Advertisement material recommendation method and device, equipment, medium and program product
By extracting and combining advertising promotion information and advertiser attribute information, and using preset material generation models to generate new materials, the problem of limited creative diversity is solved, and the diversity expansion and practicality of creatives is achieved.
Patent Information
- Application Number
- CN202411671072.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-21
- Publication Date
- 2025-03-18
AI Technical Summary
In the prior art, advertisers' creative diversity is limited and it is difficult to effectively expand.
By determining the creative materials in the target advertising promotion information, extracting the advertising promotion attribute information and the advertiser attribute information, depositing them as combination attribute information into the database, and entering the preset material generation model to generate new materials that are different from the original material.
The diversity expansion of creative materials is achieved, and the generated new materials are consistent with the actual application scenarios and are more practical.
Smart Images
Figure CN119646050A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of artificial intelligence technology, and in particular to a method, device, equipment, medium and program product for recommending advertising materials. Background Art
[0002] In the scenario of advertising promotion information, advertisers need to upload advertising materials and edit corresponding promotional copy, etc., and then generate advertising promotion information based on the uploaded advertising materials and promotional copy. Among them, the promotion effect of advertising promotion information is closely related to the advertising materials.
[0003] In the related art, the advertising materials used by advertisers are from local materials uploaded by advertisers, or advertisers perform secondary processing on local materials, which results in very limited diversity of advertising materials. Therefore, a method that can expand the diversity of advertising materials is urgently needed. Summary of the invention
[0004] In order to solve the above technical problems, the present disclosure provides a method, device, equipment, medium and program product for recommending advertising materials.
[0005] In one embodiment of the present disclosure, a method for recommending advertising materials is proposed, comprising: determining a first advertising material included in target advertising promotion information created by a first advertiser, wherein any multimedia material included in the target promotion information is the first advertising material; extracting first advertising promotion attribute information in the target advertising promotion information, wherein the first advertising promotion attribute information includes text information in the target advertising promotion information used to describe a corresponding promotion product; obtaining first advertiser attribute information of the first advertiser, wherein the first advertiser attribute information includes identity attribute information of the first advertiser and product attribute information of the promotion product; storing the first advertising promotion attribute information and the first advertiser attribute information as first combination attribute information in a preset combination attribute database; inputting the first combination attribute information and the first advertising material in the preset combination attribute database into a preset material generation model, obtaining a second advertising material output by the preset material generation model, wherein the second advertising material is different from the first advertising material, and the preset material generation model pre-learns to generate other advertising materials different from the input advertising material according to the input combination attribute information and advertising material; storing the second advertising material in the preset advertising material database so as to perform material recommendation processing according to the preset advertising material database.
[0006] In one embodiment of the present disclosure, a device for recommending advertising materials is proposed, including: a determination module, used to determine a first advertising material included in target advertising promotion information created by a first advertiser, wherein any multimedia material included in the target promotion information is the first advertising material; an extraction module, used to extract first advertising promotion attribute information in the target advertising promotion information, wherein the first advertising promotion attribute information includes text information in the target advertising promotion information for describing a corresponding promotional product; a first acquisition module, used to acquire first advertiser attribute information of the first advertiser, wherein the first advertiser attribute information includes identity attribute information of the first advertiser and product attribute information of the promotional product; a first storage module , used to store the first advertising promotion attribute information and the first advertiser attribute information as the first combination attribute information into a preset combination attribute database; a second acquisition module, used to input the first combination attribute information and the first advertising material in the preset combination attribute database into a preset material generation model, and obtain a second advertising material output by the preset material generation model, wherein the second advertising material is different from the first advertising material, and the preset material generation model pre-learns to generate other advertising materials different from the input advertising material based on the input combination attribute information and advertising material; a second storage module, used to store the second advertising material in the preset advertising material database, so as to perform material recommendation processing according to the preset advertising material database.
[0007] In one embodiment of the present disclosure, an electronic device is proposed, comprising: a processor; a memory for storing instructions executable by the processor; the processor is configured to read the executable instructions from the memory and execute the instructions to implement the above-mentioned advertising material recommendation method.
