Target object putting method and device and related product

Abstract

Embodiments of the invention provide a target object delivery method and apparatus, and a related product. The method comprises the steps of obtaining behavior data of a plurality of users for a target object and a resource quantity generated by the target object based on the behavior data of the users; dividing each user into a first category of users and a second category of users according to the resource quantity corresponding to each user; a first resource quantity generated by the target object based on the behavior data of the first category of users is greater than a second resource quantity generated based on the behavior data of the second category of users; determining a target behavior feature of at least one feature dimension according to the difference between the behavior data of the first category of users and the behavior data of the second category of users; the first category of users have target behavior characteristics; and determining a first target user with the target behavior characteristic in each first category of users, determining a first similar user of the first target user, and pushing a target object to a terminal device of the first similar user.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to a method, apparatus and related products for targeting objects. Background Technology

[0002] Currently, when targeting users, such as by placing advertisements, it's common practice to pre-screen user groups who might be interested in the target audience and then target those groups. Related technologies often rely on the experience of marketing personnel to determine which user behaviors are key behaviors, and then target users similar to those exhibiting these key behaviors. Key behaviors refer to actions that demonstrate a user's strong interest in the target audience, such as an advertisement; examples include clicking, registering, and adding items to the shopping cart. However, this approach, which relies on manual determination of key behaviors, suffers from low accuracy in identifying them, resulting in inaccurate targeting. Summary of the Invention

[0003] The purpose of this disclosure is to provide a method, apparatus, and related products for targeting specific objects, which can accurately determine the key behaviors of users, identify the user groups for targeting based on the key behaviors of users, and improve the accuracy of target targeting.

[0004] To achieve the above objectives, the embodiments disclosed herein employ the following technical solutions: In a first aspect, embodiments of this disclosure provide a method for targeting objects, including: The system acquires behavioral data from multiple users targeting a target object and the resource quantity generated by the target object based on the users' behavioral data; the target object is then pushed to the user's terminal device. Based on the resource amount corresponding to each user, the users are divided into a first category of users and a second category of users; the first resource amount generated by the target object based on the behavioral data of the first category of users is greater than the second resource amount generated based on the behavioral data of the second category of users; Based on the differences between the behavioral data of the first category of users and the behavioral data of the second category of users, a target behavioral feature of at least one feature dimension is determined; the first category of users possesses the target behavioral feature. Among the users in each of the first category, a first target user with the target behavioral characteristics is identified, and a first similar user of the first target user is identified, and the target object is pushed to the terminal device of the first similar user.

[0005] Secondly, embodiments of this disclosure provide a target object delivery device, comprising: The data acquisition unit is used to acquire behavioral data of multiple users targeting a target object and the amount of resources generated by the target object based on the user's behavioral data; the target object is pushed to the user's terminal device; The user classification unit is used to divide each user into a first category of users and a second category of users according to the resource amount corresponding to each user; the first resource amount generated by the target object based on the behavior data of the first category of users is greater than the second resource amount generated based on the behavior data of the second category of users. A feature determination unit is configured to determine a target behavioral feature of at least one feature dimension based on the difference between the behavioral data of the first category of users and the behavioral data of the second category of users; the first category of users possesses the target behavioral feature; The object push unit is configured to determine a first target user with the target behavioral characteristics among users of the first category, and to determine a first similar user of the first target user, and to push the target object to the terminal device of the first similar user.

[0006] Thirdly, embodiments of this disclosure provide an electronic device, including: Processor; and, A memory configured to store computer-executable instructions, which, when executed, cause the processor to implement the method described in the first aspect above.

[0007] Fourthly, embodiments of this disclosure provide a computer-readable storage medium for storing computer-executable instructions that, when executed by a processor, implement the method described in the first aspect.

[0008] Fifthly, embodiments of this disclosure provide a computer program product, the computer program product including a computer program, which, when executed by a processor, implements the method described in the first aspect above.

[0009] The above-described at least one technical solution adopted in the embodiments of this disclosure can achieve the following beneficial effects: First, behavioral data of multiple users targeting a target object and the resource volume generated by the target object based on the user behavioral data are acquired. The target object is pushed to the user's terminal device. Then, based on the resource volume corresponding to each user, the users are divided into a first category of users and a second category of users. The first resource volume generated by the target object based on the behavioral data of the first category of users is greater than the second resource volume generated based on the behavioral data of the second category of users. Next, based on the difference between the behavioral data of the first category of users and the behavioral data of the second category of users, at least one feature dimension of target behavioral features is determined. The first category of users has the target behavioral features. Finally, among the first category of users, a first target user with the target behavioral features is determined, and a first similar user of the first target user is determined. The target object is pushed to the terminal device of the first similar user. As can be seen, this embodiment can divide users into a first category and a second category based on the amount of resources each user has. Based on the differences between the behavioral data of the first category and the behavioral data of the second category, at least one target behavioral feature of a feature dimension can be determined. The target behavioral feature is the key behavioral feature. By classifying users and comparing features, the key behaviors of users can be accurately determined. Based on the key behaviors of users, the user group for targeted advertising can be accurately determined. Compared with the method of determining key behaviors manually in related technologies, this method effectively improves the accuracy of targeted advertising. Attached Figure Description

[0010] The accompanying drawings, which are included to provide a further understanding of the embodiments of this disclosure and form part of the embodiments of this disclosure, are illustrative embodiments of this disclosure and, together with their description, are used to explain the embodiments of this disclosure, and do not constitute an improper limitation of the embodiments of this disclosure. In the drawings: Figure 1 A flowchart illustrating a target object delivery method provided in an embodiment of this disclosure; Figure 2 This is a schematic diagram of the structure of a target object delivery device provided in an embodiment of the present disclosure; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. Detailed Implementation

[0011] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of the embodiments of this disclosure.

