An internet advertisement intelligent putting optimization method and system

Abstract

The application is suitable for the field of advertisement putting technology, and particularly relates to an internet advertisement intelligent putting optimization method and system.The method comprises the following steps: delimiting a target area for advertisement putting, opening wireless access permission, receiving an access request uploaded by a user in the target area, identifying a user ID, obtaining data access permission of an internet shopping platform corresponding to the target area based on an authorization result of the user ID, judging whether there is a friend relationship between all user IDs, defining the user IDs as a friend pair if yes, extracting preference tags of each user ID in the friend pair from the internet shopping platform, and defining an intersection part as a common preference.The application realizes the change of advertisement content from extensive fixed putting to group collaborative accurate putting through the mining of the friend relationship and common preference between users, improves the advertisement matching precision, enhances the guiding ability of instant consumption, and significantly improves the overall conversion efficiency of peer users.

Description

Technical Field

[0001] This invention relates to the field of advertising delivery technology, and in particular to an intelligent optimization method and system for internet advertising delivery. Background Technology

[0002] In existing offline commercial advertising scenarios, advertising content is usually pre-set by merchants and played periodically on a display screen. This method mainly targets the general population in the area, lacks the identification and analysis of the characteristics of the on-site crowd, and is difficult to reflect the potential related consumption needs among users in the same industry.

[0003] In real life, users typically enter shopping malls in groups, but existing fixed advertising mechanisms usually display generic content uniformly, making it difficult to provide targeted consumption guidance to groups of people. If advertisements for products in categories that are of common interest to those in the same group could be played, the advertising content would be closer to the group's immediate consumption intentions, increasing the probability of interaction and discussion among users in the same group, and improving guidance and conversion effects.

[0004] Therefore, "how to identify the common preferences of peer users based on user preference data in internet shopping platforms and deliver corresponding product advertisements" is the technical problem that this invention needs to solve. Summary of the Invention

[0005] The purpose of this invention is to provide an intelligent optimization method and system for internet advertising, in order to solve the problem raised in the background art of "how to identify the common preferences of peer users based on user preference data in internet shopping platforms and deliver corresponding product advertisements".

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A method for intelligent optimization of internet advertising delivery, the method comprising:

[0008] Define the target area for advertising, grant wireless access permissions, receive access requests uploaded by users within the target area, identify user IDs, obtain data access permissions for the internet shopping platform corresponding to the target area based on the authorization results of user IDs, and determine whether there are friend relationships between all user IDs. If so, define the user IDs as friend pairs.

[0009] From the aforementioned online shopping platform, the preference tags of each user ID in the friend pair are extracted, the intersection is defined as common preferences, stores selling products corresponding to common preferences in the target area are found, candidate stores are obtained, the corresponding products are defined as matching products, promotional advertisements for matching products are generated, and sent to the display devices of the candidate stores.

[0010] Using signal enhancement devices pre-installed in the target area, the signal strength of the friend pair is collected to estimate the approximate location of the friend pair. When the approximate location coincides with the candidate store, the product activity data of the candidate store is obtained, promotional information is generated, and it is sent to all user terminals of the friend pair in parallel.

[0011] Extract multi-source data from friends that has been pre-uploaded to an online shopping platform. The multi-source data includes at least group-buying data for dining and entertainment. Traverse the common items, record the initiation time of the access request, generate an itinerary recommendation table, and distribute it to all user terminals.

[0012] Furthermore, the steps of defining the target area for advertising, granting wireless access permissions, receiving access requests uploaded by users within the target area, identifying user IDs, and authorizing results based on user IDs include:

[0013] In response to the access request, a communication link is established between the user and the target area, and the user is redirected to the login interface;

[0014] Based on the account information entered by the user on the login screen, the user ID is identified, and an authorization request selection window is sent to the user's terminal.