[0008] In one embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned method for recommending advertising materials is implemented.
[0009] In one embodiment of the present disclosure, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the computer program implements the above-mentioned advertising material recommendation method.
[0010] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:
[0011] Determine a first advertising material included in the target advertising promotion information created by a first advertiser, wherein any multimedia material included in the target promotion information is the first advertising material, and then extract first advertising promotion attribute information in the target advertising promotion information, wherein the first advertising promotion attribute information includes text information in the target advertising promotion information for describing the corresponding promotion product, and obtain first advertiser attribute information of the first advertiser, wherein the first advertiser attribute information includes identity attribute information of the first advertiser and product attribute information of the promotion product, store the first advertising promotion attribute information and the first advertiser attribute information as first combination attribute information in a preset combination attribute database, input the first combination attribute information and the first advertising material in the preset combination attribute database into a preset material generation model, obtain a second advertising material output by the preset material generation model, and store the second advertising material in the preset advertising material database so as to perform material recommendation processing according to the preset advertising material database. In this technical solution, based on the target advertising promotion information created by the first advertiser, the first advertising material and the first advertising promotion attribute information are determined, and the first advertiser attribute information of the first advertiser is obtained. The first advertising promotion attribute information and the first advertiser attribute information are used as the first combined attribute, and based on the pre-trained preset material generation model, the derived second advertising material is generated according to the first combined attribute and the first advertising material, so as to facilitate the subsequent material recommendation based on the second advertising material. Therefore, not only the generation of the derived second advertising material is achieved, and the diversity of advertising materials is expanded, but also the second advertising material generated based on the target advertising promotion information created by the first advertiser in the actual scene ensures that the second advertising material does not deviate from the actual application scene and has higher practicality. BRIEF DESCRIPTION OF THE DRAWINGS
[0012] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.
[0013] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0014] Figure 1 A flowchart of a method for recommending advertising materials provided by an embodiment of the present disclosure;
[0015] Figure 2 A schematic diagram of a scenario of target advertising promotion information provided by an embodiment of the present disclosure;
[0016] Figure 3A schematic diagram of a generation process of an advertisement material provided by an embodiment of the present disclosure;
[0017] Figure 4 A flowchart of another method for recommending advertising materials provided by an embodiment of the present disclosure;
[0018] Figure 5 A schematic diagram of another generation process of advertising material provided by an embodiment of the present disclosure;
[0019] Figure 6 A flowchart of another method for recommending advertising materials provided by an embodiment of the present disclosure;
[0020] Figure 7 A flowchart of another method for recommending advertising materials provided by an embodiment of the present disclosure;
[0021] Figure 8 A schematic diagram of the structure of a device for recommending advertising materials provided by an embodiment of the present disclosure;
[0022] Fig. 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION
[0023] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.
[0024] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.
[0025] Figure 1 This is a flow chart of a method for recommending advertising materials provided in an embodiment of the present disclosure. The method provided in an embodiment of the present disclosure can be executed by a device for recommending advertising materials, which can be implemented in software and / or hardware and can be integrated on any electronic device with computing capabilities.
[0026] like Figure 1 As shown, the method for recommending advertising materials provided by the embodiment of the present disclosure may include:
[0027] Step 101: determine a first advertising material included in target advertising promotion information created by a first advertiser, wherein any multimedia material included in the target promotion information is the first advertising material.
[0028] Step 102: extract first advertisement promotion attribute information from the target advertisement promotion information, wherein the first advertisement promotion attribute information includes text information in the target advertisement promotion information that is used to describe the corresponding promotion product.
[0029] Among them, the target advertising promotion information can be understood as the promotional information created by the first advertiser to promote the corresponding promotional product. The target promotion information usually includes the first advertising material and advertising promotion attribute information. The promotional product is related to the application scenario, for example, it can include "books", "electrical appliances", etc. The first advertising material can be any multimedia material included in the target promotion information, including but not limited to pictures, videos, etc.
