Time-sharing recommendation method and system for media information bits, medium and product

Abstract

The invention provides a time-sharing recommendation method and system for media information bits, a computer readable storage medium and a computer program product. The media information bit time-sharing recommendation method comprises the following steps of: firstly, determining an existing target user group in a divided time-sharing carousel period of each media information bit on the basis of a user travel, and estimating a click expected value of putting commodities into the media information bits in the time-sharing carousel period for the target user group; therefore, the media information bit corresponding to the expected click value for the commodity needing to be put and the time-sharing carousel time period on the media information bit can be determined according to the numerical value of the expected click value, and the media information bit corresponding to the expected click value and the time-sharing carousel time period are found for the commodity needing to be put. Accurate selection of the media information bits and the time-sharing carousel time periods on the media information bits is achieved, and it is guaranteed that commodities can be accurately put to target crowds.

Description

Technical Field

[0001] The present application relates to the field of computer application technology, and in particular to a time-sharing recommendation method and system for media information bits, a computer-readable storage medium, and a computer program product. Background Art

[0002] In public scenarios such as travel, there are numerous media information positions. A large number of commodities are continuously broadcasted with relevant commodity media content to passers-by through the media information positions, in the hope that the continuous broadcast of commodity media content can trigger the purchase of the placed commodities, thereby achieving value conversion for the target population passing through the media information positions.

[0003] In order to increase the capacity of the media information position to place goods, the goods placed in the media information position often correspond to a specified time-sharing carousel period. Multiple goods are placed in the same media information position, and each of the goods has a corresponding time-sharing carousel period in this media information position. In other words, the media information position places different goods in different time-sharing carousel periods, so as to achieve the purpose of cyclic carousel of multiple goods in this media information position.

[0004] In this case, for the product placement, choosing which media information position to place the product in and in which time-sharing carousel period of the media information position to place the product so that the product can be accurately placed to the target group at the location and time period where the target group appears has become a difficult problem that needs to be solved urgently. Summary of the invention

[0005] One purpose of the present application is to solve the technical problem of how to accurately select media information positions and time-sharing carousel periods on the media information positions so that the products can be accurately delivered to the target population.

[0006] According to one aspect of an embodiment of the present application, a time-sharing recommendation method for media information bits is disclosed, the method comprising:

[0007] For the time-sharing carousel period split into the media information position, a target user group for placing the product at the media information position in the time-sharing carousel period is obtained according to the user's itinerary;

[0008] estimating the expected clicks of the product placed on the media information position for the target user group, and obtaining the expected click value of the product at the media information position during the time-sharing carousel period;

[0009] According to the expected click values ​​of the commodity at each media information position corresponding to each time-sharing carousel period, the media information position with high expected click value and the time-sharing carousel period at the media information position are recommended for the commodity.

[0010] According to one aspect of an embodiment of the present application, the time-sharing carousel period divided into media information positions, and obtaining a target user group for the merchandise placed at the media information position during the time-sharing carousel period according to the user's itinerary, includes:

[0011] Corresponding to the split time-sharing carousel period, obtaining the user's travel data, wherein the travel data is consistent with the time-sharing carousel period in terms of time;

[0012] Determine the site to which the user's travel belongs in time-sharing according to the travel data of the user in the time-sharing carousel period;

[0013] The users belonging to the site in the time-sharing carousel period are aggregated to form a target user group for placing merchandise in the time-sharing carousel period by media information positions mapped by the site.

[0014] According to one aspect of an embodiment of the present application, estimating the expected click value of the product placed on the media information position for the target user group and obtaining the expected click value of the product at the media information position during the time-sharing carousel period includes:

[0015] For the user's travel data during the time-sharing carousel period, the user's time-sharing exit times at each gate of the subway station gate group are obtained from the gate information according to the user's exit station and exit gate;

[0016] The exit to which the user belongs during the time-sharing carousel period is determined based on the distribution of the number of times the user exits the station at each gate group at the subway station. The exit is the exit that can be used by the gate group to exit the station.

[0017] According to one aspect of the embodiment of the present application, for each product, the click rate of each user on the product is estimated for the target user group in the media information position in the time-sharing carousel period, including:

[0018] For the target user group whose media information is located in the time-sharing carousel period, a user-product pair is constructed through the user portrait of each user and the product features corresponding to the product;

[0019] By predicting the product click rate of the user-product pair, the click rate of the product by each user in the target user group of the media information position in the time-sharing carousel period 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 method of recommending a media information position with a high click expectation value and a time-sharing carousel period at the media information position for the product according to the click expectation value of each media information position corresponding to each time-sharing carousel period includes:

[0022] Compare the expected click values ​​of the product in each time-sharing carousel period of each media information position, and recommend the media information position with the highest expected click value and the time-sharing carousel period of the product in the media information position to the product.

[0023] According to one aspect of the embodiment of the present application, the media information position in the time-sharing carousel period is competed for by more than two commodities;

[0024] The method further comprises: recommending a media information position with a high click expectation value for the product according to the click expectation value of each media information position corresponding to each time-sharing carousel period, and after the time-sharing carousel period of the media information position.

[0025] For two or more products competing for the media information position, respectively obtain the click value of the products;

[0026] Calculate the conversion value of each product through the click value and the expected click value of the media information position of the product in the time-divided carousel period that the product competes for;

[0027] The time-sharing carousel period of the media information position is recommended for the delivery of high-conversion-value commodities.

[0028] According to one aspect of an embodiment of the present application, a media advertising position recommendation system for time-sharing recommendation of media information positions based on user travel portraits is disclosed. The system includes a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement the steps of the method described above.

[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] In the embodiment of the present application, for media information positions and the time-sharing carousel time periods divided by the media information positions, the target user groups existing in the divided time-sharing carousel time periods of each media information position are first determined based on the user itinerary, and the expected click values ​​of the products delivered to the media information positions in the time-sharing carousel time periods are estimated for the target user groups. Thus, the media information positions and the time-sharing carousel time periods corresponding to the high expected click values ​​for the products to be delivered can be determined based on the numerical values ​​of the expected click values, and the media information positions and the time-sharing carousel time periods corresponding to the high expected click values ​​can be found for the products to be delivered, thereby achieving accurate selection of the media information positions and the time-sharing carousel time periods on the media information positions, and ensuring that the products can be accurately delivered to the target population.

[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 time-sharing recommendation of media information bits according to an embodiment of the present application is shown.

[0035] Figure 2 is based on Figure 1 A flowchart of a method for obtaining a target user group for a commodity placed at a media information position in a time-sharing carousel period according to a user's itinerary for splitting the media information position into time-sharing carousel periods shown in the corresponding embodiment.

[0036] Figure 3 is based on Figure 2 The corresponding embodiment shows a method flow chart describing the steps of determining the site to which the user's travel belongs in time-sharing based on the user's travel data in the time-sharing carousel period.

[0037] Figure 4 is based on Figure 3 The corresponding embodiment shows a method flow chart describing the steps of determining the exit gate to which the user belongs in the time-sharing carousel period according to the distribution of the number of time-sharing exits of the user at each gate group at the subway station.

[0038] Figure 5 The present invention is a flowchart of a method for describing the step of determining the exit gate to which a user belongs through exit gate bias statistics according to an exemplary embodiment.