[0015] Furthermore, the step of extracting preference tags from each user ID in the friend pair from the internet shopping platform and defining the intersection as common preferences includes:

[0016] Collect user behavior data on online shopping platforms, wherein the behavior data includes at least: browsing and liking, generate preference tags, and each user corresponds to several preference tags;

[0017] Determine if there are any common preferences among the user IDs within a friend group. If so, define the preference tags corresponding to the common preferences as shared interests.

[0018] Furthermore, the steps of obtaining candidate stores, defining the corresponding products as matching products, generating promotional advertisements for the matching products, and sending them to the display devices of the candidate stores include:

[0019] Create a fluctuation range. When the signal strength is within the fluctuation range, sort the promotional advertisements in descending order of signal strength to generate a queue to be played.

[0020] The queue to be played is updated according to a preset frequency.

[0021] Furthermore, the steps of obtaining product activity data from candidate stores, generating promotional information, and distributing it in parallel to all user terminals of the friend pair include:

[0022] Integrate all promotional information, generate a promotional list, and publish it to the aforementioned online shopping platform;

[0023] Receive user feedback messages regarding promotional information, generate an order link, and send it to the user's terminal.

[0024] Furthermore, the steps of recording the initiation time of the access request, generating a trip recommendation table, and distributing it to all user terminals include:

[0025] The itinerary recommendation table is divided into several individual items, and influencing factors are set, wherein the influencing factors include at least: queuing time and distance;

[0026] Based on the aforementioned influencing factors, the order of individual items in the itinerary recommendation table is updated according to a preset time step.

[0027] Furthermore, the system includes:

[0028] The judgment module is used to define the target area for advertising, grant wireless access permissions, receive access requests uploaded by users in the target area, identify user IDs, obtain data access permissions for the internet shopping platform corresponding to the target area based on the authorization results of user IDs, and determine whether there is a friend relationship between all user IDs. If so, the user IDs are defined as a friend pair.

[0029] The sending module is used to extract the preference tags of each user ID in the friend pair from the Internet shopping platform, define the intersection as common preferences, find stores in the target area that sell products corresponding to common preferences, obtain candidate stores, define the corresponding products as matching products, generate promotional advertisements for matching products, and send them to the display devices of the candidate stores.

[0030] The delivery module is used to collect the signal strength of the friend pair using signal enhancement equipment pre-installed in the target area, estimate the approximate location of the friend pair, and when the approximate location coincides with the candidate store, obtain the product activity data of the candidate store, generate promotional information, and send it to all user terminals of the friend pair in parallel.

[0031] The extraction module is used to extract multi-source data of friends that have been pre-uploaded to an online shopping platform. The multi-source data includes at least: group-buying data for catering and entertainment. It iterates through common items, records the initiation time of access requests, generates a trip recommendation table, and distributes it to all user terminals.

[0032] Furthermore, the determination module includes:

[0033] The response unit is used to respond to the access request, establish a communication link between the user and the target area, and redirect to the login interface;

[0034] The identification unit is used to identify the user ID based on the account information entered by the user in the login interface and send an authorization request to the user terminal via a selection window.

[0035] Furthermore, the sending module includes:

[0036] The data collection unit is used to collect user behavior data on the online shopping platform, wherein the behavior data includes at least: browsing and liking, generating preference tags, and each user corresponds to several preference tags;

[0037] Define a unit to determine whether there are any common parts in the preference tags of each user ID within a friend group. If so, define the preference tags corresponding to the common parts as common preferences.

[0038] The sorting unit is used to create a fluctuation range. When the signal strength is within the fluctuation range, the promotional advertisements are sorted in descending order of signal strength to generate a queue to be played.

[0039] The update unit is used to update the queue to be played according to a preset frequency.

[0040] Furthermore, the distribution module includes:

[0041] The publishing unit is used to integrate all promotional information, generate a promotional list, and publish it to the internet shopping platform.

[0042] The feedback unit is used to receive user feedback messages about promotional information, generate an order link, and send it to the user's terminal.