[0012] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms are interchangeable where appropriate; this is merely a way of distinguishing objects with the same attributes in the embodiments of this disclosure. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, so that a process, method, system, product, or apparatus that comprises a series of units is not necessarily limited to those units, but may include other units not expressly listed or inherent to those processes, methods, products, or apparatuses.

[0013] This disclosure provides a method, apparatus, and related products for targeting specific objects, which can accurately determine key user behaviors, identify user groups for targeting based on these key user behaviors, and improve the accuracy of target targeting.

[0014] Figure 1 This is a flowchart illustrating a target object delivery method provided in an embodiment of this disclosure, as shown below. Figure 1 As shown, the process includes: Step S102: Obtain behavioral data of multiple users targeting the target object and the resource quantity generated by the target object based on the user behavioral data; the target object is pushed to the user's terminal device; Step S104: Based on the resource amount corresponding to each user, the users are divided into a first category of users and a second category of users; the first resource amount generated by the target object based on the behavior data of the first category of users is greater than the second resource amount generated based on the behavior data of the second category of users. Step S106: Based on the difference between the behavioral data of the first category of users and the behavioral data of the second category of users, determine at least one target behavioral feature of a feature dimension; the first category of users has the target behavioral feature. Step S108: Determine the first target user with the target behavior characteristics among the users in each first category, and determine the first similar user of the first target user, and push the target object to the terminal device of the first similar user.

[0015] First, behavioral data of multiple users targeting a target object and the resource volume generated by the target object based on the user behavioral data are acquired. The target object is pushed to the user's terminal device. Then, based on the resource volume corresponding to each user, the users are divided into a first category of users and a second category of users. The first resource volume generated by the target object based on the behavioral data of the first category of users is greater than the second resource volume generated based on the behavioral data of the second category of users. Next, based on the difference between the behavioral data of the first category of users and the behavioral data of the second category of users, at least one feature dimension of target behavioral features is determined. The first category of users has the target behavioral features. Finally, among the first category of users, a first target user with the target behavioral features is determined, and a first similar user of the first target user is determined. The target object is pushed to the terminal device of the first similar user. As can be seen, this embodiment can divide users into a first category and a second category based on the amount of resources each user has. Based on the differences between the behavioral data of the first category and the behavioral data of the second category, at least one target behavioral feature of a feature dimension can be determined. The target behavioral feature is the key behavioral feature. By classifying users and comparing features, the key behaviors of users can be accurately determined. Based on the key behaviors of users, the user group for targeted advertising can be accurately determined. Compared with the method of determining key behaviors manually in related technologies, this method effectively improves the accuracy of targeted advertising.

[0016] In this embodiment, the target object refers to an object that can be pushed to the user's terminal device, such as a mobile phone or computer, for example, an advertisement. This advertisement can be an application advertisement; no specific limitation is made here. The following explanation uses an advertisement as the target object.

[0017] In step S102 above, multiple users' behavioral data regarding the target object and the resource volume generated by the target object based on the users' behavioral data are obtained. In this step, behavioral data of multiple users regarding the targeted advertisement is obtained, such as at least one of click data, registration data, login data, browsing data, order data, and purchase data. Additionally, the resource volume generated by the target object based on each user's behavioral data is also obtained. The resource volume can be exemplified as the revenue generated by the advertisement due to the users' behavioral data.

[0018] In one example, for each user, user behavior data targeting an object such as an advertisement is obtained from multiple data sources using at least one of the following methods: 1. Obtain user behavior data on the target object on the web through JavaScript technology interfaces; 2. Collect user behavior data such as browsing, clicking, dwell time, and scrolling depth on the website through SDK (Software Development Kit) or server-side tracking; 3. Collect user behavior data such as page visits, button clicks, and gesture operations on mobile devices through the mobile SDK; 4. Extract business data such as user registration, purchase, repeat purchase, and customer service inquiries from the backend databases of business systems such as CRM (Customer Relationship Management) systems, order systems, and membership systems.

[0019] In this embodiment, considering that the format of user behavior data obtained from different data sources may be different, a data unification model can also be used to unify the data format of user behavior data obtained from various data sources to obtain behavior data in the following format: User ID (Identity), Event Type, Event Time, Event Attribute (JSON format), Device Information, and Source Channel.

[0020] The event type and event attributes represent events such as clicks, views, orders, and payments. Event time can be UTC standard time, and device information refers to the identifier of the user device acquiring the data. The source channels include, but are not limited to, any of the four channels mentioned above. Furthermore, a cross-platform user ID mapping table can be established to associate the behavioral data of the same user on different devices and platforms using login account information.

[0021] In this embodiment, after obtaining the user's behavior data, the behavior data of each user can be arranged in chronological order to construct the user's behavior data sequence. For example, if the target is an advertisement on an e-commerce platform, the behavior data sequence of user A can be exemplified as follows: [Time 1, Browse the homepage] → [Time 2, Search for "running shoes"] → [Time 3, View product details] → [Time 4, Add to cart] → [Time 5, Browse reviews] → [Time 6, Complete payment].

[0022] In step S104 above, users are divided into a first category and a second category based on the resource amount corresponding to each user. The purpose of this step is to classify users based on the resource amount generated by the advertising based on the behavioral data of different users, thus obtaining a user group that can generate a higher resource amount (the first category) and a user group that can generate a lower resource amount (the second category). Specifically, the first resource amount generated by the target audience based on the behavioral data of the first category users is greater than the second resource amount generated based on the behavioral data of the second category users.

