Promotion Information Display Method, Device, Electronic Device, and Storage Medium

Abstract

An embodiment of the present invention discloses a method, device, electronic device, and storage medium for promoting information display, including: collecting historical display information of a terminal; calculating the probability of the terminal displaying promotion information in multiple future time periods according to the historical display information; predicting the stop broadcast times corresponding to multiple promotion information in a database, and determining at least one promotion information with the highest revenue in each future time period in the database as candidate promotion information based on the predicted stop broadcast times, generating an expected revenue corresponding to each future time period based on the probability of displaying promotion information in each future time period and the revenue of the candidate promotion information, selecting at least one promotion information with the highest expected revenue in multiple future time periods, and sending the selected at least one promotion information to the terminal so that the terminal can display the selected promotion information to the user. This solution can not only avoid waste of network resources but also improve the accuracy of content distribution (i.e., promotion information display).

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and particularly to a method, device, electronic device and storage medium for promoting information display. Background Art

[0002] With the development of computer technology, more and more promotion information is presented to users in an online form. For example, during the process of using an application, the terminal will display a splash advertisement (promotion information) of the application to the user. For example, an advertisement for promoting a certain product or thing. Different from the promotion information displayed by real-time request, for the splash advertisement of the application, it is necessary to cache the promotion information locally in advance. When the user opens the application, a real-time request is sent to the background service to determine whether the locally loaded promotion information can be played. However, if the total delivery volume of the pre-loaded promotion information has been consumed when the user opens the application, resulting in the splash advertisement displayed by the terminal not being the pre-loaded promotion information, which will lead to a waste of network resources and reduce the accuracy of promotion information display. Summary of the Invention

[0003] Embodiments of the present invention provide a method, device, electronic device and storage medium for promoting information display, which can not only avoid wasting network resources, but also improve the accuracy of promoting information display.

[0004] Embodiments of the present invention provide a method for promoting information display, including:

[0005] Collecting historical display information of the terminal, where the historical display information includes time information of the terminal displaying each historical promotion information, and the historical promotion information is promotion information that the terminal has displayed within a preset time period in the past based on the current moment;

[0006] Calculating the probability of the terminal displaying promotion information in multiple future time periods according to the historical display information;

[0007] Predicting the stop broadcast time corresponding to multiple promotion information in the database, and determining at least one promotion information with the highest revenue in each future time period in the database as candidate promotion information according to the predicted stop broadcast time, where the stop broadcast time of the candidate promotion information is later than the corresponding future time period;

[0008] Generating an expected revenue corresponding to each future time period based on the probability of displaying promotion information in each future time period and the revenue of the candidate promotion information;

[0009] Select at least one promotional message with the highest expected revenue in multiple future time periods, and send the selected at least one promotional message to the terminal, so that the terminal displays the selected at least one promotional message to the user when a promotional message display request is triggered.

[0010] Correspondingly, an embodiment of the present invention further provides a promotional message display device, including:

[0011] An acquisition module, configured to acquire historical display information of the terminal, where the historical display information includes time information of the terminal displaying each historical promotional message, and the historical promotional message is a promotional message that the terminal has displayed in a preset time period in the past with the current moment as a reference;

[0012] A calculation module, configured to calculate the probability of the terminal displaying promotional messages in multiple future preset time periods according to the historical display information;

[0013] A prediction module, configured to predict the stop broadcast times corresponding to multiple promotional messages in the database, and determine at least one promotional message with the highest revenue in each future time period in the database as candidate promotional messages according to the predicted stop broadcast times;

[0014] A determination module, configured to determine at least one promotional message with the highest revenue in each future time period in the database as candidate promotional messages, and the stop broadcast time of the candidate promotional messages is later than the corresponding future time period;

[0015] A generation module, configured to generate the expected revenue corresponding to each future time period based on the probability of displaying promotional messages in each future time period and the revenue of the candidate promotional messages;

[0016] A display module, configured to select at least one promotional message with the highest expected revenue in multiple future time periods, and send the selected at least one promotional message to the terminal, so that the terminal displays the selected at least one promotional message to the user when a promotional message display request is triggered.

[0017] Optionally, in some embodiments of the present invention, the prediction module includes:

[0018] An acquisition sub-module, which acquires the placement strategies and total placement amounts corresponding to multiple promotional messages in the database;

[0019] A prediction sub-module, configured to predict the stop broadcast times corresponding to multiple promotional messages in the database based on the acquired placement strategies and total placement amounts.

[0020] Optionally, in some embodiments of the present invention, the prediction sub-module includes:

[0021] A calculation unit for calculating the consumption speed of each promotion message based on the obtained delivery strategy and total delivery volume;

[0022] A prediction unit for predicting the stop broadcast time corresponding to multiple promotion messages in the database according to the consumption speed of each promotion message.

[0023] Optionally, in some embodiments of the present invention, the calculation unit includes:

[0024] An addition subunit for adding candidate promotion messages with a display volume greater than a preset display volume to the same set to obtain a first promotion message set;

[0025] A calculation subunit for calculating the consumption speed of each candidate promotion message in the first promotion message set according to the total delivery volume and delivery strategy of each promotion message in the first promotion message set.

[0026] Optionally, in some embodiments of the present invention, the calculation subunit is specifically configured to:

[0027] Obtain the number of display times corresponding to each promotion message in the first promotion message set in each past time period;

[0028] Based on the obtained number of display times, determine the display weight corresponding to each promotion message in the first promotion message set in each past time period;

[0029] According to the determined display weight, the total delivery volume of each promotion message in the first promotion message set, and the delivery strategy, calculate the consumption speed of each promotion message in the first promotion message set.

[0030] Optionally, in some embodiments of the present invention, the calculation unit is further specifically configured to:

[0031] Add promotion messages with a display volume less than or equal to the preset display volume to the same set to obtain a second promotion message set;

[0032] Remove the second promotion message set from the database to obtain a retained promotion message set;

[0033] Calculate the average consumption speed corresponding to the retained promotion message set, and determine the average consumption speed as the consumption speed of each promotion message in the second promotion message set.

[0034] Optionally, in some embodiments of the present invention, the prediction unit is specifically configured to:

[0035] Predict the total consumption volume corresponding to each promotion message in each future time period according to the consumption speed of each promotion message;

[0036] Based on the total consumption volume, determine the stop broadcast time corresponding to multiple promotion messages.

[0037] Optionally, in some embodiments of the present invention, the prediction module is specifically configured to:

[0038] Determine the promotion information with a delivery duration less than or equal to the first preset delivery duration among the multiple promotion information as the third promotion information;

[0039] Obtain the promotion information at the same promotion position as the third promotion information to obtain the fourth promotion information, and the delivery duration of the fourth promotion information is greater than the second preset delivery duration;

[0040] Collect the consumption speed of the fourth promotion information;

[0041] Calculate the stop broadcast time of the third promotion information according to the consumption speed of the fourth promotion information and the total delivery amount of the third promotion information.

[0042] Optionally, in some embodiments of the present invention, the calculation module is specifically configured to:

[0043] Obtain the display times of each historical promotion information displayed by the terminal in multiple historical time periods according to the time information of the terminal displaying the historical promotion information;

[0044] Determine the probability of the terminal displaying the promotion information in a future preset time period according to the display times of the historical promotion information displayed by the terminal in multiple historical time periods.

[0045] Optionally, in some embodiments of the present invention, the generation module is specifically configured to:

[0046] Determine the probability of the candidate promotion information being displayed in the corresponding future time period based on the probability of the promotion information being displayed in each future time period;

[0047] Calculate the product of the probability of the candidate promotion information being displayed in the corresponding future time period and the revenue of the candidate promotion information to generate the expected revenue corresponding to each future time period.

[0048] After the historical display information of the acquisition terminal is collected, the historical browsing information includes the time information of the terminal displaying each historical promotion information. The historical promotion information is the promotion information displayed by the terminal within a preset time period in the past based on the current moment. According to the historical display information, calculate the probability of the terminal displaying promotion information in multiple future time periods. Then, predict the stop broadcast times corresponding to multiple promotion information in the prediction database, and based on the predicted stop broadcast times, determine at least one promotion information with the highest revenue in each future time period in the database as candidate promotion information. The stop broadcast time of the candidate promotion information is later than the corresponding future time period. Next, generate the expected revenue corresponding to each future time period based on the probability of displaying promotion information in each future time period and the revenue of the candidate promotion information. Finally, select the promotion information with the highest expected revenue in the future time period from the database, and send the selected promotion information to the terminal so that the terminal can display the selected promotion information to the user when a promotion information display request is triggered. Therefore, this solution can not only avoid waste of network resources, but also improve the accuracy of promotion information display. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative efforts.

