Material group association relationship determination method and device, equipment and storage medium

Abstract

The application provides a method, device and equipment for determining the correlation of a material group, and a storage medium. The method comprises: sorting the scores of media materials in a first media material set in descending order, the first media material set including a plurality of media materials with a similarity greater than a first preset threshold; selecting a second media material set from the first media material set according to the sorting result, the second media material set including media materials with the top N scores; putting the media materials in the second media material set into each user group for testing to obtain a delivery effect value between the media materials and the group types; and establishing a correlation between the media materials and the group types based on the delivery effect value, the correlation being used to push different media materials to different group types. The embodiments of the application can improve the effectiveness of media material delivery and achieve a win-win goal for advertisers and platforms.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and particularly relates to a material group association relationship determination method and device, equipment and a storage medium. BACKGROUND

[0002] In the process of advertising, advertisers usually upload a large number of similar materials on the platform in order to obtain more product exposure.

[0003] However, a large number of similar material delivery will cause excessive consumption of platform traffic. In order to avoid excessive consumption of traffic, the platform will limit the delivery amount of similar materials.

[0004] How to deliver different materials to different audiences to improve the effectiveness of the materials and achieve a win-win situation for advertisers and platforms is a problem to be solved. SUMMARY

[0005] In order to solve the above technical problems, the present application provides a material group association relationship determination method, device, equipment and storage medium, which can improve the effectiveness of media material delivery and achieve a win-win situation for advertisers and platforms in the case of reducing the delivery amount.

[0006] In a first aspect, the present application provides a material group association relationship determination method, which comprises: sorting the scores of media materials in a first media material set in descending order, the score of a media material being used to represent the quality of the media material, the first media material set comprising a plurality of media materials with a similarity greater than a first preset threshold; selecting a second media material set from the first media material set according to the sorting result, the second media material set comprising media materials with the top N scores; delivering the media materials in the second media material set to each user group for testing to obtain a delivery effect value between the media materials in the second media material set and the group type, each user group comprising users with the same group type; and establishing an association relationship between the media materials in the second media material set and the group type based on the delivery effect value, the association relationship being used to push different media materials to different group types.

[0007] In a second aspect, the present application provides a device for determining a correlation between a media group, the device comprising: a media score sorting module configured to sort scores of media in a first media set in descending order, the score of the media being used to represent a quality of the media, the first media set comprising a plurality of media with a similarity greater than a first preset threshold; a second media set determining module configured to filter a second media set from the first media set according to the sorting result, the second media set comprising media with a top N score; a media delivery testing module configured to deliver the media in the second media set to each user group for testing, to obtain a delivery effect value between the media in the second media set and a group type, each user group comprising users with the same group type; and a correlation establishing module configured to establish a correlation between the media in the second media set and the group type based on the delivery effect value, the correlation being used to push different media to different groups.

[0008] In a third aspect, the present application provides an electronic device, which can comprise a device for determining a correlation between a media group, the device comprising: one or more processors; a storage device configured to store one or more programs; and when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method for determining a correlation between a media group in the first aspect.

[0009] In a fourth aspect, the present application provides a storage medium, which can be a computer readable storage medium, and the storage medium has stored thereon a computer program, which is executed by a processor to implement the method for determining a correlation between a media group in the first aspect.

[0010] In a fifth aspect, the present application provides a computer program product, which comprises a computer program or instructions, and the computer program or instructions are executed by a processor to implement the method for determining a correlation between a media group in any one of the first aspect.

[0011] The technical scheme provided by the embodiments of the present application has the following advantages compared with the prior art: the embodiments of the present application provide a material group association relationship determining method, device, equipment and storage medium, the method comprises the following steps: ranking the scores of media materials in a first media material set in descending order, the score of a media material is used to represent the quality of the media material, the first media material set comprises a plurality of media materials with a similarity greater than a first preset threshold; selecting a second media material set from the first media material set according to the ranking result, the second media material set comprises media materials with top N scores; putting the media materials in the second media material set into each user group for testing to obtain a delivery effect value between the media materials in the second media material set and a group type, each user group comprises users with the same group type; and establishing an association relationship between the media materials in the second media material set and the group type based on the delivery effect value, the association relationship is used to push different media materials for different group types. In the embodiments of the present application, the media materials with top N scores are used for grouping and delivery testing to determine the association relationship between the media materials and the group type, and the association relationship is used to put different media materials for different groups. The effectiveness of media material delivery is improved in the case of reducing the delivery amount, and the purpose of win-win of the advertiser and the platform is achieved. BRIEF DESCRIPTION OF DRAWINGS

[0012] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and serve to explain the principles of the present application together with the specification.