[0023] In one embodiment, based on the amount of resources corresponding to each user, users are divided into a first category of users and a second category of users, including: using a user classification model, based on the amount of resources corresponding to each user, dividing users into a first number of first category users and a second number of second category users; the ratio of the first number to the second number is a first ratio; the ratio of the first amount of resources to the second amount of resources is a second ratio; the first ratio is less than the second ratio.

[0024] In this embodiment, a pre-trained binary classification model, specifically a user classification model, is used. This model divides users into a first category and a second category based on the amount of resources available to each user. The ratio of the first category to the second category is a first ratio, which can be 2:8. The ratio of the first resource amount generated by the target object based on the behavior data of the first category users to the second resource amount generated by the target object based on the behavior data of the second category users is a second ratio, which is 8:2. Therefore, the first ratio is less than the second ratio.

[0025] This user classification model, based on the 20 / 80 rule, can classify users into two categories: the first category consists of 20% of users who generate 80% of the resources (revenue), and the second category consists of 80% of users who generate 20% of the resources (revenue). This allows for accurate user classification based on resource volume.

[0026] In step S106 above, at least one target behavioral feature is determined based on the difference between the behavioral data of the first category of users and the behavioral data of the second category of users. The first category of users possesses the target behavioral feature.

[0027] After classifying users, behavioral characteristics possessed by users in the first category but not by users in the second category are identified as target behavioral characteristics. These target behavioral characteristics belong to one or more feature dimensions. Feature dimensions include at least one of the following: single behavioral characteristic dimensions, combined behavioral characteristic dimensions, and user attribute characteristic dimensions.

[0028] Among them, a single behavioral feature dimension refers to a dimension determined based on a single behavioral feature, such as the frequency of a single behavior, the time of occurrence of a single behavior, and the duration of a single behavior. Taking advertising on an e-commerce platform as an example, the frequency of a single behavior can be exemplified by the number of times product details are viewed, the time of occurrence of a single behavior can be exemplified by the time the page is first visited, and the duration of a single behavior can be exemplified by the length of time a user stays on a particular page.

[0029] Combined behavioral feature dimensions refer to dimensions determined based on two or more behavioral features. Examples include the frequency of occurrence of behavioral sequences involving multiple behaviors, the conversion rate between multiple behaviors, and the time interval between multiple behaviors. Taking advertising on an e-commerce platform as an example, the frequency of occurrence of behavioral sequences involving multiple behaviors can be exemplified by the frequency of occurrence of the pattern "browse product → add to cart → abandon → browse again → purchase". The conversion rate between multiple behaviors can be exemplified by the conversion rate from "add to cart" to "payment". The time interval between multiple behaviors can be exemplified by the time interval from "first visit" to "registration".

[0030] User attribute characteristics include, but are not limited to, a user's historical conversion count, user lifecycle stage, and the source channels from which the user acquires ads. Historical conversion count refers to the number of times a user has triggered an ad after seeing it. User lifecycle stages include, but are not limited to, new users, active users, and churned users who have viewed ads. The source channels from which users acquire ads include, but are not limited to, organic search, paid ads, and social media.

[0031] In one embodiment, based on the difference between the behavioral data of a first category of users and the behavioral data of a second category of users, a target behavioral feature of at least one feature dimension is determined, including: Based on the behavioral data of the first category of users, determine the first behavioral feature of the first feature dimension of the first category of users; the first feature dimension includes at least one of the single behavioral feature dimension, the combined behavioral feature dimension, and the user attribute feature dimension. Based on the behavioral data of the second category of users, determine the second behavioral features of the second feature dimension of the second category of users; the second feature dimension includes at least one of the following: single behavioral feature dimension, combined behavioral feature dimension, and user attribute feature dimension. The first behavioral feature and the second behavioral feature are compared to obtain the distinguishing behavioral feature between the first behavioral feature and the second behavioral feature. The target behavioral feature is determined based on the distinguishing behavioral feature. The distinguishing behavioral feature belongs to at least one of the following dimensions: single behavioral feature dimension, combined behavioral feature dimension, and user attribute feature dimension.

[0032] First, based on the behavioral data of the first category of users, determine the first behavioral features of the first feature dimension for the first category of users. The first feature dimension includes at least one of a single behavioral feature dimension, a combined behavioral feature dimension, and a user attribute feature dimension. In one example, determine the first behavioral features corresponding to the first category of users under each first feature dimension. For example, determine multiple features belonging to the single behavioral feature dimension for the first category of users, such as the time of first page visit, the duration of the first page visit, and the number of page visits. Determine multiple features belonging to the combined behavioral feature dimension for the first category of users, such as the frequency of occurrence of the "page visit"-"purchase" behavior sequence, the conversion rate from "add to cart" to "payment", and the time interval from "first visit" to "registration". Determine multiple features belonging to the user attribute feature dimension for the first category of users, such as the number of times the user has triggered an ad after seeing an ad in the past and the source channel from which the user obtained the ad.

[0033] Then, based on the behavioral data of the second category of users, the second behavioral features of the second feature dimension of the second category of users are determined. The second feature dimension includes at least one of a single behavioral feature dimension, a combined behavioral feature dimension, and a user attribute feature dimension. In one example, the second behavioral features corresponding to the second category of users under each second feature dimension are determined. For example, multiple features belonging to the single behavioral feature dimension, multiple features belonging to the combined behavioral feature dimension, and multiple features belonging to the user attribute feature dimension are determined for the second category of users.