[0050] Figure 1a is a schematic diagram of the scenario of the promotion information display method provided by the embodiment of the present invention;

[0051] Figure 1b is an optional structural schematic diagram of the distributed system applied to the blockchain system provided by the embodiment of the present invention;

[0052] Figure 1c is an optional schematic diagram of the block structure (Block Structure) provided by the embodiment of the present invention;

[0053] Figure 1d is a schematic flowchart of the promotion information display method provided by the embodiment of the present invention;

[0054] Figure 2a is another schematic flowchart of the promotion information display method provided by the embodiment of the present invention;

[0055] Figure 2b is another schematic diagram of the scenario of the promotion information display method provided by the embodiment of the present invention;

[0056] Figure 2c It is an interaction flowchart of the promotion information display method provided by an embodiment of the present invention;

[0057] Figure 3 It is a schematic structural diagram of the promotion information display device provided by an embodiment of the present invention;

[0058] Figure 4 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. Specific embodiments

[0059] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention.

[0060] An embodiment of the present invention provides a promotion information display method, device, electronic device and storage medium.

[0061] Among them, the promotion information display device can be specifically integrated in a server or a terminal. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, as well as big data and artificial intelligence platforms. The terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited thereto. The terminal and the server can be directly or indirectly connected through wired or wireless communication methods, and this application does not make any restrictions here.

[0062] For example, please refer to Figure 1a, the present invention provides a promotion information display device (hereinafter referred to as the display device), which is integrated in the server. After the server collects the historical browsing information of the terminal, the historical browsing information includes the time information of each historical promotion information displayed by the terminal. The historical promotion information is the promotion information that the terminal has displayed to the user within a preset time period in the past based on the current moment. The server calculates the probability of the terminal displaying promotion information in multiple future time periods according to the historical display information, where the multiple future time periods are all later than the current moment, and each future time period corresponds to one of the multiple probabilities. Then, the server predicts the stop broadcast time corresponding to multiple promotion information in the database, and according to the predicted stop broadcast time, determines at least one promotion information with the highest revenue in each future time period in the database as the candidate promotion information. The stop broadcast time of the candidate promotion information is later than the corresponding future time period, and the revenue of the candidate promotion information is the highest among multiple promotion information in the corresponding time period. For example, the stop broadcast times of promotion information a and promotion information b are May 9th, and their revenues on May 8th are H1 and H2 respectively, where H1 is greater than H2, and H1 is the highest revenue value among all promotion information on that day. Therefore, promotion information a is determined as the candidate promotion information for May 8th. Then, the server generates the expected revenue corresponding to each future time period based on the probability of displaying promotion information in each future time period and the revenue of the candidate promotion information. Finally, the server selects the promotion information with the highest expected revenue in the future time period from the database and sends the selected promotion information to the terminal so that the terminal can display the selected promotion information to the user when triggering the promotion information display request. In this embodiment, by calculating the probability of the terminal displaying promotion information in multiple future time periods, and at the same time, according to the predicted stop broadcast time, determining at least one promotion information with the highest revenue in each future time period in the database, and finally, generating the expected revenue corresponding to each future time period based on the probability of displaying promotion information in each future time period and the revenue of the candidate promotion information, it avoids the problem that the total amount of pre-loaded promotion information has been consumed, resulting in the splash screen advertisement displayed by the terminal not being the pre-loaded promotion information. It can not only avoid the waste of network resources, but also improve the accuracy of promotion information display. At the same time, displaying the promotion information with the maximum expected revenue to the user can also improve the utilization rate of the promotion information inventory.

[0063] It should be noted that the system involved in the embodiment of the present invention can be a distributed system formed by connecting a client and multiple nodes (any form of computing device accessing the network, such as a server, a user terminal) through network communication.

[0064] Taking the distributed system as a blockchain system as an example, see Figure 1b , Figure 1bFIG. 0 is an optional schematic diagram of the distributed system provided by the embodiments of the present invention applied to a blockchain system, formed by multiple nodes (any form of computing device accessing the network, such as a server, a user terminal) and a client. A peer-to-peer (P2P) network is formed among the nodes. The P2P protocol is an application layer protocol running on top of the Transmission Control Protocol (TCP). In the distributed system, any machine such as a server or a terminal can join and become a node. A node includes a hardware layer, an intermediate layer, an operating system layer, and an application layer.

[0065] Refer to Figure 1b the functions of each node in the blockchain system shown, and the functions involved include:

[0066] 1) Routing, a basic function of a node, used to support communication between nodes.

[0067] In addition to the routing function, a node may also have the following functions:

[0068] 2) Application, which is used to be deployed in the blockchain, implement specific services according to actual business requirements, record the data related to the implemented functions to form record data, carry a digital signature in the record data to indicate the source of the task data, and send the record data to other nodes in the blockchain system. When other nodes verify the source and integrity of the record data successfully, they add the record data to a temporary block.

[0069] 3) Blockchain, including a series of blocks (Blocks) that are sequentially connected in the order of generation. Once a new block is added to the blockchain, it will not be removed again. The block records the record data submitted by the nodes in the blockchain system. For example, the block records the promotion information browsed by users in a preset past time period.

[0070] Refer to Figure 1c , Figure 1c FIG. 24 is an optional schematic diagram of the block structure provided by the embodiments of the present invention. Each block includes the hash value of the transaction records stored in this block (the hash value of this block) and the hash value of the previous block. The blocks are connected through the hash values to form a blockchain. In addition, the block may also include information such as a timestamp when the block is generated. A blockchain, essentially a decentralized database, is a string of data blocks generated by using cryptographic methods. Each data block contains relevant information for verifying the validity of its information (anti-counterfeiting) and generating the next block.

[0071] The following will be described in detail respectively. It should be noted that the description order of the following embodiments does not limit the priority order of the embodiments.

[0072] A promotion information display method, comprising: collecting historical display information of a terminal, calculating the probabilities of the terminal displaying promotion information in a plurality of future time periods according to the historical display information, predicting the stop broadcast times corresponding to a plurality of promotion information in a prediction database, and determining at least one promotion information with the highest revenue in each future time period in the database as candidate promotion information according to the predicted stop broadcast times, generating an expected revenue corresponding to each future time period based on the probabilities of displaying promotion information in each future time period and the revenue of the candidate promotion information, selecting at least one promotion information with the highest expected revenue in the plurality of future time periods, and sending the selected at least one promotion information to the terminal so that the terminal displays the selected promotion information to the user when a promotion information display request is triggered.

[0073] Please refer to Figure 1d , Figure 1d which is a schematic flowchart of the promotion information display method provided by an embodiment of the present invention. The specific process of this promotion information display method can be as follows:

[0074] 101. Collect the historical browsing information of the terminal.

[0075] Among them, the historical browsing information includes the time information of the terminal displaying historical promotion information. The historical promotion information is the promotion information displayed by the terminal in the past time period based on the current moment, that is, the promotion information browsed by the user through the terminal in the past time period. Moreover, the historical browsing information of the terminal can be stored in the local database or obtained by accessing the network interface, depending on the actual situation. In addition, the length of the preset time period can be set according to the actual situation. For example, if the preset time period is set to 30 days and the current moment is October 31st, then the historical promotion information is the promotion information browsed by the user between October 1st and October 30th; of course, the preset time period can also be set to 5 hours and the current moment is 6 pm on October 1st, then the historical promotion information is the promotion information browsed by the user between 1 pm and 5 pm on October 1st.

[0076] 102. Calculate the probabilities corresponding to the terminal displaying promotion information in a plurality of future time periods according to the historical display information.

