned performance parameters, and methods are operations used to change the way ads are pushed. In some embodiments, attributes and metrics can be used as variables in the aforementioned boolean expression, participating in calculations using the operations in the aforementioned operation expression.

[0111] The following tables 4, 5, and 6 introduce the three-tiered advertising model entities. Table 4 introduces the Advertiser model entity, Table 5 introduces the Campaign model entity, and Table 6 introduces the AdGroup model entity.

[0112] Table 4

[0113]

[0114]

[0115] Table 5

[0116] property Advertiser ID Campaign ID Daily Budget Status index Cost View Count Click Count Conversion Count method Start Pause Change Daily Budget

[0117] Table 6

[0118] property Advertiser ID Campaign ID Ad Group ID Daily Budget Promoted Object Type (Advertisement Type) Promoted Object ID (Advertisement Identifier) Begin Time End Time Optimization Goal Bid Amount (Total Bid Amount) index Cost View Count Click Count Conversion Count method Start Pause Change Bid Amount Change Daily Budget

[0119] For example, using the three-layer advertising model entities mentioned above, we can define a push notification message. For instance, a push notification message might state that when the advertising cost is greater than or equal to 500 yuan, but the user click count is less than 30, the advertising should be paused. This push notification message, expressed using DSL language, would be:

[0120]

[0121]

[0122] To provide a clearer explanation of the embodiments of this application, the method for generating push guidance information is described below.

[0123] In one possible implementation, the server obtains the push performance information of multiple reference advertisements and the operations performed by the target object on each of the multiple reference advertisements. These operations are used to adjust the push method of the reference advertisements, and the target object is the object corresponding to the target advertisement. Based on the push performance information of the multiple reference advertisements and the operations performed by the target object on the multiple reference advertisements, the server generates the push guidance information.

[0124] The target object has different meanings depending on the application scenario. In the context of push advertising, the target object can be the advertiser or the advertiser. Correspondingly, the reference advertisement is the reference advertisement. The operation performed by the target object on the multiple reference advertisements refers to the operation performed by the advertiser or advertiser during the push of multiple reference advertisements. The reference advertisement is the advertisement that the advertiser has pushed in the past.

[0125] In this implementation, the server can generate push guidance information based on the push effect information during the process of pushing multiple reference ads and the operations performed by the target audience. This generated push guidance information reflects the target audience's operational habits. If the target audience is an experienced operator, the push guidance information is essentially a summary of that operator's experience. Pushing ads based on this guidance information is equivalent to the operator controlling the ad push process, resulting in better ad push effectiveness. In the scenario of pushing ads, if the target audience is a high-performing advertiser, the operational behavior analysis of the high-performing advertiser transforms their daily work experience judgments (e.g., what constitutes a high-performing ad and how to maximize revenue; what constitutes a low-performing ad and how to minimize losses) into digitized push guidance information. Using this push guidance information to operate ads can replace the high-performing advertiser in making judgments and performing related operations.

[0126] For example, the server clusters the push performance information of multiple reference ads and the operations performed by the target object on these multiple reference ads to generate push guidance information. For instance, the server generates an operation table based on the push performance information of the multiple reference ads and the corresponding operations of the target object, and clusters the information in the operation table to obtain the push guidance information. In some embodiments, the operation table is formatted with push performance information displayed on the left and the corresponding operations displayed on the right. For example, the server identifies a target operation from the operations performed by the target object on the multiple reference ads and obtains multiple target push performance information corresponding to that target operation. The server clusters the multiple target push performance information to obtain the target push performance information corresponding to the target operation. The process of clustering the multiple target push performance information is also the process of determining the parameter range in the multiple target push performance information. Based on the target push performance information and the target operation, the server generates push guidance information that can guide under what circumstances the target operation will be executed.

[0127] In one possible implementation, the server obtains information to generate a table, and based on the information generated table, obtains push guidance information. The information generated table is used to collect push effect information.

[0128] This implementation method enables convenient and rapid communication with excellent ad pushers, extracting superior push strategies and thereby improving the efficiency of obtaining push guidance information.