[0034] It should be noted that there are multiple users in the first category. We can determine the behavioral characteristics of each user in the first category belonging to the first feature dimension, and then take the union of the behavioral characteristics of all users to obtain the first behavioral characteristic of the first feature dimension for the first category of users. Similarly, there are multiple users in the second category. We can determine the behavioral characteristics of each user in the second category belonging to the second feature dimension, and then take the union of the behavioral characteristics of all users to obtain the second behavioral characteristic of the second feature dimension for the second category of users.

[0035] Finally, the first behavioral feature and the second behavioral feature are compared to obtain the distinguishing behavioral feature between the first and second behavioral features. This distinguishing behavioral feature belongs to at least one of the following dimensions: a single behavioral feature dimension, a combined behavioral feature dimension, and a user attribute feature dimension. The first behavioral feature includes this distinguishing behavioral feature, while the second behavioral feature does not. Furthermore, the target behavioral feature is determined based on the distinguishing behavioral feature.

[0036] This embodiment can identify the distinguishing behavioral characteristics between the first category of users and the second category of users, and determine the target behavioral characteristics based on these distinguishing behavioral characteristics, thereby improving the accuracy of determining the target behavioral characteristics.

[0037] In one embodiment, determining the target behavioral characteristics based on distinguishable behavioral characteristics includes: For each distinguishing behavioral feature, the contribution of the distinguishing behavioral feature is determined based on the proportion of the number of key users with distinguishing behavioral features in each category of users to the total number of users in each category, and the average amount of resources generated by each key user with distinguishing behavioral features. Based on the contribution of each distinguishing behavioral feature, candidate behavioral features are determined from among the distinguishing behavioral features. The behavioral parameters of the candidate behavioral features are then adjusted to obtain the target behavioral feature.

[0038] For each distinguishing behavioral feature, since the union of the behavioral features belonging to the first feature dimension for each user in the first category yields the first behavioral feature of the first feature dimension for the first category of users, and the distinguishing behavioral feature is the behavioral feature included in the first behavioral feature, there may be a situation where some users in the first category have the distinguishing behavioral feature while others do not. Therefore, users with the distinguishing behavioral feature are identified as key users in each category of users, and the number of each key user is determined. Furthermore, the proportion of each key user to the total number of users is determined. Next, the amount of resources generated by each key user with the distinguishing behavioral feature is determined, and the average value of this resource amount is calculated.

[0039] Based on the aforementioned proportions and average values, the contribution of this distinguishing behavioral characteristic is determined. The contribution can be equal to the proportion multiplied by the average value, so that the more users in the first category have this distinguishing behavioral characteristic, the greater the amount of resources generated by this distinguishing behavioral characteristic, and the higher the contribution of this distinguishing behavioral characteristic.

[0040] Next, based on the contribution of each distinguishing behavioral feature, candidate behavioral features are determined from among them. These candidate features can be multiple distinguishing behavioral features with the highest contribution ranking. The behavioral parameters of the candidate behavioral features are then adjusted to obtain the target behavioral feature.

[0041] In one embodiment, adjusting the behavioral parameters of candidate behavioral features to obtain target behavioral features includes: Obtain the historical resource quantity generated based on the target object; Analyze the acquired historical resource data to obtain the correlation between historical resource data and behavioral parameters of candidate behavioral features; Based on the correlation, the behavioral parameters of the candidate behavioral features are increased or decreased to obtain the target behavioral features.

[0042] First, acquire historical resource data generated based on the target object. This historical resource data can be historical revenue generated based on the target object. Then, analyze the acquired historical resource data to obtain the correlation between the historical resource data and the behavioral parameters of candidate behavioral features. This correlation can include the relationship between the behavioral parameters of behavioral features corresponding to single behavioral feature dimensions, combined behavioral feature dimensions, and user attribute feature dimensions, and the historical resource data. For example, this correlation could be illustrated as follows: if a user stays in the app corresponding to the advertisement for 5 seconds, the advertisement has a high probability of generating significant revenue.

[0043] Finally, based on the correlation, the behavioral parameters of the candidate behavioral features are increased or decreased to obtain the target behavioral features. For example, if the correlation reveals that the ad has a high probability of generating significant revenue after a user stays in the app corresponding to the ad for 5 seconds, the duration of the user stays in the app corresponding to the ad in the candidate behavioral feature can be changed to 5 seconds by increasing or decreasing the duration.

[0044] In this embodiment, by combining the correlation between the historical resource volume generated by the target object and the behavioral parameters of the candidate behavioral features, the behavioral parameters of the candidate behavioral features are increased or decreased to obtain the target behavioral features. This achieves the goal of adjusting the candidate behavioral features according to the actual situation, resulting in more accurate target behavioral features that can better assist the target object in generating resource volume.

[0045] In this embodiment, a unique feature identifier can also be generated for each target behavioral feature.

[0046] In one embodiment, the execution entity of the above method embodiment is a server that integrates advertisers and advertising placement terminals. After determining the target behavioral characteristics, the server directly executes step S108.

[0047] In another embodiment, the execution entity of the above method embodiment is the server corresponding to the advertising delivery end. After determining the target behavior characteristics, the server sends the target behavior characteristics back to the server corresponding to the advertiser. The server corresponding to the advertiser then executes step S108.

[0048] In the specific data transmission process, the target behavioral characteristics need to be transmitted back to the advertiser's server according to the advertiser's corresponding server's API (Application Programming Interface) protocol and data format. Furthermore, the target behavioral characteristics can be transmitted back to the advertiser's server using both real-time and batch transmission methods.