[0077] For example, specifically, user A opens different application programs at different times in a day, and, in two adjacent days, the times of opening the same application program may also be different. Therefore, based on the time information of the user opening application programs in a preset past time period, the probability that the user will open different application programs in a preset future time period can be predicted, that is, the probability that the terminal will display promotion information in multiple future time periods can be predicted. That is, optionally, in some embodiments, the step of "calculating the probability corresponding to the terminal displaying promotion information in multiple future time periods according to historical display information" may specifically include:

[0078] (11) Obtain the display times of each historical promotion information displayed by the terminal in multiple historical time periods according to the time information of the terminal displaying historical promotion information;

[0079] (12) Determine the probability that the terminal will display promotion information in a preset future time period according to the display times of the terminal displaying historical promotion information in multiple historical time periods.

[0080] In some embodiments, the probability that the terminal will display promotion information in multiple preset future time periods respectively corresponding to the multiple historical time periods can be determined according to the display times of the terminal displaying historical promotion information in multiple historical time periods. For example, the probability that the terminal will display promotion information in a preset future time period of the same category can be determined according to the display times of the promotion information in multiple historical time periods of the same category in a past time cycle. The category may include, for example, hours, weeks, dates, months, and so on.

[0081] Specifically, taking the splash screen advertisement of an application as an example, the number of times different splash screen advertisements are displayed on the terminal varies. Based on the number of times of display promotion information (number of displays) in each historical time period, the probability of displaying promotion information in the future time period is determined. For example, according to the user's historical login application habits, the time distribution probability of the user opening the application next time is calculated. Then, a day is divided into 12 time periods, with each time period being two hours. Record the number of times the user logs in at each time period every day. Using the login data of the user in the most recent month as the experimental sample, generally, the number of times a user logs in does not change significantly. The average method is used to calculate the probability that the terminal displays promotion information in the corresponding next cycle. When receiving a request for obtaining a splash screen advertisement triggered by the user, predict the time probability distribution of the user triggering the splash screen advertisement request next time. According to the user's historical login application habits and combined with external factors (foreseeable hot events, hot drama displays, important activities, etc.), calculate the time distribution probability of the user opening the application next time. In this solution, a day is divided into 12 time periods, with each time period being two hours. Record the number of times the user logs in at each time period every day. Using the login data of the user in the most recent month as the experimental sample, generally, the number of times a user logs in does not change significantly. The average method is used to calculate the probability M that the terminal plays an advertisement (i.e., promotion information) in the next cycle t+1 :

[0082]

[0083] where N is one cycle (i.e., the number of future time periods), y t 、y t-1 and y t-N+1 are historical observation data (i.e., the number of logins in the historical time period), θ is an external factor adjustment coefficient, which can be set according to factors such as hot events, hot drama displays, and important activities in the previous cycle. For example, for a promotion information a launched by a certain merchant for its product, in order to increase the sales volume of this product, the number of times of launching this promotion information a in a certain time period increases. At this time, according to the proportion of this promotion information a in all promotion information in this time period, an external factor adjustment coefficient can be generated. If M t+1 ≥1, it is considered that the login probability P of the user in this time period is 100%, that is, the probability that the user views this splash screen advertisement is 100%; if M t+1 <1, such as M t+1 =0.6, it is considered that the login probability P of the user in this time period is 60%, that is, the probability that the user views this splash screen advertisement is 60%.

[0084] It should be noted that in this embodiment, only the splash screen advertisement of the application is used as an example for introduction, and it does not limit this application

[0085] 103. Predict the stop broadcast times corresponding to multiple promotion messages in the database, and based on the predicted stop broadcast times, determine at least one promotion message with the highest revenue in each future time period in the database as candidate promotion messages.

[0086] Among them, a database, in short, can be regarded as an electronic filing cabinet - a place for storing electronic files. Users can perform operations such as adding, querying, updating, and deleting data in the files. The so-called "database" is a data set stored together in a certain way, shared by multiple users, with the smallest possible redundancy, and independent of application programs.

[0087] A database management system (English: Database Management System, abbreviated as DBMS) is a computer software system designed to manage databases, generally having basic functions such as storage, interception, security guarantee, and backup. Database management systems can be classified according to the database models they support, such as relational, XML (Extensible Markup Language); or classified according to the types of computers they support, such as server clusters, mobile phones; or classified according to the query languages they use, such as SQL (Structured Query Language), XQuery; or classified according to the key points of performance impulse, such as the maximum scale, the highest running speed; or other classification methods. Regardless of the classification method used, some DBMSs can cross categories. For example, they can support multiple query languages at the same time.

[0088] For each promotion message, there is a corresponding placement strategy and total placement volume. The placement strategy refers to the strategy of placing promotion messages at multiple placement time intervals within a preset time period. Each merchant will adopt different placement strategies for different promotion messages. For example, for a promotion message placed in some specific time periods (such as from 7 pm to 9 pm), in order to let more users see the promotion message during this time period, then the "unlimited display" placement strategy can be adopted during this time period, that is, quickly consume the placement volume of the promotion message during the placement time period. Another example is that if a merchant hopes that the promotion message can be displayed every day of a month, then the "limited display" placement strategy can be adopted. For example, the daily placement volume can be limited to 1200 times, and the hourly placement volume of the day can be set to 50 times. If the placement volume of the day is not displayed completely, the remaining placement volume will not be added to the placement volume of the next day. Therefore, in some embodiments, the stop broadcast time corresponding to the promotion message can be predicted based on the placement strategy and the total placement volume, that is, the step of "predicting the stop broadcast times corresponding to multiple promotion messages in the database" can specifically include:

[0089] (21) Obtain the delivery strategies and total delivery volumes corresponding to multiple promotion messages in the database;

[0090] (22) Predict the stop broadcast times corresponding to multiple promotion messages in the database based on the obtained delivery strategies and total delivery volumes.

[0091] Further, the consumption speed of each promotion message can be calculated through the delivery strategy and the total delivery volume, and then, based on the consumption speed, the stop broadcast time of the promotion message is predicted. That is, optionally, in some embodiments, the step of "predicting the stop broadcast times corresponding to multiple promotion messages in the database based on the obtained delivery strategies and total delivery volumes" may specifically include:

[0092] (31) Calculate the consumption speed of each promotion message based on the obtained delivery strategies and total delivery volumes;

[0093] (32) Predict the stop broadcast times corresponding to multiple promotion messages in the database according to the consumption speed of each promotion message.

[0094] It should be noted that the stop broadcast time refers to the time when the total delivery volume of the promotion message is consumed. For example, if the total delivery volume of the promotion message is 1000, and at 19:35 on May 10th, the terminal displays the 1000th such promotion message, then 19:35 on May 10th is determined as the stop broadcast time of the promotion message. That is, according to the consumption speed of each promotion message, the total consumption volume corresponding to each promotion message in each future time period can be predicted, and then, based on the total consumption volume, the stop broadcast times corresponding to multiple promotion messages are determined.

[0095] However, for some promotion messages that have just been launched or whose delivery strategy has been changed to increase the delivery speed, they have not yet generated consumption data or the display volume is very low. Therefore, the calculated consumption speed through the display volume, total delivery volume, and delivery strategy of these promotion messages is relatively low. To avoid this situation and cause inaccurate display of subsequent promotion messages, therefore, multiple promotion messages can be classified according to the display volume of each promotion message, the promotion messages with higher display volume are extracted, and the consumption speed of these promotion messages with higher display volume is used to determine the consumption speed of these promotion messages. The specific method is as follows:

[0096] Add the promotion messages with a display volume greater than the preset display volume to the same set to obtain the first set of promotion messages. Then, according to the total delivery volume and delivery strategy of each promotion message in the first set of promotion messages, calculate the consumption speed of each candidate promotion message in the first set of promotion messages;

[0097] Add the promotion information with the display volume less than or equal to the preset display volume to the same set to obtain the second promotion information set. Then, remove the second promotion information set from the database to obtain the remaining promotion information set. Finally, calculate the average display speed corresponding to the remaining promotion information set and determine the consumption speed of each promotion information in the second promotion information set as the average display speed. It should be noted that in this embodiment, "removing the second promotion information set from the database" means not including the promotion information in the second promotion information set in the subsequent calculations, rather than deleting it from the database.