[0129] For example, the server sends an initial information generation form to the target audience. This initial information generation form is a blank form, containing topics to be filled in, such as attribute parameters, effect parameters, and operations. In the context of push advertising, the attribute parameters are the relevant attributes of the ads that the target audience would care about when pushing ads daily; the operations are the actions that would be performed on the ads during daily push advertising, such as pausing, starting, and adjusting the budget; the effect parameters are which ad metrics the target audience would mainly focus on when performing a specific operation (e.g., pausing) during daily push advertising, and at what level these metrics would the operation of pausing push advertising be executed. After the target audience completes the information generation form, it sends the completed information generation form to the server, which receives it. The server converts the information in the information generation form into push guidance information. If the push guidance information is in the form of DSL, this means converting the information in the information generation form into DSL. If the information generation form is missing information, technical personnel first fill in the missing information to form a complete information generation form.

[0130] Taking the scenario of pushing advertisements as an example, the information generated in the form of a table can be Table 7.

[0131] Table 7

[0132]

[0133]

[0134] 303. Based on the push effect information and the structured information, the server determines the second push method for the target advertisement.

[0135] In one possible implementation, the server obtains at least one of the effect parameters and attribute parameters corresponding to the structured information from the push effect information. The effect parameters are parameters that change when the target advertisement is pushed, and the attribute parameters are parameters that do not change when the target advertisement is pushed. Based on the structured information, the server processes at least one of the effect parameters and attribute parameters to obtain the second push method for the target advertisement.

[0136] For example, the server uses reflection to retrieve at least one of the effect parameters and attribute parameters from the push effect information. This structured information includes target relationship data. Based on this target relationship data, the server performs a Boolean operation on at least one of the effect parameters and attribute parameters to obtain the push method identifier for the target advertisement. Based on this push method identifier, the server determines the second push method for the target advertisement. Here, reflection refers to the ability of a program to access, detect, and modify its own state or behavior. By employing reflection, it is possible to achieve self-representation and examination of its own behavior.

[0137] For example, the server determines at least one of the effect parameters and attribute parameters required for calculation based on the structured information. The server retrieves at least one of the effect parameters and attribute parameters from the push effect information using a reflection mechanism. Based on the target relationship data carried in the structured information, the server performs a Boolean operation on at least one of the effect parameters and attribute parameters to obtain a push method identifier for the target advertisement. This push method identifier indicates whether to execute the operation corresponding to the target relationship data. In some embodiments, the push method identifier includes two results: True and False. True indicates that the operation corresponding to the target relationship data is executed; False indicates that the operation corresponding to the target relationship data is not executed. Based on the push method identifier, the server determines a second push method for the target advertisement. When the push method identifier indicates that the operation corresponding to the target relationship data is executed, the second push method is different from the first push method; when the push method identifier indicates that the operation corresponding to the target relationship data is not executed, the second push method is the same as the first push method.

[0138] For example, in the scenario of pushing advertisements, a push notification message might be:

[0139]

[0140] The server parses the delivery instructions and generates a syntax tree corresponding to the push notification information. Based on this syntax tree, the server determines that two effect parameters are needed for Boolean operations: one effect parameter is the cost of pushing the ad, and the other effect parameter is the number of clicks when pushing the ad. Therefore, the server uses reflection to retrieve the effect parameter 600 corresponding to `AdGroup.Cost` and the effect parameter 20 corresponding to `AdGroup.ClickCount` from the push notification effect information. The server performs a Boolean operation on the effect parameters 600 and 20 based on the target relationship data `AdGroup.Cost>=500&&AdGroup.ClickCount<30`, obtaining the push method identifier `True` for the target ad. This indicates that the action `AdGroup.Pause()` corresponding to the target relationship data will be executed, which is to pause the ad push. This paused ad push is the second push method.

[0141] 304. The server adjusts the push method of the target advertisement from the first push method to the second push method.

[0142] After step 304, the server can repeat steps 301-304. During the re-execution of steps 301-304, the second push method is regarded as the first push method, and the newly determined push method can be recorded as the third push method.