[0049] This can be achieved by converting the target behavioral features according to the data format of the advertiser's server. For example, the behavioral identifiers in the target behavioral features can be mapped to the standard behavioral identifiers of the advertiser's platform, and the user information in the target behavioral features can be hashed and encrypted according to the requirements of the advertiser's platform.

[0050] In real-time transmission, each time a target behavioral feature is analyzed, it is transmitted to the advertiser's server in real time, using an asynchronous queue mechanism. In batch transmission, the target behavioral features identified within that hour can be uploaded at regular intervals, such as every hour. Furthermore, regardless of whether it's real-time or batch transmission, a retry strategy can be used to retransmit if transmission fails until successful.

[0051] In step S108 above, a first target user with target behavioral characteristics is identified among each first category of users, and a first similar user of the first target user is identified, and the target object is pushed to the terminal device of the first similar user.

[0052] For each target behavioral feature, the first behavioral feature of the first feature dimension for each user in the first category is obtained by taking the union of the behavioral features belonging to the first feature dimension. The distinguishing behavioral feature is the behavioral feature included in the first behavioral feature, and the target behavioral feature is determined based on the distinguishing behavioral feature. Therefore, some users in the first category may possess the target behavioral feature while others may not. Thus, users with the target behavioral feature are identified as the first target users within each first category. Then, based on user profiling and other methods, the first similar users of the first target users are identified, and the target object is pushed to their terminal devices. Since the first similar users and the first target users have similar behavioral features, the first similar users are more likely to trigger the target object, such as clicking on advertisements and generating more resources based on the target object.

[0053] In one embodiment, after pushing the target object to the terminal device of the first similar user, the method further includes: Obtain the amount of resources generated by the target object based on the target behavior characteristics, and obtain the amount of resources deployed by the target object based on the target behavior characteristics; Based on the amount of resources generated and deployed, identify the problematic behavioral features to be deleted from each target behavioral feature, and then delete the problematic behavioral features from each target behavioral feature. Among the users in each first category, identify a second target user with the remaining target behavior characteristics after deletion, and identify a second similar user of the second target user, and push the target object to the terminal device of the second similar user.

[0054] In this embodiment, firstly, the amount of resources generated by the target object based on the target behavior characteristics is obtained, and secondly, the amount of resources deployed by the target object based on the target behavior characteristics is obtained. The amount of resources generated by the target object based on the target behavior characteristics refers to the amount of resources generated by the target object based on users with the target behavior characteristics, which can be obtained from the system monitoring the amount of resources generated by the target object. The amount of resources deployed by the target object based on the target behavior characteristics refers to the amount of resources consumed in pushing the target object to users, which can be obtained from the system used to push the target object.

[0055] Then, based on the generated and deployed resource amounts, problematic behavioral features to be deleted are identified from each target behavioral feature. These problematic behavioral features are then deleted from each target behavioral feature. The problematic behavioral features can be determined using the following two formulas: Formula 1 ROI (Return on Investment) = (Amount of resources generated by the target object based on target behavioral characteristics - Amount of resources allocated by the target object based on target behavioral characteristics) / Amount of resources allocated by the target object based on target behavioral characteristics; Formula 2: ROAS (Return on Ad Spend) = Amount of resources generated by the target audience based on target behavioral characteristics / Amount of resources delivered to the target audience based on target behavioral characteristics; If the ROI calculated by Formula 1 is less than the first threshold, or if the ROAS calculated by Formula 2 is less than the second threshold, then the target behavioral feature is identified as a problematic behavioral feature to be deleted, and the problematic behavioral feature is deleted from each target behavioral feature. Specifically, if the ROI calculated by Formula 1 is less than the first threshold for a certain period of time, or if the ROAS calculated by Formula 2 is less than the second threshold for a certain period of time, then the target behavioral feature is identified as a problematic behavioral feature to be deleted, and the problematic behavioral feature is deleted from each target behavioral feature.

[0056] Finally, among the users in each of the first category, second target users with the remaining target behavior characteristics after deletion are identified, and second similar users of the second target users are identified. Target objects are then pushed to the terminal devices of the second similar users. Second similar users of the second target users can be identified based on user profiles or other methods, and target objects are pushed to their terminal devices. Since the second similar users have similar behavioral characteristics to the second target users, they are more likely to trigger the target objects, such as clicking on advertisements and generating more resources based on the target objects.

[0057] This embodiment can also identify and delete problematic behavioral features with low resource content generated from target behavioral features, thereby re-identifying the target audience for the advertisement, improving the accuracy of identifying the target audience for the advertisement, and improving the accuracy of advertisement delivery.

[0058] Furthermore, in this embodiment, new target behavioral characteristics can be continuously discovered. For example, this can be repeated every certain period of time, such as a week. Figure 1 Steps S102-S106 in the method flow yield new target behavioral characteristics. Step S108 is then repeated to determine the target audience based on the new target behavioral characteristics, thereby improving the accuracy of audience identification and advertising placement.

[0059] In this embodiment, during execution Figure 1 The server-side implementation of the methodological process also includes a visual dashboard. This dashboard allows users to view the ROI and ROAS corresponding to each target behavioral feature, enabling the automatic or manual timely removal of problematic behavioral features. The dashboard also allows for the manual addition or deletion of target behavioral features, as well as the adjustment of their behavioral parameters.