[0098] It should be noted that the promotion information in the same promotion position will show a certain degree of consistency, which can be specifically reflected in the type of promotion information, the presentation form of promotion information, the click-through rate or conversion rate of promotion information, etc. Among them, the promotion position is the display position, which is the position where the promotion information is displayed. The promotion positions and presentation forms of different promotion platforms are different. Therefore, in some other embodiments, for the newly launched promotion information, its delivery duration is 0. Therefore, calculating the consumption speed of the newly launched promotion information based on the display volume and delivery duration is inaccurate. Therefore, the consumption speed of this promotion information can be estimated based on the consumption speed of other promotion information in the same promotion position of this promotion information. That is, optionally, in some embodiments, the step of "predicting the stop broadcast time corresponding to multiple promotion information in the database" may further include: determining the promotion information with the delivery duration less than or equal to the first preset delivery duration among the multiple promotion information as the third promotion information, obtaining the promotion information on the same promotion position as this third promotion information to obtain the fourth promotion information, the delivery duration of this fourth promotion information is greater than the second preset delivery duration, and obtaining the consumption speed of this fourth promotion information. Then, based on the consumption speed of this fourth promotion information and the total delivery volume of the third promotion information, calculate the stop broadcast time of the third promotion information. Here, the delivery duration of the promotion message refers to the time when the promotion message has been launched and is available for delivery to the promotion position. For example, for the newly launched promotion information, the delivery duration is 0. The total delivery volume of the promotion message refers to the pre-specified quantity available for delivery of this promotion information, which is generally specified according to the promotion information order or contract. For example, the total delivery volume of the promotion message can be set to 1000. Then, after this promotion message is delivered to the promotion position 1000 times, this promotion message stops being delivered. The first preset delivery duration and the second preset delivery duration can be determined based on empirical values or delivery data analysis, and the second preset delivery duration is greater than or equal to the first preset delivery duration.

[0099] Among them, the delivery duration of the fourth promotion information is greater than the second preset delivery duration. For example, in promotion position F, the delivery duration of the just-launched promotion information G is 0. At this time, the consumption speed of promotion information G is estimated based on other promotion information that has been displayed on promotion position F. To ensure the reliability of the estimated consumption speed, in this embodiment, promotion information with a delivery duration greater than the second preset delivery duration is used as the promotion information, which can improve the reliability of the estimated consumption speed.

[0100] Furthermore, in some embodiments, for the just-launched third promotion information (initial promotion information), the delivery duration and display volume of the promotion information that has been displayed on the same promotion position can also be used to select promotion information that meets the preset conditions as the reference promotion information in the same promotion position, and then the consumption speed of the initial promotion information is calculated. Among them, there are many ways to select promotion information that meets the preset conditions as the reference promotion information in the same promotion position. Promotion information with a delivery duration greater than the preset delivery duration and a display volume greater than the preset display volume can be used as the reference promotion information, or promotion information with a delivery duration greater than the preset delivery duration or a display volume greater than the preset display volume can be used as the reference promotion information. It is specifically set according to the actual situation and will not be elaborated here.

[0101] Specifically, if the total delivery volume of promotion information z is 10,000 times and the delivery duration is 30 days, and the delivery time period corresponding to the delivery strategy is from 7 pm to 9 pm every day, there are two ways to calculate the consumption speed of promotion information z:

[0102] Method 1: Obtain the display volume c of promotion information z on the nth day n , calculate the ratio of the display volume c n to the delivery time period to obtain the consumption speed v of candidate promotion information z on the nth day n , where n is a positive integer. In addition, before obtaining the display volume c n of promotion information z on the nth day, it is also necessary to detect whether the remaining display volume of promotion information z on the nth day is greater than 0. When the remaining display volume of promotion information z is greater than 0, the display volume c n of candidate promotion information z on the nth day is obtained. For example, when calculating the display volume of promotion information z on the 10th day, based on the sum of the display volumes of promotion information z from the 1st day to the 9th day, determine the remaining display volume of promotion information z on the 10th day, detect whether the remaining display volume of candidate promotion information z is greater than 0, and if the remaining display volume of candidate promotion information z is greater than 0, obtain the display volume of promotion information z on the 10th day; it can be understood that after calculating the consumption speed of each day, calculate the average value of the consumption speeds within these 30 days, and then obtain the consumption speed of candidate promotion information z within 30 days, as shown in the following formula:

[0103]

[0104] Among them, V is the consumption rate of candidate promotion information z within n days, and v n is the consumption rate on the nth day.

[0105] In addition, if the remaining display volume of promotion information z is less than 0, the display volume of candidate promotion information z on the 10th day is not obtained, and the average value of the consumption rates of candidate promotion information z from the 1st day to the 9th day is calculated to obtain the consumption rate of candidate promotion information z within 30 days.

[0106] Method 2: Statistically sum up the display volumes of promotion information z within 30 days, then calculate the product of the delivery duration and the delivery time period to obtain the actual delivery duration. Finally, calculate the ratio of the sum of the display volumes of promotion information z within 30 days to the actual delivery duration to obtain the consumption rate of promotion information z, which can be calculated by the following formula:

[0107]

[0108] The consumption rate V of the promotion information is equal to the ratio of the sum C of the display volumes of the candidate promotion information in the past preset time period to the actual delivery duration T.

[0109] It should be noted that there may be significant differences in the display volumes in adjacent time intervals. For example, the display volume in the time interval from 5 am to 8 am on the same day may be very different from the display volume in the time interval from 8 am to 11 am on the same day. There may be a situation where the display volume in the time interval from 5 am to 8 am is 100 times, while the display volume in the time interval from 8 am to 11 am on the same day is 1000 times. That is, the adopted delivery strategy is the "limited display" strategy. That is to say, the corresponding delivery time intervals and the delivery volumes corresponding to each delivery time interval can be determined. Then, based on the determined delivery time intervals and the delivery volumes corresponding to each delivery time interval, the consumption rates of each candidate promotion information in the second candidate information set are generated. That is, the number of delivery time intervals corresponding to the delivery strategy and the delivery volumes corresponding to each delivery time interval are determined, and based on the number of delivery time intervals and the delivery volumes corresponding to each delivery time interval, the consumption rates of each candidate promotion information are generated.

[0110] Specifically, according to the display weights of each promotion information in the first promotion information set in different historical time periods, where the display weight is determined by the number of times the promotion information is displayed in the historical time period. That is, optionally, in some embodiments, the step of "calculating the consumption speed of each promotion information in the first promotion information set according to the total delivery volume and delivery strategy of each promotion information in the first promotion information set" may specifically include: obtaining the number of times each promotion information in the first promotion information set is displayed in each historical time period, determining the display weight of each promotion information in the first promotion information set corresponding to each historical time period based on the obtained number of times, and calculating the consumption speed of each promotion information in the first promotion information set according to the determined display weight, the total delivery volume of each promotion information in the first promotion information set, and the delivery strategy.

[0111] Taking a promotion information x as an example, the delivery strategy indicates that the total delivery volume of promotion information x within 30 consecutive days is 36,000 times, where the delivery volume from 0:00 to 8:00 is 200 times, the delivery volume from 8:00 to 16:00 is 600 times, and the delivery volume from 16:00 to 24:00 is 400 times. That is to say, the number of delivery time intervals is 3. Therefore, promotion information x has 3 consumption speeds corresponding to each day. Then, according to the delivery volume corresponding to each delivery time interval, the weight corresponding to the consumption speed of the promotion information is determined. In this embodiment, it is 2:6:4. Immediately afterwards, based on the determined weight, the daily consumption speed of the candidate promotion information x is calculated. Finally, the average value of all consumption speeds within 30 days is calculated to obtain the consumption speed of the candidate promotion information x within 30 days.

[0112] 104. Generate the expected revenue corresponding to each future time period based on the probability of displaying the promotion information in each future time period and the revenue of the candidate promotion information.

[0113] For example, specifically, taking 2 hours as a preset time period, assuming the current time is 12:00 am, the current time to 12:00 am the next day is divided into different future time periods at 2-hour intervals. For each future time period, according to the stop broadcast time of each promotion information determined in step 103, the promotion information that can be broadcast in each future time period is determined, and all promotion information within each future time period is sorted according to the revenue, and the promotion information with the highest revenue is selected. The expected revenue for a future time period can be expressed by the following formula:

[0114] Q = Pn(t) * C

[0115] It means that the expected revenue Q is equal to the product of the probability that the terminal will display the promotional information n in the future time period t and the revenue C of the promotional information n. That is, the step of "generating the expected revenue corresponding to each future time period based on the probability of displaying the promotional information in each future time period and the revenue of the candidate promotional information" can specifically include: determining the probability that the candidate promotional information will be displayed in the corresponding future time period based on the probability of displaying the promotional information in each future time period, calculating the product of the probability that the candidate promotional information will be displayed in the corresponding future time period and the revenue of the candidate promotional information, and generating the expected revenue corresponding to each future time period.