[0143] In one possible implementation, steps 301-304 are implemented by a push strategy engine running on the server. This push strategy engine can parse push guidance information, perform Boolean calculations using attributes and metrics on the business model, and invoke corresponding operations of the business model. In some embodiments, the push strategy engine uses reflection to obtain various attributes and methods from the business model, performs calculations based on the push guidance information, and executes the corresponding methods based on the calculation results.

[0144] In some embodiments, the push strategy engine consists of three parts: the push strategy engine body, the AST syntax parser, and the context manager. The push strategy engine body is responsible for overall coordination, including obtaining push guidance information, passing the push guidance information to the AST syntax parser to obtain the corresponding syntax tree, using reflection to retrieve at least one of the effect parameters and attribute parameters from the context manager based on the syntax tree result, and performing Boolean operations and corresponding operations based on the retrieved effect parameters and attribute parameters. The AST syntax parser is responsible for parsing the push guidance information to obtain the corresponding syntax tree for subsequent judgments. The context manager is responsible for storing the context object for strategy execution, i.e., the push effect information. The context manager is also responsible for storing the actual memory mapping of the push strategy engine, facilitating the retrieval of relevant attributes, metrics, and invocation operations.

[0145] Figure 4 and Figure 5 The workflow of the push strategy engine is shown in the image. Figure 4 and Figure 5 The server retrieves the target advertisement's performance parameters from the target business's metrics service and the corresponding attribute parameters from the target business's attribute service using the Domain Fetcher 401. Here, the domain in the Domain Fetcher refers to the advertising domain; in other scenarios, it refers to the domain corresponding to the scenario. The retrieved performance parameters and attribute parameters constitute a Domain Context object 402. The server inputs this Domain Context object 402 and push guidance information 403 (DSLRule) into the push strategy engine. The push strategy engine 404 is initialized. The push strategy engine body sends the Domain Context object to the Context Manager 405, which initializes it, i.e., stores the Domain Context object. The push strategy engine body sends the push guidance information to the AST syntax parser 406, which parses the push guidance information and generates a syntax tree corresponding to the push guidance information. Based on this syntax tree, the push strategy engine body retrieves at least one of the corresponding performance parameters and attribute parameters from the Context Manager. The push strategy engine performs a Boolean operation on at least one of the effect parameter and the attribute parameter to obtain the push method identifier. If the push method identifier is True, the push strategy engine retrieves the corresponding method from the context model, which is the operation; if the push method identifier is False, the push strategy engine terminates.

[0146] The following describes how advertisers invoke the advertising push method provided in this application embodiment through a terminal.

[0147] In one possible implementation, the terminal displays an advertising push page for uploading advertisements and setting the push method for those advertisements. This advertising push page includes an automatic push control. In response to a click on this automatic push control, the terminal sends an automatic push instruction to the server. This instruction carries the uploaded advertisement and the set push method, and is used to instruct the server to automatically push the uploaded advertisement, i.e., to instruct the server to perform steps 301-304 as described above.

[0148] For example, see Figure 6 The terminal displays an ad push page 600, which includes an ad upload area 601, a push method setting area 602, and an automatic push control 603. Users can upload ads they want to push in the ad upload area 601 and configure the default push method for the ads in the push method setting area 602, such as configuring the start time, end time, and daily budget. In response to a click on the automatic push control 603, the terminal sends an automatic push command to the server. This command carries the ad uploaded in the ad upload area 601 and the push method set in the push method setting area 602, instructing the uploaded ad to be automatically pushed. The server receives the automatic push command and pushes the ad accordingly, while simultaneously executing steps 301-304. In this scenario, routine operations such as pausing, starting, adjusting budgets, and adjusting bids for ads are all automatically performed by the server, requiring no user intervention and reducing the user's burden.

[0149] In some embodiments, during the execution of steps 301-304 by the server, the effectiveness information of the pushed advertisement, the operations performed, and the corresponding time can be sent to the terminal. The terminal can then display the effectiveness information of the pushed advertisement, the operations performed, and the corresponding time in real time, allowing users to understand the status of the advertisement push. For example, see... Figure 6 The terminal displays the advertising effect information, the operations performed, and the corresponding time in the information display area 604 of the advertising push page 600.