[0043] Compared with the prior art, the beneficial effects of the present invention are:

[0044] By identifying user IDs and combining them with friend relationships to form peer user groups, the target audience for advertising can be expanded from individual users to groups of users with social connections. This accurately identifies the common preferences of peers, improving ad matching accuracy. By playing promotional ads for matched products, the ability to guide peers towards immediate consumption is enhanced, attracting their attention and amplifying the peer decision-making effect. Parallel distribution of promotional information for products with shared preferences to peers facilitates the creation of topics of conversation among them, ensuring that peer users receive consistent information at similar decision-making points. This also makes it easier to trigger group discussions and collaborative decision-making, enhancing the stimulus effect of immediate consumption and further improving conversion efficiency. By mining the friend relationships and common preferences among users, the advertising content has shifted from broad, fixed targeting to precise, collaborative targeting across groups. While improving ad matching accuracy, this also enhances the ability to guide immediate consumption and significantly improves the overall conversion efficiency of peer users. Attached Figure Description

[0045] Figure 1 A flowchart illustrating the intelligent internet advertising delivery optimization method provided in this embodiment of the invention;

[0046] Figure 2 This is a first sub-flowchart of the intelligent internet advertising delivery optimization method provided in an embodiment of the present invention;

[0047] Figure 3 This is a second sub-flow flowchart of the intelligent internet advertising delivery optimization method provided in this embodiment of the invention;

[0048] Figure 4 This is a third sub-process flowchart of the intelligent internet advertising delivery optimization method provided in this embodiment of the invention;

[0049] Figure 5 This is a fourth sub-flow flowchart of the intelligent internet advertising delivery optimization method provided in this embodiment of the invention;

[0050] Figure 6 A block diagram illustrating the components of the intelligent internet advertising delivery optimization system provided in this embodiment of the invention;

[0051] Figure 7 A block diagram showing the composition of the judgment module in the intelligent internet advertising delivery optimization system provided in this embodiment of the invention;

[0052] Figure 8 A block diagram of the sending module in the intelligent internet advertising delivery optimization system provided in this embodiment of the invention;

[0053] Figure 9 A block diagram of the distribution module in the intelligent internet advertising delivery optimization system provided in this embodiment of the invention;

[0054] Figure 10 The diagram shows the composition of the extraction module in the Internet advertising intelligent delivery optimization system provided in this embodiment of the invention. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0056] In Example 1, Figure 1 The implementation flow of the intelligent internet advertising delivery optimization method provided in this embodiment of the invention is illustrated below, and is described in detail below:

[0057] S100: Define the target area for advertising, grant wireless access permissions, receive access requests uploaded by users within the target area, identify user IDs, obtain data access permissions for the internet shopping platform corresponding to the target area based on the authorization results of user IDs, determine whether there are friend relationships between all user IDs, and if so, define the user IDs as friend pairs.

[0058] The area to be advertised, i.e., the target area, is defined. The target area can be a shopping mall, transportation hub, tourist attraction, or large community commercial center, etc. In this embodiment, a shopping mall is used as an example. Wireless access nodes (i.e., Wi-Fi access points) are deployed in the target area, and access permissions are granted to these nodes. In other words, users in the target area can connect to the wireless access nodes after logging in. When a user terminal enters the shopping mall and detects the corresponding wireless access signal, the wireless access node responds to the access request and establishes a communication link. Pre-established identity recognition rules are used to parse the terminal identification information to obtain the user's user ID on the online shopping platform. For example, a user's mobile phone number input window is set up in the Wi-Fi access interface to receive the user's entered mobile phone number, which is also the user ID.

[0059] After determining the user ID corresponding to the access request, a request to read personal data from the online shopping platform is sent to the user's terminal. Upon user authorization, data access permissions are granted, including access to data items such as friend relationships, historical shopping records, and user preference tags. The system retrieves the friend relationships of all users to determine if any friends exist between users entering the mall on the online shopping platform. If friends exist, the corresponding user IDs are grouped into friend pairs. The online shopping platform is a mall management platform that integrates a social interaction module.