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced as follows, and obviously, other drawings can also be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0014] Figure 1 A flowchart of a material group association relationship determining method provided by the embodiments of the present application;

[0015] Figure 2 A flowchart of a media material display method provided by the embodiments of the present application;

[0016] Figure 3 A structural diagram of a material group association relationship determining device provided by the embodiments of the present application;

[0017] Figure 4 A structural diagram of an electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0018] In order to enable a more complete understanding of the above-mentioned objects, features and advantages of the present application, the following will further describe the solutions of the present application. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict, if possible.

[0019] In the following description, a large number of specific details are set forth in order to facilitate a thorough understanding of the present application, but the present application can also be implemented in other different manners from those described herein; obviously, the embodiments described in the specification are only some embodiments of the present application, and not all embodiments.

[0020] The term "comprising" and its variants used herein are open and inclusive, i.e., "including but not limited to". The term "based on" is "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The related definitions of other terms will be given in the following description.

[0021] It should be noted that the concepts of "first", "second", etc. mentioned in the present application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0022] It should be noted that the modification of "one" or "multiple" mentioned in the present application is illustrative and not restrictive, and those skilled in the art should understand that, unless otherwise explicitly indicated in the context, it should be understood as "one or more".

[0023] The material group association relationship determination method and the media material display method provided by the embodiments of the present application will be described in detail below in combination with the drawings and specific embodiments.

[0024] Figure 1 A flowchart of a material group association relationship determination method in the embodiments of the present application, the present embodiment can be applied to the case of providing different media materials for different audience groups, and the method can be executed by a material group association relationship determination device. The material group association relationship determination method device can be realized in the form of software and / or hardware, and the material group association relationship determination method device can be configured in an electronic device, and the electronic device can be a server.

[0025] As shown in Figure 1 The material group association relationship determination method provided by the embodiments of the present application mainly includes steps S101-S103.

[0026] S101, sort the scores of the media materials in the first media material set in descending order, the score of the media material being used to represent the quality of the media material, the first media material set including a plurality of media materials with a similarity greater than a first preset threshold.

[0027] The media material refers to a product for propagating information to a user through a medium (such as television, radio, Internet, newspaper, magazine, etc.). The media material can include one or more combinations of text material, audio material, picture material, video material, etc. In the embodiments of the present application, the media material is taken as an example of picture material.

[0028] The first media material set includes a plurality of media materials with a similarity greater than a first preset threshold. The first preset threshold is used to measure the similarity between the media materials in the first media material set.

[0029] The first media material set can be understood as a material set composed of a plurality of media materials of the same object. Further, the similarity between any two media materials in the first media material set is greater than the first preset threshold, indicating that the media materials in the first media material set are very similar, that is, the plurality of media materials in the first media material set are media materials for the same object. The same object means that the shooting subject of the plurality of media materials in the first media material set is the same. For example, the plurality of media materials are pictures taken at different angles for the same model of mobile phone, and for another example, the plurality of media materials are pictures taken for the same model of mobile phone with different colors.

[0030] In one possible implementation, before sorting the scores of the media materials in the first media material set in descending order, the method further includes: receiving a plurality of media materials uploaded by a third party; performing similarity calculation on each of the plurality of media materials by using a similarity algorithm to obtain the first media material set, the first media material set including a plurality of media materials with a similarity greater than the first preset threshold.

[0031] The third party can be understood as an advertiser providing media materials. The third party generates a large number of media materials and uploads them to the server. Since the third party wants to obtain more product exposure, the third party usually uploads a large number of similar or identical media materials to the server. Therefore, the server limits the delivery amount of similar or identical media materials in order to avoid excessive traffic consumption. In order to limit the delivery amount of similar or identical media materials, the similar or identical media materials need to be found first, and then the delivery test is performed. The media materials to be classified refer to the media materials uploaded by the third party platform and not classified.

[0032] In the embodiments of the present application, the picture similarity algorithm is used to calculate the similarity between each pair of media materials to be classified, and the media materials to be classified with a similarity greater than a first set threshold are divided into the same media material set to obtain a plurality of first media material sets.

[0033] The first media material set is a media material set obtained after similarity calculation and classification of the media materials uploaded by the third party. The picture similarity algorithm can include a hash algorithm, a scale invariant feature transform (SIFT), a cosine similarity, a histogram algorithm, a mean square error algorithm, a structural similarity algorithm, etc.

[0034] Further, a plurality of picture similarity algorithms can be used to calculate the similarity between each pair of media materials to be classified, and the plurality of similarities are weighted to obtain the final similarity between each pair of media materials to be classified.

[0035] For a specific object, the third party may upload a large amount of media materials, and if all the media materials of the object are put into use, it may cause excessive consumption of platform traffic, therefore, high-quality media materials can be selected from the media materials uploaded by the third party for use.