[0150] In one possible implementation, the server collects a sample dataset of target advertisements pushed using steps 301-304 described above. This sample dataset includes multiple sample data points. Each sample data point includes a first push method before adjustment, the type of the target advertisement, push effect information of pushing the target advertisement using the first push method, and a second push method obtained using steps 301-304. The server can use the collected sample dataset to train a push method determination model. During training, the first push method, the type of the target advertisement, and the push effect information of pushing the target advertisement using the first push method are used as inputs to the model, and the second push method is used as the annotation. The trained push method determination model can then be used to determine the push method, leveraging the model's generalization ability to improve the effectiveness of push method determination. In some embodiments, the structure of the push method determination model is a Deep Neural Network (DNN), a Convolutional Neural Network (CNN), a Multilayer Perceptron (MLP), or other types of structures, etc., which are not limited in this application embodiment.

[0151] It should be noted that the above description is based on the example of a server as the execution subject. In other possible implementations, the technical solutions provided in this application embodiment can also be executed by a terminal, and this application embodiment does not limit this.

[0152] All of the above-mentioned optional technical solutions can be combined in any way to form the optional embodiments of this application, and will not be described in detail here.

[0153] Using the technical solution provided in this application, during the advertising push process, the push effect information of the target advertisement is obtained. The push effect information can reflect the quality of the push effect when the target advertisement is pushed using the first push method. Subsequently, a second push method is determined based on the push guidance information and the push effect information. Since the push guidance information can guide the push of the target advertisement according to the quality of the push effect, that is, it provides a correspondence between the push effect and the push method, the determined second push method is more matched with the current push effect of the target advertisement. Using the second push method to push the target advertisement can achieve a better push effect.

[0154] Figure 7 This is a schematic diagram of the structure of an advertising push device provided in an embodiment of this application. See also... Figure 7 The device includes: a push effect information acquisition module 701, a push method determination module 702, and a push module 703.

[0155] The push effect information acquisition module 701 is used to acquire the push effect information of the target advertisement, which is used to indicate the push effect of pushing the target advertisement based on the first push method.

[0156] The push method determination module 702 is used to parse the push guidance information to obtain the structured information corresponding to the push guidance information. The push guidance information is generated based on the push effect information of multiple reference advertisements and the target object's operation on the multiple reference advertisements. The push guidance information is used to guide the push of advertisements based on the push effect information. Based on the push effect information and the structured information, the second push method of the target advertisement is determined.

[0157] The push module 703 is used to push the target advertisement using the second push method.

[0158] In one possible implementation, the push method determination module 702 is used to input the push guidance information into a syntax parser, and then use the syntax parser to structure the push guidance information to obtain the structured information corresponding to the push guidance information.

[0159] In one possible implementation, the push method determination module 702 is used to perform lexical analysis on the push guidance information using the grammar parser to obtain multiple words in the push guidance information and the types of the multiple words. Based on the types of the multiple words, grammatical analysis is performed on the multiple words to obtain the structured information corresponding to the push guidance information.

[0160] In one possible implementation, the push method determination module 702 is used to segment the push guidance information using the syntax parser to obtain multiple words in the push guidance information. The multiple words are then compared with a vocabulary type table to determine the type of the multiple words.

[0161] In one possible implementation, the push notification method determination module 702 is used to determine the hierarchy among the multiple words based on their types. Based on this hierarchy, the multiple words are rearranged to obtain structured information corresponding to the push notification guidance information.

[0162] In one possible implementation, the push method determination module 702 is configured to obtain at least one of the effect parameters and attribute parameters corresponding to the structured information from the push effect information. The effect parameters are parameters that change when the target advertisement is pushed, and the attribute parameters are parameters that do not change when the target advertisement is pushed. Based on the structured information, at least one of the effect parameters and attribute parameters is processed to obtain the second push method for the target advertisement.

[0163] In one possible implementation, the push method determination module 702 is used to obtain at least one of the effect parameter and the attribute parameter from the push effect information based on a reflection mechanism.