[0039] Figure 6is based on Figure 1 The corresponding embodiment shows a method flow chart describing the steps of estimating the expected click value of the product placed on the media information position for the target user group and obtaining the expected click value of the product at the media information position during the time-sharing carousel period.

[0040] Figure 7 is based on Figure 6 The corresponding embodiment shows a method flow chart describing the steps of estimating the click rate of each user for each product in the target user group in the time-sharing carousel period of the media information. 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] In order to achieve the media placement of goods, a region is often distributed with many media information positions, and each media information position rotates different goods at different time periods for people passing by to watch. People passing by pay attention to the goods through the placement of goods on the media information position and then purchase the goods. For the product placement carried out by the media information position, the rotation of goods in the media information position is effective, realizing the value conversion of the product placement.

[0045] Therefore, for the release of a product, how to deliver the product to the target user group at the right time and place is a difficult problem that needs to be solved urgently in media information position recommendation.

[0046] To this end, an embodiment of the present application provides a time-sharing recommendation method for media information positions, so as to recommend media information positions determined by the time period and location passed by the target user group and the time-sharing carousel period of the media information positions for commodities.

[0047] See also Figure 1 , Figure 1 A flowchart of a time-sharing recommendation method for media information bits according to an embodiment of the present application is shown. The embodiment of the present application provides a time-sharing recommendation method for media information bits, the method comprising:

[0048] Step S110, for the time-sharing carousel period divided into the media information position, a target user group for placing merchandise in the media information position in the time-sharing carousel period is obtained according to the user's itinerary;

[0049] Step S120, estimating the expected clicks of the products placed on the media information position for the target user group, and obtaining the expected clicks of the products on the media information position during the time-sharing carousel period;

[0050] Step S130 , recommending media information positions with high click expectation values ​​and time-sharing carousel periods in the media information positions for the product according to the click expectation values ​​of the product in each media information corresponding to each time-sharing carousel period.

[0051] These steps are described in detail below.

[0052] In step S110, the media information position corresponds to a plurality of time-sharing carousel periods, and the merchandise placed in the media information position will play the placed content according to the corresponding time-sharing carousel period, so that a plurality of merchandise are cyclically played in the media information position.

[0053] The time-sharing carousel period is the temporal division of the media playback of the media information position, and the divided time period is the time-sharing carousel period of the media information position.

[0054] For each time-sharing carousel period of a media information position, the target user group of the media information position in each time-sharing carousel period is determined by executing step S110. The target user group of the media information position in a time-sharing carousel period refers to the group of people passing by the media information position in this time-sharing carousel period.

[0055] To further illustrate, the target user group determined for the time-sharing carousel period of the media information position according to the user's itinerary is composed of all users who pass by the media information position during the time-sharing carousel period.

[0056] Therefore, in step 110, the media information positions that each traveling user passes through and the time when passing through the media information positions are determined based on the user's itinerary. For example, the media information positions covered by the travel trajectory corresponding to the user's itinerary are the media information positions passed by the user, and the time period that can correspond to the travel time is the time-sharing carousel period of the media information positions passed by the user.

[0057] In an exemplary embodiment, all users corresponding to the media information position in each time-sharing carousel period are obtained according to the user trips occurring in the split time-sharing carousel period to form a target user group for the media information position in each divided carousel period.

[0058] By analogy, for each media information position, the target user group of the media information position in each time-sharing carousel broadcast period is obtained.

[0059] For example, see also Figure 2 , Figure 2 is based on Figure 1 A flowchart of a method for obtaining a target user group for a commodity placed at a media information position in a time-sharing carousel period according to a user's itinerary for splitting the media information position into time-sharing carousel periods shown in the corresponding embodiment.

[0060] The embodiment of the present application provides a step S110 of splitting the media information position into time-sharing carousel periods, and obtaining the target user group of the merchandise placed at the media information position in the time-sharing carousel period according to the user's itinerary, including:

[0061] Step S111, corresponding to the split time-sharing carousel period, obtaining the user's travel data, the travel data being consistent with the time-sharing carousel period in terms of time;

[0062] Step S112, determining the site to which the user's travel belongs in time-sharing mode through the user's travel data in the time-sharing carousel period;

[0063] Step S113, aggregating users belonging to the site during the time-sharing carousel period to form a target user group for placing merchandise in the time-sharing carousel period mapped by the media information position of the site.

[0064] These steps are described in detail below.

[0065] First of all, it should be explained that the determination of the target user group for a media information position in each time-sharing carousel period will be based on the user travel portrait, that is, the user itinerary, so as to accurately locate the user in each time-sharing carousel period for the media information position.

[0066] The user travel portrait referred to includes but is not limited to user itineraries in travel scenarios such as subways and buses.

[0067] As the user travels, for example, on the subway, the triggering of his travel behavior will generate corresponding travel data. Exemplarily, as the entry and exit behaviors in the subway trip are triggered, the corresponding user trip is generated, and the user trip exists in the form of trip data. Therefore, it should be understood that as the user travels, he is in a time-sharing carousel period in time and is related to a media information position in space. Then the media information position and the time-sharing carousel period on the media information position are corresponding to the current user, and the current user will become the target user of the media information position in this time-sharing carousel period, and form a target user group together with other users.

[0068] Therefore, in the execution of step S111, the travel data corresponding to each time-sharing carousel period is firstly checked according to the split time-sharing carousel period, and then the media information position corresponding to the user is determined based on the travel data corresponding to the time-sharing carousel period, so as to finally determine which media information position the user corresponds to and which time-sharing carousel period on the media information position.

[0069] The trip data (OriginDestination, OD for short) indicates the user's trip, including the user identification, the site identification that triggered the travel behavior, and the triggering time of the travel behavior. For example, for the trip data generated by subway travel, the user's trip data indicates the user trip generated when the user enters and exits the station from the gate, as well as the exit station and exit gate involved in the generated user trip. The user trip includes the trip identification (trip id), user identification (user id), city identification (city id), line number, entry time, entry station code, entry gate code, exit time, exit station code, and exit gate code.

[0070] Therefore, the user's travel data in the split time-sharing carousel period can be obtained corresponding to the split time-sharing carousel period, so as to determine the target user group for each media information position according to each split time-sharing carousel period.

[0071] For each time-sharing carousel period, after obtaining the user's travel data in each time-sharing carousel period through the action of step S111, the execution of step S112 can be used to determine for each time-sharing carousel period which station the user who generated the travel itinerary belongs to in the time-sharing carousel period.

[0072] It is understandable that the site to which the user belongs refers to the site that triggers the travel behavior in the user's itinerary. For example, in a subway trip, the entry and exit sites indicated by the user's itinerary are the sites to which the user belongs in the corresponding time-sharing carousel period.

[0073] That is to say, during this time-sharing carousel period, the user passes through the site to which he belongs, and it can be determined that the user will also pass through the media information position mapped by the site.

[0074] Therefore, by taking user travel, that is, user itinerary, as the entry point, we can determine the target user group for the time-sharing delivery of goods for each media information position, and accurately locate all users passing through each media information position in time and space.

[0075] The acquisition of travel data according to the split time-sharing carousel period provides an orderly and reliable data source for determining the site to which the user's travel belongs during the time-sharing period, thereby ensuring that the site ownership determined in this way corresponds to the split time-sharing carousel period in time.

[0076] In an exemplary embodiment, the user behavior includes subway travel, so the station referred to includes an exit station, and the exit station includes several exit gates.