[0060] For example, if several users enter a shopping mall and connect to a Wi-Fi access node, the system can search their friend lists on an online shopping platform using the phone numbers they enter on the Wi-Fi access interface to determine if there are any friendships between the users.

[0061] S200: Extract the preference tags of each user ID in the friend pair from the internet shopping platform, define the intersection as common preferences, find stores in the target area that sell products corresponding to common preferences, obtain candidate stores, define the corresponding products as matching products, generate promotional advertisements for matching products, and send them to the display devices of the candidate stores.

[0062] The system acquires behavioral data for each user ID in a friend pair across online shopping platforms. This data includes browsing history, click history, favorites history, add-to-cart history, and transaction history. Through weighted analysis, rule mapping, or model analysis, the system determines user preference tags. Preference tags refer to a user's interest in different products; for example, a user ID might have preference tags for camping products or home appliances. The system also identifies the overlap in preference tags among all friends in the friend pair, representing shared shopping preferences among multiple friends.

[0063] Within the target area, stores selling products corresponding to shared preferences are identified and defined as candidate stores. The products corresponding to shared preferences within these candidate stores are the matching products. Advertisements corresponding to the matching products are selected from the ad library; these are then promoted and distributed to the display devices within the candidate stores. These display devices can be screens or other display equipment within the candidate stores. In this embodiment, when multiple friend pairs exist within the mall, multiple promotional advertisements are generated. Each promotional advertisement is set with a corresponding display duration and is then rotated. The advantage of this method is that it can attract users corresponding to friend pairs to the candidate stores through remote display, thereby attracting user attention and increasing the probability of them entering the store.

[0064] S300: Using signal enhancement equipment pre-installed in the target area, collect the signal strength of the friend pair, estimate the approximate location of the friend pair, and when the approximate location coincides with the candidate store, obtain the product activity data of the candidate store, generate promotional information, and send it to all user terminals of the friend pair in parallel.

[0065] By utilizing signal enhancement devices (such as Wi-Fi probes or Wi-Fi signal boosters) installed in the target area, the wireless signals emitted or received by surrounding user terminals are continuously collected and analyzed to determine signal strength. Combining the spatial distribution of different signal enhancement devices, the approximate location of each user in the friend pair is estimated through multi-point signal strength difference comparison or signal attenuation models. When the approximate location overlaps with or falls within the preset coverage radius of candidate stores in the target area, it indicates that the user in the friend pair is near a candidate store. Product activity data and matching product activity data of candidate stores are retrieved from public data or online shopping platforms, and key semantic features (such as specific discounts) are extracted. The product activity data is then structured to generate promotional information. This promotional information displays the store's currently available promotional activities and is distributed in parallel to all user terminals in the friend pair using the user ID. The advantage of this approach is that when users in a friend group receive promotional information, they may simultaneously open their phones to check it, which significantly increases the probability of information being exposed synchronously and forming a shared understanding, greatly increasing the likelihood of discussion. Users may discuss based on their shared interests, making it easier to establish topics and further increase the store visit rate.

[0066] S400: Extract multi-source data of friends that have been pre-uploaded to the Internet shopping platform, wherein the multi-source data includes at least: catering and entertainment group purchase data, traverse out common items, record the initiation time of access request, generate a trip recommendation table, and send it to all user terminals.

[0067] This process extracts multi-source data from friend pairs pre-uploaded to online shopping platforms. This data originates from other internet platforms, such as group-buying and food delivery platforms. Common elements within the multi-source data of the friend pairs are identified. These common elements refer to similar categories of food and group-buying data, such as braised chicken rice and escape room games. The initiation time of the access request is recorded, which can be considered the time when the user corresponding to the friend pair enters the target area. Potential activity paths of users in dining, entertainment, candidate shops, and other lifestyle service scenarios are integrated to generate a trip recommendation table. This table includes recommended consumption locations, dining locations, and corresponding time arrangements. The trip recommendation table is then distributed to the user terminals of all users in the friend pair. The advantage of this method is that by comparing and cross-matching the dining and entertainment group-buying behaviors of all users in the same friend pair, overlapping characteristics in consumption categories and preferences can be obtained. This allows for accurate characterization of friends' shared consumption tendencies in offline lifestyle service consumption, providing data support for guiding shared consumption.