[0164] In one possible implementation, the push method determination module 702 is used to perform a Boolean operation on at least one of the effect parameter and the attribute parameter based on the target relationship data to obtain a push method identifier for the target advertisement. Based on the push method identifier, the second push method for the target advertisement is determined.

[0165] In one possible implementation, the device further includes:

[0166] The push notification guidance information generation module is used to obtain push performance information of multiple reference ads and the operations performed by the target object on each of the multiple reference ads. These operations are used to adjust the push method of the reference ads, and the target object is the object corresponding to the target ad. Based on the push performance information of the multiple reference ads and the operations performed by the target object on the multiple reference ads, the push notification guidance information is generated.

[0167] In one possible implementation, the push guidance information generation module is used to cluster the push effect information of the multiple reference advertisements and the operations performed by the target object on the multiple reference advertisements to generate the push guidance information.

[0168] In one possible implementation, the push effect information of the target advertisement includes effect parameters and attribute parameters. The push effect information acquisition module 701 is used to acquire the effect parameters of the target advertisement based on a target service, where the target service is the push service for pushing the target advertisement, and the effect parameters are parameters that describe the effect of pushing the target advertisement and are parameters that change during the push process. Based on the target service, the module also acquires the attribute parameters of the target service, where the attribute parameters are parameters that do not change during the push process of the target advertisement.

[0169] It should be noted that the advertising push device provided in the above embodiments is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above. In addition, the advertising push device and the advertising push method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0170] Using the technical solution provided in this application, during the advertising push process, the push effect information of the target advertisement is obtained. The push effect information can reflect the quality of the push effect when the target advertisement is pushed using the first push method. Subsequently, a second push method is determined based on the push guidance information and the push effect information. Since the push guidance information can guide the push of the target advertisement according to the quality of the push effect, that is, it provides a correspondence between the push effect and the push method, the determined second push method is more matched with the current push effect of the target advertisement. Using the second push method to push the target advertisement can achieve a better push effect.

[0171] This application provides a computer device for performing the above-described method. This computer device can be implemented as a terminal or a server. The structure of the terminal will be described below:

[0172] Figure 8 This is a schematic diagram of the structure of a terminal provided in an embodiment of this application. The terminal 800 can be a smartphone, tablet computer, laptop computer, desktop computer, smartwatch, etc. The terminal 800 may also be referred to as user equipment, portable terminal, laptop terminal, desktop terminal, or other names.

[0173] Typically, terminal 800 includes one or more processors 801 and one or more memories 802.

[0174] Processor 801 may include one or more processing cores, such as a quad-core processor or an octa-core processor. Processor 801 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 801 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 801 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, processor 801 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0175] The memory 802 may include one or more computer-readable storage media, which may be non-transitory. The memory 802 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 802 are used to store at least one computer program, which is executed by the processor 801 to implement the advertising push method provided in the method embodiments of this application.

[0176] In some embodiments, the terminal 800 may also optionally include a peripheral device interface 803 and at least one peripheral device. The processor 801, memory 802, and peripheral device interface 803 can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface 803 via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of the following: a radio frequency circuit 804, a display screen 805, a camera assembly 806, an audio circuit 807, and a power supply 808.

[0177] Peripheral device interface 803 can be used to connect at least one I / O (Input / Output) related peripheral device to processor 801 and memory 802. In some embodiments, processor 801, memory 802 and peripheral device interface 803 are integrated on the same chip or circuit board; in some other embodiments, any one or two of processor 801, memory 802 and peripheral device interface 803 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0178] The radio frequency (RF) circuit 804 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 804 communicates with communication networks and other communication devices via electromagnetic signals. The RF circuit 804 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals back into electrical signals. Optionally, the RF circuit 804 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc.

[0179] Display screen 805 is used to display a user interface (UI). This UI may include graphics, text, icons, video, and any combination thereof. When display screen 805 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 801 for processing. In this case, display screen 805 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard.

[0180] The camera assembly 806 is used to capture images or videos. Optionally, the camera assembly 806 includes a front-facing camera and a rear-facing camera. Typically, the front-facing camera is located on the front panel of the terminal, and the rear-facing camera is located on the back of the terminal.