[0077] Correspondingly, the media information bits are located around the exits. Therefore, each exit is distributed with its own mapped media information bits, and the media playback of each media information bit is divided into several time-sharing rotation periods.

[0078] So far, please refer to Figure 3 , Figure 3 is based on Figure 2 The corresponding embodiment shows a method flow chart describing the steps of determining the site to which the user's travel belongs in time-sharing based on the user's travel data in the time-sharing carousel period.

[0079] The step S112 of determining the site to which the user's travel belongs in time-sharing according to the travel data of the user in the time-sharing carousel period provided in the embodiment of the present application includes:

[0080] Step S1121, for the user's travel data during the time-sharing carousel period, obtain the user's time-sharing exit times at each gate of the subway station gate group from the gate information according to the user's exit station and exit gate;

[0081] Step S1122, determining the exit to which the user belongs in the time-sharing carousel period according to the distribution of the number of time-sharing exits of the user at each gate group at the subway station, the exit being the exit through which the gate group can exit.

[0082] These two steps are described in detail below.

[0083] First of all, it should be explained that the travel data belongs to a time-sharing carousel period in time. Therefore, the number of time-sharing exits of users at each gate of the subway station gate group obtained from the travel data, and the exit gate to which the user belongs determined thereby, also correspond to this time-sharing carousel period in time.

[0084] The entry and exit behaviors of users triggered by 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. The user trips generated when the user enters and exits the gate are stored in the constructed user trip table.

[0085] 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.

[0086] In step S1121, the distribution of the number of time-sharing exits of each user at the station gate group gate is obtained based on the user's travel data during the time-sharing carousel period, so as to determine the user's preferred exit direction and even the exit, and then obtain the exit trajectory mapped to the preferred exit direction and even the exit, and the media information bits covered by the exit trajectory are the media information bits mapped to the exit.

[0087] The number of times a user exits a station at each gate is obtained by counting the OriginDestination (OD) data of the user. For example, the OD data of the user indicates the user trip generated when the user enters and exits the station from the gate, as well as the exit station and exit gate involved in the generated user trip.

[0088] For each user trip generated by the user, it is possible to obtain the exit from a certain gate at a certain station. Therefore, by counting all the user trips of the user, the time-sharing exit times of each gate at one station can be determined.

[0089] On this basis, combined with the existing gate information, the gate group of each gate is determined, as well as the line and city where the gate group is located. Finally, the user obtains complete information on the time-sharing exit times of each gate in the subway station gate group.

[0090] In an exemplary embodiment, the travel data exists in the form of a user travel table. Each user travel generated when the user enters or exits the station through the gate is stored in the constructed user travel table.

[0091] Among them, the fields in the user itinerary include: date, itinerary identification (trip id), user identification (user id), city identification (city id), line number, entry time, entry station code, entry gate code, exit time, exit station code and exit gate code, etc., which are not listed here one by one.

[0092] In an exemplary embodiment, gate information is collected based on site design to indicate the location of each gate. The gate information exists in the form of a gate information table, and the field information in the table includes: gate code, city identification, line number, site code, gate group number in the station, gate station number, and device type.

[0093] By counting the travel data and matching the travel data with the gate information, we can determine the time-sharing exit times of the user at a gate and the location of the gate, especially the gate group where the gate is located, so as to ultimately determine the time-sharing exit times of the user at each gate in the subway station gate group.

[0094] By counting the travel data and matching the travel data with the gate information, we can determine the time-sharing exit times of the user at a gate and the location of the gate, especially the gate group where the gate is located, so as to ultimately determine the time-sharing exit times of the user at each gate in the subway station gate group.

[0095] Through the execution of step S1121, the gates used by the user to exit the subway at each station through the gate group are recorded and counted, so as to be used to match the corresponding exit for the user at this station.

[0096] During the execution of step S111, the travel data of each user during the time-sharing carousel period is obtained. For example, the travel data is the user travel table referred to above, and the user travel and the exit gate code in the user travel are obtained from the user travel table.

[0097] For the statistics of the number of times a user exits a gate, the number of times the user exits the station at the corresponding gate is counted according to the exit gate code of each user's trip, and the gate group to which the gate belongs is determined based on the gate information, so as to finally obtain the time-sharing exit times of the user at each gate in the subway station gate group.

[0098] Exemplarily, the gate information is a gate information table. For each subway station, each gate group in the station and each gate on the gate group are collected to build a relational database to obtain the gate information table.

[0099] To further explain, the gate information table represents the location of the gate, and the gate code it contains indicates the unique code of the gate in the city. For example, the gate code can be composed of the site code, equipment type and equipment number, and the equipment number is the serial number within the gate station in the gate information table.

[0100] For example, if the site code is 0253, the device type is 01, and the device number is 07, then the gate number is 02530107.

[0101] As mentioned above, in addition to the gate code, the fields in the gate information table also include city identification, line serial number, station code, gate group serial number within the station, gate station serial number and equipment type.

[0102] The city ID is used to uniquely identify the city. In other words, each city has a unique city ID. The station code is used to uniquely identify the station in the city, so that each subway station has a unique code in the city. The gate group serial number in the station is used to identify each group of gates in the station. For example, if there are 4 rows of gates in the station, they correspond to serial numbers 1-4 respectively. The gate station serial number is the equipment number. For example, if there are 10 gates in the station, the equipment number can be a serial number 1-10.

[0103] Based on the gate information table and the user itinerary table, the user's time-sharing exit times at each gate at the subway station gate group are obtained, and the exit times describe the user's exit behavior. For users who have a user trip due to subway travel, the time-sharing exit times of the exit gates on the subway station gate group corresponding to the destination station in their user trip are obtained, and then based on this data, the user's user trip to the corresponding subway station is accurately mapped to the exit, realizing the exit location of the user during the travel process.

[0104] Through step S1121, the time-sharing exit times of each gate group at a subway station are obtained for the user. In the execution of step S1122, the station to which the user belongs is determined based on the distribution of the time-sharing exit times, so as to determine the most likely exit gate for the user's itinerary.

[0105] In step S1122, the distribution of the number of times a user exits each gate in a gate group at a subway station describes the number of times a single user exits gate 1 of the gate group, the number of times a single user exits gate 2 of the gate group, and so on, and the number of gates n_zj of the gate group (n_zj is the number of gates in the entire gate group).

[0106] For example, on the one hand, the exit gate to which the user belongs can be determined based on the distribution of the number of times the user exits the station at each problematic gate in the subway station. On the other hand, the distribution of the number of times the user exits the station at each gate in the subway station and the user portrait can be used as the characteristics of the user to predict the exit gate to which the user belongs.

[0107] See also Figure 4 , Figure 4 is based on Figure 3 The corresponding embodiment shows a method flow chart describing the steps of determining the exit gate to which the user belongs in the time-sharing carousel period according to the distribution of the number of time-sharing exits of the user at each gate group at the subway station.

[0108] The step S1122 of determining the exit to which the user belongs in the time-sharing carousel period according to the distribution of the number of time-sharing exits of the user at each gate of the subway station gate group provided in the embodiment of the present application includes:

[0109] Step S301, predicting the user's exit times at each gate on the subway station gate group and the user portrait, and obtaining the probability of the user's exit direction, where the exit direction corresponds to at least one exit;

[0110] Step S302, determining the exit to which the user belongs in the time-sharing carousel period according to the probability of the user's exit direction.