[0068] In Example 2, Figure 2The first sub-flowchart of the intelligent internet advertising delivery optimization method provided in this embodiment of the invention is shown. The following details the steps of defining the target area for advertising delivery, granting wireless access permissions, receiving access requests uploaded by users within the target area, identifying user IDs, and authorizing based on user IDs:

[0069] S101: In response to the access request, establish a communication link between the user and the target area, and redirect to the login interface.

[0070] Establish a communication link between the access gateway and the user terminal, and after the link is established, guide the user terminal to the platform login interface.

[0071] S102: Based on the account information entered by the user in the login interface, identify the user ID and send an authorization request selection window to the user terminal.

[0072] On the login screen, users authenticate their identity by entering preset account information (mobile phone number and login password). After successful authentication, the mobile phone number is defined as the user ID, and an authorization request selection window is sent to the user's terminal. This window prompts the user to confirm and authorize data access permissions on the online shopping platform. The user can agree to or refuse authorization in this window.

[0073] In Example 3, Figure 3 The diagram shows the second sub-process flowchart of the intelligent internet advertising delivery optimization method provided in this embodiment of the invention. The following details the step of extracting the preference tags of each user ID in a friend pair from the internet shopping platform and defining the intersection as common preferences:

[0074] S201: Collect user behavior data on the online shopping platform, wherein the behavior data includes at least: browsing and liking, generating preference tags, with each user corresponding to several preference tags.

[0075] Collect user behavior data, including page browsing history, product dwell time, and likes on products or content. Generate preference tags through weighting, rule mapping, or model analysis. These preference tags are product category preference tags, and each user has several preference tags.

[0076] S202: Determine whether there are any common parts in the preference tags of each user ID within the friend group. If so, define the preference tags corresponding to the common parts as common preferences.

[0077] The preference tags for each user are standardized. Through semantic analysis, the common parts of the preference tags are identified, and the preference tags corresponding to the common parts are defined as common preferences.

[0078] In Example 4, Figure 3 The diagram shows the second sub-process flowchart of the intelligent internet advertising delivery optimization method provided in this embodiment of the invention. The steps of obtaining candidate stores, defining the corresponding products as matching products, generating promotional advertisements for the matching products, and sending them to the display devices of the candidate stores are described in detail below:

[0079] S203: Create a fluctuation range. When the signal strength is within the fluctuation range, sort the promotional advertisements in descending order of signal strength to generate a queue to be played.

[0080] Based on signal strength, combined with historical signal strength statistics and network environment conditions during the same period, a fluctuation range is created. When the signal strength corresponding to a user terminal falls within this fluctuation range, it indicates that the user is near the signal enhancement device. The specific fluctuation range is determined by the administrators within the target area. A friend pair corresponds to multiple signal strengths, with the highest signal strength defined as the signal strength of that friend pair. Each friend pair also corresponds to one or more promotional advertisements; in other words, each promotional advertisement corresponds to a signal strength. The promotional advertisements are sorted according to their signal strength from highest to lowest, generating a queue for playback. Based on this queue, the advertisements are then played through the display device.

[0081] S204: Update the queue to be played according to the preset frequency.

[0082] Update the queue to be played according to a preset frequency, where the preset frequency can be once per minute.

[0083] In Example 5, Figure 4 The diagram shows the third sub-process flowchart of the intelligent internet advertising delivery optimization method provided in this embodiment of the invention. The following details the steps of obtaining product activity data of candidate stores, generating promotional information, and sending it in parallel to all user terminals of the friend pair:

[0084] S301: Integrate all promotional information, generate a promotional list, and publish it to the aforementioned online shopping platform.