[0181] The audio circuit 807 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, and convert the sound waves into electrical signals that are input to the processor 801 for processing, or input to the radio frequency circuit 804 to realize voice communication.

[0182] The power supply 808 is used to supply power to the various components in the terminal 800. The power supply 808 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery.

[0183] In some embodiments, the terminal 800 further includes one or more sensors 809. The one or more sensors 809 include, but are not limited to, an accelerometer 810, a gyroscope 811, a pressure sensor 812, an optical sensor 813, and a proximity sensor 814.

[0184] Accelerometer 810 can detect the magnitude of acceleration on the three coordinate axes of a coordinate system established by terminal 800.

[0185] The gyroscope sensor 811 can detect the orientation and rotation angle of the terminal 800. The gyroscope sensor 811 can work in conjunction with the accelerometer sensor 810 to collect the user's 3D operations on the terminal 800.

[0186] The pressure sensor 812 can be installed on the side bezel of the terminal 800 and / or on the lower layer of the display screen 805. When the pressure sensor 812 is installed on the side bezel of the terminal 800, it can detect the user's grip signal on the terminal 800, and the processor 801 can perform left / right hand recognition or quick operation based on the grip signal collected by the pressure sensor 812. When the pressure sensor 812 is installed on the lower layer of the display screen 805, the processor 801 can control the operable controls on the UI interface based on the user's pressure operation on the display screen 805.

[0187] The pressure sensor 812 can be installed on the side bezel of the terminal 800 and / or on the lower layer of the display screen 805. When the pressure sensor 812 is installed on the side bezel of the terminal 800, it can detect the user's grip signal on the terminal 800, and the processor 801 can perform left / right hand recognition or quick operation based on the grip signal collected by the pressure sensor 812. When the pressure sensor 812 is installed on the lower layer of the display screen 805, the processor 801 can control the operable controls on the UI interface based on the user's pressure operation on the display screen 805.

[0188] An optical sensor 813 is used to collect ambient light intensity. In one embodiment, a processor 801 can control the display brightness of a display screen 805 based on the ambient light intensity collected by the optical sensor 813.

[0189] The proximity sensor 814 is used to detect the distance between the user and the front of the terminal 800.

[0190] Those skilled in the art will understand that Figure 8 The structure shown does not constitute a limitation on terminal 800 and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0191] The aforementioned computer equipment can also be implemented as a server. The structure of a server is described below:

[0192] Figure 9 This is a schematic diagram of a server structure provided in an embodiment of this application. The server 900 can vary significantly due to different configurations or performance. It may include one or more Central Processing Units (CPUs) 901 and one or more memories 902. The one or more memories 902 store at least one computer program, which is loaded and executed by the one or more processors 901 to implement the methods provided in the various method embodiments described above. Of course, the server 900 may also have wired or wireless network interfaces, a keyboard, and input / output interfaces for input and output. The server 900 may also include other components for implementing device functions, which will not be elaborated upon here.

[0193] In an exemplary embodiment, a computer-readable storage medium is also provided, such as a memory including a computer program that can be executed by a processor to perform the advertising push method in the above embodiments. For example, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage device, etc.

[0194] In an exemplary embodiment, a computer program product or computer program is also provided, which includes program code stored in a computer-readable storage medium. The processor of a computer device reads the program code from the computer-readable storage medium and executes the program code, causing the computer device to perform the above-described advertising push method.

[0195] In some embodiments, the computer program involved in the present application embodiments may be deployed and executed on a computer device, or executed on multiple computer devices located in one location, or executed on multiple computer devices distributed in multiple locations and interconnected through a communication network. Multiple computer devices distributed in multiple locations and interconnected through a communication network may constitute a blockchain system.

[0196] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0197] The above are merely optional embodiments of this application and are not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. An advertisement pushing method characterized by comprising: The method includes: Obtain the push effect information of the target advertisement, wherein the push effect information is used to indicate the push effect of pushing the target advertisement based on the first push method; The push guidance information is input into a syntax parser, which then structures the push guidance information to obtain the structured information corresponding to the push guidance information. The push guidance information is generated based on the push effect information of multiple reference ads and the target object's operations on the multiple reference ads. The push guidance information is used to guide the push of ads based on the push effect information. The push guidance information is a push strategy. The structured information is obtained by splitting and reorganizing the push guidance information according to the hierarchical relationship of the information. Based on the push effect information and the structured information, a second push method for the target advertisement is determined; The method of pushing the target advertisement is changed from the first method to the second method.