[0030] In addition, the first advertising promotion attribute information is text information describing the corresponding promotion product, for example, it can be promotional copy information of the promotion product, advertising promotion theme information in the first advertising promotion attribute information, etc. For example, if the promotion copy corresponding to the target advertising promotion information A is "Reading the Encyclopedia of Puzzles, Developing Brain Intelligence", and the promotion theme is "Puzzle Encyclopedia TV Picture Creativity", the text information of the promotion product includes "Reading the Encyclopedia of Puzzles, Developing Brain Intelligence" and "Puzzle Encyclopedia TV Picture Creativity".
[0031] In one embodiment of the present disclosure, a first advertising material included in target advertising promotion information created by a first advertiser is determined.
[0032] In some possible examples, the step of obtaining the first advertising material may include: identifying the element type of each information element included in the target advertising promotion information, wherein the information element is a basic component unit in the target advertising promotion information, for example, Figure 2 As shown, when the target advertising promotion information B includes three parts: advertising promotion picture, advertising promotion theme and advertising promotion copy, the advertising promotion picture, advertising promotion theme and advertising promotion copy can be respectively used as an information element.
[0033] In this embodiment, it is determined that the information element whose element type is a picture type or a video type is the first advertisement material, and the like.
[0034] In this embodiment, the first advertising promotion attribute information in the target advertising promotion information is also extracted, for example, the information element whose element type in the target advertising promotion information is a text type is identified as the first advertising promotion attribute information.
[0035] Step 103: Acquire first advertiser attribute information of the first advertiser, wherein the first advertiser attribute information includes identity attribute information of the first advertiser and product attribute information of the promoted product.
[0036] In one embodiment of the present disclosure, first advertiser attribute information of the first advertiser is also obtained, wherein the first advertiser attribute information includes identity attribute information of the first advertiser, and the identity attribute information indicates relevant identity information of the first advertiser in a promotion scenario, and may include basic identity information such as the advertiser entity name and the advertiser industry, and the first advertiser attribute information also includes product attribute information of a promoted product, and the product attribute information indicates relevant attribute information of the promoted product, and may include category information of the promoted product, etc.
[0037] In some possible embodiments, a correspondence between product attribute information of a promotional product and a promotional product identifier may be pre-constructed. After extracting the promotional product identifier (including any identifier information that may indicate the promotional product, such as the product name) in the target advertising promotion information, the above correspondence may be queried to obtain the corresponding product attribute information.
[0038] In this embodiment, the identity attribute information of the first advertiser that is pre-registered and authorized to be queried by the first advertiser may be queried.
[0039] Step 104: store the first advertisement promotion attribute information and the first advertiser attribute information as first combined attribute information in a preset combined attribute database.
[0040] In an embodiment of the present disclosure, the first advertising promotion attribute information and the first advertiser attribute information are stored as the first combined attribute information in a preset combined attribute database, wherein the first advertising promotion attribute information can be regarded as unique attribute information corresponding to the target advertising promotion information. The corresponding unique attribute information is different for different target advertising promotion information. The first advertiser attribute information can be regarded as basic attribute information. The unique information and the basic attribute information are regarded as a combined attribute information, which facilitates the subsequent determination of the degree of fit between the derived advertising materials and the actual promotion scenario.
[0041] Step 105, input the first combination attribute information and the first advertising material in the preset combination attribute database into the preset material generation model, and obtain the second advertising material output by the preset material generation model, wherein the second advertising material is different from the first advertising material, and the preset material generation model pre-learns to generate other advertising materials different from the input advertising material based on the input combination attribute information and advertising material.
[0042] It should be understood that the preset material generation model is pre-trained based on a large amount of sample data. The preset material generation model pre-learns to generate other advertising materials different from the input advertising materials based on the input combined attribute information and advertising materials. The preset material generation model includes but is not limited to deep learning models, convolutional neural network models, etc.
[0043] In one embodiment of the present disclosure, the first combination attribute information and the first advertising material in the preset combination attribute database are input into a preset material generation model to obtain a second advertising material output by the preset material generation model, wherein the second advertising material is different from the first advertising material, and the second advertising material is generated based on relevant information of the target advertising promotion information actually created, thereby ensuring the practicability of the second advertising material while expanding the diversity of the materials.