[0111] These two steps are described in detail below.

[0112] The user portrait is used to describe the user status of the user, which may be composed of constructed user tags. Exemplarily, the user portrait exists in the form of a user tag table, which includes a user ID and a number of user tags corresponding to the user ID.

[0113] The user ID will uniquely identify the subway user. User tags include but are not limited to gender, age, life stage, occupation, total number of rides in the past 7 / 14 / 30 / 90 days, total ride duration in the past 7 / 14 / 30 / 90 days, average entry time for the first user trip on a weekday in the past 7 / 14 / 30 / 90 days, average exit time for the most recent 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, high-frequency stops, total number of commercial benefits received, total number of commercial benefits write-offs, total amount of commercial benefits write-offs, average customer order value for commercial benefits write-offs, total number of travel benefits received, number of each card voucher, and frequency of card use.

[0114] It should be understood that for a user, the number of time-sharing exits at a single group of gates in a certain time range, such as a single month, may be low, and is affected by multiple factors such as actual conditions. Therefore, the distribution of the number of time-sharing exits at each gate group at a subway station and the user portrait are used as the characteristics of the user, which provides a data basis for predicting the exit to which the user belongs, and also improves the richness and scalability of the features, which is conducive to achieving accurate predictions based on existing data.

[0115] It should be noted that the exit port predicted by the user is an exit port corresponding to the gate group, and is an exit port through which the user can exit from the gate group.

[0116] One gate group corresponds to at least one exit, and the exit that a user is most likely to pass through after exiting from a gate on this gate group is the predicted exit to which the user belongs.

[0117] The prediction of the exit to which the user belongs can be achieved by obtaining the probability of the user belonging to each exit through a pre-trained classification model, and then the exit to which the user belongs is finally determined by the probability.

[0118] Exemplarily, the pre-trained model can be a binary classification model, which is characterized by the distribution of the number of times users exit the subway station at each gate group and the user portrait. Under this feature, the corresponding direction value of 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 accessed from the gate group.

[0119] 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.

[0120] Based on this, construct a training data set

[0121] Among them, each training data set D train In a single record in It is the feature of this record, which is used to describe the user status of the corresponding user.

[0122] Specifically, It includes the distribution of the number of times users exit each gate at a subway station at a certain time and the user portrait, and the user portrait can be represented by multiple user tags. is the characteristic of user i in gate group j, R m is the m-dimensional real space of the m-dimensional feature map of user i.

[0123] For example, x ij ∈R m = [date (YYYYMM), user tag 1 of user i, user tag 2 of user i, ..., user tag n of user i label , the number of time-sharing exits of user i at gate 1 of gate group j, the number of time-sharing exits of user i at gate 2 of gate group j, ..., the number of time-sharing exits of user i at gate n of gate group j zj The date (YYYYMM) represents the month, such as 202312, which means December 2023. The date feature indicates the time range corresponding to other features. label Refers to the nth label User tags, that is, n r Represents the number of users, n i represents the number of gate groups that user i faces when exiting the subway, n label Represents the number of user tags, y ij∈{0,1} is the direction value of the feature annotation in a single record of the corresponding training data set. ij ∈{0,1} represents the final exit direction of user i under the corresponding characteristics (especially the actual number of exits).

[0124] That is, y in a single record of the training data set ij is the marked direction value. For example, if user i turns left after exiting gate group j, then y ij =0, if going right, then y ij =1.

[0125] 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.

[0126] 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.

[0127] Specifically, the time-sharing exit times of the user at each gate of the gate group in the subway station are obtained through the travel data and gate information, that is, the user gate group exit data of subway user-subway station-gate group-gate-exit times is obtained. The data can be in a tabular form, that is, a table maintained according to fields such as user, subway station, gate group, gate, and time-sharing exit times, and the user gate group exit data corresponding only to the only exit is obtained therefrom. The time-sharing exit times of the user at each gate of the gate group in the subway station are obtained from the user gate group exit data corresponding only to the only exit, and the features are constructed based on this.

[0128] 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.

[0129] 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.

[0130] 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 for the user to exit the gate, it can be directly mapped to the nearest exit based on the gate group entrance and exit distance relationship. This exit is the exit to which the predicted user belongs.

[0131] 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 the gate group based on the time-sharing exit times of each gate on the subway station gate group and the user portrait, and the exit mapped by the direction is used as the exit to which the user belongs.

[0132] To further illustrate, a prediction data set is constructed based on the number of subway users exiting each gate at the subway station gate group and the user portrait. Among them, 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. All the data of the subway user will be used to construct the prediction data set, and then the exit to which the subway user belongs will be predicted based on the characteristics of the constructed prediction data set.

[0133] 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.

[0134] According to the distribution of the number of times the user exits the station at each gate group at the site, 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 exit port to which the user belongs is determined by the preferred exit direction. This exit port is based on the distribution of the number of times the user exits the station at each gate group at the site. Therefore, this exit port is the exit port to which the user belongs in the corresponding time-sharing carousel period.

[0135] To further illustrate, a prediction data set is constructed based on the number of time-sharing exits of users at each gate on the subway station gate group and the user portrait. Among them, 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 characteristics of the constructed prediction data set.

[0136] Prediction dataset D predict In each record Represents the characteristics of user i in gate group j whose exit gate has not yet been determined. As mentioned above, the characteristics describe the number of exits of user i at each gate in gate group j and the user tag. The characteristics list included is similar.

[0137] Specifically, to obtain the applicable two-class model model exit , first construct the problem loss function for the tth iteration as:

[0138]

[0139] in, is the predicted value of the ijth record in the tth iteration, f t is the tth tree, f t (x) = w q (x), q represents the tree f t The structure of w is a tree f t The weight of the leaves in the i To represent the weight of the i-th leaf, Ω(f t ) is about tree f t The complexity of the regular term, then L (t) At point f t (x i ) makes a second-order approximation to obtain:

[0140]

[0141] in,

[0142]

[0143] So far, the optimal solution to the problem is:

[0144]

[0145] Among them, q is a tree with a fixed structure, γ and λ are the first-order and second-order regularization coefficients respectively.

[0146] The optimal solution of each round based on the training data set can be iteratively converged to obtain a binary classification model exit .

[0147] Based on the obtained binary classification model exit , the prediction data set D predict Each record of Use the two-classification model model one by one exitImplement prediction and obtain the probability that the characteristics of user i in gate group j are biased in one direction, that is, the probability that the user i belongs to the exit corresponding to gate group j.

[0148] For example, if the gate group j corresponds to two exits. In other words, after exiting the gate group j, user i has 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

[0149] At this time, if there are more than two exits in one direction of gate group j, that is, the exit in this direction is not unique, then when the binary classification model predicts that user i tends to go in a direction with more than two exits after exiting gate group j, the exit that user i is most likely to pass through will be determined based on the traffic flow of each exit, and this exit is the exit to which user i belongs.

[0150] Specifically, each exit in one direction has its flow, which can be sensed by the passenger flow counter set at the exit. The flow rate corresponding to each exit is used to determine the flow ratio of each exit, and then the exit to which user i belongs is determined based on the flow ratio.

[0151] To further explain, determining the exit that user i has a high probability of passing through based on the traffic of each exit is an execution process of taking a random number in proportion to determine the belonging of user i. The proportion referred to is the proportion of the traffic of each exit.

