Media information display method, device, equipment and storage medium

Abstract

Embodiments of the present application disclose a media information display method, device and equipment and a storage medium, which are suitable for computer technology and big data field. The method comprises the following steps: in response to a media information display request, determining a media information set corresponding to the media information display request; obtaining display state information of each first type of media information and each second type of media information; obtaining display competition information of each first type of media information and each second type of media information according to the display state information; determining display evaluation values of each first type of media information and each second type of media information according to the display competition information; and determining target media information from the media information set according to the display evaluation values of each first type of media information and each second type of media information, and displaying the target media information. The embodiments of the present application can reasonably arrange the target media information displayed by the media information display request, and have high applicability.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, and particularly relates to a media information display method and device, equipment and storage medium. BACKGROUND

[0002] In a media information display scenario, different types of media information often have different display requirements or display methods. For example, in an advertisement display scenario, a contract advertisement needs to be displayed according to the contract content requirements, or a bid advertisement with a higher bid needs to be displayed.

[0003] In the existing media information display method, for a plurality of types of media information corresponding to a media information display request, which media information needs to be displayed is often determined based on the priority of different types of media information, or the display media information is performed based on the media information sequence corresponding to the media information display request.

[0004] However, since the display requirements of different types of media information at different times are not the same, the existing media information display method cannot reasonably arrange the target media information to be displayed for a media information display request, and the flexibility is poor. SUMMARY

[0005] The embodiments of the present application provide a media information display method, device, equipment and storage medium, which can reasonably arrange the target media information to be displayed for a media information display request, and have high applicability.

[0006] In one aspect, the embodiments of the present application provide a media information display method, which comprises:

[0007] In response to a media information display request, a media information set corresponding to the media information display request is determined, and the media information set comprises at least one first type of media information and at least one second type of media information;

[0008] Obtain the display state information of each of the first type of media information and each of the second type of media information, and the display state information comprises at least one of the displayed amount, the preset display amount, the preset access amount and the display object;

[0009] According to the display state information, obtain the display competition information of each of the first type of media information and each of the second type of media information;

[0010] According to the display competition information of each of the first type of media information and each of the second type of media information, the display evaluation value of each of the first type of media information and each of the second type of media information is determined respectively;

[0011] According to the display evaluation values of the media information of the first type and the media information of the second type, target media information is determined from the media information set, and the target media information is displayed.

[0012] In an aspect, an embodiment of the present application provides a media information display device, which comprises:

[0013] A media information determination module is configured to determine a media information set corresponding to a media information display request in response to the media information display request, wherein the media information set comprises at least one media information of a first type and at least one media information of a second type.

[0014] A display state information acquisition module is configured to acquire display state information of the media information of the first type and the media information of the second type, wherein the display state information comprises at least one of a displayed amount, a preset display amount, a preset access amount and a display object.

[0015] A display competition information acquisition module is configured to acquire display competition information of the media information of the first type and the media information of the second type according to the display state information.

[0016] A display evaluation value determination module is configured to determine display evaluation values of the media information of the first type and the media information of the second type respectively according to the display competition information of the media information of the first type and the media information of the second type.

[0017] A media information display module is configured to determine target media information from the media information set according to the display evaluation values of the media information of the first type and the media information of the second type, and display the target media information.

[0018] In an aspect, an embodiment of the present application provides an electronic device, which comprises a processor and a memory, and the processor and the memory are connected to each other.

[0019] The memory is configured to store a computer program.

[0020] The processor is configured to execute a media information display method provided by an embodiment of the present application when the computer program is invoked.

[0021] In an aspect, an embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement a media information display method provided by an embodiment of the present application.

[0022] In an aspect, the embodiments of the present application provide a computer program product or computer program, which comprises computer instructions stored in a computer readable storage medium. A processor of an electronic device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device executes the media information display method provided by the embodiments of the present application.

[0023] In the embodiments of the present application, the display competition information of each type of media information is obtained through the display state information of each type of media information. The display competition information of each type of media information is obtained by fully considering at least one of the displayed amount, the preset display amount, the preset access amount, and the display object of each media information. The display evaluation value of each type of media information is determined according to the display competition information of each type of media information. Therefore, the target media information to be finally displayed by each media information display request can be determined based on the display evaluation value, the display flexibility of each type of media information is improved, and the applicability is high. BRIEF DESCRIPTION OF DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiments will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0025] Figure 1 is a system flowchart of the media information display method provided by the embodiments of the present application;

[0026] Figure 2 is a flowchart of the media information display method provided by the embodiments of the present application;

[0027] Figure 3a is a scene diagram of displaying media information provided by the embodiments of the present application;

[0028] Figure 3b is another scene diagram of displaying media information provided by the embodiments of the present application;

[0029] Figure 4 is a flowchart of the training method of the media information evaluation model provided by the embodiments of the present application;

[0030] Figure 5 is a method diagram for determining an advertisement revenue score provided by the embodiments of the present application;

[0031] Figure 6 is an adjustment diagram of a contract advertisement squeeze relationship provided by the embodiments of the present application;

[0032] Figure 7 is a schematic diagram of constructing a competitive correlation graph provided by an embodiment of the present application;

[0033] Figure 8 is an application schematic diagram of a media information evaluation model provided by an embodiment of the present application;

[0034] Figure 9 is a framework diagram of a media information display system provided by an embodiment of the present application;

[0035] Figure 10 is a revenue schematic diagram of a contract advertisement and a bid advertisement provided by an embodiment of the present application;

[0036] Figure 11 is a structural schematic diagram of a media information display device provided by an embodiment of the present application;

[0037] Figure 12 is a structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0038] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0039] The media information display method provided by the embodiments of the present application relates to the fields of big data, block chain, computer, artificial intelligence (AI) and cloud technology, and can be specifically combined with Figure 1 to be described in detail.

[0040] Referring to Figure 1 , Figure 1 is a system flowchart of a media information display method provided by an embodiment of the present application. As shown in Figure 1 , in response to a media information display request 100, a media information set 200 corresponding to the media information display request 100 is determined, wherein the media information set 200 includes at least one first type of media information and at least one second type of media information. Further, for any media information in the media information set 200, display state information of the media information can be obtained, the display state information of the media information including at least one of a displayed amount of the media information, a preset access amount and a display object. Then, according to the display state information of the media information, display competition information of the media information is obtained.

[0041] Based on the above implementation manner, the display competition information of each first type of media information in the media information set 200 and the display competition information of each second type of media information can be obtained, so as to determine the display evaluation value of each first type of media information and each second type of media information respectively according to the display competition information of each first type of media information and each second type of media information.

[0042] Further, according to the display evaluation value of each first type of media information and each second type of media information, the target media information 300 can be determined from the media information set 200, and the target media information 300 is displayed through the display device 400.

[0043] In the embodiment of the present application, the machine learning or reinforcement learning in artificial intelligence can be used to learn how to respond to the media information display request 100, and then determine the target media information 300 corresponding to the media information display request 100, so as to display the target media information 300 through the display device 400.

[0044] Among them, artificial intelligence is to use digital computers or digital computer controlled machine simulation, extension and expansion of human intelligence, perception of environment, knowledge acquisition and use of knowledge to obtain the best results of theory, method, technology and application system. In other words, artificial intelligence is a comprehensive technology of computer science, which tries to understand the essence of intelligence, and produces a new intelligent machine that can react in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines, so that the machine has the functions of perception, reasoning and decision-making.

[0045] Artificial intelligence technology is a comprehensive discipline, involving a wide range of fields, both hardware and software level technology. Artificial intelligence basic technology generally includes such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction system, mechatronics and other technologies. Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology and machine learning (Machine Learning, ML), reinforcement learning (Reinforcement Learning, RL) and other major directions.

[0046] Machine learning is a multi-disciplinary subject involving probability theory, statistics, approximation theory, convex analysis, algorithmic complexity theory, etc. It is a specialized study of how computers simulate or implement human learning behavior to acquire new knowledge or skills, reorganize existing knowledge structure, and continuously improve performance. Machine learning is the core of artificial intelligence and the fundamental approach to making computers intelligent. It is applied in various fields of artificial intelligence. Machine learning and deep learning usually include artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and teaching learning. Reinforcement learning, also known as reward learning, evaluation learning, or enhancement learning, is one of the paradigms and methodologies of machine learning, which is used to describe and solve the problem of maximizing rewards or achieving specific goals through learning strategies in the interaction process between agents and environment.