[0044] Step 106: Store the second advertising material in a preset advertising material database so as to perform material recommendation processing according to the preset advertising material database.
[0045] After obtaining the second promotional material, the second advertising material is stored in the preset advertising material database so as to perform material recommendation processing according to the preset advertising material database. Thus, the recommended material no longer depends on the advertiser's active uploading or manual secondary editing, thereby realizing the automatic generation of derivative materials.
[0046] In general, refer to Figure 3 In an embodiment of the present disclosure, after the first advertiser creates the target advertising promotion information, the first advertising material is first extracted from the target advertising promotion information, and the first advertising promotion attribute information is extracted, and the first advertiser attribute information of the first advertiser is obtained, and the first advertising promotion attribute information and the first advertiser attribute information are stored as the first combined attribute information in a preset combined attribute database. In this embodiment, a preset preset material generation model calling interface is called, and the first combined attribute information and the first advertising material in the preset combined attribute database are input into the preset material generation model to obtain the second advertising material output by the preset material generation model.
[0047] In summary, the advertising material recommendation method of the embodiment of the present invention determines the first advertising material included in the target advertising promotion information created by the first advertiser, wherein any multimedia material included in the target promotion information is the first advertising material, and then extracts the first advertising promotion attribute information in the target advertising promotion information, wherein the first advertising promotion attribute information includes text information in the target advertising promotion information used to describe the corresponding promotion product, and obtains the first advertiser attribute information of the first advertiser, wherein the first advertiser attribute information includes the identity attribute information of the first advertiser and the product attribute information of the promotion product, stores the first advertising promotion attribute information and the first advertiser attribute information as the first combination attribute information in a preset combination attribute database, and inputs the first combination attribute information and the first advertising material in the preset combination attribute database into a preset material generation model, obtains the second advertising material output by the preset material generation model, and stores the second advertising material in the preset advertising material database so as to perform material recommendation processing according to the preset advertising material database. In this technical solution, based on the target advertising promotion information created by the first advertiser, the first advertising material and the first advertising promotion attribute information are determined, and the first advertiser attribute information of the first advertiser is obtained. The first advertising promotion attribute information and the first advertiser attribute information are used as the first combined attribute, and based on the pre-trained preset material generation model, the derived second advertising material is generated according to the first combined attribute and the first advertising material, so as to facilitate the subsequent material recommendation based on the second advertising material. Therefore, not only the generation of the derived second advertising material is achieved, and the diversity of advertising materials is expanded, but also the second advertising material generated based on the target advertising promotion information created by the first advertiser in the actual scene ensures that the second advertising material does not deviate from the actual application scene and has higher practicality.
[0048] Before generating the first advertising material, in order to avoid repeated generation of derivative advertising materials, before inputting the first combination attribute information and the first advertising material into the preset material generation model, it is also necessary to determine whether corresponding derivative advertising materials have been generated based on the first combination attribute information and the first advertising material.
[0049] That is, in one embodiment of the present disclosure, before the first combination attribute information and the first advertising material are input into the preset material generation model, such as Figure 4 As shown, the method also includes:
[0050] Step 401: Identify all combination attribute information corresponding to all current advertising materials included in a preset advertising material database.
[0051] Step 402: determine whether all current advertising materials and all corresponding combination attribute information include first combination attribute information and corresponding first advertising material.
[0052] Step 403: determine that all current advertising materials and all corresponding combination attribute information do not include the first combination attribute information and the corresponding first advertising material.
[0053] In this embodiment, all combination attribute information corresponding to all current advertising materials included in the preset advertising material database is identified, and it is determined whether all current advertising materials and all corresponding combination attribute information include first combination attribute information and corresponding first advertising material. For example, in some possible embodiments, when generating derivative advertising materials (for example, the above-mentioned second advertising material), a binding correspondence between the material identifier of each generated derivative advertising material and the combination attribute identifier of the corresponding combination attribute information can be pre-stored, and the material identifier corresponding to all current advertising materials included in the preset advertising material database can be identified. Based on the material identifier, the above-mentioned binding correspondence is queried to obtain all corresponding combination attribute information.