[0152] After the binary classification model predicts the direction that user i will take after exiting gate group j, if there are multiple exits in the desired exit direction, the exit to which user i belongs will be determined based on the traffic proportion of each exit and the random number taken for user i.

[0153] For multiple exits in the outbound direction, the random number ranges mapped to each are constructed according to the traffic proportion of each exit. For example, there are three exits in the same outbound direction, and the traffic proportions of each of these three exits are 0.3, 0.2, and 0.5 respectively. Thus, the random number range mapped to each exit is constructed, that is, the random number range constructed for the first exit with a traffic proportion of 0.3 is [0, 0.3), the random number range constructed for the second exit with a traffic proportion of 0.2 is [0.3, 0.3 + 0.2), and the random number range constructed for the third exit with a traffic proportion of 0.5 is [0.3 + 0.2, 0.3 + 0.2 + 0.5).

[0154] For user i, a random number between 0 and 1 is taken, and the exit belonging to user i is determined according to the random number range in which the obtained random number falls. If the random number falls within [0, 0.3), the user itinerary of user i corresponds to the first exit; if the random number falls within the random number range [0.3, 0.3 + 0.2), the user i belongs to the second exit; if the random number falls within the random number range [0.3 + 0.2, 0.3 + 0.2 + 0.5), the user i belongs to the third exit.

[0155] At this point, as mentioned above, in the execution of step S301, features are constructed based on the number of time-sharing exits of the user at each gate on the gate group at the subway station and the user labels contained in the user portrait, and predictions are made through a pre-trained model, such as the binary classification model mentioned above, to obtain the probability of each exit direction after the user exits the gate group at the designated subway station.

[0156] There are more than one direction that a user can go out of a gate unit. For example, in many cases, a user will have one or two exit directions after exiting a gate unit, and each exit direction has an accessible exit.

[0157] After obtaining the probability of the user's exit direction, the user's travel direction after exiting the station from the gate group can be determined based on the probability in step S302, that is, the exit direction corresponding to the high probability.

[0158] The exit in the exit direction corresponding to the high probability is determined. In an exemplary embodiment, when there is only one exit in the exit direction corresponding to the high probability, the exit closest to the exit direction is determined based on the distance relationship between the exit and entrance of the gate group obtained in the exit direction corresponding to the high probability, and this exit is used as the exit to which the user belongs.

[0159] In another exemplary embodiment, there are more than two exits in the exit direction corresponding to the high probability. For example, the import and export channels in this exit direction are further branched into more than two exits. At this time, the exit to which the user belongs will be determined from the two or more exits based on the traffic proportion of each exit and the obtained random number.

[0160] As a result, there is no need to obtain the user's location, that is, there is no need to obtain location permission and then perform GPS positioning. The user's itinerary and user trajectory can also be accurately matched to the predicted exit, thereby accurately inferring the user's trajectory after exiting the station.

[0161] In another exemplary embodiment of the present application, Figure 3The step S1122 of determining the exit to which the user belongs in the time-sharing carousel period according to the distribution of the number of time-sharing exits of the user at each gate group of the subway station shown in the corresponding embodiment also includes:

[0162] Determine whether the number of time-sharing exits of the user at each gate on the subway station gate group is less than the set threshold. If it is less than the set threshold, jump to step S301. If it is not less than the threshold, then

[0163] Jump to the step of determining the exit port to which the user belongs through exit port bias statistics.

[0164] Specifically, it should be noted first that if a user frequently exits a station from a gate group, it means that the gate corresponding to the gate group in an exit direction is preferred by the user. For such subway users, the exit direction will no longer be predicted. The exit gate to which the subway user belongs can be determined only through the preference statistics of the historical exit gates, thereby reducing the computational complexity and improving execution efficiency.

[0165] The number of times a user exits a subway station gate group is used to determine whether the user exits the current subway station gate group more frequently. The number of times a user exits a subway station gate group can be obtained based on the user's travel data and gate information, and further, can be obtained from the user's gate group exit data constructed by the travel data and gate information. Of course, it is not limited to this, and can also be obtained by counting the exit data of each gate of the user's subway station gate group, which is not limited here.

[0166] Exemplarily, the set threshold may be 5. That is to say, if a user exits a gate group at a subway station no less than 5 times within a set time range, it means that an exit direction corresponding to the gate group and an 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.

[0167] To further explain, for the number of exits not less than the set threshold, the gate machine preferred by the user will be respectively counted, that is, according to the distribution of the number of exits of the user in the gate machine group, the user prefers the left half or the right half of the gate machine group. Regardless of the left half or the right half of the gate machine, it corresponds to an exit direction. The exit direction that the user will pass through after exiting the station can be determined by the gate machine to which the user prefers, and then the exit in the exit direction is the exit to which the user belongs.

[0168] At this point, it should be added that if the number of gates in a gate group is an odd number, the middle gate will belong to both the left and right half groups of gates. Therefore, for users exiting the station at the middle gate, it will be counted as the number of times the user exits the station at the left half group of gates and the number of times the user exits the station at the right half group of gates.

[0169] If the number of times a user exits a subway station gate is less than the set threshold, it means that neither the subway station nor the gate is frequently used by users. Therefore, it is necessary to construct features based on richer data, that is, the distribution of the number of times users exit each gate at the subway station gate and the user portrait as mentioned above, and then implement predictions through the pre-built model.

[0170] See also Figure 5 , Figure 5 The present invention is a flowchart of a method for describing the step of determining the exit gate to which a user belongs through exit gate bias statistics according to an exemplary embodiment.

[0171] The steps of determining the exit gate to which the user belongs through exit gate bias statistics provided in the embodiment of the present application include:

[0172] Step S401, determining the gate that the user prefers in the gate group according to the distribution statistics of the number of times the user exits the station at each gate group in the subway station;

[0173] Step S402, determining the exit located on the same side as the exit to which the user belongs during the time-sharing carousel period according to the location of the gate.

[0174] The following is a detailed description of these two steps.

[0175] Among them, for a gate group, the time-sharing exit frequency distribution of a user at each gate in the gate group is statistically implemented to determine whether the user prefers to exit from the left half of the gates in the gate group or the right half of the gate group.

[0176] According to the statistical determination of the user's preference at the gate group, the exit direction and exit gate can be determined, and then the exit gate on the same side is the user's frequently used exit gate. This exit gate is used as the user's belonging exit gate, and the user's itinerary and travel trajectory are matched with this exit gate.

[0177] After determining the site to which the user belongs during the time-sharing carousel period through the execution of the aforementioned step S112, the users belonging to the site during the time-sharing carousel period can be aggregated through the execution of step S113, that is, users belonging to the same site are aggregated together, and the aggregated users form the target user group to which the media information of the site is mapped during the time-sharing carousel period.

[0178] The user aggregation referred to is to determine the subway user group corresponding to the location at the exit, and to describe and characterize the aggregated subway user group through the user profiles of the aggregated subway users.

[0179] The user portrait of the aggregated user will be assigned to the site, as well as the media information bit mapped to the site's exit, to serve as the portrait of the media information bit in the corresponding time-sharing carousel period.

[0180] After the target user groups corresponding to the media information positions in the split time-sharing carousel periods are determined in step S110, the expected click values ​​of the products to be placed in the media information positions in each time-sharing carousel period can be determined based on the target user groups in step S120.