[0047] In the embodiments of the present application, determining the media information set 200 corresponding to the media information display request 100, obtaining the display state information of each media information, and obtaining the display competition information of each media information can be implemented based on big data, blockchain, etc. In addition, the media information corresponding to each media information display request, and the display competition information and display state information of each media information can be stored in a database, a database management system, or a blockchain, or based on big data, cloud storage technology, etc. Through the functions of cluster application, grid technology, and distributed storage file system, a large number of various types of storage devices (storage devices are also called storage nodes) in the network are collected and work together through application software or application interface to store data.

[0048] The blockchain is a new application mode of distributed data storage, peer-to-peer transmission, consensus mechanism, and encryption algorithm. Essentially, the blockchain is a decentralized database, which is a series of data blocks associated using cryptographic methods, and each data block is used to store data. The blockchain can include a blockchain underlying platform, a platform product service layer, and an application service layer.

[0049] In the embodiments of the present application, the determination of the display evaluation value of each media information in the media information set 200 can be based on computer technology and cloud computing, etc. Cloud computing is the product of the development and integration of traditional computer and network technologies such as grid computing, distributed computing, parallel computing, utility computing, network storage, virtualization, load balancing, etc. Based on cloud computing, the computing efficiency of determining the display evaluation value in the embodiments of the present application can be improved.

[0050] In the embodiments of the present application, the media information display method provided by the present application can be executed by any terminal device or server.

[0051] In the embodiments of the present application, when the media information display method provided by the present application is executed by a server, the server can be a stand-alone physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server or a server cluster providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content distribution networks (CDN), and big data and artificial intelligence platforms, etc. basic cloud computing services. In addition, the server has media information display capability in addition to relevant data processing capability. In other words, when the media information display method provided by the present application is executed by a server, the server is the display device 400 in Figure 1 In the embodiments of the present application, when the media information display method provided by the present application is executed by a terminal device, the terminal device is the display device 400 in Figure 1 The terminal device can be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, an MP3 (Moving Picture Experts Group Audio Layer III) player, an MP4 (Moving Picture Experts Group Audio Layer IV) player, and a smart watch, etc., but is not limited thereto.

[0052] In the media information display method provided in the embodiments of the present application, the server and the terminal device can interact, for example, the server determines the media information set corresponding to the media information display request 100, obtains the display state information of each media information, obtains the display competition information of each media information, determines the display evaluation value of each media information, and determines the target media information 300 from the media information set 200 in response to the media information display request 100. The server sends the target media information 300 to the terminal device, and the terminal device (display device 400) displays the target media information 300.

[0053] In the embodiments of the present application, the target media information 300 can be displayed on the display page of an application when the target media information 300 is displayed, and the application includes but is not limited to a video playback application, a video live broadcast application, a news application, a reading application, a music playback application, a social application, a game application, a communication application, and a browser application, etc. The specific application can be determined based on the actual application scenario requirements, which is not limited herein.

[0054] Referring to Figure 2 , Figure 2 FIG. 1 is a flowchart of a media information display method provided in the embodiments of the present application. As shown in FIG. 1, the media information display method provided in the embodiments of the present application can include the following steps: Figure 2

[0055] In step S21, in response to a media information display request, a media information set corresponding to the media information display request is determined, and the media information set includes at least one first type of media information and at least one second type of media information.

[0056] In some possible implementation manners, the media information display request is a related request for requesting media information display, for example, a request for requesting to play an advertisement before playing a TV series, or a request for requesting to display a system announcement in a game, etc. The specific application can be determined based on the actual application scenario requirements, which is not limited herein.

[0057] In some possible implementation manners, the media information set corresponding to the media information display request is a media information set composed of media information matched with the media information display request. The media information display request indicates specific display requirement information, for example, for an advertisement, the display requirement information can be used to indicate the display object of the advertisement, including but not limited to fixed users, a playback platform, etc. For a game announcement, the display requirement information can be used to indicate a specified player, a specified game announcement playback mode, etc. It should be particularly noted that the specific display requirement information can be determined based on the actual application scenario requirements, which is not limited herein. ​

[0058] Based on this, after responding to the media information display request, the media information matched with the media information display request can be determined based on the display requirement information indicated by the media information display request, and the media information matched with the media information display request is determined as the media information set.

[0059] Optionally, if the number of media information matched with the media information display request exceeds a preset number threshold, that is, in the case that the number of media information matched with the media information display request is large, the part of media information can be screened, and the media information set is constituted based on the screened media information.

[0060] The screening manner includes but is not limited to screening based on the importance of each media information, the importance of the media information publishing user corresponding to the media information, and the data volume of the media information, and the specific screening manner can be determined based on the actual application scene requirement, which is not limited here.

[0061] Optionally, the media information matched with the media information display request can be screened based on the display device currently used for displaying the media information, for example, in the case that the display device does not have the function of displaying animation, the media information without animation can be screened to constitute the media information set.

[0062] In some possible embodiments, the media information set includes at least one first type of media information and at least one second type of media information. The first type of media information is media information with display quantity and display object requirements, and the second type of media information is media information obtained by resource payment to obtain display opportunities.

[0063] For example, the media information is an advertisement, the first type of media information can be a contract advertisement, and the second type of media information can be a bidding advertisement. The contract advertisement is that the advertiser signs a contract with the media party, and the media party plays a certain amount (predetermined amount) of advertisements to the advertiser for a specified type of user within a specified time. If the contract is reached, the advertiser pays a certain fee to the media, the media needs to compensate the advertiser if the play quantity does not reach the standard, and the media party will not charge the advertiser for additional fees when the advertisement play quantity exceeds the predetermined amount. For the bidding advertisement, the advertiser will give a bid for the same request, and multiple advertisers will bid for the same request, and the advertiser with the highest bid will win the advertisement display opportunity corresponding to the request.

[0064] For another example, the media information is a game announcement, and the first type of media information can be a system announcement, such as a system announcement of a player winning a prize, a system announcement of a map refreshing resource, etc. The second type of game announcement can be a player-purchased top announcement through game virtual assets.

[0065] It should be particularly pointed out that the first type of media information and the second type of media information can be determined based on actual application scene requirements, and are not limited herein.

[0066] Step S22, obtaining display state information of each first type of media information and each second type of media information.

[0067] In some possible implementation manners, the display state information of the first type of media information and the second type of media information includes at least one of a displayed quantity, a preset display quantity, a preset access quantity, and a display object. The displayed quantity is used to indicate the number of times that the media information has been displayed; the preset display quantity is used to indicate the display requirement of the media information, that is, the preset number of times of display required; the preset access quantity is used to indicate the number of times of browsing or accessing that the media information is expected to have; and the display object is used to indicate the object that the media information faces, such as a user group that browses the media information.

[0068] In the case where the media information is an advertisement, the displayed quantity, the preset display quantity, the preset access quantity, and the display object can be advertisement targeting, advertisement requirement, advertisement supply, and broadcasted data of the advertisement, respectively. The advertisement targeting is the people targeting corresponding to the advertisement, and the advertisement can only be displayed to users that meet the people targeting, such as “people under 30 years old in Shanghai”, “viewing people of a certain variety show or television series”, and the like. The advertisement requirement is the advertisement reservation quantity, that is, the exposure quantity of the advertisement reserved by an advertiser. The advertisement supply is the inventory corresponding to the advertisement, and since the advertisement has advertisement targeting, for example, the advertisement targeting of a certain advertisement is Shanghai users, and therefore the advertisement can only be displayed to Shanghai users. Based on this, the inventory corresponding to the advertisement refers to the expected access quantity of the corresponding advertisement targeting that can be matched by the advertisement. The broadcasted data is the exposed quantity of the advertisement.

[0069] Step S23, obtaining display competition information of each first type of media information and each second type of media information according to the display state information.

