Media advertising position recommendation method, system, medium, and product based on user travel

Abstract

The present application provides a method and system for recommending media advertising slots based on user travel, a computer-readable storage medium, and a computer program product, which implement click expectation estimation of the proposed products in the media advertising slots based on the user travel portrait in the travel scenario, and then objectively and accurately implement media advertising slot marketing recommendations based on the click expectation value of the proposed products in the media advertising slots, thereby abandoning the reliance of media resource marketing recommendations on subjective experience and effectively improving the accuracy of delivery.

Description

Technical Field

[0001] The present application relates to the field of computer application technology, and in particular to a method and system for recommending media advertising positions based on user travel, a computer-readable storage medium, and a computer program product. Background Art

[0002] There are numerous media resources, such as media advertising space, in public scenarios such as travel. The placement of relevant commodity media content through media resources is called commodity placement on media resources.

[0003] Advertisers often classify media advertising spaces distributed on sites based on their own subjective experience, investigate the site's population portrait, and use this as a basis to make marketing recommendations for media resources, thereby achieving the goal of placing products on media resources.

[0004] However, whether it is the classification of media advertising positions or the research on site population portraits, on the one hand, they rely on subjective experience and are limited by the instability of subjective experience and have poor quality. On the other hand, they also have the defects of huge workload and low timeliness.

[0005] To this end, it is necessary to abandon media resource marketing recommendations that rely on subjective experience and build a media advertising space recommendation process that is objective and improves delivery accuracy. Summary of the invention

[0006] One purpose of this application is to abandon the media resource marketing recommendation that relies on subjective experience, and to build a media advertising space recommendation process that is objective and improves the accuracy of delivery.

[0007] According to one aspect of an embodiment of the present application, a method for recommending media advertising positions based on user travel is disclosed, the method comprising:

[0008] Acquire all users corresponding to the media advertising position, whose travel trajectories cover the media advertising position;

[0009] estimating the click expectations of the product to be placed in the media advertising position for all users, and obtaining the click expectation value of the product to be placed in the media advertising position;

[0010] According to the expected click value of the product to be placed on the media advertisement position, a media advertisement position is recommended for the product to be placed.

[0011] According to one aspect of an embodiment of the present application, acquiring all users corresponding to the media advertising position includes:

[0012] Determine the user's exit trajectory based on the distribution of the number of times the user exits each gate at the station gate group;

[0013] The users are aggregated for the media advertising slots covered by the outbound track to obtain all users corresponding to the media advertising slots, and the aggregated users all correspond to the outbound track covering the media advertising slots.

[0014] According to one aspect of an embodiment of the present application, estimating the click expectations of the product to be placed in the media advertising position for all users and obtaining the click expectation value of the product to be placed in the media advertising position includes:

[0015] For the product to be placed, estimating the click rate of each user on the product to be placed among all users corresponding to the media advertising position;

[0016] The click rates are accumulated to obtain the expected click value of the product to be placed on the media advertising position.

[0017] According to one aspect of the embodiment of the present application, the estimating the click rate of each user for the product to be placed among all users corresponding to the media advertising position includes:

[0018] For each user corresponding to the media advertising position, a user-product pair is constructed through the user portrait and the product features corresponding to the product to be placed;

[0019] By predicting the product click-through rate of the user-product pair, the click-through rate of the product to be placed by each user among all users corresponding to the media advertising position is obtained.

[0020] According to one aspect of an embodiment of the present application, the user portrait corresponds to the user's own travel data, and a combination of the user's own travel data and third-party supplementary data.

[0021] According to one aspect of an embodiment of the present application, the step of recommending a media advertising position for the product to be placed according to the expected click value of the product to be placed on the media advertising position includes:

[0022] The expected click values ​​of the product to be placed on each media advertising position are compared, and the media advertising position with the highest expected click value is recommended to the product to be placed.

[0023] According to one aspect of an embodiment of the present application, the step of recommending a media advertising position for the product to be placed according to the expected click value of the product to be placed on the media advertising position includes:

[0024] Obtaining the click value of the product to be placed;

[0025] The conversion value of the product to be placed on the media advertising position is obtained by calculating the click value and the expected click value of the product to be placed on the media advertising position;

[0026] The media advertising position is recommended to the planned product corresponding to the highest conversion value.

[0027] According to one aspect of an embodiment of the present application, a media advertising spot recommendation system based on user travel is disclosed, the system comprising a memory, a processor, and a computer program stored in the memory, the processor executing the computer program to implement the steps of the method described above.

[0028] According to one aspect of an embodiment of the present application, a computer-readable storage medium is disclosed, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described above are implemented.

[0029] According to one aspect of an embodiment of the present application, a computer program product is disclosed, including a computer program, wherein the computer program is executed by a processor to implement the steps of the method described above.

[0030] The embodiments of the present application first obtain all the corresponding users of a given media advertising position, such as an idle media advertising position, whose travel trajectories cover the given media advertising position, and then estimate the expected click value of the product to be placed on the given media advertising position for all users. Finally, based on the expected click value of the product to be placed on the media advertising position, the media advertising position is recommended for the product to be placed. In this way, media advertising position recommendations can be implemented based on objective data, such as all users corresponding to the media advertising position and the estimated expected click value, thereby eliminating the reliance of media resource marketing recommendations on subjective experience and effectively improving the accuracy of placement.

[0031] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.

[0032] It should be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The above and other objects, features and advantages of the present application will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.

[0034] Figure 1 A flow chart of a method for recommending media advertising slots based on user travel according to an embodiment of the present application is shown.

[0035] Figure 2 is based on Figure 1 A flowchart of a method for describing the steps of obtaining all corresponding users for a media advertising position is shown in a corresponding embodiment.

[0036] Figure 3 is based on Figure 2 The corresponding embodiment shows a flow chart of the method for determining the user's exit trajectory based on the distribution of the number of times the user exits the station at the station gate group.

[0037] Figure 4 is based on Figure 1 The corresponding embodiment shows a method flow chart describing the steps of estimating the expected click values ​​of the products to be placed in the media advertising slots for all users and obtaining the expected click values ​​of the products to be placed in the media advertising slots.

[0038] Figure 5 is based on Figure 4 A flowchart of a method for estimating the click rate of a product to be placed by each user among all users corresponding to a media advertising position, shown in a corresponding embodiment.

[0039] Figure 6 It is a method flow chart describing the steps of recommending media advertising positions for products to be placed according to the expected click value of the products to be placed on the media advertising positions according to an embodiment of the present application.

[0040] Figure 7 The figure is a schematic diagram of a data link for media advertisement slot marketing recommendation according to an exemplary embodiment. DETAILED DESCRIPTION

[0041] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present application will be more comprehensive and complete and the concepts of the example embodiments will be fully conveyed to those skilled in the art. The accompanying drawings are only schematic illustrations of the present application and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted.

[0042] In addition, the described features, structures or characteristics may be combined in one or more example embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the example embodiments of the present application. However, those skilled in the art will appreciate that the technical solution of the present application may be practiced while omitting one or more of the specific details, or other methods, components, steps, etc. may be adopted. In other cases, known structures, methods, implementations or operations are not shown or described in detail to avoid obscuring the present application and making the various aspects of the present application obscure.

[0043] Some of the blocks shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0044] There are many travel routes in a city, and there are many stations on each travel route. There are many media advertising spaces inside and outside each station, and they are adapted to different locations and have different media types, such as temporary exhibitions, light boxes, ladder signs, track areas, etc.