[0181] That is to say, for a product, in order to improve the conversion of product placement, it is necessary to determine the recommended media information positions and time-sharing carousel periods for the product through the click expectation estimates of each media information position and each media information position in each time-sharing carousel period.

[0182] The expected click value refers to the degree of attention a product receives from users passing through a media information position when it is placed in a time-sharing carousel period. The expected click value of a product placed in a media information position in a time-sharing carousel period is used to measure the degree to which users passing through the media information position are attracted by the media content of the product and the product itself if the media content of the product is placed in the media information position in a time-sharing carousel period.

[0183] It should be understood that the higher the expected click value of the product placed in the media information position, the more suitable the product is for placement in the media information position and the corresponding time-sharing carousel period, and the higher the possibility that users passing by will be attracted by the product.

[0184] The click expectation of a target user group on a product at a specific media information position and a specific time-sharing carousel period corresponds to the click expectation of all users in the target user group on the product, which is calculated through a pre-trained click rate prediction model.

[0185] Exemplarily, the click rate of the products by users in the target user group is estimated through a click rate prediction model, and the click rate of the products by each user in the target user group is obtained.

[0186] The goods referred to are goods to be placed on the media information position. Exemplarily, the goods include goods in the recommended media information position, such as when a media information position is recommended to a product for corresponding media placement in a certain time-sharing carousel period on the media information position, the product is the goods referred to in this application.

[0187] It should be noted that the click expectation value estimation is performed for a time-sharing carousel period on a media information position and a product to all users in the target user group corresponding to the media information position in this time-sharing carousel period.

[0188] The click expectation estimation includes the click rate estimation between users and products, and the execution process of cumulative weighted summation of click rates of all users in the target user group, so as to finally obtain the click expectation value of the product when it is placed in the time-sharing carousel period of the media information position.

[0189] In an exemplary embodiment, a click rate prediction model for estimating the click rate between users and products is trained through the click records of users on the exposed products on the travel application.

[0190] 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.

[0191] Thus, the training data set is constructed

[0192] Among them, the constructed training data set D train A single record in y ij ,Right now The user portrait is composed of multiple parts of data, and the data sources include but are not limited to the embedded data on travel applications.

[0193] Specifically,

[0194]

[0195] corresponds to the user's own travel data, and It corresponds to third-party supplementary data. For example,

[0196] For product features, exemplary,

[0197] y ij ∈{0,1}, when the value is 0, it means that no click event occurs after product j is exposed to user i; when the value is 1, it means that a click event occurs after product j is exposed to user i.

[0198] As a result, travel applications have been dFor each user i in the day, all n i Product generation records to form the training data set for the click rate prediction model.

[0199] Correspondingly, the click-through rate between users and products is estimated 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 information position, the prediction data set is constructed through the user portrait and the product features of the product. Each record of the prediction data set is the constructed user-product pair.

[0200] 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.

[0201] Each record in the prediction data set represents the recommendation of product j to all users corresponding to a media information position in a time-sharing carousel period, i.e., users 1, 2, …, n user Each record will be used as the input of the click-through rate prediction model to obtain the click-through rate of each user on the product corresponding to the media information position in a time-sharing carousel period. Similarly, the click-through rate of all users on the product corresponding to the media information position in a time-sharing carousel period is obtained, and finally the expected value of clicks on the product in the media information position in a time-sharing carousel period is obtained.

[0202] In another exemplary embodiment, for the click rate prediction model, the problem loss function constructed at the t-th iteration is:

[0203]

[0204] in, is the predicted value of the ijth record in round t, f t is the tth tree, f t (x) = w q (x) represents the tree f t The structure of w is a tree f t The weight of the leaf, w i is the weight of the i-th leaf, Ω(f t ) is about tree f t The complexity of the regular term, then L (t) At the point The second-order approximation is:

[0205]

[0206] in,

[0207] The optimal solution is:

[0208]

[0209] Among them, q is a tree with a fixed structure, γ and λ are the first-order regularization coefficient and the second-order regularization coefficient, respectively.

[0210] Click rate prediction model recommend The optimal solution of each round is obtained through iterative convergence based on the training data set.

[0211] The constructed prediction data set D predict Every record of The binary classification model, i.e., the click rate prediction model, is used to predict the click rate of the product for all users corresponding to the media information position in a time-sharing carousel period. Then, the weighted sum of the click rates is calculated based on the number of times the user passes by the media information position in the time-sharing carousel period to obtain the expected click value of the product for the target user group corresponding to the media information position in the time-sharing carousel period. Among them, n user It is the number of users in the target user group corresponding to the media information position in the time-sharing carousel period. The weight of the weighted sum is actually the number of times each user in the target group passes through the media information position during the time-sharing carousel period, and also the number of times the user exits the station at the corresponding exit during the i-th time-sharing carousel period, that is, the number of time-sharing exits.

[0212] In summary, in an exemplary embodiment, the specific execution process of step S120 is as follows: Figure 6 As shown, Figure 6 is based on Figure 1 The corresponding embodiment shows a method flow chart describing the steps of estimating the expected click value of the product placed on the media information position for the target user group and obtaining the expected click value of the product at the media information position during the time-sharing carousel period.

[0213] The step S120 of estimating the expected clicks of the products placed on the media information position for the target user group and obtaining the expected clicks of the products on the media information position during the time-sharing carousel period includes:

[0214] Step S121, for each product, the click rate of each user on the product is estimated for the target user group in the media information position in the time-sharing carousel period;

[0215] Step S122, performing a weighted summation of the user's estimated click rate on the product according to the number of times the user visits the media information in the time-sharing carousel period, and obtaining the media information position in the time-sharing carousel period.

[0216] The target user group corresponding to a time-sharing carousel period is the media information position, that is, all users in the target user group. Each user and the product form a user-product pair, which is used to estimate the click rate of the user on the product. The click rate is used to represent the attractiveness of the product to the user. The higher the click rate, the more attractive the product is to the user. Conversely, the lower the click rate, the less attractive the product is to the user.

[0217] For the user-product pair consisting of a user and a product, the click rate of the user for the product is estimated by the click rate estimation model as described above, and so on, the click rate of the product for all users in the target user group corresponding to a media information position in a time-sharing carousel period is obtained.

[0218] That is to say, all users corresponding to the media information position in the time-sharing carousel period have corresponding click-through rates for each product, which can numerically describe the degree of attractiveness of the product to all users passing by, and then evaluate whether to recommend this media information position and the time-sharing carousel period to the product for media delivery, or evaluate the product that is most suitable for delivery in this media information position and the time-sharing carousel period on it.

[0219] After obtaining the click rate of each user on the product, the expected click value of the product corresponding to the media information position and the time-sharing carousel period can be obtained through weighted sum operation.

[0220] At this point, for step S121, please refer to Figure 7 , Figure 7 is based on Figure 6 The corresponding embodiment shows a method flow chart describing the steps of estimating the click rate of each user for each product in the target user group in the time-sharing carousel period of the media information.

[0221] The step S121 of estimating the click rate of each user for each product in the target user group in the time-sharing carousel period of the media information provided in the embodiment of the present application includes:

[0222] Step S1211, for the target user group whose media information is in the time-sharing carousel period, construct a user-product pair through the user portrait of each user and the product features corresponding to the product;

[0223] Step S1212, by predicting the product click rate of user-product pairs, the click rate of each user in the target user group whose media information is located in the time-sharing carousel period for the product is obtained.