[0116] 105. Select at least one promotional information with the highest expected revenue in the future time period, and send the selected at least one promotional information to the terminal so that the terminal can display the selected at least one promotional information to the user when triggering a promotional information display request.

[0117] For example, specifically, the promotional information is a splash screen advertisement. A splash screen advertisement is an advertisement form that is loaded when the application is launched, displayed for a fixed time, and automatically closed and enters the main application page after display. Select at least one splash screen advertisement with the highest expected revenue from each future time period, send the advertisement materials of the at least one splash screen advertisement to the terminal, and cache them locally on the terminal. When the application program in the terminal is opened, trigger a splash screen advertisement acquisition request (i.e., a promotional information display request), and display some or all of the at least one splash screen advertisement on the interface of the application program.

[0118] Since the advertisement may be consumed in advance or for other reasons, the advertisement cached locally on the terminal may not be playable. In some embodiments, when triggering a promotional information display request, the advertisement list cached locally on the terminal can be sent to the advertisement server. The advertisement server checks the received advertisement list. When it is confirmed that the advertisement in the advertisement list is playable, the advertisement server sends a confirmation message to the terminal. And when the terminal receives the confirmation message of the advertisement, the advertisement is displayed on the interface of the application program, thus preventing the application program from playing a banned advertisement.

[0119] After the historical display information of the acquisition terminal is collected in the embodiment of the present invention, the historical browsing information includes the time information of the terminal displaying each historical promotion information, and the historical promotion information is the promotion information displayed by the terminal within a preset time period in the past with the current moment as the reference. According to the historical display information, calculate the probability of the terminal displaying promotion information in multiple future time periods. Then, predict the stop broadcast time corresponding to multiple promotion information in the database, and based on the predicted stop broadcast time, determine at least one promotion information with the highest revenue in each future time period in the database as the candidate promotion information. Next, generate the expected revenue corresponding to each future time period based on the probability of displaying promotion information in each future time period and the revenue of the candidate promotion information. Finally, select at least one promotion information with the highest expected revenue in multiple future time periods, and send the selected at least one promotion information to the terminal so that the terminal displays the selected at least one promotion information to the user when triggering a promotion information display request. Compared with the existing promotion information display scheme, in this embodiment, according to the predicted stop broadcast time, at least one promotion information with the highest revenue in each future time period is determined in the database. Finally, based on the probability of displaying promotion information in each future time period and the revenue of the candidate promotion information, the expected revenue corresponding to each future time period is generated, avoiding the problem that the total amount of pre-loaded promotion information has been consumed, resulting in the splash screen advertisement displayed by the terminal not being the pre-loaded promotion information. This can not only avoid the waste of network resources, but also improve the accuracy of promotion information display. At the same time, displaying the promotion information with the largest expected revenue to the user can also improve the utilization rate of the promotion information inventory.

[0120] The method according to the embodiment will be further described in detail with examples below.

[0121] In this embodiment, it will be described by taking the promotion information display device being specifically integrated in the server as an example. It can be understood that the following method steps are not limited to being executed in the server, and any one or more of the method steps can be executed by one or two of the server and the terminal, or can also be jointly executed by two or more servers and / or terminals.

[0122] Please refer to Figure 2a , a method for displaying promotion information, and the specific process can be as follows:

[0123] 201. The server collects the historical browsing information of the terminal.

[0124] Among them, the historical browsing information includes the time information of the terminal displaying historical promotion information. The historical promotion information is the promotion information displayed by the terminal in the past time period based on the current moment, that is, the promotion information browsed by the user through the terminal in the past preset time period. Moreover, the historical browsing information of the terminal can be stored in the local database of the server or obtained by the server pulling through accessing the network interface, depending on the actual situation. In some embodiments, the promotion information may be a splash advertisement, which refers to an advertisement displayed to the user when opening an application on the terminal. In this embodiment, collecting the historical browsing information of the terminal can be collecting the historical opening time records of the application on the terminal, that is, the time of each past opening of the application.

[0125] 202. The server calculates the probabilities of the terminal displaying promotion information in multiple future time periods according to the historical display information.

[0126] In some embodiments, the promotion information may be a splash advertisement, and the time of displaying the promotion information is also the time of opening the application. The probabilities of displaying the splash advertisement in multiple future time periods can be determined according to the historical opening time records of the application on the terminal. For example, specifically, User A opens different applications at different times in a day, and, in two adjacent days, the time of opening the same application may also be different. Therefore, the server can predict the probabilities of the user opening different applications in the future preset time period based on the time information of the user opening the application in the past preset time period, that is, predict the probabilities of the terminal displaying promotion information in multiple future time periods. It can be understood that this application is not limited to splash advertisements, and the probabilities of any advertisement being displayed in multiple future time periods can be estimated according to the historical display information of the advertisement.

[0127] 203. The server predicts the stop broadcast times corresponding to multiple promotion information in the database, and determines at least one promotion information with the highest revenue in each future time period in the database as candidate promotion information according to the predicted stop broadcast times.

[0128] For example, specifically, the server calculates the consumption speed of each promotion information through the delivery strategy and the total delivery volume. Then, the server predicts the total consumption volume corresponding to each promotion information in each future time period according to the consumption speed of each promotion information. Next, the server determines the stop broadcast times corresponding to multiple promotion information based on the total consumption volume. Finally, the server determines at least one promotion information with the highest revenue in each future time period in the database as candidate promotion information according to the predicted stop broadcast times.

[0129] 204. The server generates the expected revenue corresponding to each future time period based on the probabilities of displaying promotion information in each future time period and the revenue of the candidate promotion information.

[0130] Among them, the server can determine the probability of the candidate promotion information being displayed in the corresponding future time period based on the probabilities of the promotion information being displayed in each future time period. Then, the server calculates the product of the probability of the candidate promotion information being displayed in the corresponding future time period and the revenue of the candidate promotion information, and generates the expected revenue corresponding to each future time period.

[0131] 205. The server selects at least one promotion information with the highest expected revenue in multiple future time periods, and sends the selected at least one promotion information to the terminal, so that the terminal can display the selected at least one promotion information to the user when triggering a promotion information display request.

[0132] In some embodiments, the promotion information is a splash screen advertisement. The server selects at least one splash screen advertisement with the highest expected revenue from each future time period, sends the advertisement materials of the at least one splash screen advertisement to the terminal, and caches them locally on the terminal. When the application program in the terminal is opened, a splash screen advertisement acquisition request is triggered, and the advertisement list cached locally on the terminal is sent to the advertisement server. The advertisement server checks the received advertisement list. When it is confirmed that the advertisement in the advertisement list is playable, the advertisement server sends a confirmation message to the terminal. And when the terminal receives the confirmation message of the advertisement, the advertisement is displayed on the interface of the application program.

[0133] Please refer to Figure 2b , taking the display of the splash screen advertisement of the application program to the user as an example for illustration. Among them, the application program stores the time information of the user logging in to the application program in the past preset time period. The advertisement placement engine is based on the time information of the user logging in to the application program in the past preset time period (hereinafter referred to as historical login time information). Then, the advertisement placement engine predicts the time when the user will log in to the application program in the future preset time period based on the historical login time information. And, the advertisement placement engine predicts the consumption speed of each advertisement (i.e., the consumption speed of the promotion information) based on the exposure data corresponding to each advertisement. The exposure data includes the display volume, total delivery volume, and delivery strategy of the advertisement. Further, please refer to Figure 2c , this embodiment provides an advertisement display system, which includes: a user, a mobile phone, and a server. Among them, the server includes an advertisement placement server, a management server, an exposure server, and a content distribution server. The advertisement placement server is used to calculate the advertisement with the maximum expected revenue and deliver the advertisement to the terminal. For example, it can be delivered to the mobile phone client (i.e., the application program). The management server is used to return the user's login information to the advertisement placement server, such as the user's account information and historical browsing information, etc. The exposure server is used to count the number of times each advertisement is viewed. The content distribution server is used to display the advertisement to the user.