[0070] In some possible implementation manners, the display competition information of the first type of media information includes at least one of a predicted click rate and a predicted click conversion rate.

[0071] For any first type of media information, the predicted click rate corresponding to the first type of media information is the expected click rate after the first type of media information is displayed in response to a media information display request. In the case where the first type of media information is a contract advertisement, the predicted click rate of the contract advertisement is the ratio of the predicted click quantity of the contract advertisement to the predicted display quantity after the contract advertisement is played.

[0072] Further, the click-through rate corresponding to the first type of media information is the revenue conversion rate corresponding to the predicted click rate of the first type of media information after the media information is displayed in response to the media information display request. In the case where the first type of media information is a contract advertisement, the predicted click-through rate of the contract advertisement is the ratio of the predicted order quantity to the predicted click rate of the contract advertisement.

[0073] In some possible embodiments, the display competition information of the second type of media information comprises a predicted revenue indicator.

[0074] For any second type of media information, the predicted revenue indicator corresponding to the second type of media information is related information for characterizing the expected revenue of the second type of media information after the media information is displayed in response to the media information display request, which can be determined based on the actual application scenario requirement and is not limited herein. In the case where the second type of media information is a bid advertisement, the predicted revenue indicator of the bid advertisement can be the expected exposure per thousand revenue, i.e., the predicted revenue per thousand plays of the bid advertisement.

[0075] In some possible embodiments, for the display competition information of any media information in the first type of media information and the second type of media information, the display competition information cannot be predicted based on the display state information of the media information, or the prediction result based on the display state information is greatly different from the actual result. Therefore, when the display competition information of the media information is obtained based on the display state information of the media information, the display competition information of the media information can be obtained based on related media information of the media information which has the same type and a certain amount of displayed information.

[0076] Specifically, for any media information in the first type of media information and the second type of media information, reference media information having the same display state information as the display state information of the media information in a first time period can be determined, and reference display competition information of the reference media information is obtained to determine the display competition information of the media information based on the reference display competition information.

[0077] The reference display competition information of the reference media information can be determined as the display competition information of the media information, or the adjusted reference display competition information can be determined as the display competition information of the media information after the reference competition information is adjusted based on a preset adjustment coefficient, and the specific adjustment manner is not limited herein.

[0078] The reference media information and the media information are media information of the same type.

[0079] The first time period is a last time period before a response time of the media information display request, and a specific time span of the time period can be one day or several hours, which can be determined based on actual application scenarios and is not limited herein.

[0080] In the case of the same display state information, the reference media information already has a certain display amount, and thus the reference display competition information corresponding to the reference media information of the same type has a certain reference to the display competition information of the media information.

[0081] For example, in the case of the first type of media information being a contract advertisement, a reference contract advertisement with the same advertisement targeting and contract content as the contract advertisement can be determined in a last time period of a response time of an advertisement play request (media information display request), and a click rate and a click conversion rate (reference display competition information) of the reference contract advertisement corresponding to the last time period can be determined. For two contract advertisements with the same advertisement targeting (display object), the advertisement browsing habit of the same advertisement targeting (display object) does not change much in a short time, and the play effect is also approximately the same, so the click rate and the click conversion rate of the reference contract advertisement corresponding to the last time period can be determined as the predicted click rate and the predicted click conversion rate of the contract advertisement.

[0082] For example, in the case of the second type of media information being a bid advertisement, a reference bid advertisement with the same advertisement targeting (user group browsing the advertisement) as the bid advertisement can be determined in a last time period of a response time of an advertisement play request, and a thousand exposure revenue of the reference bid advertisement corresponding to the last time period can be determined, and then the thousand exposure revenue of the reference bid advertisement is determined as the expected exposure revenue per thousand times (predicted revenue index) of the bid advertisement.

[0083] In step S24, display evaluation values of the first type of media information and the second type of media information are respectively determined according to the display competition information of the first type of media information and the second type of media information.

[0084] In some possible implementation manners, for any media information in the first type of media information and the second type of media information, the display evaluation value of the media information is used to represent a revenue brought by displaying the media information, such as an advertisement revenue brought by playing an advertisement. The higher the display evaluation value of the media information is, the higher the revenue brought by displaying the media information in response to a media information display request is. In the specific determination process, weights of each part of the display competition information of the media information can be determined, and then the display evaluation value of the media information is determined based on each part of the display competition information of the media information and the corresponding weights.

[0085] Specifically, for each first type of media information, a weight (for convenience of description, referred to as a first weight below) corresponding to the predicted click rate and the predicted click conversion rate in the display competition information of the media information can be determined, and a display evaluation value of the media information is determined according to the predicted click rate and the predicted click conversion rate in the display competition information of the media information and the first weight corresponding thereto.

[0086] For example, the click rate (Click Through Rate, ctr) and the click conversion rate (Conversion Rate, cvr) of the reference media information corresponding to the media information in the last period are determined as the predicted click rate and the predicted click conversion rate of the media information respectively, the first weight of the predicted click rate of the media information is w_ctr, and the first weight of the predicted click conversion rate is w_cvr, and the display evaluation value of the media information can be determined based on w_ctr*ctr+w_cvr*cvr.

[0087] Optionally, for each first type of media information, in addition to determining the first weight corresponding to the predicted click rate and the predicted click conversion rate in the display competition information of the media information, the display revenue of the media information and a corresponding weight (for convenience of description, referred to as a third weight below) also need to be obtained. The display revenue of the media information can be used to represent the revenue brought by displaying the media information once. Based on this, the display evaluation value of the media information can be determined based on the display revenue corresponding to the media information and the corresponding third weight, the predicted click rate and the predicted click conversion rate corresponding to the media information and the first weight corresponding thereto.

[0088] For example, the click rate and the click conversion rate of the reference media information corresponding to the media information in the last period are determined as the predicted click rate and the predicted click conversion rate of the media information respectively, the display revenue of the media information is play, the first weight of the predicted click rate of the media information is w_ctr, the first weight of the predicted click conversion rate is w_cvr, and the third weight corresponding to the display revenue is w_play, and the display evaluation value of the media information can be determined based on w_ctr*ctr+w_cvr*cvr+w_play*play. The specific value of the display revenue play of the media information can be determined based on the actual application scenario requirement, which is not limited here.

[0089] Specifically, for each second type of media information, a weight (for convenience of description, referred to as a second weight below) corresponding to the predicted revenue indicator in the display competition information of the media information can be determined, and then a display evaluation value of the media information is determined according to the predicted revenue indicator in the display competition information of the media information and the second weight corresponding thereto.

[0090] For example, a reference media information corresponding to the media information is determined as a cost per mile (cpm) of each thousand exposure in a last period, an expected cost per mile (ecpm) of each thousand exposure of the media information is determined as the cost per mile (cpm) of each thousand exposure of the reference media information, a second weight corresponding to the expected cost per mile (ecpm) of each thousand exposure of the media information is w_ecpm, and then the display evaluation value of the media information is determined based on w_ecpm*w_ecpm.

[0091] It should be particularly pointed out that the specific weight values of the first weight, the second weight, and the third weight can be determined based on actual application scene requirements, and are not limited herein.

[0092] In step S25, the target media information is determined from the media information set based on the display evaluation values of the media information of each first type and the media information of each second type, and the target media information is displayed.

[0093] In some possible implementations, since the display evaluation value is used to represent the benefit brought by displaying the corresponding media information at the requested response time of the media information display, the media information of each first type and the media information of each second type can be sorted based on the display evaluation values of the media information of each first type and the media information of each second type, and the target media information can be determined from the media information set based on the sorting result.

[0094] Specifically, the media information with the highest display evaluation value can be selected from the media information set based on the sorting result as the target media information, and the target media information is displayed. Alternatively, a preset number of media information can be sequentially selected from the media information set based on the sorting result as the target media information, and the target media information is displayed. The preset number can be determined based on actual media information display mode and requirements, and is not limited herein. For example, if there are two advertisement display positions in an advertisement pop-up window, when the target media information is determined, the two advertisements with the highest display evaluation values can be selected from the media information set based on the sorting result, and the selected two advertisements are played in the two advertisement display positions, respectively.