[0224] First of all, it should be noted 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 products.

[0225] The media information positions and time-sharing carousel periods used to evaluate the click-through rate of products belong to a specific site. Therefore, the user itinerary 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.

[0226] 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.

[0227] 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.

[0228] 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.

[0229] 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;

[0230] 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;

[0231] 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, corresponding number of times the top 10 product categories were viewed in the past 1 / 3 / 7 / 14 / 30 / 90 days, average price of the top 10 product categories viewed in the past 1 / 3 / 7 / 14 / 30 / 90 days).

[0232] It should be understood that the user's own travel data will be adapted to the travel application as the marketing recommendation output of the media information position and its time-sharing carousel period to obtain the corresponding user portrait.

[0233] 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.

[0234] 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.

[0235] For each user corresponding to the media information position and time-sharing carousel period, a user portrait 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.

[0236] 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.

[0237] The commodity features of a commodity are used to describe the features of the commodity. Exemplarily, the commodity features of a commodity include descriptive features, statistical features, statistical generalized features, etc. of the commodity.

[0238] Specifically, the product characteristics of a product include 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, and the number of purchase conversions of the third-level category to which the product belongs in the past 1 / 3 / 7 / 14 / 30.

[0239] For each user in the media information position and time-sharing carousel period, a user-product pair is constructed based on the user portrait and the product features, thereby predicting the user's click rate on the product based on the user-product pair.

[0240] It should be understood that media information positions are physical resources that actually exist offline. Users are attracted by the media content on which products are exposed, which is analogous to clicks on products exposed on the Internet. Therefore, the degree of attraction of products exposed offline through media information positions during time-sharing carousel periods can be accurately measured by the click rate of users on products.

[0241] For the recommendation of a media information position and its time-sharing carousel period, the expected click value of the product corresponding to the media information position and the carousel period is obtained by executing step S120. For multiple products competing for the same media information position and time-sharing carousel period, the expected click value of each product on the media information position and time-sharing carousel period can also be used to determine the media information position and time-sharing carousel period that can obtain the highest expected click, that is, the product that is most likely to be attracted by passing users, so that the media information position and time-sharing carousel period are recommended for this product.

[0242] In summary, through the execution of step S130, for each media information position and its time-sharing carousel period, according to the expected click value of the product on the media information position and its time-sharing carousel period, the media information position and its time-sharing carousel period are recommended for the product.

[0243] In step S130, based on the click expectations of the products on the media information positions and their time-sharing carousel periods, the media information positions and their time-sharing carousel periods of the products are recommended, so that the media information positions and their time-sharing carousel periods currently being recommended for marketing can be matched with the most suitable products.

[0244] In an exemplary embodiment, the execution process of step S130 includes:

[0245] Compare the expected click values ​​of the product in each time-sharing carousel period of each media information position, and recommend the media information position with the highest expected click value and the time-sharing carousel period of the product in the media information position to the product.

[0246] That is, according to the expected click values ​​of the products in the media information positions and time-sharing carousel periods, the media information positions and time-sharing carousel periods with the highest expected click values ​​are directly selected for the products.

[0247] For a product, each idle media information position and the idle time-sharing carousel period on it are objects that can be considered for implementing the corresponding media content delivery. Therefore, by executing the aforementioned steps, the expected click value of the product in each media information position and time-sharing carousel period is obtained. At this time, the expected click values ​​of the products are compared, and the media information position and time-sharing carousel period with the highest expected click value are recommended to the product.

[0248] This is a product that selects a media information position and a time-sharing carousel period with a high click expectation value from multiple media information positions and time-sharing carousel periods, and then recommends the selected media information position and time-sharing carousel period with a high click expectation value to the product.

[0249] In the marketing recommendation of media information positions and time-sharing carousel periods for a product, the expected click values ​​of the product in each media information position and time-sharing carousel period are estimated for all idle media information positions and time-sharing carousel periods respectively, thereby obtaining the expected click value of the product in each media information position and time-sharing carousel period.

[0250] This is a recommendation of a media information position and a time-sharing carousel time period implemented for a product. For a media information position and a time-sharing carousel time period, if it is recommended to more than two products, there will be a situation where the same media information position and the same time-sharing carousel time period thereon are competed by more than two products. At this time, after step S130, the method as described above further includes:

[0251] For two or more products in competing media information positions, obtain the click value of each product;

[0252] The conversion value of each product is calculated by the click value and the expected click value of the media information position of the product in the time-segmented carousel period in which the product competes;

[0253] The time-sharing rotation period of the media information position is recommended for the delivery of high-conversion-value products.

[0254] Among them, when there are more than two products competing for a media information position and a time-sharing carousel period on it, it is necessary to consider their respective conversion values ​​based on the expected click value of each product in the media information position and the time-sharing carousel period, so as to determine to which intended product the media information position and the time-sharing carousel period can be recommended.

[0255] For two or more products competing for the same media information position and time-sharing carousel period, their corresponding click values ​​are obtained. The click value is related to the value of the product itself. For example, the click value of a product represents the revenue brought to the product by users attracted by the exposed product in the past. Specifically, the click value of a product can be an evaluation of the product, or it can be the contribution rate of the exposed product in the media information position and time-sharing carousel period to the transaction. Therefore, the click value of a product can be an evaluation of the product itself, or it can be the corresponding click value obtained for the product in different media information positions and time-sharing carousel periods. It is not limited here and will be determined according to the needs of specific operations.

[0256] When more than two products compete for a media information position and a time-sharing carousel period, that is, when more than two products have calculated the expected click value for the media information position and the time-sharing carousel period, the conversion value of each product in the media information position and the time-sharing carousel period is obtained by obtaining the product between the click value and the click expectation.

[0257] The conversion value of a product in a media information position and a time-sharing carousel period takes into account the degree to which the product's exposure in this media information position and time-sharing carousel period has attracted past users, and quantifies the value that can be converted by its exposure in the media information position and time-sharing carousel period. Therefore, the conversion value of a product in a media information position and a time-sharing carousel period can accurately determine the most suitable product for conversion in the media information position and time-sharing carousel period, so that the marketing recommendations in the media information position and time-sharing carousel period can give priority to the delivery of products with the highest conversion value.

[0258] For example, a media information position and time-sharing carousel period are high-quality media, which has multiple products competing, and the click value of each product is obtained. j , and then combine the expected click value of the product in the media information position and time-sharing carousel period Calculate the conversion value of the product in the media information position and time-sharing carousel period, as shown in the following formula:

[0259]

[0260] At this point, the product with the highest conversion value is determined, and the media information position and time-sharing carousel period are recommended for the product.

[0261] At this point, it should be supplemented that, in the specific example, the distribution of the number of times a user exits the station in a gate group at a station is obtained through the user itinerary table and the gate information table. In the case where a user exits the station by scanning the QR code of a travel application, the distribution of the number of times a user exits the station in a gate group at a station describes the number of times a user scans the code at each gate during a time-sharing carousel period, that is, the user gate group scan code table is obtained.

[0262] 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.

[0263] 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.

[0264] 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.

[0265] For each exit, the media information bits mapped by the exit are recorded to construct and maintain a media exit relationship table.