[0036] The first media material set is obtained, the first media material set including a plurality of media materials with a similarity greater than a first preset threshold, the scores of the media materials in the first media material set are obtained, and the scores of the media materials are sorted in descending order.

[0037] The score of each media material in the first media material set can be determined by the following method: for each media material in the first media material set, the score of the media material input by the review expert is obtained. Alternatively, the media material and the score indication word are input into the AI model to obtain the score of the media material output by the AI model.

[0038] The score of the media material is used to represent the quality of the media material. Specifically, the higher the score of the media material, the higher the quality of the media material, and the lower the score of the media material, the lower the quality of the media material.

[0039] Further, a scoring system is set to ensure the effectiveness and consistency of the scoring of the media materials. First, specific scoring criteria for the dimensions of picture quality, relevance, and creativity are determined. Picture quality can mainly include: image clarity: whether it is clear enough, without blur or out-of-focus phenomenon. Relevance can mainly include: target audience matching, for example: whether the content is directly aimed at the interests and needs of the intended audience. Brand positioning consistency, for example: whether it is consistent with the brand image and values. Marketing activity theme fitting. For example: whether the content closely revolves around the core information of the activity. Creativity can mainly include: novelty, for example: the uniqueness of ideas or expression methods. Attractiveness, for example: whether it can quickly attract the attention of the audience. Emotional resonance ability, for example: whether it can evoke emotional responses from the audience.

[0040] According to the requirements of the above different dimensions, scoring criteria can be set, for example: in the relevance dimension, it is highly relevant, completely consistent with all the above conditions, so the score in the relevance dimension is 5 points, in the creativity dimension, it has some creativity, although there is some novelty, but still ordinary, so the score in the creativity dimension is 3 points, in the picture quality dimension, it is very good, all aspects reach the highest level, there is no any detectable problem, so the score in the creativity dimension is 5 points.

[0041] After receiving the scores of the review experts for each dimension, the scores of different dimensions are weighted and calculated to obtain the score of the media material.

[0042] Further, the above score can be manually scored by a professional, and then the score is input as the annotation information of the media material to the server, so that the server can receive the score of each media material.

[0043] Further, the above score can be output by a trained AI scoring model. The media material is input into the AI scoring model, and the server can receive the score of each media material output by the AI scoring model.

[0044] S102, according to the sorting result, the second media material set is screened out from the first media material set, and the second media material set includes the media materials with the top N scores.

[0045] After the scores of the media materials in the first media material set are sorted in descending order in S101, the top N media materials are screened out from the first media material set and divided into the second media material set. In other words, the top N media materials with the highest scores are screened out from the first media material set and divided into the second media material set.

[0046] In the embodiments of the present application, the high-quality media materials are selected from a large number of media materials as the media materials in the second media material set by scoring, so as to reduce the number of media materials for delivery test and improve the efficiency of delivery test. The media materials in the second media material set are high-quality materials selected according to the score, so as to display high-quality materials to different audience groups and improve the delivery effect of the materials.

[0047] The value N can be set according to actual conditions. Specifically, the value N can be a constant, for example, if the value N is 10, the media materials ranked in the top 10 in the first media material set are selected and divided into the second media material set.

[0048] Further, the value N can also be dynamically adjusted according to the number of media materials in the first media material set, for example, the value N is the product of the number of media materials in the first media material set and a set proportion. The set proportion can be set by itself, for example, the set proportion is 20%, so the value N is the product of the number of media materials in the first media material set and 20%. That is, the media materials ranked in the top 20% in the first media material set are selected and divided into the second media material set.

[0049] In a possible implementation, after the second media material set is selected from the first media material set according to the sorting result, the method further includes: determining a third media material set having the same object identifier as the first media material set, the third media material set including a plurality of media materials having an association relationship with the group type; and merging the media materials in the third media material set into the second media material set.

[0050] The object identifier refers to the identifier of the subject in the first media material set. For example, the object identifier can be the model of the mobile phone in the first media material set, and the object identifier can also be the code of the clothes in the first media material set. The object identifier is mainly used to identify the shooting object of the media materials in the first media material set.

[0051] The third media material set having the same object identifier as the first media material set can be understood as that the object identifier of the first media material set is the same as the object identifier of the third media material set, that is, the first media material set and the third media material set are media materials shot or generated for the same object.

[0052] The third media material set includes a plurality of media materials having an association relationship with the group type, which means that the media materials in the third media material set are media materials uploaded by a third party before this time, and the corresponding group type is determined after delivery test.

[0053] In the embodiments of the present application, the media materials that have passed the delivery test and are determined to correspond to the group type are subjected to the delivery test together with the top N media materials in the first media set in terms of the score. In this way, the range of media materials subjected to the delivery test can be increased, so as to screen out more suitable media materials for different groups, and further increase the delivery effect of the media materials.