[0095] In some possible implementations, the media information includes but is not limited to one or a combination of media elements such as pictures, animations, texts, and voices, and is not limited in the embodiments of the present application.

[0096] In some possible implementations, when the target media information is displayed, the target media information can be displayed based on a preset media information display position and a display position corresponding to the media information display request.

[0097] Referring to Figure 3a , Figure 3ais a scene schematic diagram of displaying media information provided by an embodiment of the present application. As shown in Figure 3a The mobile terminal shown in FIG. 2B can play the target advertisement on the playing interface of the mobile terminal after responding to the media information display request and determining the target advertisement from the numerous advertisements.

[0098] Based on the media information display method provided by the embodiment of the present application, in the case that the first type of media information is contract advertisement and the second type of media information is bidding advertisement, the target advertisement corresponding to each media information display request can be determined, so that in the case that contract advertisement and bidding advertisement exist simultaneously, the advertisements played at different times can be reasonably allocated to improve the advertisement playing income.

[0099] Referring to Figure 3b , Figure 3b is another scene schematic diagram of displaying media information provided by an embodiment of the present application. Figure 3b The game interface based on the mobile terminal is shown, and game announcements are continuously displayed above the game interface, and each game announcement is a target game announcement determined in response to a different announcement playing request (media information display request). For the game announcement 1, the game announcement 1 is a target game announcement (target media information) corresponding to the announcement playing request triggered by player Zhang San when he obtains the gold coins after opening the “Autumn Lucky Bag” (time 1). In addition to the “Autumn Lucky Bag”, there are other lucky bags in the game, and after a plurality of players open different lucky bags at a certain time, the announcement playing request at the time can correspond to a plurality of game announcements about the rewards of different lucky bags.

[0100] For the game announcement 2, the game announcement 2 is a game announcement obtained by player “Li Si” through virtual assets at time 2, and the content is to congratulate “Zhang San”. Similarly, since the number of players is large, a plurality of players will obtain game announcements through virtual assets at the same time.

[0101] Similarly, for the announcement playing requests at time 1 and time 2, the game announcements corresponding to the announcement playing requests can include game announcements about lucky bag rewards and game announcements obtained by players through virtual assets. Based on the media information display method provided by the embodiment of the present application, the target game announcement corresponding to the announcement playing request at the time can be determined at different times, and the target game announcement is displayed in the game interface. For example, if the game announcement 1 is displayed at time 1, more players can be attracted to purchase the “Autumn Lucky Bag” to maximize the game income. If the game announcement 2 is displayed at time 2, the virtual assets paid by the players are the maximum income that the game system at the time can obtain.

[0102] In some possible implementation manners, the display evaluation values of the media information of the first type and the media information of the second type are determined by a media information evaluation model according to the display competition information of the media information of the first type and the media information of the second type.

[0103] The training manner of the media information evaluation model can be referred to Figure 4 , Figure 4 is a flowchart of a training method of a media information evaluation model provided in the embodiments of the present application. As shown in Figure 4 , the training method of the media information evaluation model provided in the embodiments of the present application can include the following steps:

[0104] In step S41, a training sample set is obtained, each training sample in the training sample set is historical display competition information of each historical media information in a historical media information set, each historical media information set is a historical media information set corresponding to a historical media information display request in a historical time period, and each historical media information set includes at least one historical media information of the first type and at least one historical media information of the second type.

[0105] In the time period, there are a plurality of historical media information display requests, and each historical media information display request is matched with a historical media information set.

[0106] The specific time span of the historical time period can also be one day, several hours, etc., and can be determined based on actual application scene requirements, which is not limited herein. The historical media information of the first type and the historical media information of the second type in the historical media information set are historical media information that has been displayed.

[0107] Similarly, in the case where the historical media information of the first type is a contract advertisement, the historical competition information of the contract advertisement includes the click rate and the click conversion rate of the contract advertisement in the corresponding historical time period. In the case where the historical media information of the second type is a bid advertisement, the revenue indicator of the bid advertisement can be the revenue per thousand exposures of the bid advertisement in the corresponding historical time period.

[0108] In some possible implementation manners, the historical display competition information of each historical media information is obtained based on historical display state information of each historical media information, and the historical display state information and the historical display competition information of each historical media information of the first type and each historical media information of the second type can be obtained in the manner shown in steps S22-S23 in Figure 2 , which will not be repeated herein.

[0109] In the embodiments of the present application, the historical display state information corresponding to each training sample also includes at least one of the corresponding displayed amount, the preset display amount, the preset access amount, and the display object, the historical display state information of the historical media information of the first type corresponding to each training sample includes at least one of the click rate and the click conversion rate, and the historical display competition information of the historical media information of the second type corresponding to each training sample includes the revenue index.

[0110] In some possible implementation manners, the training sample set for training the media information evaluation model can be obtained from a database, the Internet, and a blockchain based on big data technology, and the present application is not limited in the embodiments.

[0111] In step S42, each training sample is input into the initial media information evaluation model to obtain the display evaluation values of the historical media information of the first type and the media information of the second type corresponding to each training sample.

[0112] In some possible implementation manners, the initial media information evaluation model in the embodiments of the present application includes, but is not limited to, an initial model for training the media information evaluation model constructed by learning algorithms, neural networks, and the like. The algorithms include, but are not limited to, a network model constructed based on a proportion integration differentiation (PID) algorithm and an asynchronous advantage actor critic (A3C) algorithm, and the present application is not limited in the embodiments.

[0113] In some possible implementation manners, the model input of the initial media information evaluation model is each training sample, that is, the historical display competition information of the historical media information of the first type and the historical media information of the second type. The output of the initial media information evaluation model is the display evaluation values of the historical media information of the first type and the historical media information of the second type.

[0114] In the embodiments of the present application, the specific implementation manner of the initial media information evaluation model for determining the display evaluation values of the historical media information of the first type and the historical media information of the second type can refer to the implementation manner shown in step S24 in Figure 2 , and details are not described herein.

[0115] In some possible implementation manners, the input of the initial media information evaluation model can be the historical display state information and the historical display competition state information of the historical media information of each first type and the historical media information of each second type, and the initial media information evaluation model can obtain the display evaluation value of the historical media information of each first type and the historical media information of each second type based on the correlation between the historical display state information and the historical display competition state information of each historical media information.

[0116] As an example, refer to Figure 5 , Figure 5 is a schematic diagram of a method for determining an advertising revenue score provided by an embodiment of the present application. As shown in Figure 5 , the historical media information of each first type is a historical contract advertisement, and the historical media information of each second type is a historical bidding advertisement, and the display evaluation value of each historical advertisement is a revenue score. Wherein, the historical display state information of each historical contract advertisement and each historical bidding advertisement includes played data (displayed quantity), demand (preset display quantity), supply (preset access quantity), and advertisement targeting (display object), the historical display competition information of each historical contract advertisement includes the click rate and the click conversion rate of the historical contract advertisement, and the historical display competition information of each historical bidding advertisement includes the revenue per thousand exposures. Based on this, the initial media information evaluation model can obtain the revenue score of each historical contract advertisement and each historical bidding advertisement based on the played data, the advertisement targeting, the demand, the supply, the cvr and the ctr of the historical contract advertisement, and the cpm of the historical bidding advertisement in each training.

[0117] In some possible implementation manners, since each media information corresponds to a respective display object, the display objects of any multiple media information can have an intersection, such as Shanghai users including Shanghai male users. Based on this, in the actual media information display process, for multiple media information of each first type with an intersection of display objects, the specific display objects of each first type of media information need to be reasonably allocated to avoid the situation that the first type of media information with a display object of Shanghai users is displayed to Shanghai male users, so that the first type of media information corresponding to Shanghai male users cannot be displayed to Shanghai male users.

[0118] For example, taking a contract advertisement as an example, refer to Figure 6 , Figure 6 is an adjustment schematic diagram of a contract advertisement squeeze relationship provided by an embodiment of the present application. In Figure 6In the figure, it is assumed that there are three contract advertisement advertisement orders, order 1 has a demand of 8 times of playing to Shanghai users, order 2 has a demand of 4 times of playing to Shanghai female users, and order 3 has a demand of 4 times of playing to Shanghai male users. Each square in the figure is an inventory. If order 1 arrives first without considering the advertisement targeting among the contract advertisements, 8 inventories of Shanghai males are allocated to order 1, order 2 arrives, 4 inventories of Shanghai females are allocated to order 2, and when order 3 arrives, there is no inventory that can be allocated to order 3, and there is waste of available inventory.