[0085] The promotional information is integrated in chronological order to generate a promotional list, which is then published on online shopping platforms.

[0086] S302: Receive user feedback messages about promotional information, generate an order link, and send it to the user's terminal.

[0087] The system receives user feedback regarding promotional information, which may include suggestions such as reducing or increasing the frequency of recommendations. It performs semantic recognition on the feedback messages, and if the feedback messages contain a clear purchase intention, it generates an order link and sends it to the user's terminal.

[0088] In Example 6, Figure 5 The fourth sub-process flowchart of the intelligent internet advertising delivery optimization method provided in this embodiment of the invention is shown. The steps of recording the initiation time of the access request, generating the itinerary recommendation table, and sending it to all user terminals are described in detail below:

[0089] S401: Divide the trip recommendation table into several individual items and set influencing factors, wherein the influencing factors include at least: queuing time and distance.

[0090] The itinerary recommendation table is divided into multiple items, such as a restaurant or a bubble tea shop. Factors that may influence the ranking of these items are defined, including queue length and distance.

[0091] S402: Based on the aforementioned influencing factors, update the order of individual items in the itinerary recommendation table according to a preset time step.

[0092] According to a preset time step (e.g., 3 minutes), the queuing time and distance corresponding to each item are updated every 3 minutes. A corresponding weight value is set for each influencing factor. Based on the sum of the weight values ​​of the influencing factors corresponding to each item, the order of items in the itinerary recommendation table is adjusted.

[0093] Figure 6 This diagram illustrates the structural block diagram of the intelligent internet advertising delivery optimization system provided in an embodiment of the present invention. The intelligent internet advertising delivery optimization system 1 includes:

[0094] The judgment module 11 is used to delineate the target area for advertising, grant wireless access permissions, receive access requests uploaded by users in the target area, identify user IDs, obtain data access permissions for the internet shopping platform corresponding to the target area based on the authorization results of user IDs, and determine whether there is a friend relationship between all user IDs. If so, the user IDs are defined as a friend pair.

[0095] The sending module 12 is used to extract the preference tags of each user ID in the friend pair from the Internet shopping platform, define the intersection as common preferences, find stores in the target area that sell products corresponding to common preferences, obtain candidate stores, define the corresponding products as matching products, generate promotional advertisements for matching products, and send them to the display devices of the candidate stores.

[0096] The distribution module 13 is used to collect the signal strength of the friend pair using a signal enhancement device pre-installed in the target area, estimate the approximate location of the friend pair, and when the approximate location coincides with the candidate store, obtain the product activity data of the candidate store, generate promotional information, and distribute it in parallel to all user terminals of the friend pair.

[0097] The extraction module 14 is used to extract multi-source data of friends that have been pre-uploaded to the Internet shopping platform. The multi-source data includes at least: group purchase data for catering and entertainment. It traverses out common items, records the initiation time of access requests, generates a trip recommendation table, and sends it to all user terminals.

[0098] Figure 7 This diagram illustrates the composition of the judgment module 11 in the intelligent internet advertising delivery optimization system provided in an embodiment of the present invention. The judgment module 11 includes:

[0099] The response unit 111 is used to respond to the access request, establish a communication link between the user and the target area, and redirect to the login interface;

[0100] The identification unit 112 is used to identify the user ID based on the account information entered by the user in the login interface and send an authorization request selection window to the user terminal.

[0101] Figure 8 This diagram illustrates the structural composition of the sending module 12 in the intelligent internet advertising delivery optimization system provided by an embodiment of the present invention. The sending module 12 includes:

[0102] The collection unit 121 is used to collect user behavior data on the Internet shopping platform, wherein the behavior data includes at least: browsing and liking, generating preference tags, and each user corresponds to several preference tags;

[0103] Definition unit 122 is used to determine whether there are any common parts in the preference tags of each user ID within a friend group. If so, the preference tags corresponding to the common parts are defined as common preferences.