[0045] For each media advertising position, it is necessary to identify the most suitable product during the marketing recommendation process, that is, the product to be placed on the media advertising position, so as to determine the corresponding media placement for the media advertising position.

[0046] In the existing implementation of media advertising space marketing recommendation, manual research and manual judgment are relied upon based on subjective experience, and the obtained results are then used to recommend media advertising spaces for products to be placed.

[0047] However, manual research and manual judgment and analysis that rely on subjective experience, on the one hand, have the defects of huge workload and low timeliness due to the large number of media advertising spaces and the large and complex population of sites; on the other hand, they are bound to lead to poor research and analysis quality due to unstable subjective experience, which in turn leads to poor media delivery effects.

[0048] Therefore, the embodiment of the present application provides a method for recommending media advertising positions based on user portraits, thereby providing offline media delivery services with high reliability and high delivery accuracy.

[0049] See also Figure 1 , Figure 1 A flow chart of a method for recommending media advertising positions based on user travel according to an embodiment of the present application is shown. A method for recommending media advertising positions based on user travel provided by an embodiment of the present application includes:

[0050] Step S110, obtaining all users corresponding to the media advertising position, whose travel tracks cover the media advertising position;

[0051] Step S130, estimating the expected click value of the product to be placed in the media advertising position for all users, and obtaining the expected click value of the product to be placed in the media advertising position;

[0052] Step S150, recommending a media advertising position for the product to be placed according to the expected click value of the product to be placed on the media advertising position.

[0053] These steps are described in detail below.

[0054] Through the execution of step S110, all users corresponding to the media advertising position are first obtained. For each media advertising position for marketing recommendation, the media recommendation for the product will be implemented based on all users corresponding to it, or the most suitable product will be selected for the media advertising position to carry out media delivery on the media advertising position.

[0055] The media advertising space may be a media advertising space distributed in the station, or may be a media advertising space located in a location radiating outward from the station exit, for example, a media advertising space located in the track area of ​​the station, a media advertising space passing by from the gate to each exit, and a media advertising space at the station exit.

[0056] Therefore, for numerous media advertising positions inside and outside the site, marketing recommendations for each media advertising position can be implemented based on the embodiments of the present application.

[0057] In the marketing recommendation for each media ad spot, the products suitable for the media ad spot are recommended through all users corresponding to the location and the click expectations of these users on the products exposed on the media ad spot, or the best products are selected for the media ad spot for media delivery.

[0058] All users corresponding to the media advertising position refer to all users whose user travel profiles are related to the media advertising position. Specifically, the user travel profile may include outbound travel tracks, user itineraries, etc. Correspondingly, the user travel profile is related to the media advertising position, which means that the outbound travel tracks and user itineraries can correspond to the location of the media advertising position.

[0059] That is, during the execution of step S110, all users whose user itineraries and / or outbound travel trajectories correspond to the location of the media advertising slot are obtained for marketing recommendations of the media advertising slot.

[0060] Exemplarily, the locations corresponding to the user's itinerary and / or exit trajectory are the locations that can be covered by the user's exit behavior. For example, all the locations that the user passes through when walking from the track area to the exit elevator to the exit gate, as well as the location of the user's exit direction from the gate, and even the location on the exit channel of the exit to which the user belongs, all the media advertising positions distributed thereon are the media advertising positions corresponding to the user.

[0061] All users whose user itineraries and / or outbound travel trajectories correspond to the locations where the media advertising slots are located are obtained by aggregating the locations corresponding to the user itineraries and / or outbound travel trajectories.

[0062] Mapping the user's itinerary and / or travel trajectory to a location can be achieved by positioning the user. In addition, it can also be achieved by determining the user's preferred exit direction based on the distribution of the number of times the user exits each gate group at the site, especially the exit gate to which each user belongs.

[0063] For details, please refer to Figure 2 , Figure 2 is based on Figure 1 A flowchart of a method for describing the steps of obtaining all corresponding users for a media advertising position is shown in a corresponding embodiment.

[0064] The step S110 of acquiring all users corresponding to the media advertising position provided in the embodiment of the present application includes:

[0065] Step S111, determining the user's exit trajectory based on the distribution of the number of times the user exits each gate at the station gate group;

[0066] Step S112, aggregating users for the media advertising slots covered by the outbound trajectory, obtaining all users corresponding to the media advertising slots, and the aggregated users all correspond to the outbound trajectory covering the media advertising slots.

[0067] These two steps are described in detail below.

[0068] First of all, it should be noted that the user's entry and exit behaviors at the gate will generate corresponding user trips, which are stored in the trip data. In an exemplary embodiment, the trip data exists in the form of a user trip table. Each user trip generated when the user enters and exits the gate is stored in the constructed user trip table.

[0069] The user's itinerary describes the user's exit gate. In terms of data, the exit gate described in the user's itinerary exists in the form of an exit gate code, and the location of the gate can be obtained from the corresponding gate information.

[0070] In step S111, the distribution of the number of exit times at the station gate group gate is obtained for each user, so as to determine the exit direction or even the exit gate preferred by the user, and then obtain the exit trajectory mapped by the preferred exit direction or even the exit gate.

[0071] A station has several gate groups for entering and / or exiting the station, and for the gate groups available for exiting the station, the gate group includes a left half group of gates and a right half group of gates. It should be understood that users exiting from the left half group of gates tend to exit in one direction, while users exiting from the right half group of gates tend to exit in another direction.

[0072] According to the distribution of the number of times the user exits the station at each gate group, it can be determined whether the user prefers the left half of the gate group or the right half of the gate group, and then the preferred exit direction is determined. The user's exit gate is then determined by the preferred exit direction. This exit gate is based on the distribution of the number of times the user exits the station at each gate group. Therefore, this exit gate is the user's commonly used exit gate.

[0073] At this point, the user's exit trajectory is matched to the exit gate determined by the exit direction, and the exit trajectory including the user's passage from the gate to the exit gate is obtained.

[0074] To further illustrate, the distribution of the number of times a user exits each gate in a site gate group describes the number of times a single user exits gate 1 in the gate group, the number of times a single user exits gate 2 in the gate group, and so on, at gate n_zj in the gate group (n_zj is the number of gates in the entire gate group).

[0075] The user's preferred exit direction and exit port can be determined by counting and comparing the number of exits corresponding to the left half of the gate group and the right half of the gate group based on the distribution of the user's exit times at each gate group at the site, so as to determine the user's preferred exit direction and exit port.

[0076] In an exemplary embodiment, if the number of exits and exits of a user at a station gate group is not less than a set threshold, the user's preferred exit direction can be determined by counting and comparing the number of exits corresponding to the left half group of gates and the right half group of gates as described above, and then the exit in that exit direction can be determined as the user's frequently used exit.

[0077] In a gate group, if users exit from this gate group more frequently, they will mostly exit from the same side or even the same gate in this gate group. Therefore, the gate on this side, such as the left half of the gate group, or the right half of the gate group, or the gate on the side where the frequent exits are located, the corresponding exit direction is the one preferred by the users.

[0078] Therefore, for such users, the preferred exit direction and exit port can be determined directly by counting and comparing the distribution of their exit times at each gate group at the site, thereby reducing the calculation complexity and improving execution efficiency.