[0054] In S103, the media materials in the second media set are respectively delivered to each user group for testing, to obtain a delivery effect value between each media material in the second media set and the group type. Each user group includes users of the same group type.

[0055] A user group, also referred to as a target audience or target market, refers to a group of people with common characteristics, which can include one or more of the following: age, gender, geographical location, interest, occupation, education level, income, etc. The group type is information describing a group with common characteristics. For example, the group type can include children, teenagers, middle-aged people, and the elderly in terms of age, men and women in terms of gender, and provinces in terms of geographical location. Each user group includes users of the same group type, that is, each user group includes users of the same group type. For example, when the user group is male, all users in the user group are male, and when the user group is children, all users in the user group are children.

[0056] It should be noted that the above describes an example in which the user group includes only one common characteristic, and the user group can also include two or more common characteristics. For example, the user group can also be a middle-aged male group in XX province.

[0057] The delivery effect value can be determined by the click rate, conversion rate, and engagement of the media materials in the second media set in the user group. Specifically, the delivery effect value of the media materials in the user group can be calculated by weighting the click rate, conversion rate, and engagement.

[0058] The users are divided into multiple user groups, for example, male and female groups. The media materials in the second media set are subjected to the delivery test in the male group, to obtain a delivery effect value between each media material in the second media set and the male type. The media materials in the second media set are subjected to the delivery test in the female group, to obtain a delivery effect value between each media material in the second media set and the female type.

[0059] For example, the users are divided into a children group, a teenager group, a middle-aged group, and an old-aged group. The media materials in the second media material set are tested in the children group to obtain the delivery effect value between each media material in the second media material set and the children type, the media materials in the second media material set are tested in the teenager group to obtain the delivery effect value between each media material in the second media material set and the teenager type, the media materials in the second media material set are tested in the middle-aged group to obtain the delivery effect value between each media material in the second media material set and the middle-aged type, and the media materials in the second media material set are tested in the old-aged group to obtain the delivery effect value between each media material in the second media material set and the old-aged type.

[0060] Specifically, an A / B / n test framework is built, and test time and test indexes are selected. The test indexes include click rate, conversion rate, and participation rate, and the test parameters include division of user groups, positioning of resources, and tracking of conversion. The media materials in the second media material set are tested in the built A / B / n test framework to obtain the click rate, conversion rate, and participation rate of each media material in the second media material set in each user group, and the delivery effect value of each media material in the second media material set in each group type corresponding group is obtained based on the weighted calculation of the click rate, conversion rate, and participation rate in each user group.

[0061] In S104, an association relationship between the media materials in the second media material set and the group types is established based on the delivery effect value, and the association relationship is used to push different media materials for different group types.

[0062] The association relationship between the media materials in the second media material set and the group types can be represented by the delivery effect value between the media materials and the group types. For example, the delivery effect value of the media material 1 in the male group is 85, and the association relationship between the media material 1 and the male group type can be represented by 85. The delivery effect value of the media material 1 in the female group is 35, and the association relationship between the media material 1 and the female group type can be represented by 35.

[0063] Further, for each user group, the media material with the maximum delivery effect value in the user group can be taken as a target media material, and an association between the user group type and the target media material is established, for example, the delivery effect value of media material 1 in the male group is 85, the delivery effect value of media material 2 in the male group is 72, and the delivery effect value of media material 3 in the male group is 60. The media material 1 corresponding to the maximum delivery effect value 85 is selected as the target media material of the male group, and an association between the media material 1 and the male group type is established.

[0064] In another implementation, for each media material, the group type with the maximum delivery effect value can be taken as a target group type, and an association between the target group type and the media material is established, for example, the delivery effect value of media material 1 in the child group is 35, the delivery effect value of media material 1 in the teenager group is 45, the delivery effect value of media material 1 in the middle-aged group is 80, and the delivery effect value of media material 1 in the elderly group is 20. The middle-aged group corresponding to the maximum delivery effect value 80 is selected as the target group type corresponding to the media material 1, and an association between the media material 1 and the middle-aged group type is established.

[0065] In another implementation, the association between the media material in the second media material set and the group type is established based on the delivery effect value, including: when the delivery effect value between the media material in the second media material set and the group type is greater than a second set threshold, establishing an association between the media material in the second media material set and a target group type, the target group type refers to the delivery effect value of the media material in the second media material set in the group corresponding to the target group type is greater than the second set threshold.

[0066] The second set threshold refers to a numerical value used to evaluate the delivery effect of the media material in the group. When the delivery effect value reaches the second preset threshold, it indicates that the media material has good delivery effect in the user group. When the delivery effect value does not reach the second preset threshold, it indicates that the media material has poor delivery effect in the user group. The second set threshold can be set according to actual conditions, which is not limited in the embodiments of the present application.