[0060] In summary, through the above embodiments, firstly, behavioral data of multiple users targeting a target object and the resource amount generated by the target object based on the user's behavioral data are acquired. The target object is pushed to the user's terminal device. Then, based on the resource amount corresponding to each user, the users are divided into a first category of users and a second category of users. The first resource amount generated by the target object based on the behavioral data of the first category of users is greater than the second resource amount generated based on the behavioral data of the second category of users. Next, based on the difference between the behavioral data of the first category of users and the behavioral data of the second category of users, at least one feature dimension of target behavioral features is determined. The first category of users has the target behavioral features. Finally, among the first category of users, a first target user with the target behavioral features is determined, and a first similar user of the first target user is determined. The target object is pushed to the terminal device of the first similar user. As can be seen, this embodiment can divide users into a first category and a second category based on the amount of resources each user has. Based on the differences between the behavioral data of the first category and the behavioral data of the second category, at least one target behavioral feature of a feature dimension can be determined. The target behavioral feature is the key behavioral feature. By classifying users and comparing features, the key behaviors of users can be accurately determined. Based on the key behaviors of users, the user group for targeted advertising can be accurately determined. Compared with the method of determining key behaviors manually in related technologies, this method effectively improves the accuracy of targeted advertising.

[0061] Figure 2This is a schematic diagram of the structure of a target object delivery device provided in an embodiment of the present disclosure, as shown below. Figure 2 As shown, the device includes: Data acquisition unit 21 is used to acquire behavioral data of multiple users targeting a target object and the amount of resources generated by the target object based on the behavioral data of the users; the target object is pushed to the user's terminal device; User classification unit 22 is used to classify each user into a first category user and a second category user according to the resource amount corresponding to each user; the first resource amount generated by the target object based on the behavior data of the first category user is greater than the second resource amount generated based on the behavior data of the second category user. Feature determination unit 23 is configured to determine at least one target behavioral feature based on the difference between the behavioral data of the first category of users and the behavioral data of the second category of users; the first category of users possesses the target behavioral feature; The object push unit 24 is configured to determine a first target user with the target behavioral characteristics among users of each of the first category, and to determine a first similar user of the first target user, and to push the target object to the terminal device of the first similar user.

[0062] Optionally, the user classification unit 22 is specifically used to: through a user classification model, divide each user into a first number of first category users and a second number of second category users according to the resource quantity corresponding to each user; the ratio of the first number to the second number is a first ratio; the resource quantity ratio of the first resource quantity to the second resource quantity is a second ratio; the first ratio is less than the second ratio.

[0063] Optionally, the feature determination unit 23 is specifically configured to: determine a first behavioral feature of a first feature dimension of the first category of users based on the behavioral data of the first category of users; the first feature dimension includes at least one of a single behavioral feature dimension, a combined behavioral feature dimension, and a user attribute feature dimension; determine a second behavioral feature of a second feature dimension of the second category of users based on the behavioral data of the second category of users; the second feature dimension includes at least one of a single behavioral feature dimension, a combined behavioral feature dimension, and a user attribute feature dimension; compare the first behavioral feature and the second behavioral feature to obtain a distinguishing behavioral feature of the first behavioral feature relative to the second behavioral feature, and determine the target behavioral feature based on the distinguishing behavioral feature; the distinguishing behavioral feature belongs to at least one dimension of a single behavioral feature dimension, a combined behavioral feature dimension, and a user attribute feature dimension.

[0064] Optionally, the feature determination unit 23 is further configured to: for each distinguishing behavioral feature, determine the contribution of the distinguishing behavioral feature based on the proportion of the number of key users with the distinguishing behavioral feature in each of the first category of users to the total number of users, and the average amount of resources generated by each key user with the distinguishing behavioral feature; determine candidate behavioral features among the distinguishing behavioral features based on the contribution of each distinguishing behavioral feature, and adjust the behavioral parameters of the candidate behavioral features to obtain the target behavioral feature.

[0065] Optionally, the feature determination unit 23 is further configured to: acquire historical resource quantities generated based on the target object; analyze the acquired historical resource quantities to obtain the correlation between the historical resource quantities and the behavioral parameters of the candidate behavioral features; and increase or decrease the behavioral parameters of the candidate behavioral features according to the correlation to obtain the target behavioral features.

[0066] Optionally, it further includes: a feature deletion unit, configured to: after pushing the target object to the terminal device of the first similar user, obtain the resource amount generated by the target object based on the target behavior feature, and obtain the resource amount deployed by the target object based on the target behavior feature; determine the problematic behavior feature to be deleted among the various target behavior features according to the generated resource amount and the deployed resource amount, and delete the problematic behavior feature among the various target behavior features; determine a second target user with the remaining target behavior feature after deletion among the various first category users, and determine a second similar user of the second target user, and push the target object to the terminal device of the second similar user.

[0067] In this embodiment, firstly, behavioral data of multiple users targeting a target object and the resource amount generated by the target object based on the user's behavioral data are acquired. The target object is pushed to the user's terminal device. Then, based on the resource amount corresponding to each user, the users are divided into a first category of users and a second category of users. The first resource amount generated by the target object based on the behavioral data of the first category of users is greater than the second resource amount generated based on the behavioral data of the second category of users. Next, based on the difference between the behavioral data of the first category of users and the behavioral data of the second category of users, at least one feature dimension of target behavioral features is determined. The first category of users has the target behavioral features. Finally, among the first category of users, a first target user with the target behavioral features is determined, and a first similar user of the first target user is determined. The target object is pushed to the terminal device of the first similar user. As can be seen, this embodiment can divide users into a first category and a second category based on the amount of resources each user has. Based on the differences between the behavioral data of the first category and the behavioral data of the second category, at least one target behavioral feature of a feature dimension can be determined. The target behavioral feature is the key behavioral feature. By classifying users and comparing features, the key behaviors of users can be accurately determined. Based on the key behaviors of users, the user group for targeted advertising can be accurately determined. Compared with the method of determining key behaviors manually in related technologies, this method effectively improves the accuracy of targeted advertising.