[0104] The sorting unit 123 is used to create a fluctuation range. When the signal strength is within the fluctuation range, the promotional advertisements are sorted in descending order of signal strength to generate a queue to be played.

[0105] The update unit 124 is used to update the queue to be played according to a preset frequency.

[0106] Figure 9 This diagram illustrates the structural composition of the distribution module 13 in the intelligent internet advertising delivery optimization system provided in this embodiment of the invention. The distribution module 13 includes:

[0107] The publishing unit 131 is used to integrate all promotional information, generate a promotional list, and publish it to the internet shopping platform;

[0108] Feedback unit 132 is used to receive user feedback messages about promotional information, generate an order link, and send it to the user terminal.

[0109] Figure 10 This diagram illustrates the structural composition of the extraction module 14 in the intelligent internet advertising delivery optimization system provided in this embodiment of the invention. The extraction module 14 includes:

[0110] The segmentation unit 141 is used to segment the trip recommendation table into several individual items and set influencing factors, wherein the influencing factors include at least: queuing time and distance;

[0111] Arrangement unit 142 is used to update the arrangement order of individual items in the itinerary recommendation table according to a preset time step based on the influencing factors.

[0112] The judgment module 11 is mainly used to complete step S100, the sending module 12 is mainly used to complete step S200, the sending module 13 is mainly used to complete step S300, and the extraction module 14 is mainly used to complete step S400.

[0113] The response unit 111 is mainly used to complete step S101, and the identification unit 112 is mainly used to complete step S102.

[0114] The acquisition unit 121 is mainly used to complete step S201, the definition unit 122 is mainly used to complete step S202, the sorting unit 123 is mainly used to complete step S203, and the update unit 124 is mainly used to complete step S204.

[0115] The publishing unit 131 is mainly used to complete step S301, and the feedback unit 132 is mainly used to complete step S302.

[0116] The segmentation unit 141 is mainly used to complete step S401, and the arrangement unit 142 is mainly used to complete step S402.

[0117] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0118] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0119] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for intelligent optimization of internet advertising delivery, characterized in that, The method includes: Define the target area for advertising, grant wireless access permissions, receive access requests uploaded by users within the target area, identify user IDs, obtain data access permissions for the internet shopping platform corresponding to the target area based on the authorization results of user IDs, and determine whether there are friend relationships between all user IDs. If so, define the user IDs as friend pairs. From the aforementioned online shopping platform, the preference tags of each user ID in the friend pair are extracted, the intersection is defined as common preferences, stores selling products corresponding to common preferences in the target area are found, candidate stores are obtained, the corresponding products are defined as matching products, promotional advertisements for matching products are generated, and sent to the display devices of the candidate stores. Using signal enhancement devices pre-installed in the target area, the signal strength of the friend pair is collected to estimate the approximate location of the friend pair. When the approximate location coincides with the candidate store, the product activity data of the candidate store is obtained, promotional information is generated, and it is sent to all user terminals of the friend pair in parallel. Extract multi-source data from friends that has been pre-uploaded to an online shopping platform. The multi-source data includes at least group-buying data for dining and entertainment. Traverse the common items, record the initiation time of the access request, generate an itinerary recommendation table, and distribute it to all user terminals.

2. The intelligent internet advertising delivery optimization method according to claim 1, characterized in that, The steps of defining the target area for advertising, granting wireless access permissions, receiving access requests uploaded by users within the target area, identifying user IDs, and authorizing based on user IDs include: In response to the access request, a communication link is established between the user and the target area, and the user is redirected to the login interface; Based on the account information entered by the user on the login screen, the user ID is identified, and an authorization request selection window is sent to the user's terminal.

3. The intelligent internet advertising delivery optimization method according to claim 2, characterized in that, The step of extracting preference tags from each user ID in the friend pair from the internet shopping platform and defining the intersection as common preferences includes: Collect user behavior data on online shopping platforms, wherein the behavior data includes at least: browsing and liking, generate preference tags, and each user corresponds to several preference tags; Determine if there are any common preferences among the user IDs within a friend group. If so, define the preference tags corresponding to the common preferences as shared interests.