[0079] The number of times a user exits a station gate group is used to determine whether the user exits the station frequently through the current station gate group. The number of times a user exits a station gate group can be obtained based on the distribution statistics of the number of times the user exits each gate of the station gate group. In addition, it can also be obtained based on the user's user itinerary and gate information. Further, it can be obtained from the user gate group exit data constructed by the itinerary data constituted by the user's itinerary and the gate information, which is not limited here.

[0080] In another exemplary embodiment, if the number of exits of a user at a site gate group is less than a set threshold, it will be necessary to determine the user's preferred exit direction through the distribution of the user's exit times at each gate of the site gate group and the user's portrait through a binary classification model, and then determine the exit gate to which the user belongs in this exit direction.

[0081] Exemplarily, the set threshold may be 5, that is, if the number of exits and exits of a gate group at a station is not less than 5 times within the set time range, it means that an exit direction corresponding to the gate group and the exit gate in the exit direction are both consistent with the user's exit passage, thereby determining that the exit gate is the user's frequently used exit gate.

[0082] If the number of times a user exits a site gate group is less than the set threshold, it means that neither the site nor the gate group is frequently visited by users. Therefore, it is necessary to construct features based on richer data, that is, the distribution of the number of times a user exits each gate in the site gate group and the user portrait as mentioned above, and then implement predictions through a pre-built model.

[0083] So far, please refer to Figure 3 , Figure 3 is based on Figure 2 The corresponding embodiment shows a flow chart of a method for determining a user's exit trajectory based on the distribution of the number of times the user exits a station gate group.

[0084] The step S111 of determining the user's exit trajectory according to the distribution of the number of times the user exits the station at the station gate group provided in the embodiment of the present application includes:

[0085] Step S201, determining the exit gate to which each user belongs based on the distribution of the number of times the user exits the station at the station gate group and the user portrait;

[0086] Step S202, mapping the user's travel trajectory to the exit, and obtaining the user's exit trajectory at the exit.

[0087] These two steps are described in detail below.

[0088] First of all, it should be explained that a binary classification model is pre-built to predict the user's preferred exit direction. Based on the distribution of the number of times the user exits the station gate group and the user portrait, the binary classification model can predict whether the user will go left or right after exiting the gate group, thereby determining the user's preferred exit based on the exit in the direction of travel.

[0089] For each user, the exit gate to which the user belongs will be determined based on the distribution of the number of exits at the station gate group and the user portrait.

[0090] The exit gate to which the user belongs indicates the travel trajectory of the user after exiting the station from the gate. In other words, by mapping the existing travel trajectory to the determined exit gate, the exit trajectory of the user passing through the exit gate can be obtained.

[0091] Based on this, each user will determine the exit they frequently use during their travels. Therefore, for marketing recommendations for media advertising spots, media advertising spots that can correspond to the user's exit trajectory in terms of location will expose the published media content to these users. Therefore, the placement of products on the media advertising spots will be targeted at these users. The media advertising marketing recommendations based on the exit trajectory will help enhance the accuracy of product placement in media advertising spots, and thus serve offline media placement.

[0092] After the outbound track of the user is determined through the execution of step S111, the users can be aggregated for the media advertising slots covered by the outbound track through the execution of step S112, thereby obtaining all users corresponding to the media advertising slots.

[0093] In other words, as the marketing recommendation of media advertising spots is carried out, the users at each media advertising spot will be aggregated to determine the user group that the media advertising spot is targeting.

[0094] The outbound track covers at least one media advertising slot. In other words, several media advertising slots are located on the outbound track of the user. Therefore, the user's user itinerary can be mapped to the media advertising slots covered by the outbound track.

[0095] In step S112, for each media advertising position, users of the media advertising position are aggregated according to the outbound trajectory, that is, users whose outbound trajectory covers this media advertising position are aggregated together, that is, the aggregated users correspond to this media advertising position.

[0096] It should be understood that for users, along with their inbound and outbound behaviors during travel, corresponding user itineraries will be generated, and the user itinerary is the description data of the user's travel. Therefore, according to the outbound trajectory, the users whose user itineraries correspond to the media advertising position are aggregated for each media advertising position, and the users whose user itineraries correspond to the media advertising position are all the users corresponding to the media advertising position.

[0097] For marketing recommendations for each media advertising position, after all users corresponding to the media advertising position are obtained through step S110, the expected click value of the product to be placed on the media advertising position can be estimated for all users corresponding to the media advertising position, as in the execution of step S130.

[0098] In step S130, the expected click value of the product to be placed on the media advertising position refers to the degree of attention of the product after it is placed on the media advertising position by the users passing by. The expected click value of the product to be placed on the media advertising position is used to measure the degree to which the users passing by the media advertising position will be attracted by the media content of the product and the product itself if the media content of the product is placed on the media advertising position. It should be understood that the higher the expected click value of the product to be placed on the media advertising position, the more suitable the product is to be placed on the media advertising position, and the higher the possibility that the users passing by will be attracted by the product.

[0099] In the media advertising position, the click expectation prediction of the user corresponding to the media advertising position on the intended product is realized by a pre-trained click rate prediction model. Exemplarily, the click expectation of the user on the intended product is predicted by the click rate prediction model to obtain the click rate of each user on the intended product.

[0100] The intended products are products that are intended to be placed in media advertising positions. Exemplarily, the intended products include products in recommended media advertising positions. For example, when a media advertising position is recommended to a product for corresponding media placement in the media advertising position, the product is the intended product in the media advertising position. In addition, the intended products also include multiple products competing for the same media advertising position. Each product competing for the same media advertising position is a intended product. By estimating the click expectation of the product and the media advertising position, it is determined which product has a higher click expectation value, and the product with the highest click expectation value is placed in the media advertising position.

[0101] It should be noted that the click expectation prediction is performed for a media advertising position and a product to be placed for all users corresponding to the media advertising position. The click expectation prediction performed includes the click rate prediction between users and the product to be placed, and the execution process of the click rate accumulation for all users, so as to finally obtain the click expectation value of the product to be placed on the media advertising position.

[0102] In an exemplary embodiment, a click rate prediction model for estimating the click rate between users and products to be placed is trained through the click records of users on the exposed products on the travel application.

[0103] Specifically, a training data set is first constructed for the click-through rate prediction model. Each record of the training data set includes a user portrait of the user and a product feature constructed for a product. The product is exposed on the travel application and clicked by the user, that is, it corresponds to the user's click record on the exposed product on the travel application.

[0104] Thus, the training data set is constructed:

[0105] .

[0106] Among them, the constructed training data set A single record in ,Right now , The user portrait is composed of multiple parts of data, and the data sources include but are not limited to travel data, application tracking data, etc.

[0107] Specifically, (Gender, age, region, occupation, total number of rides in the past 7 / 14 / 30 / 90 days, total ride time in the past 7 / 14 / 30 / 90 days, (travel habits) average arrival time of the first trip on a weekday in the past 7 / 14 / 30 / 90 days, average departure time of the last trip on a weekday in the past 7 / 14 / 30 / 90 days, average commuting distance per trip in the past 7 / 14 / 30 / 90 days, total number of rides, top 10 most frequent stops, and receipt of commercial Total number of benefits, total number of commercial benefits redemption, total amount of commercial benefits redemption, average customer order value of commercial benefits redemption, total number of travel benefits redemption, number of each card voucher, frequency of card use, top 10 product categories viewed in the past 1 / 3 / 7 / 14 / 30 / 90 days, corresponding number of top 10 product categories viewed in the past 1 / 3 / 7 / 14 / 30 / 90 days, average price of top 10 product categories viewed in the past 1 / 3 / 7 / 14 / 30 / 90 days).