[0134] Step 1: When the server receives a request for obtaining a splash screen advertisement triggered by a user, it predicts the probability distribution of the time when the user will trigger the next splash screen advertisement request. By combining the user's historical application login habits with external factors (such as foreseeable hot events, popular drama shows, and important activities), it calculates the probability distribution of the time when the user will open the application next. In this solution, a day is divided into 12 time periods, each time period being two hours. Record the number of logins of the user in each time period every day. Using the login data of the user in the most recent month as the experimental sample, since the number of logins of general users does not change significantly, the average method is used to calculate the probability M that the terminal will play an advertisement (i.e., promotional information) in the next cycle. t+1 :

[0135]

[0136] Among them, N is a cycle (i.e., the number of future time periods), y t 、y t-1 and y t-N+1 are historical observation data (i.e., the number of logins in historical time periods), θ is an external factor adjustment coefficient, which can be set according to factors such as hot events, popular drama shows, and important activities in the previous cycle. For example, for a promotional information a launched by a certain merchant for its product, in order to increase the sales volume of this product, the number of times this promotional information a is launched in a certain time period increases. At this time, according to the proportion of this promotional information a in all promotional information in this time period, an external factor adjustment coefficient can be generated. If M t+1 ≥1, it is considered that the login probability P of the user in this time period is 100%, that is, the probability that the user views this splash screen advertisement is 100%; if M t+1 <1, such as M t+1 = 0.6, it is considered that the login probability P of the user in this time period is 60%, that is, the probability that the user views this splash screen advertisement is 60%.

[0137] Step 2: Extract the corresponding advertisement space information (also known as promotional space information) from the splash screen advertisement acquisition request, and obtain all advertisement orders on the advertisement space. For each advertisement, according to its effective time, delivery mode (such as smooth broadcast, broadcast as soon as possible, etc.) and the total budget amount, predict the consumption curve of this advertisement over time. The consumption speed can be calculated by the following formula according to the total consumption of the advertisement order in the recent period and the time slice length:

[0138]

[0139] That is, the consumption speed costspeed of the splash screen advertisement is equal to the ratio of the sum Cost of the display volume of the candidate promotional information in the past cycle to the actual delivery duration Time.

[0140] After obtaining the consumption speed, the consumption curve of the predicted advertisement over time can be determined.

[0141] It should be noted that when an advertisement order starts to be delivered and no consumption data has been generated yet, the average consumption speed of other advertisement orders on the same advertisement slot can be used as the initial value. After the advertisement starts to be displayed, a relatively accurate consumption speed value can be obtained. That is to say, when the advertisement delivery time is less than the threshold, the server can obtain the advertisement slot information identifying the advertisement slot from the advertisement acquisition request sent by the terminal, and obtain the historical advertisement delivery data of multiple advertisements on the advertisement slot from the advertisement database according to the advertisement slot information, and determine the average consumption speed of the advertisements on the advertisement slot according to the historical advertisement delivery data, so as to use the average consumption speed as the advertisement consumption speed of the newly delivered advertisement or the advertisement with a short delivery time.

[0142] Step 3: Divide the future time into different target time periods at intervals of 2 hours. For each target time period, calculate the difference between it and the current time respectively. Combining with the predicted advertisement consumption curve in the second step, it can be determined whether the advertisement has been completely displayed within the target time period. If it has not been completely displayed, it is considered that it can be played within the target time period. Sort all the advertisements that can be played within the target time period by price, and select the advertisement with the highest price. Then the expected revenue of the user's advertisement exposure within the target time period is equal to the product of the probability of the user opening the application program within the time period and the highest price of the playable advertisement within the time period. An expected revenue will be obtained for each target time period, and then the advertisement corresponding to the maximum expected revenue is selected and returned to the client.

[0143] After the server in the embodiment of the present invention collects the historical display information of the terminal, the historical browsing information includes the time information of the terminal displaying each historical promotion information, and the historical promotion information is the promotion information displayed by the terminal within a preset time period in the past based on the current moment. The server calculates the probability of the terminal displaying the promotion information in multiple future time periods according to the historical display information. Then, the server predicts the stop broadcast time corresponding to multiple promotion information in the database, and determines at least one promotion information with the highest revenue in each future time period in the database as the candidate promotion information according to the predicted stop broadcast time. Next, the server generates the expected revenue corresponding to each future time period based on the probability of displaying the promotion information in each future time period and the revenue of the candidate promotion information. Finally, the server selects at least one promotion information with the highest expected revenue in multiple future time periods and sends the selected at least one promotion information to the terminal, so that the terminal displays the selected at least one promotion information to the user when triggering the promotion information display request. Compared with the existing promotion information display scheme, the server in this embodiment determines at least one promotion information with the highest revenue in each future time period in the database according to the predicted stop broadcast time. Finally, based on the probability of displaying the promotion information in each future time period and the revenue of the candidate promotion information, the expected revenue corresponding to each future time period is generated, avoiding the problem that the total amount of pre-loaded promotion information has been consumed, resulting in the splash screen advertisement displayed by the terminal to the user not being the pre-loaded promotion information. It can not only avoid the waste of network resources, but also improve the accuracy of promotion information display. At the same time, displaying the promotion information with the highest expected revenue to the user can also improve the utilization rate of the promotion information inventory.

[0144] To facilitate better implementation of the promotion information display method in the embodiment of the present invention, the embodiment of the present invention also provides a promotion information display device (hereinafter referred to as the display device) based on the above. The meanings of the nouns are the same as those in the above promotion information display method, and the specific implementation details can refer to the description in the method embodiment.

[0145] Please refer to Figure 3 , Figure 3 which is a schematic structural diagram of the promotion information display device provided by the embodiment of the present invention. The recognition device may include a collection module 301, a calculation module 302, a prediction module 303, a determination module 304, a generation module 305, and a display module 306, specifically as follows:

[0146] The collection module 301 is used to collect the historical browsing information of the terminal.

[0147] Among them, the historical browsing information includes multiple historical promotion information and the time information of the terminal displaying each historical promotion information. The historical promotion information is the promotion information displayed by the terminal within a past time period based on the current moment, that is, the promotion information browsed by the user through the terminal within a past preset time period. Moreover, the historical browsing information of the terminal can be stored in the local database of the acquisition module 301 or obtained by the acquisition module 301 pulling through accessing the network interface, depending on the actual situation.

[0148] The calculation module 302 is configured to calculate the probability of the terminal displaying promotion information in multiple future time periods according to the historical display information.

[0149] Optionally, in some embodiments, the calculation module 302 may specifically be configured to: obtain the display times of the terminal displaying the historical promotion information in multiple historical time periods according to the time information of the terminal displaying the historical promotion information, and determine the probability of the terminal displaying promotion information in a future preset time period according to the display times of the terminal displaying the historical promotion information in multiple historical time periods.

[0150] Optionally, in some embodiments, the second calculation unit may specifically be configured to: determine the display weight of each historical promotion information according to the browsing times of the user terminal displaying each historical promotion information, and calculate the probability of the terminal displaying each promotion information in a future preset time period based on the multiple historical promotion information and the display weight of each historical promotion information.

[0151] The prediction module 303 is configured to predict the stop broadcast times corresponding to multiple promotion information in the database.

[0152] For example, specifically, the prediction module 303 calculates the consumption speed of each promotion information through the delivery strategy and the total delivery volume. Then, the prediction module 303 predicts the total consumption volume corresponding to each promotion information in each future time period according to the consumption speed of each promotion information. Finally, the prediction module 303 determines the stop broadcast times corresponding to the multiple promotion information based on the total consumption volume.

[0153] Optionally, in some embodiments, the prediction module 303 may specifically include:

[0154] An acquisition sub-module that acquires the delivery strategy and the total delivery volume corresponding to multiple promotion information in the database;

[0155] A prediction sub-module configured to predict the stop broadcast times corresponding to multiple promotion information in the database based on the acquired delivery strategy and total delivery volume.

[0156] Optionally, in some embodiments, the prediction sub-module may specifically include:

[0157] A calculation unit configured to calculate the consumption speed of each promotion information based on the acquired delivery strategy and total delivery volume;

[0158] A prediction unit, configured to predict the stop broadcast time corresponding to multiple promotion messages in a database according to the consumption speed of each promotion message.