2. The method of claim 1, wherein, The step of structuring the push notification information using the syntax parser to obtain the structured information corresponding to the push notification information includes: The parser performs lexical analysis on the push guidance information to obtain multiple words and their types; based on the types of the multiple words, it performs grammatical analysis on the multiple words to obtain the structured information corresponding to the push guidance information.

3. The method of claim 2, wherein, The step of performing lexical analysis on the push guidance information using the syntax parser to obtain multiple words in the push guidance information and the types of the multiple words includes: The push notification information is segmented by the parser to obtain multiple words in the push notification information; the multiple words are compared with the word type table to obtain the type of the multiple words.

4. The method of claim 2, wherein, The grammatical analysis of the multiple words based on their types to obtain the structured information corresponding to the push guidance information includes: Based on the types of the multiple words, the hierarchy among the multiple words is determined; based on the hierarchy among the multiple words, the multiple words are rearranged to obtain the structured information corresponding to the push guidance information.

5. The method of claim 1, wherein, The second push method for determining the target advertisement based on the push effect information and the structured information includes: Obtain at least one of the effect parameters and attribute parameters corresponding to the structured information from the push effect information, wherein the effect parameters are parameters that change when the target advertisement is pushed, and the attribute parameters are parameters that do not change when the target advertisement is pushed; Based on the structured information, at least one of the effect parameters and the attribute parameters is processed to obtain the second push method of the target advertisement.

6. The method of claim 5, wherein, The step of obtaining at least one of the effect parameters and attribute parameters corresponding to the structured information from the push effect information includes: Based on the reflection mechanism, at least one of the effect parameters and the attribute parameters is obtained from the push effect information.

7. The method of claim 5, wherein, The structured information includes target relationship data. The second push method for the target advertisement, based on the structured information, involves processing at least one of the effect parameters and attribute parameters. Based on the target relationship data, a Boolean operation is performed on at least one of the effect parameters and the attribute parameters to obtain the push method identifier of the target advertisement; Based on the push method identifier, the second push method of the target advertisement is determined.

8. The method of claim 1, wherein, Before obtaining the push effect information of the target advertisement, the method further includes: The system obtains the push effect information of the multiple reference advertisements and the operations performed by the target object on the multiple reference advertisements respectively. The operations are used to adjust the push method of the reference advertisements, and the target object is the object corresponding to the target advertisement. The push guidance information is generated based on the push effect information of the multiple reference ads and the operations performed by the target object on the multiple reference ads.

9. The method according to claim 8, characterized in that, The process of generating the push guidance information based on the push effect information of the multiple reference ads and the operations performed by the target object on the multiple reference ads includes: The push effect information of the multiple reference ads and the operations performed by the target object on the multiple reference ads are clustered to generate the push guidance information.

10. The method according to claim 1, characterized in that, The target ad's push performance information includes performance parameters and attribute parameters. Obtaining the target ad's push performance information includes: Based on the target business, obtain the performance parameters of the target advertisement. The target business is the push service for pushing the target advertisement. The performance parameters are parameters that describe the performance of pushing the target advertisement. The performance parameters are parameters that will change during the process of pushing the target advertisement. Based on the target business, obtain the attribute parameters of the target business. The attribute parameters are parameters that will not change during the process of pushing the target advertisement.

11. An advertising push device, characterized in that, The device includes: The push effect information acquisition module is used to acquire push effect information of the target advertisement, wherein the push effect information is used to indicate the push effect of pushing the target advertisement based on the first push method; The push method determination module is used to input push guidance information into a syntax parser, and to structure the push guidance information through the syntax parser to obtain structured information corresponding to the push guidance information. The push guidance information is generated based on the push effect information of multiple reference advertisements and the target object's operations on the multiple reference advertisements. The push guidance information is used to guide the push of advertisements based on the push effect information. The push guidance information is a push strategy. The structured information is obtained by splitting and reorganizing the push guidance information according to the hierarchical relationship of the information. Based on the push effect information and the structured information, a second push method for the target advertisement is determined. The push module is used to change the push method of the target advertisement from the first push method to the second push method.