[0108] corresponds to the user's own travel data, and This corresponds to third-party supplementary data. =(Whether pregnant women, degree of gaming interest, whether a person is thrifty, whether a person with high net worth, whether a person often flies, whether a person is interested in financial management, whether a person is interested in the second dimension, whether a person is thrifty, whether a person who is addicted to his / her phone, whether a person likes shopping in supermarkets, whether a person likes to take his / her kids out for a walk, whether a person is willing to buy a car, whether a person wants to buy a house or a hospital, whether a person likes to go to museums, whether a person likes to go to historical and cultural sites, whether a person likes to go to natural scenic areas).

[0109] For product features, exemplary, = (the first / second / third-level category to which the product belongs, the price of the product, the number of exposures of the product in the past 1 / 3 / 7 / 14 / 30, the number of clicks on the product in the past 1 / 3 / 7 / 14 / 30, the number of purchase conversions of the product in the past 1 / 3 / 7 / 14 / 30, the number of days the product has been on the shelves, the number of exposures of the third-level category to which the product belongs in the past 1 / 3 / 7 / 14 / 30, the number of clicks on the third-level category to which the product belongs in the past 1 / 3 / 7 / 14 / 30, the number of purchase conversions of the third-level category to which the product belongs in the past 1 / 3 / 7 / 14 / 30).

[0110] , when the value is 0, it means the product j For users i After exposure, no click event occurs; when the value is 1, it means that the product j For users i After exposure, a click event occurred.

[0111] As a result, travel applications are For each user i , all the Product generation records to form the training data set for the click rate prediction model.

[0112] Correspondingly, the click-through rate between users and the products to be placed is estimated, and the click-through rate of the users corresponding to the media advertising slots for the products to be placed will be obtained through the trained click-through rate estimation model. The click-through rate estimation performed by the click-through rate estimation model requires the construction of a corresponding prediction data set, that is, for each user corresponding to the media advertising slot, the prediction data set is constructed through the user portrait and the product features of the products to be placed. Each record of the prediction data set is the constructed user-product pair.

[0113] The constructed prediction data set is Each record, that is, the user product pair The feature list of is the same as the training dataset.

[0114] Each record in the prediction data set represents a product to be launched. j Recommended to all users corresponding to a media ad slot, that is, users Each record will be used as the input of the click-through rate prediction model to obtain the click-through rate of each user corresponding to the media advertising position for the proposed product. Similarly, the click-through rate of all users corresponding to the media advertising position for the proposed product is obtained, and finally the expected value of clicks on the proposed product on the media advertising position is obtained.

[0115] In another exemplary embodiment, for the click rate prediction model, the problem loss function constructed at the t-th iteration is:

[0116]

[0117] in, For the ij The predicted value of the record in round t, is the t-th tree, Representation Tree The structure of w is a tree The weight of the leaves in It is i The weight of a leaf, It's about trees The regular term of the complexity of At the point The second-order approximation is:

[0118]

[0119] in, , .

[0120] The optimal solution is:

[0121]

[0122] in, q is a tree with a fixed structure, γ and λ are the first-order regularization coefficient and the second-order regularization coefficient, respectively.

[0123] Click-through rate prediction model The optimal solution of each round is obtained through iterative convergence based on the training data set.

[0124] The constructed prediction data set Every record of , predict one by one through the binary classification model, that is, the click rate prediction model to obtain the click rate of all users corresponding to the media advertising position for the proposed product, and then sum up the obtained click rates to obtain the expected click value of the proposed product placed on the media advertising position ,in, It is the number of users corresponding to the media advertisement.

[0125] Based on this, in the following exemplary embodiment, by comparing the proposed product in each media advertising position The expected click value on the media ad slot with the highest expected click value is determined as the media ad slot recommended for the product to be placed. That is, the expected click value corresponding to the media ad slot is .

[0126] Further, in another exemplary embodiment described below, when there are multiple products to be placed competing for a high-quality media advertising position, the expected value of clicks is combined with the click value. , calculate the conversion value of each product to be placed in the high-quality media advertising position, and select the optimal conversion value, that is, , j=1,2,…, so that the media placement of the products with the highest conversion value is given priority in this high-quality media advertising space.

[0127] See also Figure 4 , Figure 4 is based on Figure 1The corresponding embodiment shows a method flow chart describing the steps of estimating the expected click values ​​of the products to be placed in the media advertising slots for all users and obtaining the expected click values ​​of the products to be placed in the media advertising slots.

[0128] The step S130 of estimating the expected click value of a product placed in a media advertising position for all users and obtaining the expected click value of a product to be placed in a media advertising position provided in the embodiment of the present application includes:

[0129] Step S131, for the product to be placed, estimating the click rate of each user for the product to be placed among all users corresponding to the media advertising position;

[0130] Step S132: accumulating click rates to obtain expected click values ​​for the products to be placed on the media advertising positions.

[0131] The following is a detailed description of these two steps.

[0132] Among all users corresponding to the media ad slot, each user forms a user-product pair with the product to be placed, which is used to estimate the click rate of the user on the product to be placed. The click rate is used to represent the attractiveness of the product to be placed to the user. The higher the click rate, the more attractive the product to the user is. Conversely, the lower the click rate, the less attractive the product to the user is.

[0133] For the user-product pair consisting of the user and the product to be placed, the click rate of the user for the product to be placed is estimated by the click rate estimation model as described above, and so on, to obtain the click rate of all users corresponding to the media advertising position for the product to be placed.

[0134] In other words, all users corresponding to the media advertising position have corresponding click-through rates for the products to be placed, which can numerically describe the degree of attractiveness of the products to be placed to all users passing through the media advertising position, and then use this to evaluate whether to recommend this media advertising position for media placement of the products to be placed, or evaluate the most suitable products to be placed in this media advertising position.

[0135] After obtaining each user's click on the product to be placed, the cumulative click rate is used to obtain the expected value of clicks on the product to be placed in the media advertising position.

[0136] The expected click value of the product to be placed on the media advertising position represents the attractiveness of the product to the user group passing through the media advertising position, and the user group passing through the media advertising position is composed of all users corresponding to the media advertising position.

[0137] For further information, see Figure 5 , Figure 5 is based on Figure 4A flowchart of a method for estimating the click rate of a product to be placed by each user among all users corresponding to a media advertising position, shown in a corresponding embodiment.

[0138] The step S131 of estimating the click rate of each user for the product to be placed among all users corresponding to the media advertising position provided in the embodiment of the present application includes:

[0139] Step S301, for each user corresponding to the media advertising position, a user-product pair is constructed through the user portrait and the product features corresponding to the product to be placed;

[0140] Step S302 , by predicting the product click-through rate of the user-product pair, the click-through rate of each user for the product to be placed among all users corresponding to the media advertising position is obtained.

[0141] These two steps are described in detail below.

[0142] First of all, it should be explained that as users initiate entry and exit behaviors, corresponding user itineraries are generated. Many users and the user itineraries of each user will constitute itinerary data. In other words, the user will exist in the form of user itineraries in the data. Therefore, it is possible to construct a user profile describing the user's travel based on this, and then characterize the user with the user profile, which is used to build user-product pairs with the products to be launched.