[0119] Therefore, if the inventory squeezing relationship of the contract advertisements is considered, the above inventory allocation manner can be adjusted, that is, 4 inventories of Shanghai males and 4 inventories of Shanghai females are allocated to order 1, order 2 can obtain 4 inventories of Shanghai females, and order 3 can obtain 4 inventories of Shanghai males, so that the contract advertisement inventory can be reasonably utilized, and the advertisement revenue maximization can be realized.

[0120] Based on this, in order to fully consider the squeezing relationship among the first type of media information when determining the display evaluation values of the first type of media information and the second type of media information by the trained media information evaluation model, when training the initial media information evaluation model, the competition correlation features of the first type of historical media information can be used as inputs of the initial media information evaluation model. The competition correlation features of the first type of historical media information can be used to represent the correlation relationship between the historical display states of the first type of historical media information.

[0121] For each training sample, the competition correlation features of the first type of historical media information corresponding to the training sample are determined based on the historical display state information of the first type of historical media information corresponding to the training sample.

[0122] Specifically, for each training sample, the competition correlation relationship between the first type of historical media information corresponding to each training sample can be determined according to the historical display state information of the first type of historical media information corresponding to each training sample, and then a competition correlation relationship graph is constructed according to the competition correlation relationship.

[0123] Referring to Figure 7 , Figure 7 is a schematic diagram for constructing a competition correlation relationship graph provided by an embodiment of the present application. Figure 7The historical contract advertisement corresponding to order 1 is an advertisement played to variety viewers, the historical contract advertisement corresponding to order 2 is an advertisement played to Shanghai viewers, the historical contract advertisement corresponding to order 3 is an advertisement played to Beijing variety viewers, and the historical contract advertisement corresponding to order n is an advertisement played to all viewers. It is assumed that there are n inventories, that is, preset access amounts in different dimensions. The inventory S1 is a preset access amount of Shanghai variety viewers, the inventory S2 is a preset access amount of Beijing variety viewers, the inventory S3 is a preset access amount of Shanghai television drama viewers, the inventory S4 is a preset access amount of Beijing television drama viewers, and the inventory Sn is a preset access amount of Shenzhen viewers.

[0124] For the historical contract advertisement corresponding to order 1, the historical contract advertisement can be played to Shanghai variety viewers and Beijing variety viewers at the time of advertisement delivery. For the historical contract advertisement corresponding to order 2, the historical contract advertisement can be played to Shanghai variety viewers and Shanghai television drama viewers at the time of advertisement delivery. For the historical contract advertisement corresponding to order 3, the historical contract advertisement can be played to Beijing variety viewers at the time of advertisement delivery. For the historical contract advertisement corresponding to order n, the historical contract advertisement can be played to Shanghai variety viewers, Beijing variety viewers, Shanghai television drama viewers, Beijing television drama viewers, and Shenzhen viewers at the time of advertisement delivery.

[0125] Based on the competitive correlation between each historical contract advertisement corresponding to each inventory, a bipartite graph (competitive correlation graph) as shown in the figure can be constructed. Figure 7 The competitive correlation between the historical contract advertisements corresponding to each order can be represented by a line with the same starting point or the same key point.

[0126] Further, in order to train the initial media information evaluation model, the competitive correlation graph can be feature extracted by a graph neural network, and the competitive correlation graph is represented by a vector to obtain the competitive correlation features of each first type of historical media information corresponding to the training sample. Further, when training the initial media information evaluation model, the competitive correlation features can be input into the model at the same time, so that when the initial media information evaluation model learns the competitive correlation between each first type of historical media information, the display evaluation values of each first type of historical media information and each second type of historical media information are determined.

[0127] In step S43, a total display evaluation value corresponding to all historical media information display requests in each sub-period is determined according to the display evaluation values of the historical media information of each first type and the media information of each second type.

[0128] In some possible embodiments, since a large number of historical media information display requests exist in each historical period, to improve the model training effect and efficiency, a total display evaluation value corresponding to all historical media information display requests in each sub-period can be determined, so as to train the initial media information evaluation model according to the total display evaluation value and each training sample. Each historical period includes at least one sub-period. For example, the above historical period is one day, and the above sub-period can be one hour.

[0129] Specifically, for each historical media information display request, after the display evaluation values of the historical media information of each first type and the media information of each second type corresponding to the historical media information display request are determined, the maximum evaluation value in the display evaluation values of the historical media information of each first type and the historical media information of each second type corresponding to the historical media information display request can be determined.

[0130] The maximum evaluation value corresponding to the historical media information display request represents that the highest income is obtained by displaying the historical media information corresponding to the maximum evaluation value in response to the historical media information display request.

[0131] Further, for each sub-period, a total display evaluation value corresponding to all historical media information display requests in the sub-period can be determined according to the maximum display evaluation values corresponding to the historical media information display requests in the sub-period.

[0132] The total display evaluation value can be the sum of all the maximum display evaluation values corresponding to the sub-period, or the weighted sum of all the maximum display evaluation values corresponding to the sub-period. The weight of each maximum display evaluation value can represent the importance of the corresponding historical media information display request, or the importance of the historical media information corresponding to the maximum display evaluation value, and the like, which is not limited in the embodiments of the present application.

[0133] For example, each historical period is one day, each sub-period is one hour, the historical media information is a historical advertisement, and the historical media information display request is a historical advertisement play request. When determining the total display evaluation value corresponding to each hour, the display evaluation values corresponding to all historical advertisements in the hour are determined, and then one maximum display evaluation value corresponding to each historical advertisement play request in the hour is determined, so that the sum of the maximum display evaluation values corresponding to all historical advertisement play requests is determined as the total display evaluation value corresponding to the hour.

[0134] The total display evaluation value corresponding to each sub-period is the total revenue corresponding to each historical media information display request in the sub-period after responding to all historical media information display requests in the sub-period and determining the historical media information that needs to be displayed. For example, for an hour, there is a maximum display evaluation value (highest revenue) corresponding to each historical advertisement display request in the hour, and the total revenue corresponding to displaying all advertisements in the hour is the sum of the highest revenues corresponding to each historical advertisement display request.

[0135] In step S44, the initial media information evaluation model is iteratively trained according to the total display evaluation value and each training sample, and when the total display evaluation value meets a preset training end condition, the model at the time of stopping training is determined as the media information evaluation model.

[0136] In some possible implementations, the input of the initial media information evaluation model is a training sample each time the training is performed, and then the total display evaluation value corresponding to a sub-period is determined based on the display evaluation value of each historical media information corresponding to the training sample. Then, the model parameters of the initial media information evaluation model are continuously adjusted according to the total display evaluation value corresponding to each sub-period, so as to continuously improve the stability and accuracy of the initial evaluation model in determining the display evaluation value of each historical media information. When the total display evaluation value of the initial media information evaluation model meets a preset training end condition, the model at the time of stopping training is determined as the final media information evaluation model.

[0137] The training end condition can be that the total display evaluation value no longer improves, or the difference between the total display evaluation values of a continuous number of training times is less than a set value (that is, the difference between the total display evaluation values of a continuous number of times is very small and tends to be stable), which is not limited herein.

[0138] The application of the media information evaluation model provided in the embodiments of the present application will be described below. Figure 8 The application of the media information evaluation model provided in the embodiments of the present application will be described below. Figure 8 , Figure 8 is a schematic diagram of the application of the media information evaluation model provided in the embodiments of the present application. In Figure 8 , one time slice is one sub-period, the training samples corresponding to each time slice in the two historical time periods of the day before yesterday and yesterday are used as the model input in the model training stage, and the final media information evaluation model is determined by combining the total display evaluation value corresponding to the time slice. If a media information display request is received at T time of today, the target media information corresponding to the media information display request at T time can be predicted by the media information evaluation model according to the display state information of each media information corresponding to the media information display request before T time and the obtained display competition information. In other words, the target media information corresponding to the media information display request of each time slice of today can be determined by the media information evaluation model.