[0067] Specifically, by conducting a user group delivery test on the media materials in the second media material set, the delivery effect values between each media material in the second media material set and each user group type are obtained; the user group type with the delivery effect value greater than the second set threshold is taken as the target group type of the media material in the second media material set, and an association between the media material in the second media material set and the target group type is established.

[0068] In another implementation, for each media material in the second set of media materials, a group type with the largest delivery effect value can be determined as a target group type, and an association between the target group type and the media material is established, for example, the delivery effect value of the media material 1 in the children group is 35, the delivery effect value of the media material 1 in the youth group is 60, the delivery effect value of the media material 1 in the middle-aged group is 80, and the delivery effect value of the media material 1 in the old group is 20. The second set threshold is set to 50, and the youth group and the middle-aged group with the delivery effect value greater than 50 are set as the target group type of the media material 1. An association between the youth group type and the media material 1 is established, and an association between the middle-aged group type and the media material 1 is established. Further, the association between the youth group type and the media material 1 is represented by the delivery effect value 60, and the association between the middle-aged group type and the media material 1 is represented by the delivery effect value 85.

[0069] In a possible implementation, the association between the media material in the second set of media materials and the group type is stored in the form of a graph data structure, the graph data structure including a first node, a second node, and an edge between the first node and the second node; the first node is used to store the media material in the second set of media materials, the second node is used to store the group type having an association with the media material in the second set of media materials, and the edge between the first node and the second node is used to store the delivery effect value between the group type and the media material in the second set of media materials.

[0070] The graph data structure is a nonlinear data structure used to represent the association in the object network. In the graph data structure, the node represents the entity, and the edge represents the association between the entities.

[0071] In the embodiment of the present application, the media material in the second set of media materials is stored in the first node, the target group type having an association with the media material in the second set of media materials is stored in the second node, and the delivery effect value between the target group type and the media material in the second set of media materials is represented by the edge between the first node and the second node.

[0072] In the above example, the association between the youth group type and the media material 1 is represented by the delivery effect value 60, and the association between the middle-aged group type and the media material 1 is represented by the delivery effect value 85. The media material 1 is stored in the first node A, the youth group type is stored in the second node a, and the middle-aged group type is stored in the second node b. The edge between the first node A and the second node a stores the delivery effect 60, and the edge between the first node A and the second node b stores the delivery effect 85.

[0073] According to the above storage method, each media material, the target group type associated with it, and the delivery effect value corresponding to the target group type are all stored in the above graph structure. In this way, the graph structure only stores media materials and group types whose delivery effect values ​​exceed the second set threshold, so as to reduce the amount of data storage in the graph structure.

[0074] Using graph data structure to store the relationship between material groups can improve data processing efficiency.

[0075] The association relationship between the material groups is used to push different media materials to users of different group types. The specific process can be referred to the description in the following embodiment.

[0076] The embodiment of the present application provides a method, apparatus, device and storage medium for determining the association relationship of material groups. The method includes: sorting the scores of media materials in a first media material set in descending order, the scores of media materials are used to characterize the quality of the media materials, and the first media material set includes multiple media materials with similarities greater than a first preset threshold; screening a second media material set from the first media material set according to the sorting result, and the second media material set includes media materials ranked in the top N by scores; delivering the media materials in the second media material set to each user group for testing, and obtaining the delivery effect value between the media materials in the second media material set and the group type, and each user group includes users of the same group type; establishing the association relationship between the media materials in the second media material set and the group type based on the delivery effect value, and the association relationship is used to push different media materials to different group types. In the embodiment of the present application, the media materials ranked in the top N by scores are used for group delivery testing to determine the association relationship between each media material and each group type, and the association relationship is used to deliver different media materials to different groups. This improves the effectiveness of media material delivery while reducing the delivery amount, achieving a win-win situation for advertisers and platforms.

[0077] Figure 2 This is a flowchart of a media material display method in an embodiment of the present application. This embodiment can be applied to situations where different media materials are provided to different audience groups. The method can be executed by a media material display determination device. The media material display method device can be implemented in software and / or hardware. The media material display method device can be configured in an electronic device, which can include a server.

[0078] like Figure 2 As shown, the media material display method provided in the embodiment of the present application mainly includes steps S201-S203.

[0079] S201, in response to the display request of the media material sent by the user terminal, determining the group type of the target user.

[0080] The display request of the media material can be understood as a request indicating that the server sends and causes the user terminal to display the media material. For example, the media material can include advertising material, and the display request of the media material includes the display request of the advertising material.