[0143] The media advertising space used to evaluate the click-through rate of the proposed products belongs to a specific site. Therefore, the user journey used to construct the user portrait is related to this specific site, thereby ensuring the accuracy of the features of the constructed user-product pairs and eliminating useless or even interfering data.

[0144] The system built for sites provides each user with travel application deployment based on user terminals. Therefore, each user only needs to interact with the travel application in the user terminal and the gate to initiate his / her own entry or exit behavior, such as entering and exiting the site by scanning the QR code provided by the travel application on the gate. The travel application running on the user terminal and the system connected to the travel application will obtain the user's own travel data such as the user's itinerary.

[0145] That is to say, the user's own travel data will be used to characterize the user in data to build the user's user profile. The user's own travel data is multiple parts of data owned by the deployed travel application, such as the user's itinerary and other travel data mentioned above.

[0146] In addition, the user's own travel data also includes user information on the travel application, tracking data on the travel application, statistical data based on travel data, user's commercial operation data on the travel application, user-related product data, etc., which are not listed here one by one.

[0147] For example, the buried data of users on travel applications is used to describe the clicks of the users on the exposed products; the user information on travel applications includes gender, age, region and occupation; the statistical data based on travel data may specifically include but are not limited to the total number of rides in the past 77 / 14 / 30 / 90 days, the total ride duration in the past 7 / 14 / 30 / 90 days, the average entry time of the first trip on weekdays in the past 7 / 14 / 30 / 90 days, the average exit time of the last trip on weekdays in the past 7 / 14 / 30 / 90 days, the average commuting distance per trip in the past 7 / 14 / 30 / 90 days, the total number of rides, and the top 10 high-frequency stations;

[0148] The business operation data of users on travel applications, including but not limited to: the total number of times commercial benefits are received, the total number of times commercial benefits are written off, the total amount of commercial benefits written off, the average price per customer of commercial benefits written off, the total number of times travel benefits are received, the number of times each card voucher is used, and the frequency of card use;

[0149] User-related product data may include but is not limited to: top 10 product categories viewed in the past 1 / 3 / 7 / 14 / 30 / 90 days, the corresponding number of times the top 10 product categories were viewed in the past 1 / 3 / 7 / 14 / 30 / 90 days, and the average price of the top 10 product categories viewed in the past 1 / 3 / 7 / 14 / 30 / 90 days).

[0150] It should be understood that the user's own travel data will be adapted to the marketing recommendation output of the travel application for media advertising space to obtain a corresponding user portrait.

[0151] The source of user portrait is not limited to the user's own travel data, but can also come from third-party supplementary data. In short, the user portrait corresponds to the user's own travel data, as well as the combination of the user's own travel data and third-party supplementary data.

[0152] The third-party supplementary data includes, but is not limited to, whether the person is a pregnant woman, the degree of his or her interest in games, whether the person is a budget-conscious person, whether the person is a high net worth person, whether the person often flies, whether the person is interested in financial management, whether the person is interested in the two-dimensional world, whether the person is a budget-conscious person, whether the person is a phone addict, whether the person likes to go shopping in supermarkets, whether the person likes to take the kids out for a walk, whether the person is willing to buy a car, whether the person wants to buy a house or a hospital, whether the person likes to go to museums, whether the person likes to go to historical and cultural sites, whether the person likes to go to natural scenic areas, etc.

[0153] During the execution of step S301, for each user corresponding to the media advertising position, a user portrait of the user is obtained through the user's own travel data, or a combination of the user's own travel data and third-party supplementary data, and the user portrait is then used as the user feature of the user in the constructed user-product pair.

[0154] In other words, the user portrait digitized by the user's own travel data, or the combination of the user's own travel data and third-party supplementary data, will serve as the user feature and constitute a user-product pair together with the product features of the product to be launched.

[0155] The commodity features of the commodities to be put on the market are used to describe the features of the commodities to be put on the market. Exemplarily, the commodity features of the commodities to be put on the market include descriptive features, statistical features, statistical generalized features, etc. of the commodities to be put on the market.

[0156] Specifically, the product characteristics of the proposed products include the first / second / third-level category to which the proposed products belong, the price of the proposed products, the number of exposures of the proposed products in the past 1 / 3 / 7 / 14 / 30, the number of clicks on the proposed products in the past 1 / 3 / 7 / 14 / 30, the number of purchase conversions of the proposed products in the past 1 / 3 / 7 / 14 / 30, the number of days the proposed products have been on the shelves, the number of exposures of the third-level category to which the proposed products belong in the past 1 / 3 / 7 / 14 / 30, the number of clicks on the third-level category to which the proposed products belong in the past 1 / 3 / 7 / 14 / 30, and the number of purchase conversions of the third-level category to which the proposed products belong in the past 1 / 3 / 7 / 14 / 30.

[0157] Through step S301, for each user of the media advertising space recommended for marketing, a user-product pair is constructed through the user portrait and the product features of the product to be placed, thereby predicting the click rate of the user on the product to be placed based on the user-product pair.

[0158] It should be understood that media advertising space is a physical resource that actually exists offline. Users are attracted by the media content on which the intended products are exposed, which is analogous to clicks on products exposed on the Internet. Therefore, the degree of attraction of the intended products to users exposed offline through media advertising space can be accurately measured by the click-through rate of users on the intended products.

[0159] In step S302, the pre-built click rate prediction model is used to predict the click rate of the user-product pair, and the click rate of the user on the intended product is obtained. It should be understood that the click rate of the user on the intended product is the probability that the user is attracted by the intended product, and is also the user's expectation of being attracted by the intended product after it is exposed in the media advertising position.

[0160] For all users corresponding to the media advertising positions recommended by marketing, each user will construct a user-product pair, and the click-through rate of the corresponding products will be predicted through the constructed user-product pairs. By analogy, the click-through rate of the products to be placed for each user among all users corresponding to the media advertising positions can be obtained.

[0161] After the click rate of each user on the product to be placed is estimated among all users corresponding to the media advertising position of the product to be placed through the execution of step S131, step S132 can be executed to accumulate the click rates corresponding to all users and obtain the expected value of clicks on the product to be placed in the media advertising position.

[0162] The click-through rate refers to a single user, while the expected value of clicks for a product to be placed on a media advertising space corresponds to a user group, which includes all users corresponding to the media advertising space.

[0163] The expected click value of a product to be placed on a media advertising position corresponding to a user group is used to represent the attractiveness of the product to be placed on the media advertising position to the user group. In other words, the expected click value of a product to be placed on a media advertising position corresponding to a user group is also the interest level of the user group passing through the media advertising position in the product to be placed.

[0164] The user group formed by all users corresponding to the media advertising positions obtained through the aforementioned step S110 can be regarded as the user group owned by the media advertising position. The marketing recommendation of the media advertising position based on the user group should consider the degree of fit between the intended products and the user group. The click-through rate estimation between the users and the intended products and the cumulative calculation based on this will accurately quantify the degree of fit between the intended products and the user group, and then determine what kind of media content of the products should be placed in each media advertising position, which greatly ensures the accuracy of the marketing recommendation of the media advertising position and the effectiveness of the product placement.