[0139] In some possible implementations, the embodiments of the present application further provide a framework diagram of a media information display system. Referring to FIG. 9, Figure 9 , Figure 9 is a framework diagram of a media information display system provided by the embodiments of the present application, and the first type of media information is contract advertisement, and the second type of media information is bidding advertisement. In Figure 9 The media information display system shown in FIG. 9, the mixed arrangement model 920 is in the center position, including the media information evaluation model in the embodiments of the present application. In addition to including the broadcast control parameter 941, the request log 944, the exposure log and the inventory 945, the input of the mixed arrangement model further includes the bidding advertisement revenue distribution, the bidding advertisement revenue feedback and the contract advertisement revenue feedback and the like, which can be determined based on the training mode of the actual mixed arrangement model.

[0140] The mixed arrangement model 920 can give parameters (ecpm target, ctr target and guaranteed quantity target and the like) for bidding target and contract target, and transmit the dictionary structure into the feature server (FeatureServer) 911, and finally get the ranking results corresponding to the bidding advertisement and the contract advertisement in the mixer 912.

[0141] Among them, the data source 950, the data transmission 940 and the data processing 930 three modules complete the processing operation from the original data to the model input, which are described as follows:

[0142] The inventory 945 is derived from the inventory system 953, which is a detailed prediction for the future using past data, accurate to each advertisement play request and each advertisement mapping, which can reflect the inventory of each advertisement order on a given day. The bipartite graph is calculated based on the inventory data, and through the bipartite graph we can get the competitive correlation relationship between the contract advertisements.

[0143] The log 952 is divided into two kinds: request log 944 and exposure log 943. For example, the log 952 can be TDW log, the request log 944 can be track_log data, and the exposure log 943 can be joined_exposure data.

[0144] Among them, the request log 944 can obtain the corresponding advertisement set (which can exist in the form of a queue) of each advertisement play request, through the precise arrangement queue for a period of time and the ecpm, pctr, filtering condition, support strategy and the like data of all advertisements in the queue, through the data simulation online competitive environment, if the distribution difference is small enough, it can be assumed that the distribution of the historical bidding advertisement and the contract advertisement is the same as the predicted environment.

[0145] The exposure log 943 can obtain specific push information actually exposed by each advertisement play request, and corresponding billing and eCPM information. Through the exposure log, feedback related to the online bidding advertisement can be obtained. Moreover, for each advertisement, the displayed quantity (played quantity) of the advertisement can be determined from the exposure log 943.

[0146] The play control parameter 941 refers to that the play control of the contract advertisement is currently affected by various play control parameters such as rate and theta, and is key information for assisting in adjusting the guaranteed quantity of the contract advertisement.

[0147] The online system 910 has two. The first is a feature server (Feature Server, fs) 911. In the embodiment of the present application, the display evaluation value of each advertisement can be transmitted to the fs, and the fs integrates and waits for the request of a mixing module 912.

[0148] The second is the mixing module 912 (mixer). The mixer is a very complex system, and the part related to the embodiment of the present application is a mixing module. After an advertisement play request arrives, the mixer receives a corresponding advertisement set including bidding advertisements and contract advertisements, then requests the display evaluation value of each advertisement from the fs, and performs bidding on each advertisement based on the display evaluation value of each advertisement to obtain the target advertisement finally displayed.

[0149] In the embodiment of the present application, the display competition information of each type of media information is obtained through the display state information of each type of media information. The display competition information of each type of media information can be obtained by fully considering at least one of the displayed quantity, the preset display quantity, the preset access quantity, and the display object of each type of media information. Moreover, the display evaluation value of each type of media information is determined according to the display competition information of each type of media information. Therefore, the target media information finally displayed by each media information display request can be determined based on the display evaluation value, the display flexibility of each type of media information is improved, and the applicability is high.

[0150] Further, the training method of the media information evaluation model provided in the embodiment of the present application can determine the display evaluation value of each historical media information by fully considering the historical display competition information of each type of historical media information and the competition association relationship between the historical media information of the first type. Therefore, after the final media information evaluation model is trained, the evaluation value of each type of media information corresponding to the current media information display request determined based on the media information evaluation model has higher accuracy and reference, so that the target media information corresponding to each media information display request is more reasonable.

[0151] And, in the case that each type of media information has a display benefit, by flexibly arranging the target media information displayed by each media information display request, the maximum media information display benefit can be achieved in the case that there are multiple types of media information in a certain period. For example, in the case that the first type of media information is a contract advertisement and the second type of media information is a bid advertisement, the actual played advertisement corresponding to each advertisement play request can be reasonably determined based on the media information display method provided in the embodiments of the present application, and then the advertisements required to be played at each time in a period (such as a day) can be reasonably allocated, so as to reasonably allocate the playing of the contract advertisement and the bid advertisement and improve the overall advertisement playing benefit.

[0152] Referring to Figure 10 , Figure 10 is a benefit diagram of the contract advertisement and the bid advertisement provided in the embodiments of the present application. Figure 10 The inventory distribution of the contract advertisement and the cpm distribution of the bid advertisement in a day under the existing advertisement playing method are shown in the figure. For the contract advertisement, the higher the inventory is, the higher the benefit is. For the bid advertisement, the higher the cpm is, the higher the benefit is. Figure 10 It can be known that the inventory of the contract advertisement is less in the morning and the cpm of the bid advertisement is higher, that is, the benefit of the contract advertisement is low in the morning and the benefit of the bid advertisement is high. In order to reasonably allocate the playing time of the bid advertisement and the contract advertisement at different times, the inventory distribution of the contract advertisement, the cpm distribution of the bid advertisement, the competition among the contract advertisements and the competition among the bid advertisements are considered, the playing of the bid advertisement and the contract advertisement is reasonably allocated, and the overall advertisement playing benefit is improved.

[0153] Referring to Figure 11 , Figure 11 is a structural schematic diagram of a media information display device provided in the embodiments of the present application. The media information display device 1 provided in the embodiments of the present application comprises:

[0154] A media information determination module 11, configured to determine a media information set corresponding to a media information display request in response to the media information display request, wherein the media information set comprises at least one first type of media information and at least one second type of media information;

[0155] An exhibition state information acquisition module 12, configured to acquire exhibition state information of each of the first type of media information and the second type of media information, wherein the exhibition state information comprises at least one of a displayed amount, a preset display amount, a preset access amount and a display object;

[0156] An exhibition competition information acquisition module 13, configured to acquire exhibition competition information of each of the first type of media information and the second type of media information according to the exhibition state information.

[0157] The display evaluation value determination module 14 is configured to determine a display evaluation value of each of the first type of media information and the second type of media information according to the display competition information of each of the first type of media information and the second type of media information.

[0158] The media information display module 15 is configured to determine a target media information from the set of media information according to the display evaluation value of each of the first type of media information and the second type of media information, and display the target media information.

[0159] In some possible implementation manners, the display competition information acquisition module 13 is configured to:

[0160] For each of the first type of media information and the second type of media information, determine a reference media information having the same display state information as the display state information of the media information in a first time period, wherein the media information and the reference media information are the same type of media information, and the first time period is a last time period of a response time corresponding to the media information display request.

[0161] Acquire reference display competition information of the reference media information, and determine the display competition information of the media information according to the reference display competition information.

[0162] In some possible implementation manners, the display competition information of the first type of media information includes at least one of the following:

[0163] A predicted click rate and a predicted click conversion rate.

[0164] The display competition information of the second type of media information includes a predicted revenue index.

[0165] In some possible implementation manners, the display evaluation value determination module 14 is configured to:

[0166] For each of the first type of media information, determine a first weight corresponding to the predicted click rate and the predicted click conversion rate in the display competition information of the media information respectively, and determine the display evaluation value of the media information according to the predicted click rate, the predicted click conversion rate and the first weight corresponding to the predicted click rate and the predicted click conversion rate respectively in the display competition information of the media information.