[0054] Then, it is determined whether all current advertising materials and all corresponding combination attribute information include the first combination attribute information and the corresponding first advertising material. If it is determined that all current advertising materials and all corresponding combination attribute information do not include the first combination attribute information and the corresponding first advertising material, the first combination attribute information and the first advertising material are input into the preset material generation model. Otherwise, the first combination attribute information and the first advertising material are not input into the preset material generation model to avoid repeated generation of derivative advertising materials.
[0055] Continue with the above Figure 3 Take the scenario shown as an example. Figure 5 As shown, before inputting the first combination attribute information and the first advertising material into the preset material generation model, it is also necessary to determine whether a derivative advertising material has been generated based on the first combination attribute information and the first advertising material. If the derivative advertising material has been generated, the process is terminated, otherwise the second advertising material continues to be generated.
[0056] In summary, the advertising material recommendation method of the embodiment of the present invention needs to determine whether a derivative advertising material has been generated based on the first combination attribute information and the first advertising material before inputting the first combination attribute information and the first advertising material into the preset material generation model, so as to avoid repeated generation of derivative advertising materials and avoid waste of computing resources.
[0057] In the actual implementation process, in order to further enrich the generated second advertising material, before the first combination attribute information and the first advertising material are input into the preset material generation model, the first combination attribute information may be further expanded.
[0058] In one embodiment of the present disclosure, before the first combined attribute information and the first advertising material are input into the preset material generation model, Figure 6As shown, the method also includes:
[0059] Step 601: query a preset combined attribute database according to first combined attribute information to determine whether the preset combined attribute database contains second combined attribute information whose attribute similarity with the first combined attribute information is greater than a preset similarity threshold.
[0060] The preset similarity threshold may be set according to scene requirements, for example, the preset similarity threshold may be 90%.
[0061] In this embodiment, a preset combination attribute database is queried based on the first combination attribute information, and the matching degree of the first combination attribute information and all the combination attribute information in the preset combination attribute database is calculated to determine whether the preset combination attribute database contains second combination attribute information whose attribute similarity with the first combination attribute information is greater than a preset similarity threshold, that is, it is determined whether it contains a second combination attribute that is similar to the first advertiser attribute information of the first advertiser corresponding to the first combination attribute information (that is, similar to the identity attribute information of the first advertiser, and also promotes a promotional product with similar product attribute information), and is also similar to the first advertisement promotion attribute information (that is, similar to the text information of the promotional product of the first advertiser).
[0062] Step 602: When the second combined attribute information is included, determine the second advertising promotion attribute information included in the second combined attribute information.
[0063] Step 603: update the first advertising promotion attribute information in the first combination attribute information according to the second advertising promotion attribute information.
[0064] When the second combined attribute information is included, the second advertising promotion attribute information included in the second combined attribute information is determined, and then the first advertising promotion attribute information in the first combined attribute information is updated according to the second advertising promotion attribute information.
[0065] It should be noted that in different application scenarios, the manner of updating the first advertising promotion attribute information in the first combination attribute information according to the second advertising promotion attribute information is different, and examples are as follows:
[0066] In some possible examples, it is identified whether the second advertising promotion attribute information contains other advertising promotion attribute information different from the first advertising promotion attribute information. If other advertising promotion attribute information is contained, the other advertising promotion attribute information is added to the first advertising promotion attribute information. That is, in this example, the other advertising promotion attribute information in the second advertising promotion attribute information that is different from the first advertising promotion attribute information is added to the first advertising promotion attribute information, so as to achieve the expansion and update of the first advertising promotion attribute information. As a result, the second advertising material generated based on the updated first combination attribute information is richer, and because the newly added other advertising promotion attribute information is extracted from the second combination attribute information that has a high similarity with the first combination attribute information, the generated second advertising material is also more in line with the actual promotion scenario and has higher practicality.