[0266] By mapping the exit to the media information position, the media information position that the user will pass through when leaving the station from an exit can be obtained. In other words, all users who pass through the media information position in a time-sharing carousel period are all users corresponding to the media information position, and thus constitute the target user group.

[0267] For each time-sharing carousel period, the user portraits of all users corresponding to the media information position are assigned to the media information position, and the label of the media information position is further enriched to obtain a media portrait table.

[0268] At this point, the most suitable media information position and time-sharing carousel period for the product can be determined based on the media portrait table, and finally marketing recommendations for the media information position can be achieved.

[0269] It should be further explained that all users corresponding to the media information position can determine the commonly used exit gates through the statistics of the user's preferred exit direction in the user gate group code scanning table, and then use this to determine all users corresponding to the media information position.

[0270] 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.

[0271] 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.

[0272] 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.

[0273] Based on this, construct a training data set

[0274] Among them, each training data set D train In a single record in It is the feature of this record, which is used to describe the user status of the corresponding user.

[0275] 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 the characteristic of user i in gate group j, R m is the m-dimensional feature of user i.

[0276] For example, x ij ∈R m = [date (YYYYMM), user tag 1 of user i, user tag 2 of user i, ..., user tag n of user i label , the number of exits of user i at gate 1 of gate group j, the number of exits of user i at gate 2 of gate group j, ..., the number of exits of user i at gate n of gate group j zj The date (YYYYMM) represents the month, such as 202312, which means December 2023. The date feature indicates the time range corresponding to other features. label Refers to the nth label User tags, that is, n r Represents the number of users, n i represents the number of gate groups that user i faces when exiting the station during travel, n label Represents the number of user tags, y ij ∈{0,1} is the direction value of the feature annotation in a single record of the corresponding training data set. ij ∈{0,1} represents the final exit direction of user i under the corresponding characteristics (especially the actual number of exits).

[0277] That is, y in a single record of the training data set ij is the marked direction value. For example, if user i turns left after exiting gate group j, then y ij =0, if going right, then y ij =1.

[0278] 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.

[0279] 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.

[0280] 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.

[0281] 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.

[0282] 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.

[0283] 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.

[0284] 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.

[0285] 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. Among them, 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 characteristics of the constructed prediction data set.

[0286] Prediction dataset D predict In each record Represents the characteristics of user i in gate group j whose exit gate has not yet been determined. As mentioned above, the characteristics describe the number of exits of user i at each gate in gate group j and the user tag. The characteristics list included is similar.

[0287] Based on the obtained binary classification model, the prediction data set D predict Each record of Use the binary classification model to implement predictions one by one, and get the probability that the characteristics of user i in gate group j are biased in one direction, that is, belonging to an exit corresponding to gate group j.

[0288] For example, if the gate group j corresponds to two exits. In other words, after exiting the gate group j, user i has 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

[0289] In addition, if there are more than two exits in one direction of gate group j, that is, the exit in this direction is not unique, then when the binary classification model predicts that user i tends to go in a direction with more than two exits after exiting gate group j, the exit that user i is most likely to pass through will be determined based on the traffic flow of each exit, and this exit is the exit to which user i belongs.

[0290] Specifically, each exit in one direction has its flow, which can be sensed by the passenger flow counter set at the exit. The flow rate corresponding to each exit is used to determine the flow ratio of each exit, and then the exit to which user i belongs is determined based on the flow ratio.

[0291] 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.

[0292] Based on the exit to which the user belongs, the target user group is determined for the media information positions around the exit. The user portrait of the target user group is then used as the media portrait to estimate the expected click value and calculate the conversion value for each media information position and its time-sharing carousel period, and obtain a media product conversion value table, which is ultimately used to execute the recommendation of the media information position.

[0293] 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 product features of the products are obtained from the constructed product label table, which will not be repeated here.

[0294] 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 methods 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, and includes 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 methods of the present application.

[0295] 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.

[0296] 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.

[0297] The program product may use 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 of the above. 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 of the above.

[0298] 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.

[0299] 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.

[0300] 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 cases involving 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., through the Internet using an Internet service provider).

[0301] 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.

[0302] 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.

[0303] 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 methods 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, and includes 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 methods of the present application.

[0304] 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 time-sharing recommendation method for media information bits, characterized in that: The method comprises: For the time-sharing carousel period split into the media information position, a target user group for placing the product at the media information position in the time-sharing carousel period is obtained according to the user's itinerary; estimating the expected clicks of the product placed on the media information position for the target user group, and obtaining the expected click value of the product at the media information position during the time-sharing carousel period; According to the expected click values ​​of the commodity at each media information position corresponding to each time-sharing carousel period, the media information position with high expected click value and the time-sharing carousel period at the media information position are recommended for the commodity.

2. The method according to claim 1, characterized in that The time-sharing carousel period for splitting the media information position, and obtaining the target user group for the product placed at the media information position during the time-sharing carousel period according to the user's itinerary, includes: Corresponding to the split time-sharing carousel period, obtaining the user's travel data, wherein the travel data is consistent with the time-sharing carousel period in terms of time; Determine the site to which the user's travel belongs in time-sharing according to the travel data of the user in the time-sharing carousel period; The users belonging to the site in the time-sharing carousel period are aggregated to form a target user group for placing merchandise in the time-sharing carousel period by media information positions mapped by the site.

3. The method according to claim 1, characterized in that The step of estimating the expected click value of the product placed on the media information position for the target user group and obtaining the expected click value of the product at the media information position during the time-sharing carousel period includes: For the user's travel data during the time-sharing carousel period, the user's time-sharing exit times at each gate of the subway station gate group are obtained from the gate information according to the user's exit station and exit gate; The exit to which the user belongs during the time-sharing carousel period is determined based on the distribution of the number of times the user exits the station at each gate group at the subway station. The exit is the exit that can be used by the gate group to exit the station.

4. The method according to claim 3, characterized in that For each product, the click rate of each user on the product is estimated in the target user group in the media information position in the time-sharing carousel period, including: For the target user group whose media information is located in the time-sharing carousel period, a user-product pair is constructed through the user portrait of each user and the product features corresponding to the product; By predicting the product click rate of the user-product pair, the click rate of the product by each user in the target user group of the media information position in the time-sharing carousel period is obtained.

5. The method according to claim 4, 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.

6. The method according to claim 1, characterized in that The method of recommending a media information position with a high click expectation value and a time-sharing carousel period at the media information position according to the click expectation value of the product at each media information position corresponding to each time-sharing carousel period includes: Compare the expected click values ​​of the product in each time-sharing carousel period of each media information position, and recommend the media information position with the highest expected click value and the time-sharing carousel period of the product in the media information position to the product.

7. The method according to claim 1, characterized in that The media information position in the time-sharing carousel period is competed for by more than two products; The method further comprises: recommending a media information position with a high click expectation value for the product according to the click expectation value of each media information position corresponding to each time-sharing carousel period, and after the time-sharing carousel period of the media information position. For two or more products competing for the media information position, respectively obtain the click value of the products; Calculate the conversion value of each product through the click value and the expected click value of the media information position of the product in the time-divided carousel period that the product competes for; The time-sharing carousel period of the media information position is recommended for the delivery of high-conversion-value commodities.

8. A time-sharing recommendation system for media information bits, 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 7.

9. 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 7 are implemented.

10. 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 7.

Images