[0068] The target object delivery device in this embodiment can implement the various processes of the target object delivery method embodiment described above and achieve the same effect and function, which will not be repeated here.

[0069] One embodiment of this disclosure also provides an electronic device. Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure, as shown below. Figure 3 As shown, electronic devices can vary considerably due to differences in configuration or performance. They may include one or more processors 301 and memories 302, with the memory 302 storing one or more application programs or data. The memory 302 can be temporary or persistent storage. The application programs stored in the memory 302 may include one or more modules (not shown), each module including a series of computer-executable instructions from the electronic device. Furthermore, the processor 301 may be configured to communicate with the memory 302, executing the series of computer-executable instructions stored in the memory 302 on the electronic device. The electronic device may also include one or more power supplies 303, one or more wired or wireless network interfaces 304, one or more input or output interfaces 305, one or more keyboards 306, etc.

[0070] In one specific embodiment, the electronic device includes a processor; and a memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the following process: The system acquires behavioral data from multiple users targeting a target object and the resource quantity generated by the target object based on the users' behavioral data; the target object is then pushed to the user's terminal device. Based on the resource amount corresponding to each user, the users are divided into a first category of users and a second category of users; the first resource amount generated by the target object based on the behavioral data of the first category of users is greater than the second resource amount generated based on the behavioral data of the second category of users; Based on the differences between the behavioral data of the first category of users and the behavioral data of the second category of users, a target behavioral feature of at least one feature dimension is determined; the first category of users possesses the target behavioral feature. Among the users in each of the first category, a first target user with the target behavioral characteristics is identified, and a first similar user of the first target user is identified, and the target object is pushed to the terminal device of the first similar user.

[0071] In this embodiment, firstly, behavioral data of multiple users targeting a target object and the resource amount generated by the target object based on the user's behavioral data are acquired. The target object is pushed to the user's terminal device. Then, based on the resource amount corresponding to each user, the users are divided into a first category of users and a second category of users. The first resource amount generated by the target object based on the behavioral data of the first category of users is greater than the second resource amount generated based on the behavioral data of the second category of users. Next, based on the difference between the behavioral data of the first category of users and the behavioral data of the second category of users, at least one feature dimension of target behavioral features is determined. The first category of users has the target behavioral features. Finally, among the first category of users, a first target user with the target behavioral features is determined, and a first similar user of the first target user is determined. The target object is pushed to the terminal device of the first similar user. As can be seen, this embodiment can divide users into a first category and a second category based on the amount of resources each user has. Based on the differences between the behavioral data of the first category and the behavioral data of the second category, at least one target behavioral feature of a feature dimension can be determined. The target behavioral feature is the key behavioral feature. By classifying users and comparing features, the key behaviors of users can be accurately determined. Based on the key behaviors of users, the user group for targeted advertising can be accurately determined. Compared with the method of determining key behaviors manually in related technologies, this method effectively improves the accuracy of targeted advertising.

[0072] The electronic device in this embodiment can implement the various processes of the above-described target object delivery method embodiment and achieve the same effect and function, which will not be repeated here.

[0073] Another embodiment of this disclosure also provides a computer-readable storage medium for storing computer-executable instructions that, when executed by a processor, implement the following process: The system acquires behavioral data from multiple users targeting a target object and the resource quantity generated by the target object based on the users' behavioral data; the target object is then pushed to the user's terminal device. Based on the resource amount corresponding to each user, the users are divided into a first category of users and a second category of users; the first resource amount generated by the target object based on the behavioral data of the first category of users is greater than the second resource amount generated based on the behavioral data of the second category of users; Based on the differences between the behavioral data of the first category of users and the behavioral data of the second category of users, a target behavioral feature of at least one feature dimension is determined; the first category of users possesses the target behavioral feature. Among the users in each of the first category, a first target user with the target behavioral characteristics is identified, and a first similar user of the first target user is identified, and the target object is pushed to the terminal device of the first similar user.

[0074] The computer-readable storage medium in this disclosure embodiment can implement the various processes of the above-described target object delivery method embodiment and achieve the same effect and function, which will not be repeated here.

[0075] Another embodiment of this disclosure also provides a computer program product, the computer program product including a computer program, which, when executed by a processor, implements the following process: The system acquires behavioral data from multiple users targeting a target object and the resource quantity generated by the target object based on the users' behavioral data; the target object is then pushed to the user's terminal device. Based on the resource amount corresponding to each user, the users are divided into a first category of users and a second category of users; the first resource amount generated by the target object based on the behavioral data of the first category of users is greater than the second resource amount generated based on the behavioral data of the second category of users; Based on the differences between the behavioral data of the first category of users and the behavioral data of the second category of users, a target behavioral feature of at least one feature dimension is determined; the first category of users possesses the target behavioral feature. Among the users in each of the first category, a first target user with the target behavioral characteristics is identified, and a first similar user of the first target user is identified, and the target object is pushed to the terminal device of the first similar user.

[0076] The computer program product in this disclosure embodiment can implement the various processes of the above-described target object delivery method embodiment and achieve the same effect and function, which will not be repeated here.

[0077] In various embodiments of this disclosure, the computer-readable storage medium includes read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, etc.