[0165] For the marketing recommendation of a media advertising position, the expected click value of the product to be placed on the media advertising position is obtained by executing step S130. For multiple products to be placed competing for the same media advertising position, the expected click value of each product to be placed on the media advertising position can also be used to determine the product to be placed that can obtain the highest expected click on the media advertising position, that is, the product that is most likely to be attracted by passing users, so as to recommend the media advertising position to the product to be placed.

[0166] In summary, through the execution of step S150, the media advertising positions recommended for marketing are recommended according to the expected click values ​​of the products to be placed on the media advertising positions, so as to implement the recommendation of the media advertising positions for the products to be placed.

[0167] In step S150, based on the expected click value of the product to be placed on the media advertising position, the media advertising position for the product to be placed is recommended, so that the media advertising position currently being recommended for marketing can match the most suitable product. In an exemplary embodiment, based on the expected click value of the product to be placed on the media advertising position, the media advertising position with the highest expected click value is directly selected for the product to be placed.

[0168] For a product to be placed, each idle media advertising position is an object that can be considered for implementing the corresponding media content placement. Therefore, by executing the aforementioned steps, the expected click value of the product to be placed on each media advertising position is obtained. At this time, the expected click value of the product to be placed on each media advertising position is compared, and the media advertising position with the highest expected click value is recommended to the product to be placed.

[0169] This is a media advertising position with a high click-through expected value selected from multiple media advertising positions for a product to be placed, and then the selected media advertising position with a high click-through expected value is recommended to the product to be placed.

[0170] In the media advertising slot marketing recommendation for a product to be placed, the expected click value of the product to be placed in the media advertising slot is estimated for all the idle media advertising slots respectively, thereby obtaining the expected click value of the product to be placed in each media advertising slot.

[0171] Specifically, for all idle media advertising slots, all users corresponding to each media advertising slot are obtained through the execution of step S110, and step S130 is executed for all the obtained users to estimate the expected click value of the products to be placed in each media advertising slot, and the expected click value of the products to be placed in each media advertising slot is obtained. At this point, the media advertising slots recommended for the products to be placed can be selected from all idle media advertising slots in the execution of step S150.

[0172] This is the process of implementing the recommendation of a media advertising slot for a product to be placed. Similarly, this process can be used to implement marketing recommendations for media advertising slots for each product to be placed in all idle media advertising slots.

[0173] It should be understood that this is also a media ad slot recommendation that is achieved by directly applying the expected click value of the product to be placed on each media ad slot. In addition, media ad slot recommendations that take into account the dimension of media ad slot conversion value can also be made based on the expected click value of the product to be placed on each media ad slot, thereby performing more accurate media ad slot recommendations among multiple products to be placed.

[0174] That is to say, by comparing the expected clicks of the proposed product on each media advertising slot, the media advertising slot to be implemented for the proposed product is recommended. In an exemplary embodiment, this execution process is for recommending a proposed product to multiple media advertising slots. When there are more than two proposed products competing for a media advertising slot, it is necessary to determine to which proposed product the media advertising slot can be recommended based on the expected clicks of each proposed product on the media advertising slot and considering their respective conversion values ​​on the media advertising slot.

[0175] That is to say, when there are two or more products competing for placement in a media advertising space, the media advertising space is determined to recommend a product to which the product should be placed based on their respective expected click values ​​and their respective conversion values ​​in the media advertising space.

[0176] In the case where there are more than two products to be placed competing in a media advertising space, in an exemplary embodiment, a marketing recommendation appears at the beginning of the media advertising space, such as the selection of the products to be placed by the media advertising space, and the media advertising space recommends the selected products to be placed by selecting the products to be placed; in another exemplary embodiment, with the execution of steps S110 to S130, each of the products to be placed obtains an expected click value in each media advertising space, that is, an expected click value of each product to be placed in a media advertising space. At this time, each product to be placed will directly apply the expected click value or compete for the same media advertising space based on the expected click value.

[0177] To further explain, the process of determining which product to recommend to a media ad slot is based on the expected click value of each product on a media ad slot, that is, determining the product with the highest conversion value on the media ad slot based on the click value of the product and its expected click value on the media ad slot, and then recommending the media ad slot to the product.

[0178] For further information, see Figure 6 , Figure 6 It is a method flow chart describing the steps of recommending media advertising positions for products to be placed according to the expected click value of the products to be placed on the media advertising positions according to an embodiment of the present application.

[0179] The step S150 of recommending a media advertising position for a product to be placed according to the expected click value of the product to be placed on the media advertising position provided in the embodiment of the present application includes:

[0180] Step S151, obtaining the click value of the product to be placed;

[0181] Step S153, obtaining the conversion value of the product to be placed in the media advertising position by calculating the click value and the expected click value of the product to be placed in the media advertising position;

[0182] Step S155, recommending media advertising positions to the products to be placed corresponding to the highest conversion values.

[0183] These steps are described in detail below.

[0184] First, it should be noted that the embodiment of the present application is a media advertising position recommendation implemented when two or more planned products compete for one media advertising position, so as to determine to which planned product the contested media advertising position will be recommended.

[0185] The click expectation of the proposed product on the media advertising slot represents the degree of attraction of the proposed product exposed on the media advertising slot to past users. For the proposed product, a high click expectation value indicates the degree of interest of past users in the proposed product exposed on the media advertising slot. Therefore, the media advertising slot will be recommended to which proposed product at least based on the click expectation of the proposed product on the media advertising slot.

[0186] On this basis, in the case where two or more products are competing for one media advertising space, the recommendation for the media advertising space will be finally determined based on the conversion value of the products in the media advertising space.

[0187] To this end, in step S151, the corresponding click values ​​are obtained for two or more intended products competing for the same media advertising position. The click value is related to the value of the intended product itself. For example, the click value of the intended product represents the revenue brought to the intended product by users attracted by the exposed intended product in the past. Specifically, the click value of the intended product can be an estimate of the intended product, or it can be the contribution rate of the exposure of the intended product on the media advertising position to guide the transaction. Therefore, the click value of the intended product can be an estimate of the intended product itself, or it can be the corresponding click value obtained for the intended product in different media advertising positions. It is not limited here and will be determined according to the needs of specific operations.

[0188] For example, the click value of the product to be placed can be expressed as the product of the click-through rate and the product value, where the click-through rate may be the click-through rate of the product to be placed exposed on the connected travel application; for another example, the click value of the product to be placed can also be expressed as the contribution rate of the transaction amount starting from the media advertising space and finally completed by past users, which are not listed here one by one.

[0189] After estimating the expected click value of each product to be placed in a media advertising position, the click value of each product to be placed is obtained by executing step S151, and then the conversion value of each product to be placed in this media advertising position is calculated by combining the click value and the expected click value through the execution of step S153.

[0190] In step S153, when more than two products to be placed compete for one media advertising position, that is, when more than two products to be placed have their expected click values ​​on the media advertising position calculated, the conversion value of each product to be placed on the media advertising position is obtained by multiplying the click value and the expected click value.

[0191] The conversion value of the product to be placed in the media advertising position takes into account the degree to which the exposure of the product to be placed in this media advertising position has attracted past users, and quantifies the value that can be converted by its exposure in the media advertising position. Therefore, the conversion value of the product to be placed in the media advertising position can accurately determine the most suitable product to be placed in the media advertising position in terms of conversion, so that the marketing recommendations of the media advertising position can give priority to the placement of products with the highest conversion value.