4. The intelligent internet advertising delivery optimization method according to claim 1, characterized in that, The steps of obtaining candidate stores, defining the corresponding products as matching products, generating promotional advertisements for the matching products, and sending them to the display devices of the candidate stores include: Create a fluctuation range. When the signal strength is within the fluctuation range, sort the promotional advertisements in descending order of signal strength to generate a queue to be played. The queue to be played is updated according to a preset frequency.

5. The intelligent internet advertising delivery optimization method according to claim 3, characterized in that, The steps of obtaining product activity data of candidate stores, generating promotional information, and distributing it in parallel to all user terminals of the friend pair include: Integrate all promotional information, generate a promotional list, and publish it to the aforementioned online shopping platform; Receive user feedback messages regarding promotional information, generate an order link, and send it to the user's terminal.

6. The intelligent internet advertising delivery optimization method according to claim 1, characterized in that, The steps of recording the initiation time of the access request, generating a trip recommendation table, and distributing it to all user terminals include: The itinerary recommendation table is divided into several individual items, and influencing factors are set, wherein the influencing factors include at least: queuing time and distance; Based on the aforementioned influencing factors, the order of individual items in the itinerary recommendation table is updated according to a preset time step.

7. An intelligent internet advertising delivery optimization system, characterized in that, The system includes: The judgment module is used to define the target area for advertising, grant wireless access permissions, receive access requests uploaded by users in the target area, identify user IDs, obtain data access permissions for the internet shopping platform corresponding to the target area based on the authorization results of user IDs, and determine whether there is a friend relationship between all user IDs. If so, the user IDs are defined as a friend pair. The sending module is used to extract the preference tags of each user ID in the friend pair from the Internet shopping platform, define the intersection as common preferences, find stores in the target area that sell products corresponding to common preferences, obtain candidate stores, define the corresponding products as matching products, generate promotional advertisements for matching products, and send them to the display devices of the candidate stores. The delivery module is used to collect the signal strength of the friend pair using signal enhancement equipment pre-installed in the target area, estimate the approximate location of the friend pair, and when the approximate location coincides with the candidate store, obtain the product activity data of the candidate store, generate promotional information, and send it to all user terminals of the friend pair in parallel. The extraction module is used to extract multi-source data of friends that have been pre-uploaded to an online shopping platform. The multi-source data includes at least: group-buying data for catering and entertainment. It iterates through common items, records the initiation time of access requests, generates a trip recommendation table, and distributes it to all user terminals.

8. The intelligent internet advertising delivery optimization system according to claim 7, characterized in that, The judgment module includes: The response unit is used to respond to the access request, establish a communication link between the user and the target area, and redirect to the login interface; The identification unit is used to identify the user ID based on the account information entered by the user in the login interface and send an authorization request to the user terminal via a selection window.

9. The intelligent internet advertising delivery optimization system according to claim 8, characterized in that, The sending module includes: The data collection unit is used to collect user behavior data on the online shopping platform, wherein the behavior data includes at least: browsing and liking, generating preference tags, and each user corresponds to several preference tags; Define a unit to determine whether there are any common parts in the preference tags of each user ID within a friend group. If so, define the preference tags corresponding to the common parts as common preferences. The sorting unit is used to create a fluctuation range. When the signal strength is within the fluctuation range, the promotional advertisements are sorted in descending order of signal strength to generate a queue to be played. The update unit is used to update the queue to be played according to a preset frequency.

10. The intelligent internet advertising delivery optimization system according to claim 9, characterized in that, The distribution module includes: The publishing unit is used to integrate all promotional information, generate a promotional list, and publish it to the internet shopping platform. The feedback unit is used to receive user feedback messages about promotional information, generate an order link, and send it to the user's terminal.

Images