[0159] Optionally, in some embodiments, the calculation unit may specifically include:

[0160] An adding subunit, configured to add candidate promotion messages with a display volume greater than a preset display volume to the same set to obtain a first promotion message set;

[0161] A calculation subunit, configured to calculate the consumption speed of each candidate promotion message in the first promotion message set according to the total delivery volume and delivery strategy of each promotion message in the first promotion message set.

[0162] Optionally, in some embodiments, the calculation subunit may specifically be configured to: obtain the display times of each promotion message in the first promotion message set corresponding to each past time period, determine the display weight of each promotion message in the first promotion message set corresponding to each past time period based on the obtained display times, and calculate the consumption speed of each promotion message in the first promotion message set according to the determined display weight, the total delivery volume of each promotion message in the first promotion message set, and the delivery strategy.

[0163] Optionally, in some embodiments, the calculation unit may specifically further be configured to: add promotion messages with a display volume less than or equal to the preset display volume to the same set to obtain a second promotion message set, remove the second promotion message set from the database to obtain a retained promotion message set, calculate the average consumption speed corresponding to the retained promotion message set, and determine the average consumption speed as the consumption speed of each promotion message in the second promotion message set.

[0164] Optionally, in some embodiments, the prediction unit may specifically be configured to: predict the total consumption volume of each promotion message corresponding to each future time period according to the consumption speed of each promotion message, and determine the stop broadcast time corresponding to multiple promotion messages based on the total consumption volume.

[0165] Optionally, in some embodiments of the present invention, the prediction module 303 may specifically be configured to: determine promotion messages with a delivery duration less than or equal to a first preset delivery duration among multiple promotion messages as third promotion messages; obtain promotion messages on the same promotion position as the third promotion messages to obtain fourth promotion messages, and the delivery duration of the fourth promotion messages is greater than a second preset delivery duration; collect the consumption speed of the fourth promotion messages; and calculate the stop broadcast time of the third promotion messages according to the consumption speed of the fourth promotion messages and the total delivery volume of the third promotion messages.

[0166] A determination module 304, configured to determine at least one promotion message with the highest revenue in each future time period in the database as a candidate promotion message according to the predicted stop broadcast time.

[0167] Among them, the stop time of the candidate promotion information is later than the corresponding future time period.

[0168] The generation module 305 is configured to generate an expected revenue corresponding to each future time period based on the probability of displaying the promotion information in each future time period and the revenue of the candidate promotion information.

[0169] Among them, the generation module 305 can determine the probability of the candidate promotion information being displayed in the corresponding future time period based on the probability of displaying the promotion information in each future time period. Then, the generation module 304 calculates the product of the probability of the candidate promotion information being displayed in the corresponding future time period and the revenue of the candidate promotion information to generate an expected revenue corresponding to each future time period.

[0170] Optionally, in some embodiments, the generation module 304 may specifically be configured to: determine the probability of the candidate promotion information being displayed in the corresponding future time period based on the probability of displaying the promotion information in each future time period, calculate the product of the probability of the candidate promotion information being displayed in the corresponding future time period and the revenue of the candidate promotion information, and generate an expected revenue corresponding to each future time period.

[0171] The display module 306 is configured to select the promotion information with the highest expected revenue in the future time period from the database and send the selected promotion information to the terminal so that the terminal can display the selected promotion information to the user when a promotion information display request is triggered.

[0172] After the acquisition module 301 of the embodiment of the present invention acquires the historical display information of the acquisition terminal, the historical browsing information includes the time information of each historical promotion information displayed by the terminal. The historical promotion information is the promotion information displayed by the terminal within a preset time period in the past with the current moment as the reference. The calculation module 302 calculates the probability of the terminal displaying the promotion information in multiple future time periods according to the historical display information. Then, the prediction module 303 predicts the stop broadcast time corresponding to multiple promotion information in the database. The determination module 304 determines at least one promotion information with the highest revenue in each future time period in the database as the candidate promotion information according to the predicted stop broadcast time. Next, the generation module 305 generates the expected revenue corresponding to each future time period based on the probability of displaying the promotion information in each future time period and the revenue of the candidate promotion information. Finally, the display module 306 selects at least one promotion information with the highest expected revenue in multiple future time periods and sends the selected at least one promotion information to the terminal, so that the terminal displays the selected at least one promotion information to the user when triggering the promotion information display request. Compared with the existing promotion information display scheme, the server of this embodiment determines at least one promotion information with the highest revenue in each future time period in the database according to the predicted stop broadcast time. Finally, based on the probability of displaying the promotion information in each future time period and the revenue of the candidate promotion information, the expected revenue corresponding to each future time period is generated, avoiding the problem that the total amount of pre-loaded promotion information has been consumed, resulting in the fact that the splash screen advertisement displayed by the terminal to the user is not the pre-loaded promotion information. It can not only avoid the waste of network resources, but also improve the accuracy of promotion information display. At the same time, displaying the promotion information with the maximum expected revenue to the user can also improve the utilization rate of the promotion information inventory.

[0173] In addition, an embodiment of the present invention further provides an electronic device, such as Figure 4 shown, which shows the structural schematic diagram of the electronic device involved in the embodiment of the present invention. Specifically:

[0174] The electronic device may include a processor 401 with one or more processing cores, a memory 402 with one or more computer-readable storage media, a power supply 403, an input unit 404 and other components. Those skilled in the art can understand that Figure 4 the structure of the electronic device shown in

[0175] The processor 401 is the control center of the electronic device, connecting various parts of the entire electronic device through various interfaces and circuits. By running or executing software programs and / or modules stored in the memory 402, and by invoking the data stored in the memory 402, it executes various functions of the electronic device and processes data, thereby performing an overall detection of the electronic device. Optionally, the processor 401 may include one or more processing cores; preferably, the processor 401 may integrate an application processor and a modem processor. Among them, the application processor mainly processes the operating system, user interface, application programs, etc., and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor may not be integrated into the processor 401 either.

[0176] The memory 402 can be used to store software programs and modules. The processor 401 executes various functional applications and data processing by running the software programs and modules stored in the memory 402. The memory 402 mainly includes a program storage area and a data storage area. Among them, the program storage area can store the operating system, application programs required for at least one function (such as a sound display function, an image display function, etc.); the data storage area can store data created according to the use of the electronic device. In addition, the memory 402 can include high-speed random access memory, and can also include non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices. Correspondingly, the memory 402 can also include a memory controller to provide the processor 401 with access to the memory 402.

[0177] The electronic device further includes a power supply 403 for supplying power to each component. Preferably, the power supply 403 can be logically connected to the processor 401 through a power management system, so as to realize functions such as management of charging, discharging, and power consumption management through the power management system. The power supply 403 can also include any components such as one or more DC or AC power supplies, a recharge system, a power failure detection circuit, a power converter or inverter, and a power status indicator.

[0178] The electronic device may further include an input unit 404, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function controls.

[0179] Although not shown, the electronic device may further include a display unit, etc., which will not be elaborated here. Specifically, in this embodiment, the processor 401 in the electronic device will load the executable files corresponding to the processes of one or more application programs into the memory 402 according to the following instructions, and the processor 401 will run the application programs stored in the memory 402 to achieve various functions as follows:

[0180] Collect the historical display information of the terminal. Based on the historical display information, calculate the probabilities of the terminal displaying promotion information in multiple future time periods, predict the stop broadcast times corresponding to multiple promotion information in the database, and based on the predicted stop broadcast times, determine at least one promotion information with the highest revenue in each future time period in the database as candidate promotion information. Based on the probabilities of displaying promotion information in each future time period and the revenues of the candidate promotion information, generate the expected revenue corresponding to each future time period, select at least one promotion information with the highest expected revenue in multiple future time periods, and send the selected at least one promotion information to the terminal so that the terminal can display the selected at least one promotion information to the user when triggering a promotion information display request.

[0181] For the specific implementation of each of the above operations, reference can be made to the previous embodiments and will not be elaborated here.