[0081] When the server receives the start instruction of the user terminal, the display request of the media material is generated and responded. Alternatively, during the playing of the multimedia resource, the user terminal generates and sends the display request of the media material to the server when the set condition is met, wherein the set condition includes that the playing time of the multimedia resource reaches the set time, or the picture of the multimedia resource includes the set object. For example, when the playing time of the multimedia resource reaches 20 minutes, the display request of the media material is generated and responded. Alternatively, when the picture of the multimedia resource includes a mobile phone pattern, the display request of the media material is generated and responded.

[0082] It should be noted that the triggering condition of the display request of the media material can be set according to actual conditions, and the display request of the media material is only described in the embodiment of the application, but not limited.

[0083] The target user can be understood as the user currently logged in the user terminal or the application program, in other words, the target user is the user currently using the user terminal or the application program. The group type of the target user refers to the group to which the target user belongs. The group type can include the group type divided by age, for example, children, teenagers, middle-aged, and the elderly. The group type can include the group type divided by gender, for example, male and female. The group type can include the group type divided by geographical location, for example, the group type divided by provinces.

[0084] The basic information and historical behavior data of the target user are analyzed to obtain the feature information of the target user, and the feature information is stored. In response to the display request of the media material sent by the user terminal, the stored group type of the target user is directly obtained.

[0085] S202, in the association relationship, querying the media material with the maximum delivery effect value and the group type of the target user as the to-be-displayed material.

[0086] The to-be-displayed media material can be understood as the media material to be displayed to the user. For example, the to-be-displayed media material can include to-be-displayed pictures or to-be-displayed videos, etc.

[0087] As can be known from the above description in the embodiments, the association relationship between each media material and the group type is stored in the association relationship, and the association relationship is represented by the delivery effect value of the media material in the group type corresponding group. The association relationship is stored in the graph structure, which can be deployed in the server.

[0088] When the graph structure is deployed in the server, the server queries the media material having the corresponding relationship with the group type of the target user in the graph structure as the to-be-displayed media material.

[0089] The media material having the association relationship with the feature information of the target user is queried in the graph structure as the to-be-displayed media material, including: querying the media material having the association relationship with the group type of the target user in the media group relationship, and if the media material having the association relationship with the group type of the target user is multiple, obtaining the media material having the maximum delivery effect value as the to-be-displayed media material.

[0090] In one possible implementation, in response to the media material display request sent by the user terminal, if the group type of the target user cannot be determined, the media material having the maximum score is obtained from the first media material set as the to-be-displayed media material.

[0091] The group type of the target user cannot be determined can be understood as that the server cannot determine the group type of the target user, for example, the target user is a new customer of the user terminal, or the target user does not add the basic information of the user, or the target user does not have historical behavior data.

[0092] When the group type of the target user cannot be determined, the media material having the maximum score is obtained from the first media material set as the to-be-displayed media material, so as to improve the effectiveness of media material delivery.

[0093] S203, the to-be-displayed media material is sent to the user terminal, so that the user terminal displays the to-be-displayed media material.

[0094] The to-be-displayed media material determined in S202 is sent to the user terminal, so that the user terminal can display the to-be-displayed media material.

[0095] The method provided in the embodiments of the present application comprises: determining the group type of a target user in response to a media material display request sent by a user terminal; querying a media material having an association relationship with the group type of the target user and having a maximum delivery effect value in the association relationship as a to-be-displayed media material; and sending the to-be-displayed media material to the user terminal, so that the user terminal displays the to-be-displayed media material. In the embodiments of the present application, the media material displayed to the target user is determined according to the group type of the target user, different media materials are delivered to different groups, and the effectiveness of media material delivery is improved in the case of reducing the delivery amount, so as to achieve the win-win purpose of the advertiser and the platform.

[0096] Figure 3 A structure schematic diagram of a material group association relationship determination device in an embodiment of the present application is shown in FIG. 1. The material group association relationship determination device 30 provided by the embodiment of the present application mainly comprises a material score sorting module 31, a second media material set determination module 32, a material delivery test module 33 and an association relationship establishment module 34. Figure 3

[0097] The material score sorting module 31 is configured to sort the scores of the media materials in the first media material set in descending order, wherein the score of a media material is used to represent the quality of the media material, and the first media material set comprises a plurality of media materials with a similarity greater than a first preset threshold. The second media material set determination module 32 is configured to filter out a second media material set from the first media material set according to the sorting result, wherein the second media material set comprises media materials with a score ranking in the top N. The material delivery test module 33 is configured to deliver the media materials in the second media material set to each user group for testing, respectively, to obtain a delivery effect value between the media materials in the second media material set and the group type, wherein each user group comprises users with the same group type. The association relationship establishment module 34 is configured to establish an association relationship between the media materials in the second media material set and the group type based on the delivery effect value, wherein the association relationship is used to push different media materials for different group types.