12. The apparatus according to claim 11, characterized in that, The step of structuring the push notification information using the syntax parser to obtain the structured information corresponding to the push notification information includes: The parser performs lexical analysis on the push guidance information to obtain multiple words and their types; based on the types of the multiple words, it performs grammatical analysis on the multiple words to obtain the structured information corresponding to the push guidance information.

13. The apparatus according to claim 12, characterized in that, The step of performing lexical analysis on the push guidance information using the syntax parser to obtain multiple words in the push guidance information and the types of the multiple words includes: The push notification information is segmented by the parser to obtain multiple words in the push notification information; the multiple words are compared with the word type table to obtain the type of the multiple words.

14. The apparatus according to claim 12, characterized in that, The grammatical analysis of the multiple words based on their types to obtain the structured information corresponding to the push guidance information includes: Based on the types of the multiple words, the hierarchy among the multiple words is determined; based on the hierarchy among the multiple words, the multiple words are rearranged to obtain the structured information corresponding to the push guidance information.

15. The apparatus according to claim 11, characterized in that, The second push method for determining the target advertisement based on the push effect information and the structured information includes: Obtain at least one of the effect parameters and attribute parameters corresponding to the structured information from the push effect information, wherein the effect parameters are parameters that change when the target advertisement is pushed, and the attribute parameters are parameters that do not change when the target advertisement is pushed; Based on the structured information, at least one of the effect parameters and the attribute parameters is processed to obtain the second push method of the target advertisement.

16. The apparatus according to claim 15, characterized in that, The step of obtaining at least one of the effect parameters and attribute parameters corresponding to the structured information from the push effect information includes: Based on the reflection mechanism, at least one of the effect parameters and the attribute parameters is obtained from the push effect information.

17. The apparatus according to claim 15, characterized in that, The structured information includes target relationship data. The second push method for the target advertisement, based on the structured information, involves processing at least one of the effect parameters and attribute parameters. Based on the target relationship data, a Boolean operation is performed on at least one of the effect parameters and the attribute parameters to obtain the push method identifier of the target advertisement; Based on the push method identifier, the second push method of the target advertisement is determined.

18. The apparatus according to claim 11, characterized in that, Before obtaining the target advertisement's push performance information, the device further includes: The system obtains the push effect information of the multiple reference advertisements and the operations performed by the target object on the multiple reference advertisements respectively. The operations are used to adjust the push method of the reference advertisements, and the target object is the object corresponding to the target advertisement. The push guidance information is generated based on the push effect information of the multiple reference ads and the operations performed by the target object on the multiple reference ads.

19. The apparatus according to claim 18, characterized in that, The process of generating the push guidance information based on the push effect information of the multiple reference ads and the operations performed by the target object on the multiple reference ads includes: The push effect information of the multiple reference ads and the operations performed by the target object on the multiple reference ads are clustered to generate the push guidance information.

20. The apparatus according to claim 11, characterized in that, The target ad's push performance information includes performance parameters and attribute parameters. Obtaining the target ad's push performance information includes: Based on the target business, obtain the performance parameters of the target advertisement. The target business is the push service for pushing the target advertisement. The performance parameters are parameters that describe the performance of pushing the target advertisement. The performance parameters are parameters that will change during the process of pushing the target advertisement. Based on the target business, obtain the attribute parameters of the target business. The attribute parameters are parameters that will not change during the process of pushing the target advertisement.

21. A computer device, characterized in that, The computer device includes one or more processors and one or more memories, wherein at least one computer program is stored in the one or more memories, and the computer program is loaded and executed by the one or more processors to implement the advertising push method as described in any one of claims 1 to 10.

22. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one computer program, which is loaded and executed by a processor to implement the advertising push method as described in any one of claims 1 to 10.

23. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the advertising push method according to any one of claims 1 to 10.

Images