[0182] In the embodiment of the present invention, after collecting the historical display information of the terminal, the historical browsing information includes the time information of the terminal displaying each historical promotion information, and the historical promotion information is the promotion information that the terminal has displayed in the past preset time period based on the current moment. Based on the historical display information, calculate the probabilities of the terminal displaying promotion information in multiple future time periods. Then, predict the stop broadcast times corresponding to multiple promotion information in the database, and based on the predicted stop broadcast times, determine at least one promotion information with the highest revenue in each future time period in the database as candidate promotion information. Next, based on the probabilities of displaying promotion information in each future time period and the revenues of the candidate promotion information, generate the expected revenue corresponding to each future time period. Finally, select at least one promotion information with the highest expected revenue in multiple future time periods, and send the selected at least one promotion information to the terminal so that the terminal can display the selected at least one promotion information to the user when triggering a promotion information display request. Compared with the existing promotion information display scheme, in this embodiment, based on the predicted stop broadcast times, at least one promotion information with the highest revenue in each future time period is determined in the database. Finally, based on the probabilities of displaying promotion information in each future time period and the revenues of the candidate promotion information, the expected revenue corresponding to each future time period is generated, avoiding the problem that the total amount of pre-loaded promotion information has been consumed, resulting in the splash screen advertisement displayed by the terminal not being the pre-loaded promotion information. This can not only avoid waste of network resources, but also improve the accuracy of promotion information display. At the same time, displaying the promotion information with the maximum expected revenue to the user can also improve the utilization rate of the promotion information inventory.

[0183] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions or by controlling relevant hardware through instructions. The instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0184] To this end, an embodiment of the present invention provides a storage medium, which stores multiple instructions that can be loaded by a processor to execute the steps in any of the promotion information display methods provided by the embodiments of the present invention. For example, the instructions can execute the following steps:

[0185] Collect the historical display information of the terminal. According to the historical display information, calculate the probabilities of the terminal displaying promotion information in multiple future time periods, predict the stop broadcast times corresponding to multiple promotion information in the database, and based on the predicted stop broadcast times, determine at least one promotion information with the highest revenue in each future time period in the database as candidate promotion information. Generate the expected revenue corresponding to each future time period based on the probabilities of displaying promotion information in each future time period and the revenues of the candidate promotion information, select at least one promotion information with the highest expected revenue in multiple future time periods, and send the selected at least one promotion information to the terminal so that the terminal can display the selected at least one promotion information to the user when a promotion information display request is triggered.

[0186] For the specific implementation of each of the above operations, reference can be made to the previous embodiments, which will not be elaborated here.

[0187] Among them, the storage medium may include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disc, etc.

[0188] Since the instructions stored in the storage medium can execute the steps in any of the promotion information display methods provided by the embodiments of the present invention, the beneficial effects that can be achieved by any of the promotion information display methods provided by the embodiments of the present invention can be realized. For details, reference can be made to the previous embodiments, which will not be elaborated here.

[0189] The above has introduced in detail a promotion information display method, device, electronic device, and storage medium provided by the embodiments of the present invention. Specific examples are used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those skilled in the art, based on the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for promoting information display, characterized in that, it includes: Collecting the historical display information of the terminal, where the historical display information includes the time information of the terminal displaying historical promotion information, and the historical promotion information is the promotion information that the terminal has displayed in the past time period based on the current moment; Calculating the probability of the terminal displaying promotion information in multiple future time periods according to the historical display information; Predicting the stop broadcast time corresponding to multiple promotion information in the database, including: obtaining the placement strategy and total placement volume corresponding to multiple promotion information in the database; predicting the stop broadcast time corresponding to multiple promotion information in the database based on the obtained placement strategy and total placement volume; According to the predicted stop broadcast time, determining at least one promotion information with the highest revenue in each future time period in the database as candidate promotion information, and the stop broadcast time of the candidate promotion information is later than the corresponding future time period; Generating the expected revenue corresponding to each future time period based on the probability of displaying promotion information in each future time period and the revenue of the candidate promotion information; Selecting at least one promotion information with the highest expected revenue in multiple future time periods, and sending the selected at least one promotion information to the terminal, so that the terminal displays the selected at least one promotion information to the user when triggering a promotion information display request.

2. The method according to claim 1, characterized in that, The predicting the stop broadcast time corresponding to multiple promotion information in the database based on the obtained placement strategy and total placement volume includes: Calculating the consumption speed of each promotion information based on the obtained placement strategy and total placement volume; Predicting the stop broadcast time corresponding to multiple promotion information in the database according to the consumption speed of each promotion information.

3. The method according to claim 2, characterized in that, The calculating the consumption speed of each promotion information based on the obtained placement strategy and total placement volume includes: Adding promotion information with a display volume greater than a preset display volume to the same set to obtain a first set of promotion information; Calculating the consumption speed of each promotion information in the first set of promotion information according to the total placement volume and placement strategy of each promotion information in the first set of promotion information.

4. The method according to claim 3, characterized in that, The calculating the consumption speed of each promotion information in the first set of promotion information according to the total placement volume and placement strategy of each promotion information in the first set of promotion information includes: Obtaining the number of display times corresponding to each promotion information in the first set of promotion information in each historical time period; Determining the display weight corresponding to each promotion information in the first set of promotion information in each historical time period based on the obtained number of display times; Calculating the consumption speed of each promotion information in the first set of promotion information according to the determined display weight, the total placement volume of each promotion information in the first set of promotion information, and the placement strategy.

5. The method according to claim 3, characterized in that, It further includes: Adding promotion information with a display volume less than or equal to the preset display volume to the same set to obtain a second set of promotion information; Removing the second set of promotion information from the database to obtain a retained set of promotion information; Calculate the average consumption speed corresponding to the reserved promotion information set, and determine the average consumption speed as the consumption speed of each promotion information in the second promotion information set.

6. The method according to claim 2, wherein, the predicting the stop time corresponding to multiple promotion information in the database according to the consumption speed of each promotion information includes: predicting the total consumption amount corresponding to each promotion information in each future time period according to the consumption speed of each promotion information; determining the stop time corresponding to multiple promotion information based on the total consumption amount.

7. The method according to claim 1, wherein, the predicting the stop time corresponding to multiple promotion information in the database includes: determining the promotion information with a placement duration less than or equal to the first preset placement duration among the multiple promotion information as the third promotion information; obtaining the promotion information on the same promotion position as the third promotion information, and obtaining the fourth promotion information, where the placement duration of the fourth promotion information is greater than the second preset placement duration; collecting the consumption speed of the fourth promotion information; calculating the stop time of the third promotion information according to the consumption speed of the fourth promotion information and the total placement amount of the third promotion information.

8. The method according to any one of claims 1 to 7, wherein, the calculating the probability that the terminal displays promotion information in multiple future time periods according to the historical display information includes: obtaining the display times of the terminal displaying historical promotion information in multiple historical time periods according to the time information of the terminal displaying historical promotion information; determining the probability that the terminal displays promotion information in a future preset time period according to the display times of the terminal displaying historical promotion information in multiple historical time periods.

9. The method according to any one of claims 1 to 7, wherein, the generating the expected revenue corresponding to each future time period based on the probability of displaying promotion information in each future time period and the revenue of the candidate promotion information includes: determining the probability that the candidate promotion information is displayed in the corresponding future time period based on the probability of displaying promotion information in each future time period; calculating the product of the probability that the candidate promotion information is displayed in the corresponding future time period and the revenue of the candidate promotion information, and generating the expected revenue corresponding to each future time period.

10. A promotion information display device, wherein, comprising: a collection module, configured to collect the historical display information of the terminal, where the historical display information includes the time information of the terminal displaying each historical promotion information, and the historical promotion information is the promotion information that the terminal has displayed in the past preset time period based on the current moment; a calculation module, configured to calculate the probability that the terminal displays promotion information in multiple future preset time periods according to the historical display information; a prediction module, configured to predict the stop time corresponding to multiple promotion information in the database, including: obtaining the placement strategy and the total placement amount corresponding to multiple promotion information in the database; predicting the stop time corresponding to multiple promotion information in the database based on the obtained placement strategy and the total placement amount; A determination module, configured to determine, in the database, at least one promotion message with the highest revenue in each future time period as candidate promotion messages, wherein the stop broadcast time of the candidate promotion messages is later than the corresponding future time period; A display module, configured to select, from the database, the promotion message with the highest expected revenue in a future time period, and send the selected promotion message to the terminal, so that the terminal displays the selected promotion message to the user when a promotion message display request is triggered.

11. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein, when the processor executes the program, the steps of the promotion message display method according to any one of claims 1-9 are implemented.

12. A storage medium, characterized in that, a computer program is stored thereon, wherein when the computer program is executed by a processor, the steps of the promotion message display method according to any one of claims 1-9 are implemented.

Images