[0167] For each of the second type of media information, determine a second weight corresponding to the predicted revenue index in the display competition information of the media information, and determine the display evaluation value of the media information according to the predicted revenue index and the second weight corresponding to the predicted revenue index in the display competition information of the media information.

[0168] In some possible implementation manners, for each media information of the first type, the display evaluation value determination module 14 is configured to:

[0169] obtain a display income of the media information and a corresponding third weight;

[0170] determine a display evaluation value of the media information according to the display income, the third weight corresponding to the display income, a predicted click rate and a predicted click conversion rate in the display competition information of the media information, and respective first weights.

[0171] In some possible implementation manners, the media information display module 15 is configured to

[0172] sort the media information of the first type and the media information of the second type according to the display evaluation values of the media information of the first type and the media information of the second type;

[0173] determine target media information from the media information set according to a sorting result.

[0174] In some possible implementation manners, the media information of the first type is media information with a display quantity and display object requirement, and the media information of the second type is media information that obtains a display opportunity by paying a resource.

[0175] In some possible implementation manners, the display evaluation value of the media information of the first type and the display evaluation value of the media information of the second type are determined according to the display competition information of the media information of the first type and the media information of the second type by using a media information evaluation model.

[0176] The media information evaluation model is obtained by training a training device, and the training device is configured to:

[0177] obtain a training sample set, each training sample in the training sample set being historical display state information and historical display competition information of historical media information in a historical media information set, each historical media information set being a historical media information set corresponding to a historical media information display request in a historical period, and each historical media information set including at least one historical media information of the first type and at least one historical media information of the second type;

[0178] input each training sample into an initial media information evaluation model to obtain a display evaluation value of each historical media information corresponding to each training sample;

[0179] determine a total display evaluation value corresponding to all historical media information display requests in each sub-period, each of the historical periods comprising at least one of the sub-periods;

[0180] perform iterative training on the initial media information evaluation model according to the total display evaluation value and each of the training samples, and when the total display evaluation value meets a preset training end condition, determine the model at the time of stopping the training as the media information evaluation model.

[0181] In some possible implementation manners, the training apparatus is configured to:

[0182] For each historical media information display request, determine a maximum display evaluation value from the display evaluation values of the historical media information corresponding to the historical media information display request;

[0183] For each sub-period, determine a total display evaluation value corresponding to all historical media information display requests in the sub-period according to the maximum display evaluation values of the historical media information corresponding to the historical media information display requests in the sub-period.

[0184] In some possible implementation manners, the input of the initial media information evaluation model further comprises competitive correlation features of the historical media information of the first type corresponding to each of the training samples;

[0185] The training apparatus is configured to:

[0186] determine the competitive correlation features of the historical media information of the first type corresponding to the training sample according to the historical display state information of the historical media information of the first type corresponding to the training sample.

[0187] In some possible implementation manners, for each training sample, the training apparatus is configured to:

[0188] determine a competitive correlation relationship between the historical media information of the first type corresponding to the training sample according to the historical display state information of the historical media information of the first type corresponding to the training sample;

[0189] construct a competitive correlation relationship graph according to the competitive correlation relationship, and determine the competitive correlation features of the historical media information of the first type corresponding to the training sample according to the competitive correlation relationship graph.

[0190] The media information display apparatus can be a computer program (including program code) running in a computer device, for example, the media information display apparatus is an application software; the apparatus can be configured to perform corresponding steps in the media information display method provided in the embodiments of the present application.

[0191] In some possible implementation manners, the media information display apparatus provided in the embodiments of the present application can be implemented in a combination of hardware and software. For example, the media information display apparatus provided in the embodiments of the present application can be a processor in the form of a hardware decoding processor, which is programmed to perform the media information display method provided in the embodiments of the present application. For example, the processor in the form of a hardware decoding processor can be implemented by using one or more application specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic elements.

[0192] In some possible implementation manners, the media information display apparatus provided in the embodiments of the present application can be implemented in software. The apparatus 1 can execute the implementation manners provided in the above steps by using the built-in function modules, and details can be referred to the implementation manners provided in the above steps, which will not be described herein again. Figure 2 and / or Figure 4 In some possible implementation manners, the media information display apparatus provided in the embodiments of the present application can be implemented in software. The apparatus 1 can execute the implementation manners provided in the above steps by using the built-in function modules, and details can be referred to the implementation manners provided in the above steps, which will not be described herein again.

[0193] Referring to Figure 12 , Figure 12 is a structural schematic diagram of an electronic device provided in the embodiments of the present application. As shown in Figure 12 , the electronic device 1000 in the embodiments can include a processor 1001, a network interface 1004 and a memory 1005. In addition, the electronic device 1000 can further include a user interface 1003 and at least one communication bus 1002. The communication bus 1002 is configured to realize the connection and communication among the components. The user interface 1003 can include a display, a keyboard, and optionally a standard wired interface and a wireless interface. The network interface 1004 can optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1004 can be a high-speed RAM memory or a non-volatile memory such as at least one disk memory. The memory 1005 can optionally be at least one storage device located away from the processor 1001. As shown in Figure 12 , the memory 1005 as a computer readable storage medium can include an operating system, a network communication module, a user interface module and a device control application program.

[0194] In Figure 12 In the electronic device 1000 shown, the network interface 1004 can provide network communication functions; the user interface 1003 is mainly used to provide an interface for user input; and the processor 1001 can be used to invoke a device control application stored in the memory 1005 to implement the media information display method provided in the embodiments of the present application.

[0195] It should be understood that, in some possible implementations, the processor 1001 described above can be a central processing unit (CPU), and the processor can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The memory can include a read-only memory and a random access memory, and provide the processor with instructions and data. Part of the memory can also include a non-volatile random access memory.

[0196] In a specific implementation, the electronic device 1000 described above can execute the implementation manners provided in each of the steps of the above Figure 2 and / or Figure 4 , and specific implementation manners provided in each of the steps are described above, which will not be described here.

[0197] The embodiments of the present application also provide a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the method provided in each of the steps of Figure 2 and / or Figure 4 , and specific implementation manners provided in each of the steps are described above, which will not be described here.

[0198] The computer readable storage medium can be an internal storage unit of the aforementioned media information presentation device and / or electronic device, such as a hard disk or a memory of the electronic device. The computer readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, and the like. The computer readable storage medium can also include a magnetic disc, an optical disc, a read-only memory (ROM) or a random access memory (RAM), and the like. Further, the computer readable storage medium can include both the internal storage unit and the external storage device of the electronic device. The computer readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer readable storage medium can also be used to temporarily store data that has been output or will be output.

[0199] The embodiments of the present application provide a computer program product or computer program, which includes computer instructions stored in a computer readable storage medium. A processor of an electronic device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to make the computer device perform the method provided by each step in Figure 2 and / or Figure 4

[0200] The terms "first", "second", and the like in the claims and specification and drawings of the present application are used to distinguish different objects, and are not used to describe a particular order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. In this document, "embodiment" means that the specific features, structures or characteristics described in connection with the embodiment can be included in at least one embodiment of the present application. The phrase is shown at various places in the specification does not necessarily refer to the same embodiment, nor is it independent or alternative to other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments. The term "and / or" used in the specification and claims of the present application means any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0201] ​Those skilled in the art can realize the units and algorithm steps of each example described in connection with the embodiments disclosed herein can be realized in electronic hardware, computer software, or a combination of both. The above described embodiments have been described in connection with the particular examples, and it will be evident to those skilled in the art that various modifications can be made thereto without parting from the spirit and scope of the application, and the application is not to be limited to the disclosed embodiments.

[0202] The above disclosure is merely preferred embodiments of the present application and cannot be used to limit the scope of the present application. Any equivalent changes made in accordance with the claims of the present application shall still fall within the scope of the present application.