[0078] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many methodological improvements today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that a methodological improvement cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program and "integrate" a digital system onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must also be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0079] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0080] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0081] For ease of description, the above apparatus is described by dividing it into various functional units. Of course, in implementing the embodiments of this disclosure, the functions of each unit can be implemented in one or more software and / or hardware.

[0082] Those skilled in the art will understand that one or more embodiments of this disclosure can be provided as a method, system, or computer program product. Therefore, one or more embodiments of this disclosure can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of this disclosure can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0083] This disclosure is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0084] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0085] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0086] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0087] One or more embodiments of this disclosure can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a particular task or implement a particular abstract data type. One or more embodiments of this disclosure can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can reside in local and remote computer storage media, including storage devices.

[0088] The various embodiments in this disclosure are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0089] The above description is merely an embodiment of this disclosure and is not intended to limit the scope of this disclosure. Various modifications and variations can be made to this disclosure by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the scope of the claims of this disclosure.

Claims

1. A method for targeting objects, characterized in that, include: Acquire behavioral data of multiple users targeting a target object and the amount of resources generated by the target object based on the users' behavioral data; The target object is pushed to the user's terminal device; Based on the amount of resources corresponding to each user, the users are divided into a first category of users and a second category of users; The first resource quantity generated by the target object based on the behavioral data of the first category of users is greater than the second resource quantity generated based on the behavioral data of the second category of users. Based on the differences between the behavioral data of the first category of users and the behavioral data of the second category of users, at least one target behavioral feature of a feature dimension is determined; The first category of users possesses the target behavioral characteristics; Among the users in each of the first category, a first target user with the target behavioral characteristics is identified, and a first similar user of the first target user is identified, and the target object is pushed to the terminal device of the first similar user.

2. The method according to claim 1, characterized in that, The step of dividing the users into a first category and a second category based on the amount of resources corresponding to each user includes: Using a user classification model, based on the amount of resources corresponding to each user, each user is divided into a first number of first category users and a second number of second category users; the ratio of the first number to the second number is a first ratio; the ratio of the first amount of resources to the second amount of resources is a second ratio; the first ratio is less than the second ratio.

3. The method according to claim 1, characterized in that, The step of determining a target behavioral feature of at least one feature dimension based on the difference between the behavioral data of the first category of users and the behavioral data of the second category of users includes: Based on the behavioral data of the first category of users, a first behavioral feature of a first feature dimension of the first category of users is determined; the first feature dimension includes at least one of a single behavioral feature dimension, a combined behavioral feature dimension, and a user attribute feature dimension. Based on the behavioral data of the second category of users, a second behavioral feature of the second feature dimension of the second category of users is determined; the second feature dimension includes at least one of a single behavioral feature dimension, a combined behavioral feature dimension, and a user attribute feature dimension. The first behavioral feature and the second behavioral feature are compared to obtain the distinguishing behavioral feature of the first behavioral feature relative to the second behavioral feature, and the target behavioral feature is determined based on the distinguishing behavioral feature; the distinguishing behavioral feature belongs to at least one of the single behavioral feature dimension, the combined behavioral feature dimension, and the user attribute feature dimension.

4. The method according to claim 3, characterized in that, Determining the target behavioral feature based on the distinguishing behavioral features includes: For each distinguishing behavioral feature, the contribution of the distinguishing behavioral feature is determined based on the proportion of the number of key users with the distinguishing behavioral feature in each of the first category of users to the total number of users, and the average amount of resources generated by each key user with the distinguishing behavioral feature. Based on the contribution of each distinguishing behavioral feature, candidate behavioral features are determined among the distinguishing behavioral features, and the behavioral parameters of the candidate behavioral features are adjusted to obtain the target behavioral feature.

5. The method according to claim 4, characterized in that, The step of adjusting the behavioral parameters of the candidate behavioral features to obtain the target behavioral features includes: Obtain the historical resource volume generated based on the target object; The acquired historical resource quantity is analyzed to obtain the correlation between the historical resource quantity and the behavioral parameters of the candidate behavioral features; Based on the correlation, the behavioral parameters of the candidate behavioral features are increased or decreased to obtain the target behavioral features.

6. The method according to claim 1, characterized in that, After pushing the target object to the terminal device of the first similar user, the method further includes: Obtain the amount of resources generated by the target object based on the target behavior characteristics, and obtain the amount of resources deployed by the target object based on the target behavior characteristics; Based on the generated resource quantity and the deployed resource quantity, identify the problematic behavior features to be deleted from each of the target behavior features, and delete the problematic behavior features from each of the target behavior features; Among each of the first category of users, a second target user with the remaining target behavior characteristics after deletion is identified, and a second similar user of the second target user is identified, and the target object is pushed to the terminal device of the second similar user.

7. A target object delivery device, characterized in that, include: The data acquisition unit is used to acquire behavioral data of multiple users targeting a target object and the amount of resources generated by the target object based on the behavioral data of the users. The target object is pushed to the user's terminal device; The user classification unit is used to classify each user into a first category user and a second category user based on the amount of resources corresponding to each user. The first resource quantity generated by the target object based on the behavioral data of the first category of users is greater than the second resource quantity generated based on the behavioral data of the second category of users. The feature determination unit is configured to determine at least one target behavioral feature based on the difference between the behavioral data of the first category of users and the behavioral data of the second category of users; The first category of users possesses the target behavioral characteristics; The object push unit is configured to determine a first target user with the target behavioral characteristics among users of the first category, and to determine a first similar user of the first target user, and to push the target object to the terminal device of the first similar user.

8. An electronic device, characterized in that, include: processor; as well as, A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the method described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store computer-executable instructions that, when executed by a processor, implement the method described in any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-6.

Images