[0067] In some possible embodiments, when the second combined attribute information is included, the second advertiser attribute information included in the second combined attribute information can be determined, and it can be identified whether the second advertiser attribute information includes other advertiser attribute information different from the first advertiser attribute information. When other advertiser attribute information is included, the other advertiser attribute information is added to the first advertiser attribute information. Thus, the second advertising material generated based on the updated first combined attribute information is richer, and because the newly added other advertiser attribute information is extracted from the second combined attribute information with a high degree of similarity to the first combined attribute information, the generated second advertising material is more in line with the actual promotion scenario and has higher practicality.
[0068] In summary, the advertising material recommendation method of the disclosed embodiment can further expand the first combination attribute information before inputting the first combination attribute information and the first advertising material into the preset material generation model. Since the newly added relevant attribute information is extracted from the second combination attribute information that has a high similarity with the first combination attribute information, the practicality of the second advertising material is improved while ensuring the richness of the second advertising material generated based on the first combination attribute information.
[0069] Based on the above embodiment, all generated derivative advertising materials are stored in a preset advertising material database, and advertising materials can be recommended based on the preset advertising material database.
[0070] In one embodiment of the present disclosure, referring to Figure 7 , the material recommendation process according to the preset advertising material database includes:
[0071] Step 701: in response to obtaining a material search keyword input by a second advertiser, identifying a recommended advertising material matching the material search keyword in a preset advertising material database.
[0072] In this embodiment, a material search interface may be provided, and the material retrieval keywords input by the second advertiser may be obtained in the material search interface. In this embodiment, in response to obtaining the material retrieval keywords input by the second advertiser, recommended advertising materials that match the material retrieval keywords are identified in a preset advertising material database.
[0073] In this embodiment, description information may be generated in advance for each advertising material in the preset advertising material database, and semantic matching may be performed between the material search keyword and the description information. Based on the matching result, advertising materials with a matching degree greater than a certain value may be determined as recommended advertising materials.
[0074] Step 702: Recommend the advertising material to the second advertiser.
[0075] After obtaining the recommended advertising material, the recommended advertising material can be recommended to the second advertiser. For example, the recommended advertising material can be displayed in a visual form on a preset interface to facilitate the second advertiser to select suitable recommended advertising materials, etc. Therefore, in this embodiment, the second advertiser is provided with a richer selection of Guangao materials when creating an advertisement, thereby improving the advertisement creation experience.
[0076] In summary, the advertising material recommendation method of the disclosed embodiment, in response to obtaining the material search keyword input by the second advertiser, identifies the recommended advertising material matching the material search keyword in the preset advertising material database, and recommends the advertising material to the second advertiser. In this technical solution, based on the preset advertising material database storing the derived advertising material, advertising materials are recommended to the advertiser user who creates the advertisement, thereby improving the richness of the recommended advertising materials and the advertising creation experience.
[0077] In order to implement the above embodiment, the present disclosure also proposes a device for recommending advertising materials.
[0078] Figure 8 A schematic diagram of a device for recommending advertising materials provided by an embodiment of the present disclosure is shown in FIG. Figure 8 As shown, the advertising material recommendation device includes: a determination module 810, an extraction module 820, a first acquisition module 830, a first storage module 840, a second acquisition module 850, and a second storage module 860, wherein:
[0079] The determination module 810 is used to determine the first advertising material included in the target advertising promotion information created by the first advertiser, wherein any multimedia material included in the target promotion information is the first advertising material;
[0080] The extraction module 820 is used to extract the first advertisement promotion attribute information in the target advertisement promotion information, wherein the first advertisement promotion attribute information includes text information in the target advertisement promotion information used to describe the corresponding promotion product;
[0081] A first acquisition module 830 is used to acquire first advertiser attribute information of a first advertiser, wherein the first advertiser attribute information includes identity attribute information of the first advertiser and product attribute information of a promoted product;
[0082] The first storage module 840 is used to store the first advertisement promotion attribute information and the first advertiser attribute information as first combined attribute information in a preset combined attribute database;
[0083] The second acquisition module 850 is used to input the first combination attribute information and the first advertising material in the preset combination attribute database into the preset material generation model, and obtain the second advertising material output by the preset material generation model, wherein the second advertising material is different from the first advertising material, and the preset material generation model pre-learns to generate other advertising materials different from the input advertising material according to the input combination attribute information and advertising material;
[0084] The second storage module 860 is used to store the second advertising material in the preset advertising material database so as to perform material recommendation processing according to the preset advertising material database.