[0192] For example, a media ad space is a high-quality media, and it has multiple products competing for it. The click value of each product is obtained. , and then combined with the expected click value of the product in the media advertising position Calculate the conversion value of the product in the media ad space as shown below:

[0193]

[0194] For two or more products to be placed that compete for the same media advertising space, their conversion values ​​are calculated, and then the highest conversion value can be determined in step S155, that is, , thereby determining the products to be placed with the highest conversion value, and recommending media advertising positions to the products to be placed with the highest conversion value.

[0195] The following is a specific example to illustrate the media advertising space marketing recommendation based on user travel provided by this application.

[0196] See also Figure 7 , Figure 7 The figure is a schematic diagram of a data link for media advertisement slot marketing recommendation according to an exemplary embodiment.

[0197] First, for a media advertising position, a media portrait is obtained based on all corresponding users, which is used to form a user-product pair on the media advertising position with the constructed product features, and then the estimated click-through rate is obtained.

[0198] Specifically, the distribution of the number of times a user exits a station at a gate group is obtained through the user itinerary table and the gate information table. When a user exits a station by scanning a QR code of a travel application, the distribution of the number of times a user exits a station at a gate group describes the number of times the user scans the code at each gate, that is, the user gate group scan code table is obtained.

[0199] That is to say, the user travel table is associated with the gate information table through the gate code to obtain the user gate group code swiping table.

[0200] Based on the user gate group code scanning table, the distribution of user code scanning in this group of gates can be known, and the distribution of user code scanning in this group of gates will indicate the user's exit direction.

[0201] Combined with the gate group entrance and exit distance relationship described in the gate group entrance and exit distance relationship table, the exits pointing to different directions of the gate group are known, and the user's frequently used exits can be determined, and the user's recently frequently used exit table can be obtained.

[0202] For each exit, the media advertising slot mapped to the exit is recorded to construct and maintain a media exit relationship table.

[0203] Through the mapping of the exit to the media advertising position, it is possible to know the media advertising position that the user will pass through when leaving the station from an exit. In other words, all users who pass through the media advertising position are all users corresponding to the media advertising position.

[0204] The user portraits of all users corresponding to the media advertising slots are assigned to the media advertising slots, and the labels of the media advertising slots are further enriched to obtain a media portrait table.

[0205] At this point, the most suitable media advertising position for the proposed product can be determined based on the media portrait table, or the proposed product with the highest conversion value can be determined for the media advertising position, ultimately achieving marketing recommendations for the media advertising position.

[0206] It should be further explained that all users corresponding to the media advertising space can determine the commonly used exit gates through statistics of the users' preferred exit directions in the user gate group's code scanning table, and then use this to determine all users corresponding to the media advertising space.

[0207] In addition, if the user has fewer trips in the user itinerary, for example, the number of exits of the user at the site gate group is less than the set threshold, it will be necessary to determine the user's preferred exit direction through the distribution of the user's exit times at each gate of the site gate group and the user portrait through a binary classification model, and then determine the exit gate to which the user belongs in this exit direction.

[0208] The probability that the user belongs to each exit is obtained through a pre-trained binary classification model, and then the exit to which the user belongs is finally determined by the probability. Exemplarily, the pre-trained model can be a binary classification model, which is characterized by the distribution of the number of times the user exits each gate group at the station and the user portrait. Under this feature, the direction value corresponding to the feature is marked according to the direction of the user after exiting the station, and each direction value uniquely corresponds to an exit that can be passed from the gate group.

[0209] For example, if the user in the feature mapping passes to the left after exiting the gate group, the marked direction value is 0; correspondingly, if the user in the feature mapping passes to the right after exiting the gate group, the marked direction value is 1.

[0210] Based on this, construct a training data set , where each training data set In a single record in It is the feature of this record, which is used to describe the user status of the corresponding user.

[0211] Specifically, It includes the distribution of the number of times users exit each gate in a site gate group at a certain time and the user portrait, and the user portrait can be represented by multiple user tags. Is a user In the gate unit j Features, Is a user of m Dimensional features.

[0212] For example, =[Date (YYYYMM), User user tag 1 of user i, user tag 2 of user i, ..., user User tags ,user In the gate unit j The number of exits from gate 1 and the number of users In the gate unit j The number of exits from gate 2, ..., user In the gate unit j Gate machine The date (YYYYMM) represents the month, such as 202312, which means December 2023. The date feature indicates the time range corresponding to other features. Refers to the user No. User tags, i.e. Represents the number of users, Representative User The number of gate groups you face when exiting the station during your trip, Represents the number of user tags, It is the direction value of the feature annotation in a single record of the corresponding training dataset. Representative User Given the corresponding features (especially the actual number of exits), the direction of the final exit traffic.

[0213] That is, in a single record of the training data set is the direction value of the annotation. For example, the user In the gate unit j Turn left after exiting the station. , if you go right, then .

[0214] By training the model with the constructed training data set, a model is obtained that can accurately predict the exit to which the user belongs, providing the user with accurate judgment of the exit affiliation. There is no need to obtain the location, that is, it is no longer restricted by GPS positioning and the acquisition of location permissions.

[0215] Furthermore, the training for exit prediction will be conducted for gate groups corresponding to only one exit. A training data set is constructed for the gate group corresponding to the only exit, and features are constructed based on all records related to the gate group, and direction values ​​are annotated for the constructed features based on the unique direction of the gate group.

[0216] Specifically, the number of times the user exits each gate of the gate group in the site is obtained through the travel data and the gate information, that is, the user gate group exit data of user-site-gate group-gate-exit number is obtained, which can be in a tabular form, that is, a table maintained according to fields such as user, site, gate group, gate, and exit number, and the user gate group exit data corresponding only to the only exit is obtained therefrom, and the number of times the user exits each gate of the gate group at the site is obtained from the user gate group exit data corresponding only to the only exit, and the feature is constructed based on this.

[0217] In addition, the corresponding user portraits will be extracted for feature construction, and the constructed features will be labeled with directional values ​​to finally form a training data set.

[0218] The constructed training data set shields the influence of other exits and only considers the prediction of the user's exit in the feature dimension, so that the subsequent predictions will not be affected by other factors, which will greatly improve the accuracy and reliability of the prediction.

[0219] Exemplarily, a gate group entrance and exit distance relationship will also be constructed. The gate group entrance and exit distance relationship is used to indicate the distance of each gate of the gate group in a site relative to the exits in each direction. Therefore, after predicting the most likely direction of the user after exiting the gate, it can be directly mapped to the closest exit based on the gate group entrance and exit distance relationship. This exit is the exit to which the predicted user belongs.

[0220] As mentioned above, the model trained by constructing the obtained training data set can be a binary classification model, and thus, the obtained binary classification model will be used to predict the exit to which the user belongs. Specifically, the binary classification model is used to predict the most likely direction of the user after exiting from the gate group according to the number of exits of the user at each gate on the station gate group and the user portrait, and the exit mapped by the direction is used as the exit to which the user belongs.

[0221] To further illustrate, a prediction data set is constructed based on the number of times a user exits each gate at the site gate group and the user profile. , where, unlike the training data set, the prediction data set is not limited to the gate group corresponding to the only exit; in other words, it will not distinguish whether the gate group corresponds to the only exit, and all the user's data will be used to construct the prediction data set, and then the exit to which the user belongs will be predicted based on the features of the constructed prediction data set.