[0098] The embodiment of the present application provides a material group association relationship determination device. The material group model device is used to execute the following processes: sorting the scores of the media materials in the first media material set in descending order, wherein the score of a media material is used to represent the quality of the media material, and the first media material set comprises a plurality of media materials with a similarity greater than a first preset threshold; filtering out a second media material set from the first media material set according to the sorting result, wherein the second media material set comprises media materials with a score ranking in the top N; delivering the media materials in the second media material set to each user group for testing, respectively, to obtain a delivery effect value between the media materials in the second media material set and the group type, wherein each user group comprises users with the same group type; and establishing an association relationship between the media materials in the second media material set and the group type based on the delivery effect value, wherein the association relationship is used to push different media materials for different group types. In the embodiment of the present application, the media materials with a score ranking in the top N are used for grouping delivery test, and the association relationship between the media materials and the group type is determined, which is used to deliver different media materials for different groups. The effectiveness of media material delivery is improved in the case of reducing the delivery amount, and the purpose of win-win of the advertiser and the platform is achieved.

[0099] ​In a possible implementation, the association between the media material in the second media material set and the group type is stored in a form of a graph data structure, the graph data structure comprising a first node, a second node, and an edge between the first node and the second node; the first node is used to store the media material in the second media material set, the second node is used to store the group type having the association with the media material in the second media material set, and the edge between the first node and the second node is used to store the delivery effect value between the group type and the media material in the second media material set.

[0100] In a possible implementation, the method further includes: receiving, by the material classification module, third-party uploaded media materials to be classified; and performing, by the material classification module, similarity calculation on each of the media materials to be classified by using a similarity algorithm to obtain a first media material set, the first media material set including a plurality of media materials having a similarity greater than a first preset threshold.

[0101] In a possible implementation, the second media material set determination module 32 is specifically configured to determine a third media material set having a same object identifier as the first media material set, the third media material set including a plurality of media materials having an association with the group type; and merge, by the second media material set determination module 32, the media materials in the third media material set to the second media material set.

[0102] In a possible implementation, the association relationship establishment module 34 is specifically configured to, when the delivery effect value between the media material in the second media material set and the group type is greater than a second preset threshold, establish an association between the media material in the second media material set and a target group type, the target group type being a group type in which the delivery effect value of the media material in the second media material set is greater than the second preset threshold.

[0103] In a possible implementation, the media material display module is configured to, in response to a media material display request sent by the user end, determine the group type of the target user; query, in the association, a media material having the greatest delivery effect value and having an association with the group type of the target user as a to-be-displayed material; and send, by the media material display module, the to-be-displayed material to the user end to enable the user end to display the to-be-displayed material.

[0104] In a possible implementation, the media material display module is further configured to, in response to a media material display request sent by the user end, if the group type of the target user cannot be determined, obtain a media material having the greatest score from the first media material set as the to-be-displayed material.

[0105] The material group association relationship determination apparatus provided in the embodiments of the present application can perform the material group association relationship determination method provided in any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of performing the method.

[0106] Figure 4 is a structural schematic diagram of an electronic device provided by the embodiment. The electronic device can include a material group association relationship determining device, such as Figure 4 As shown in the figure, the electronic device 400 includes a processor 410, a memory 420, an input device 430, and an output device 440; the number of processors 410 in the electronic device can be one or more, Figure 4 In the figure, the processor 410 is taken as an example; the processor 410, the memory 420, the input device 430, and the output device 440 in the electronic device can be connected through a bus or other means, Figure 4 In the figure, the connection through the bus is taken as an example.

[0107] The memory 420, as a kind of computer readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the material group association relationship determining method in the embodiment of the application. The processor 410 executes the software programs, instructions and modules stored in the memory 420, thereby performing various functional applications and data processing of the electronic device, that is, realizing the material group association relationship determining method provided by the embodiment of the application.

[0108] The memory 420 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system and application programs required by at least one function; the data storage area can store data created according to the use of the terminal and the like. In addition, the memory 420 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state memory device. In some examples, the memory 420 can further include a memory remotely arranged with respect to the processor 410, which can be connected to the electronic device through a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0109] The input device 430 can be used to receive input digital or character information, and generate key signal input related to user settings and function control of the electronic device, and can include a keyboard, a mouse, and the like. The output device 440 can include a display device such as a display screen.

[0110] The embodiment also provides a storage medium containing computer executable instructions, which are used to implement the material group association relationship determining method provided by the embodiment of the application when executed by a computer processor.

[0111] Of course, the storage medium provided by the embodiment of the present application includes computer executable instructions, which are not limited to the method operations as above, but can also perform the related operations in the material group association relationship determination method provided by any embodiment of the present application.