[0085] The advertisement material recommendation provided in the embodiment of the present disclosure can execute the advertisement material recommendation method provided in the embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method. The contents not described in detail in the embodiment of the present disclosure device can refer to the description in any method embodiment of the present disclosure.
[0086] In order to implement the above embodiments, the present disclosure further proposes a computer program product, including a computer program / instruction, which implements the method for recommending advertising materials in the above embodiments when executed by a processor.
[0087] Fig. 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure.
[0088] The following specific reference Fig. 9 , which shows a schematic diagram of the structure of an electronic device 900 suitable for implementing the embodiment of the present disclosure. The electronic device 900 in the embodiment of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig. 9The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.
[0089] like Fig. 9 As shown, the electronic device 900 may include a processor (e.g., a central processing unit, a graphics processing unit, etc.) 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a memory 908 into a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the electronic device 900 are also stored. The processor 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.
[0090] Typically, the following devices may be connected to the I / O interface 905: an input device 906 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 907 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a memory 908 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 909. The communication device 909 may allow the electronic device 900 to communicate with other devices wirelessly or by wire to exchange data. Although Fig. 9 The electronic device 900 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.
[0091] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 909, or installed from the memory 908, or installed from the ROM 902. When the computer program is executed by the processor 901, the above functions defined in the method for recommending advertising materials in the embodiment of the present disclosure are executed.
[0092] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.
[0093] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.
[0094] The computer-readable medium may be included in the electronic device, or may exist independently without being installed in the electronic device.
[0095] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device:
[0096] Determine a first advertising material included in the target advertising promotion information created by a first advertiser, wherein any multimedia material included in the target promotion information is the first advertising material, and then extract first advertising promotion attribute information in the target advertising promotion information, wherein the first advertising promotion attribute information includes text information in the target advertising promotion information for describing the corresponding promotion product, and obtain first advertiser attribute information of the first advertiser, wherein the first advertiser attribute information includes identity attribute information of the first advertiser and product attribute information of the promotion product, store the first advertising promotion attribute information and the first advertiser attribute information as first combination attribute information in a preset combination attribute database, input the first combination attribute information and the first advertising material in the preset combination attribute database into a preset material generation model, obtain a second advertising material output by the preset material generation model, and store the second advertising material in the preset advertising material database so as to perform material recommendation processing according to the preset advertising material database. In this technical solution, based on the target advertising promotion information created by the first advertiser, the first advertising material and the first advertising promotion attribute information are determined, and the first advertiser attribute information of the first advertiser is obtained. The first advertising promotion attribute information and the first advertiser attribute information are used as the first combined attribute, and based on the pre-trained preset material generation model, the derived second advertising material is generated according to the first combined attribute and the first advertising material, so as to facilitate the subsequent material recommendation based on the second advertising material. Therefore, not only the generation of the derived second advertising material is achieved, and the diversity of advertising materials is expanded, but also the second advertising material generated based on the target advertising promotion information created by the first advertiser in the actual scene ensures that the second advertising material does not deviate from the actual application scene and has higher practicality.
[0097] The electronic device may be written in one or more programming languages or a combination thereof to write computer program code for performing the operations of the present disclosure, including but not limited to object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0098] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0099] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.
[0100] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.
[0101] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0102] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.
[0103] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.
[0104] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.