Claims

1. A method of presenting media information, characterized by, The method comprises: in response to a media information display request, determining a media information set corresponding to the media information display request, the media information set comprising at least one first type of media information and at least one second type of media information; obtaining display state information of each of the first type of media information and the second type of media information, the display state information comprising at least one of a displayed amount, a preset display amount, a preset access amount, and a display object; for each of the first type of media information and the second type of media information, determining reference media information whose display state information is the same as that of the media information in a first time period, wherein the media information and the reference media information are of the same type, and the first time period is a last time period of a response time corresponding to the media information display request; obtaining reference display competition information of the reference media information, and determining display competition information of the media information according to the reference display competition information; determining display evaluation values of the first type of media information and the second type of media information respectively according to the display competition information of the first type of media information and the second type of media information; determining target media information from the media information set according to the display evaluation values of the first type of media information and the second type of media information, and displaying the target media information.

2. The method of claim 1, wherein, The display competition information of the first type of media information comprises at least one of: a predicted click rate and a predicted click conversion rate; The display competition information of the second type of media information comprises a predicted revenue indicator.

3. The method of claim 2, wherein, The display evaluation values of the first type of media information and the second type of media information are determined respectively according to the display competition information of the first type of media information and the second type of media information, comprising: for each of the first type of media information, determining a first weight corresponding to the predicted click rate and the predicted click conversion rate in the display competition information of the media information respectively, and determining the display evaluation value of the media information according to the predicted click rate, the predicted click conversion rate, and the first weight corresponding thereto in the display competition information of the media information; for each of the second type of media information, determining a second weight corresponding to the predicted revenue indicator in the display competition information of the media information, and determining the display evaluation value of the media information according to the predicted revenue indicator and the second weight corresponding thereto in the display competition information of the media information.

4. The method of claim 3, wherein, For each of the first type of media information, the display evaluation value of the media information is determined according to the predicted click rate, the predicted click conversion rate, and the first weight corresponding thereto in the display competition information of the media information, comprising: obtaining a display revenue of the media information and a third weight corresponding thereto; determining the display evaluation value of the media information according to the display revenue, the third weight corresponding to the display revenue, the predicted click rate, the predicted click conversion rate, and the first weight corresponding thereto in the display competition information of the media information.

5. The method of claim 1, wherein, The target media information is determined from the media information set according to the display evaluation values of each of the first type of media information and each of the second type of media information, comprising: The first type of media information and the second type of media information are sorted according to the display evaluation values of each of the first type of media information and each of the second type of media information; The target media information is determined from the media information set according to the sorting result.

6. The method according to any one of claims 1 to 5, characterized in that, The first type of media information is media information with display quantity and display object requirements, and the second type of media information is media information that obtains display opportunities through resource payment.

7. The method of claim 1, wherein, The display evaluation values of each of the first type of media information and each of the second type of media information are determined respectively according to the display competition information of each of the first type of media information and each of the second type of media information, which is realized by a media information evaluation model; The media information evaluation model is obtained by training in the following way: A training sample set is obtained, each training sample in the training sample set being historical display state information and historical display competition information of each historical media information in a historical media information set, each historical media information set being a historical media information set corresponding to a historical media information display request in a historical period, and each historical media information set including at least one historical media information of the first type and at least one historical media information of the second type; Each training sample is input into an initial media information evaluation model to obtain display evaluation values of each historical media information corresponding to each training sample; Total display evaluation values corresponding to all historical media information display requests in each sub-period are determined according to the display evaluation values of each historical media information, and each historical period includes at least one sub-period; The initial media information evaluation model is iteratively trained according to the total display evaluation values and each training sample, and the model at the time when the training is stopped is determined as the media information evaluation model when the total display evaluation values meet a preset training end condition.

8. The method of claim 7, wherein, The total display evaluation values corresponding to all historical media information display requests in each sub-period are determined according to the display evaluation values of each historical media information, comprising: For each historical media information display request, a maximum display evaluation value in the display evaluation values of each historical media information corresponding to the historical media information display request is determined; For each sub-period, a total display evaluation value corresponding to all historical media information display requests in the sub-period is determined according to the maximum display evaluation values corresponding to each historical media information display request in the sub-period.

9. The method according to claim 7 or 8, characterized in that, The input of the initial media information evaluation model further includes competition correlation features of each historical media information of the first type corresponding to each training sample; For each training sample, the competition correlation features corresponding to the training sample are determined in the following way: The competition correlation features corresponding to the training sample are determined according to the historical display state information of each historical media information of the first type corresponding to the training sample.

10. The method of claim 9, wherein, For each training sample, the determining of the competition correlation feature corresponding to the training sample according to the historical display state information of the historical media information of the first type corresponding to the training sample comprises: determining a competition correlation relationship between the historical media information of the first type corresponding to the training sample according to the historical display state information of the historical media information of the first type corresponding to the training sample; constructing a competition correlation graph according to the competition correlation relationship, and determining the competition correlation feature of the historical media information of the first type corresponding to the training sample according to the competition correlation graph.

11. A media information presentation device, characterized by The apparatus comprises: a media information determining module configured to determine a media information set corresponding to a media information display request in response to the media information display request, the media information set comprising at least one media information of a first type and at least one media information of a second type; a display state information obtaining module configured to obtain display state information of each of the media information of the first type and the media information of the second type, the display state information comprising at least one of a displayed amount, a preset display amount, a preset access amount, and a display object; a display competition information obtaining module configured to, for each of the media information of the first type and the media information of the second type, determine a reference media information having the same display state information as the display state information of the media information within a first time period, wherein the media information and the reference media information are media information of the same type, and the first time period is a last time period of a response time corresponding to the media information display request; obtain reference display competition information of the reference media information, and determine display competition information of the media information according to the reference display competition information; a display evaluation value determining module configured to determine a display evaluation value of each of the media information of the first type and the media information of the second type according to the display competition information of each of the media information of the first type and the media information of the second type; a media information display module configured to determine target media information from the media information set according to the display evaluation value of each of the media information of the first type and the media information of the second type, and display the target media information.

12. The apparatus of claim 11, wherein, The display competition information of the media information of the first type comprises at least one of: a predicted click rate and a predicted click conversion rate; The display competition information of the media information of the second type comprises a predicted revenue indicator.

13. The apparatus of claim 12, wherein, When the display evaluation value determining module determines the display evaluation value of each of the media information of the first type and the media information of the second type according to the display competition information of each of the media information of the first type and the media information of the second type, the display evaluation value determining module is configured to: for each of the media information of the first type, determine a first weight corresponding to the predicted click rate and the predicted click conversion rate in the display competition information of the media information, respectively, and determine the display evaluation value of the media information according to the predicted click rate, the predicted click conversion rate, and the first weight corresponding thereto, respectively, in the display competition information of the media information. For each of the second type of media information, a second weight corresponding to the predicted revenue indicator in the display competition information of the media information is determined, and a display evaluation value of the media information is determined according to the predicted revenue indicator in the display competition information of the media information and the corresponding second weight.

14. The apparatus of claim 13, wherein, For each of the first type of media information, when the display evaluation value determination module determines the display evaluation value of the media information according to the predicted click rate, the predicted click conversion rate in the display competition information of the media information, and the corresponding first weight, the display evaluation value determination module is configured to: obtain the display revenue of the media information and a corresponding third weight; determine the display evaluation value of the media information according to the display revenue, the third weight corresponding to the display revenue, the predicted click rate, the predicted click conversion rate in the display competition information of the media information, and the corresponding first weight.

15. The apparatus of claim 11, wherein, When the display evaluation value determination module determines the target media information from the set of media information according to the display evaluation values of the first type of media information and the second type of media information, the display evaluation value determination module is configured to: sort the first type of media information and the second type of media information according to the display evaluation values of the first type of media information and the second type of media information; determine the target media information from the set of media information according to the sorting result.

16. The apparatus of any one of claims 11 to 15, wherein, The first type of media information is media information with display quantity and display object requirements, and the second type of media information is media information that obtains display opportunities through resource payment.

17. An electronic device, comprising: The computer device comprises a processor and a memory, and the processor and the memory are connected to each other. The memory is configured to store a computer program. The processor is configured to execute the method according to any one of claims 1 to 10 when the computer program is invoked.

18. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method according to any one of claims 1 to 10.

19. A computer program product, the computer program product comprising computer instructions stored in a computer readable storage medium, a processor of an electronic device reading the computer instructions from the computer readable storage medium, and the processor executing the computer instructions to cause the computer device to execute the method according to any one of claims 1 to 10.

Images