[0112] Through the above description of the embodiments, those skilled in the art can clearly understand that the present application can be realized by means of software and necessary general hardware, and of course can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH, a hard disk, or an optical disc, etc., and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods of various embodiments of the present application.

[0113] It is worth noting that the embodiments of the material group association relationship determination device described above include various units and modules only according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy distinction, and do not limit the protection scope of the present application.

[0114] It should be noted that in this paper, such as "first" and "second" and other relational terms are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations. Moreover, the term "includes", "contains" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device. Without more limitations, the element defined by the statement "includes a" does not exclude the presence of another identical element in the process, method, article or device including the element.

[0115] The foregoing detailed description of the application has been presented for purposes of illustration and description. Various modifications and changes can be made to these embodiments without departing from the spirit and scope of the application. It is intended that the scope of the application should not be limited by the particular representative embodiments described above.

Claims

1. A method for determining the association relationship of a material group, characterized in that: The method comprises: sorting scores of media materials in a first media material set in descending order, wherein the scores of the media materials are used to represent the quality of the media materials, and the first media material set includes a plurality of media materials having similarities greater than a first preset threshold; Filtering a second media material set from the first media material set according to the ranking result, wherein the second media material set includes media materials ranked in the top N by score; delivering the media materials in the second media material set to each user group for testing, and obtaining delivery effect values ​​between the media materials in the second media material set and the group types, wherein each user group includes users of the same group type; establishing an association relationship between the media materials in the second media material set and the group type based on the delivery effect value, wherein the association relationship is used to push different media materials to different group types; The association relationship between the media materials in the second media material set and the group type is stored in the form of a graph data structure, wherein the graph data structure includes a first node, a second node, and an edge between the first node and the second node; The first node is used to store the media materials in the second media material set, the second node is used to store the group type that has an associated relationship with the media materials in the second media material set, and the edge between the first node and the second node is used to store the delivery effect value between the group type and the media materials in the second media material set.

2. The method according to claim 1, characterized in that Also includes: Receive media materials to be classified uploaded by third parties; A similarity algorithm is used to calculate the similarity of each media material to be classified to obtain a first media material set, wherein the first media material set includes a plurality of media materials whose similarity is greater than a first preset threshold.

3. The method according to claim 1, characterized in that After the second media material set is selected from the first media material set according to the sorting result, the method further includes: Determining a third media material set having the same object identifier as the first media material set, wherein the third media material set includes a plurality of media materials associated with the group type; The media materials in the third media material set are merged into the second media material set.

4. The method according to claim 1, wherein The establishing of an association relationship between the media material in the second media material set and the group type based on the delivery effect value includes: When the delivery effect value between the media material in the second media material set and the group type is greater than a second set threshold, an association relationship is established between the media material in the second media material set and the target group type, and the target group type refers to the delivery effect value of the media material in the second media material set within the group of the target group type being greater than the second set threshold.

5. The method according to claim 1, wherein Also includes: In response to a media material display request sent by a user terminal, determining a group type of target users; Searching the association relationship for a media material that is associated with the target user's group type and has the largest delivery effect value as the material to be displayed; The material to be displayed is sent to the user terminal, so that the user terminal displays the material to be displayed.

6. The method according to claim 5, characterized in that Also includes: In response to the media material display request sent by the user terminal, if the group type of the target user cannot be determined, the media material with the highest score is obtained from the first media material set as the material to be displayed.

7. A device for determining the association relationship of a material group, characterized in that: The device comprises: a material scoring sorting module, configured to sort the scores of media materials in a first media material set in descending order, wherein the scores of the media materials are used to represent the quality of the media materials, and wherein the first media material set includes a plurality of media materials having a similarity greater than a first preset threshold; a second media material set determining module, configured to select a second media material set from the first media material set according to the ranking result, wherein the second media material set includes media materials ranked in the top N by score; a material delivery testing module, configured to deliver the media materials in the second media material set to each user group for testing, and obtain delivery effect values ​​between the media materials in the second media material set and the group types, wherein each of the user groups includes users of the same group type; an association relationship establishing module, configured to establish an association relationship between the media materials in the second media material set and the group type based on the delivery effect value, wherein the association relationship is used to push different media materials to different group types; The association relationship between the media materials in the second media material set and the group type is stored in the form of a graph data structure, wherein the graph data structure includes a first node, a second node, and an edge between the first node and the second node; The first node is used to store the media materials in the second media material set, the second node is used to store the group type that has an associated relationship with the media materials in the second media material set, and the edge between the first node and the second node is used to store the delivery effect value between the group type and the media materials in the second media material set.

8. An electronic device, characterized in that: The device comprises: one or more processors; a storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining an association relationship of a material group according to any one of claims 1 to 6.

9. A storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for determining the association relationship of a material group according to any one of claims 1 to 6 is implemented.

Images