[0222] Prediction Dataset In each record Indicates users whose exit port has not yet been determined i In the gate unit j The feature, as mentioned above, describes the user in terms of content i In the gate unit j The number of exits and user tags of each gate, the list of features included and similar.

[0223] Based on the obtained binary classification model, the prediction data set Each record of Use the binary classification model to implement predictions one by one and get user i In the gate unit j The characteristics of the gate are biased towards one direction, that is, they belong to the gate unit. j The probability of the corresponding exit .

[0224] For example, if the gate unit j Corresponding to two exits. In other words, the gate unit j Post-exit users There are two directions, each direction corresponds to an exit, then the probability of leaning towards the other direction, that is, belonging to the other exit, is 1- .

[0225] In addition, if the gate unit j There are more than two exits in one direction, that is, the exit in this direction is not unique, then the binary classification model is used to predict the user i In the gate unit j When exiting the station and heading towards a direction with more than two exits, the user will be determined based on the traffic of each exit. i The exit that is most likely to be passed by, which is the user i The exit gate to which you belong.

[0226] Specifically, each exit in one direction has its own flow, which can be sensed by the passenger flow counter set at the exit. The flow ratio of each exit is determined by the flow corresponding to each exit, and then the user is determined according to the flow ratio. i The exit gate to which you belong.

[0227] Therefore, after the user's belonging exit is determined, the user's travel trajectory is mapped to the belonging exit according to the user's belonging exit, and the user's itinerary during travel will also be mapped to this exit.

[0228] In other words, for the exit corresponding to the travel trajectory, on the one hand, we can know which users have passed through this exit, and then we can match these users to the positions at this exit, that is, determine which users correspond to the positions at this exit, and match the user portraits of these users to the positions at this exit, such as media locations, shop locations, etc.

[0229] On the other hand, the exit corresponding to the travel trajectory provides the tracked travel trajectory within the station, breaking out of the restricted GPS positioning and the required location permissions, and can also obtain the user's in-station trajectory, enhancing the in-station tracking performance.

[0230] As the user's travel trajectory out of the station and the exit in the user's itinerary can be matched, the user is aggregated at the location at the exit, and the aggregated user is assigned a location at the exit.

[0231] The user aggregation referred to is to determine the corresponding user group for the location at the exit, and to describe and characterize the aggregated user group through the user profiles of the aggregated users.

[0232] The travel trajectory is mapped to the corresponding exit so that the corresponding user trip can be mapped to the exit, and then the user who generated the user trip is also mapped to the exit, so that the users corresponding to the same exit are aggregated.

[0233] The location mapped by the exit refers to the location on the exit. For example, in terms of location type, the location includes but is not limited to the media location, the store location, etc.; in terms of geographical location, the location mapped by the exit is any location in the direction of the exit, such as the location inside the station in the direction of the exit, the exit passage in the direction of the exit, and the location outside the station exiting from the exit.

[0234] In terms of data, users exist in the form of user portraits and their travel trajectories. Therefore, user aggregation is achieved in the form of travel trajectories and user portraits, so that the user portraits corresponding to the aggregated users are assigned to the location mapped by the exit, so as to accurately locate and describe the user characteristics of the location through the assigned user portraits. For example, the user portraits of the aggregated users are assigned to the media location to construct the corresponding media portrait.

[0235] For the obtained media portrait, a click-through rate prediction recommendation algorithm will be used for each user corresponding to the media advertising position. That is, the constructed click-through rate prediction model will estimate the click-through rate of the product to be placed on the media advertising position, and then the click-through rate on the media advertising position will be accumulated to obtain the expected value of clicks, that is, the media product click-through rate estimation table will be obtained.

[0236] The expected click value of the product to be placed on the media advertising position is provided through the media product click rate estimation table, and the conversion value of the product to be placed on the media advertising position is obtained by combining the click value of the product to be placed, and the media product conversion value table is obtained, which is finally used to execute the recommendation of the media advertising position.

[0237] It should be added that the click-through rate prediction recommendation algorithm, that is, the click-through rate prediction model, is trained based on online product exposure click data from platforms such as travel applications. The training data set and the product features of the products to be launched are obtained from the constructed product label table, which will not be elaborated here.

[0238] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software, or by combining software with necessary hardware. Therefore, the technical solution according to the implementation method of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation method of the present application.

[0239] In an exemplary embodiment of the present application, a computer program medium is further provided, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor of a computer, the computer is enabled to execute the method described in the above method embodiment.

[0240] According to one embodiment of the present application, a program product for implementing the method in the above method embodiment is also provided, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited to this. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0241] The program product may be any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0242] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0243] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0244] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0245] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0246] In addition, although the steps of the method in the present application are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0247] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software, or by combining software with necessary hardware. Therefore, the technical solution according to the implementation method of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation method of the present application.

[0248] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the appended claims.

Claims

1. A method for recommending media advertising positions based on user travel, characterized in that: The method comprises: Acquire all users corresponding to the media advertising position, wherein the travel trajectory of the user covers the media advertising position; the acquiring all users corresponding to the media advertising position comprises: determining the exit trajectory of the user through the distribution of the number of exits of the user at each gate of the station gate group; aggregating the user for the media advertising position covered by the exit trajectory, and obtaining all users corresponding to the media advertising position, wherein the aggregated users all correspond to the exit trajectory covering the media advertising position; estimating the click expectations of the product to be placed in the media advertising position for all users, and obtaining the click expectation value of the product to be placed in the media advertising position; According to the expected click value of the product to be placed on the media advertisement position, a media advertisement position is recommended for the product to be placed.

2. The method according to claim 1, characterized in that The step of estimating the click expectations of the product to be placed in the media advertisement position for all users and obtaining the click expectation value of the product to be placed in the media advertisement position includes: For the product to be placed, estimating the click rate of each user on the product to be placed among all users corresponding to the media advertising position; The click rates are accumulated to obtain the expected click value of the product to be placed on the media advertising position.

3. The method according to claim 2, characterized in that The estimating the click rate of each user for the product to be placed among all users corresponding to the media advertising position includes: For each user corresponding to the media advertising position, a user-product pair is constructed through the user portrait and the product features corresponding to the product to be placed; By predicting the product click-through rate of the user-product pair, the click-through rate of the product to be placed by each user among all users corresponding to the media advertising position is obtained.

4. The method according to claim 3, characterized in that The user portrait corresponds to the user's own travel data, and a combination of the user's own travel data and third-party supplementary data.

5. The method according to claim 1, characterized in that The step of recommending a media advertising position for the product to be placed according to the expected click value of the product to be placed on the media advertising position includes: The expected click values ​​of the product to be placed on each media advertising position are compared, and the media advertising position with the highest expected click value is recommended to the product to be placed.

6. The method according to claim 1, characterized in that The step of recommending a media advertising position for the product to be placed according to the expected click value of the product to be placed on the media advertising position includes: Obtaining the click value of the product to be placed; The conversion value of the product to be placed on the media advertising position is obtained by calculating the click value and the expected click value of the product to be placed on the media advertising position; The media advertising position is recommended to the proposed product corresponding to the highest conversion value.

7. A media advertising position recommendation system based on user travel, the system comprising a memory, a processor, and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 6.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer program product, comprising a computer program, characterized in that The computer program is executed by a processor to implement the steps of the method according to any one of claims 1 to 6.

Images