Claims
1. A method for recommending advertising materials, characterized in that: include: Determining a first advertising material included in the target advertising promotion information created by the first advertiser, wherein any multimedia material included in the target promotion information is the first advertising material; Extracting first advertising promotion attribute information from the target advertising promotion information, wherein the first advertising promotion attribute information includes text information in the target advertising promotion information used to describe a corresponding promotion product; Acquire first advertiser attribute information of the first advertiser, wherein the first advertiser attribute information includes identity attribute information of the first advertiser and product attribute information of the promoted product; storing the first advertisement promotion attribute information and the first advertiser attribute information as first combined attribute information in a preset combined attribute database; Inputting the first combination attribute information and the first advertising material in the preset combination attribute database into a preset material generation model, obtaining a second advertising material output by the preset material generation model, wherein the second advertising material is different from the first advertising material, and the preset material generation model pre-learns to generate other advertising materials different from the input advertising material according to the input combination attribute information and advertising material; The second advertising material is stored in a preset advertising material database so as to perform material recommendation processing according to the preset advertising material database.
2. The method according to claim 1, characterized in that Before inputting the first combined attribute information and the first advertising material into a preset material generation model, the method further includes: Identify all combination attribute information corresponding to all current advertising materials included in the preset advertising material database; Determine whether all the current advertising materials and all the corresponding combination attribute information include the first combination attribute information and the corresponding first advertising material; Determine that all current advertising materials and all corresponding combination attribute information do not include the first combination attribute information and the corresponding first advertising material.
3. The method according to claim 1, characterized in that Before inputting the first combined attribute information and the first advertising material into a preset material generation model, the method further includes: According to the first combined attribute information, the preset combined attribute database is searched to determine whether the preset combined attribute database contains second combined attribute information whose attribute similarity with the first combined attribute information is greater than a preset similarity threshold; When the second combined attribute information is included, determining the second advertising promotion attribute information included in the second combined attribute information; The first advertising promotion attribute information in the first combined attribute information is updated according to the second advertising promotion attribute information.
4. The method according to claim 3, characterized in that The updating of the first advertising promotion attribute information in the first combined attribute information according to the second advertising promotion attribute information includes: identifying whether the second advertising promotion attribute information includes other advertising promotion attribute information different from the first advertising promotion attribute information; When the other advertising promotion attribute information is included, the other advertising promotion attribute information is added to the first advertising promotion attribute information.
5. The method according to any one of claims 1 to 4, characterized in that: The performing material recommendation processing according to the preset advertising material database includes: In response to obtaining the material search keyword input by the second advertiser, identifying the recommended advertising material matching the material search keyword in the preset advertising material database; The recommended advertising material is recommended to the second advertiser.
6. A device for recommending advertising materials, characterized in that: include: A determination module, configured to determine a first advertising material included in the target advertising promotion information created by the first advertiser, wherein any multimedia material included in the target promotion information is the first advertising material; An extraction module, configured to extract first advertisement promotion attribute information from the target advertisement promotion information, wherein the first advertisement promotion attribute information includes text information in the target advertisement promotion information used to describe a corresponding promotion product; A first acquisition module is used to acquire first advertiser attribute information of the first advertiser, wherein the first advertiser attribute information includes identity attribute information of the first advertiser and product attribute information of the promoted product; A first storage module, configured to store the first advertisement promotion attribute information and the first advertiser attribute information as first combined attribute information in a preset combined attribute database; A second acquisition module is used to input the first combination attribute information and the first advertising material in the preset combination attribute database into a preset material generation model, and obtain a second advertising material output by the preset material generation model, wherein the second advertising material is different from the first advertising material, and the preset material generation model pre-learns to generate other advertising materials different from the input advertising material according to the input combination attribute information and advertising material; The second storage module is used to store the second advertising material in a preset advertising material database so as to perform material recommendation processing according to the preset advertising material database.
7. The device according to claim 6, characterized in that The device also includes: The recommendation module is used to, in response to obtaining the material search keyword input by the second advertiser, identify the recommended advertising material matching the material search keyword in the preset advertising material database, and recommend the recommended advertising material to the second advertiser.
8. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the advertising material recommendation method described in any one of claims 1-5.
9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method for recommending advertising materials described in any one of claims 1 to 5 is implemented.
10. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the method for recommending advertising materials as claimed in any one of claims 1 to 5.